[go: up one dir, main page]

WO2022239250A1 - Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program - Google Patents

Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program Download PDF

Info

Publication number
WO2022239250A1
WO2022239250A1 PCT/JP2021/018495 JP2021018495W WO2022239250A1 WO 2022239250 A1 WO2022239250 A1 WO 2022239250A1 JP 2021018495 W JP2021018495 W JP 2021018495W WO 2022239250 A1 WO2022239250 A1 WO 2022239250A1
Authority
WO
WIPO (PCT)
Prior art keywords
state transition
logical
rule
rule set
state
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/018495
Other languages
French (fr)
Japanese (ja)
Inventor
宏治 田中
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to PCT/JP2021/018495 priority Critical patent/WO2022239250A1/en
Priority to JP2023519246A priority patent/JP7350216B2/en
Priority to DE112021007256.0T priority patent/DE112021007256B4/en
Publication of WO2022239250A1 publication Critical patent/WO2022239250A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/04—Conjoint control of vehicle sub-units of different type or different function including control of propulsion units
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/20—Conjoint control of vehicle sub-units of different type or different function including control of steering systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4041—Position
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle
    • B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data

Definitions

  • This disclosure relates to technology for determining the behavior of self-driving cars.
  • Patent Literature 1 discloses a technique for calculating the state of the own vehicle to be taken next.
  • the state of the own vehicle and the observed values of the sensors are obtained.
  • Observed values of the sensors correspond to motion information of other vehicles.
  • the state transition graph of the own vehicle and the motion models of the own vehicle and other vehicles the state of the own vehicle to be taken next is calculated.
  • a state transition graph is a set of transitions between states of the vehicle. For example, a portion of the state transition graph shows the transition from the state "approaching the intersection” to the state "stop before the intersection” and the condition of the transition "the light is red or yellow”.
  • the purpose of this disclosure is to enable the behavior of self-driving cars to be determined while ensuring compliance with traffic laws.
  • the behavior decision device of the present disclosure includes: a rule system building unit that refers to a rule set, which is a set of traffic rules expressed by logical formulas, and builds a logical system of the rule set; A conversion unit that refers to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converts the state transition into a logical expression for each state transition in the state transition graph; a false transition detector that determines, for each state transition in the state transition graph, whether the logical expression of the state transition contradicts the logical system of the rule set; a false transition removal unit for removing from the state transition graph as a false transition a state transition corresponding to each logical expression determined to be inconsistent with the logical system of the rule set; and a behavior determination unit that determines behavior of the automatic driving vehicle using the state transition graph after each false transition is removed.
  • a rule system building unit that refers to a rule set, which is a set of traffic rules expressed by logical formulas, and builds a
  • the state transition graph is modified based on the rule set, and the behavior of the autonomous vehicle is determined using the modified state transition graph. Therefore, it is possible to determine the behavior of the autonomous vehicle while ensuring compliance with traffic laws.
  • FIG. 1 is a configuration diagram of an automatic driving vehicle 100 according to Embodiment 1.
  • FIG. 1 is a configuration diagram of an action determining device 200 according to Embodiment 1.
  • FIG. 1 is a functional configuration diagram of an automatic driving system 110 according to Embodiment 1.
  • FIG. 4 is a flowchart of a behavior determination method according to Embodiment 1;
  • FIG. 3 is a configuration diagram of a design support device 300 according to Embodiment 2;
  • FIG. 5 is a functional configuration diagram of a design support device 300 according to Embodiment 2;
  • 10 is a flowchart of a design support method (transition) according to Embodiment 2;
  • 10 is a flowchart of a design support method (rule) according to Embodiment 2;
  • FIG. 2 is a hardware configuration diagram of the action determining device 200 according to the first embodiment;
  • FIG. FIG. 2 is a hardware configuration diagram of a design support device 300 according to Embodiment 2;
  • Embodiment 1 A mode for determining the behavior of the automatic driving vehicle 100 will be described based on FIGS. 1 to 4.
  • FIG. 1 A mode for determining the behavior of the automatic driving vehicle 100 will be described based on FIGS. 1 to 4.
  • FIG. 1 A mode for determining the behavior of the automatic driving vehicle 100 will be described based on FIGS. 1 to 4.
  • FIG. 1 A mode for determining the behavior of the automatic driving vehicle 100 will be described based on FIGS. 1 to 4.
  • the configuration of the automatic driving vehicle 100 will be described based on FIG.
  • the automatic driving vehicle 100 is a vehicle having an automatic driving function.
  • An autonomous vehicle 100 includes an autonomous driving system 110 .
  • the automatic driving system 110 is a system for realizing automatic driving.
  • the automatic driving system 110 includes a sensor group 111, an information acquisition device 112, a behavior determination device 200, and an automatic driving device 113.
  • the sensor group 111 is one or more sensors provided in the automatic driving vehicle 100 .
  • the sensor group 111 includes one or more sensors (first sensor group) for acquiring own vehicle information and one or more sensors (second sensor group) for acquiring other vehicle information. and including.
  • a specific example of the own vehicle information is position information and speed information of the self-driving vehicle 100 (own vehicle).
  • Examples of the first sensor group are satellite positioning system receivers and speedometers.
  • a specific example of the other vehicle information is position information of each automobile (other vehicle) located around the autonomous vehicle 100 .
  • Specific examples of the sensors of the second sensor group are visible cameras or millimeter wave radars.
  • the information acquisition device 112 is a computer that acquires own vehicle information and other vehicle information using the sensor group 111 .
  • the receiver of the satellite positioning system measures the position of the automatic driving vehicle 100, and the information acquisition device 112 acquires the position information of the automatic driving vehicle 100 from the receiver of the satellite positioning system.
  • a visible camera captures the surroundings of the autonomous vehicle 100 to generate image data.
  • the image data represents an image showing the surroundings of the automatic driving vehicle 100 .
  • the information acquisition device 112 acquires image data from the visible camera, processes the image data, calculates the relative position of each other vehicle with respect to the autonomous vehicle 100, and generates position information indicating the relative position of each other vehicle. do.
  • a millimeter wave radar calculates the relative direction and relative distance of each other vehicle with respect to the self-driving vehicle 100 . Then, the information acquisition device 112 acquires the relative direction and relative distance of each other vehicle from the millimeter wave radar, and calculates the relative position of each other vehicle with respect to the self-driving vehicle 100 based on the relative direction and relative distance of each other vehicle. and generate position information indicating the relative position of each other vehicle.
  • the behavior determination device 200 is a computer that determines the behavior of the self-driving vehicle 100 based on own vehicle information, other vehicle information, and the like.
  • actions of the automatic driving vehicle 100 include acceleration/deceleration and steering.
  • the automatic driving device 113 is a computer that performs automatic driving by controlling the automatic driving vehicle 100 according to the behavior determined by the behavior determination device 200.
  • the configuration of the behavior determination device 200 will be described based on FIG.
  • the action determination device 200 is a computer including hardware such as a processor 201 , a memory 202 , an auxiliary storage device 203 and an input/output interface 204 . These pieces of hardware are connected to each other via signal lines.
  • a processor 201 is an IC that performs arithmetic processing and controls other hardware.
  • processor 201 is a CPU.
  • IC is an abbreviation for Integrated Circuit.
  • CPU is an abbreviation for Central Processing Unit.
  • Memory 202 is a volatile or non-volatile storage device. Memory 202 is also referred to as main storage or main memory. For example, memory 202 is RAM. The data stored in memory 202 is saved in auxiliary storage device 203 as needed. RAM is an abbreviation for Random Access Memory.
  • Auxiliary storage device 203 is a non-volatile storage device.
  • the auxiliary storage device 203 is ROM, HDD or flash memory. Data stored in the auxiliary storage device 203 is loaded into the memory 202 as required.
  • ROM is an abbreviation for Read Only Memory.
  • HDD is an abbreviation for Hard Disk Drive.
  • the input/output interface 204 is an interface used for data input/output.
  • input/output interfaces 204 are various ports.
  • the behavior determination device 200 includes elements such as an update unit 211, a rule system construction unit 212, a conversion unit 213, a false transition detection unit 214, a false transition removal unit 215, and an action determination unit 216. These elements are implemented in software.
  • the auxiliary storage device 203 stores an action determination program for causing the computer to function as an update unit 211, a rule system construction unit 212, a conversion unit 213, a false transition detection unit 214, a false transition removal unit 215, and an action determination unit 216. ing.
  • the action determination program is loaded into memory 202 and executed by processor 201 .
  • the auxiliary storage device 203 further stores an OS. At least part of the OS is loaded into memory 202 and executed by processor 201 .
  • the processor 201 executes the action determination program while executing the OS.
  • OS is an abbreviation for Operating System.
  • Input/output data of the action determination program are stored in the storage unit 290 .
  • Memory 202 functions as storage unit 290 .
  • a storage device such as the auxiliary storage device 203 , a register within the processor 201 and a cache memory within the processor 201 may function as the storage unit 290 instead of or together with the memory 202 .
  • the behavior determination device 200 may include multiple processors that substitute for the processor 201 .
  • the action determination program can be computer-readable (stored) in a non-volatile recording medium such as an optical disc or flash memory.
  • FIG. 3 shows the functional configuration of the automatic driving system 110. As shown in FIG. Arrows in the figure indicate the flow of data or the flow of processing. The operations of the elements (221 to 226) of the action determining device 200 and the contents of the data (291, 292) will be described later.
  • the procedure of operation of the behavior determination device 200 corresponds to the behavior determination method. Further, the procedure of operation of the behavior determination device 200 corresponds to the procedure of processing by the behavior determination program.
  • step S ⁇ b>110 the rule system construction unit 212 constructs a logical system of the rule set 292 by referring to the rule set 292 .
  • the rule set 292 is a set of traffic rules expressed by logical formulas and stored in the storage section 290 . Traffic rules are legal rules to be observed in driving. However, the traffic rules may be rules other than legal rules as long as they should be complied with.
  • a traffic rule is expressed by a logical expression as follows. Let 'a' be the propositional symbol 'a traffic light is red'. Let 'b' be the propositional symbol that 'the traffic light is yellow'. Let “c” be the propositional symbol “enter the intersection”. The traffic rule "do not enter the intersection when the light is red or yellow” is expressed by the following logical expression. "
  • traffic rules may be expressed in other ways as long as a logical system can be constructed.
  • rule set 292 is constructed as follows.
  • a rule set 292 consists of traffic rule A, traffic rule B and traffic rule C.
  • the logic of rule set 292 is expressed as follows. A&B&C
  • the logic system of the rule set 292 may be constructed by other construction methods as long as it is possible to detect false transitions, which will be described later.
  • step S120 the update unit 211 updates the state transition graph 291 based on the own vehicle information and the other vehicle information.
  • the state transition graph 291 is graph data representing a plurality of state transitions for a plurality of states of the autonomous vehicle 100 and is stored in the storage unit 290 .
  • State transition means transition between states.
  • each state transition is represented by two nodes and an edge.
  • Each node represents a state.
  • Edges represent transition directions and transition conditions.
  • the updating unit 211 calculates various information based on the host vehicle information and the other vehicle information, and updates the state transition graph 291 based on the calculated various information.
  • State transition graph 291 may be updated in any manner.
  • step S120 may be omitted. That is, the state transition graph 291 does not have to be updated based on own vehicle information and other vehicle information.
  • step S130 the conversion unit 213 selects one unselected state transition from the state transition graph 291.
  • Steps S140 to S160 are executed for the state transition selected in step S130.
  • step S140 the conversion unit 213 converts the state transition into a logical expression.
  • a state transition is represented by a logical expression as follows.
  • the transition source state is “s1”.
  • the transition destination state is “s2”.
  • the transition conditions are "c1" and "c2 or ⁇ c3".
  • the state transition is expressed by the following logical expression. (s1&(c1&(c2
  • the state transition may be converted by another conversion method as long as it is possible to detect a false transition, which will be described later.
  • step S ⁇ b>150 the false transition detection unit 214 determines whether the state transition logical expression contradicts the logical system of the rule set 292 .
  • a state transition is considered to violate rule set 292 if the state transition's formula contradicts the logic of rule set 292 .
  • the false transition detector 214 determines whether the logical formula A is true or false in the logical system L by solving the L&P satisfiability problem.
  • the false transition detection unit 214 may make determination by other methods.
  • step S160 If the state transition logic is inconsistent with the logic of rule set 292, processing proceeds to step S160. If the state transition formula is consistent with the logical system of rule set 292, processing proceeds to step S170.
  • a state transition corresponding to a logical expression determined to be inconsistent with the logical system of the rule set 292 is called a "false transition”.
  • step S ⁇ b>160 the false transition removal unit 215 temporarily removes false transitions from the state transition graph 291 .
  • Temporarily removing false transitions means preventing false transitions from being considered in determining the next action of the autonomous vehicle 100 .
  • step S ⁇ b>170 the conversion unit 213 determines whether there is an unselected state transition in the state transition graph 291 . If there is an unselected state transition in state transition graph 291, the process proceeds to step S130. If there is no unselected state transition in state transition graph 291, the process proceeds to step S180.
  • step S180 the action determination unit 216 determines the next action of the self-driving vehicle 100 using the state transition graph 291 after each false transition is removed.
  • the behavior determination unit 216 determines the next behavior of the self-driving vehicle 100 based on the state transition graph 291, the own vehicle information, and the other vehicle information as follows. First, the action determination unit 216 selects a state (transition source state) that matches the current state of the automatic driving vehicle 100 from the state transition graph 291, and selects one or more states (transition destination) that are transition destinations of the selected state. previous state) is extracted from the state transition graph 291 . Next, the action determination unit 216 determines one transition destination state from one or more transition destination states of the autonomous vehicle 100 based on the own vehicle information, the other vehicle information, and the motion model of the autonomous vehicle 100. Decide on the next state.
  • a state transition source state
  • states transition destination
  • the action determination unit 216 determines one transition destination state from one or more transition destination states of the autonomous vehicle 100 based on the own vehicle information, the other vehicle information, and the motion model of the autonomous vehicle 100. Decide on the next state.
  • next state of the self-driving vehicle 100 is determined by the method described in Patent Document 1. Then, the action determination unit 216 determines the next action of the autonomous vehicle 100 based on the current state of the autonomous vehicle 100 and the next state of the autonomous vehicle 100 . The next action of autonomous vehicle 100 is determined in any manner.
  • the rule system construction unit 212 may reflect dynamic environment information acquired by the sensor group 111 in the logical system of the rule set 292 .
  • a specific example of dynamic environmental information is weather information indicating the weather or time information indicating the time.
  • the sensor group 111 includes a receiver that receives weather information and a receiver that receives time information.
  • dynamic environmental information is reflected in traffic rules as dynamic conditions.
  • the time information is reflected in traffic rules such as "no traffic after xx o'clock”.
  • weather information is reflected in traffic rules such as "you must drive when it is foggy".
  • the rule system construction unit 212 may add to the logical system of the rule set 292 a logical expression indicating that two or more states of the self-driving vehicle 100 are not true at the same time.
  • Behavior decision device 200 can ensure compliance with rule set 292 as follows.
  • the behavior determination device 200 determines the behavior of the self-driving vehicle 100 using a state transition graph 291 consisting only of state transitions that do not violate the rule set 292 . In other words, the behavior determination device 200 can determine behavior that does not violate the rule set 292 .
  • the action determination device 200 modifies the state transition graph 291 so as to satisfy the rule set 292 by logical reasoning using the rule set 292 .
  • the behavior determination algorithm described in Patent Literature 1 can be used as it is.
  • the action determination algorithm described in Patent Document 1 is closely tied to the motion model.
  • the set of legal rules is extensive and detailed. Therefore, it is difficult to grasp all legal rule sets and manually create a state transition graph that is consistent with all legal rule sets. Since the state transition graph 291 is modified based on the rule set 292 in the first embodiment, the creator can create the state transition graph 291 without being aware of the rule set 292 .
  • the expression and application of statutory rules need to be strict and are compatible with expression by logical formulas and logical reasoning.
  • determination based on logical inference as in the first embodiment is suitable for determining the behavior of the self-driving vehicle 100 .
  • Embodiment 2 A mode for supporting the design of state transition graph 291 and rule set 292 will be described mainly with reference to FIGS. 5 to 8 for differences from the first embodiment.
  • the configuration of the design support device 300 is a computer having hardware such as a processor 301 , a memory 302 , an auxiliary storage device 303 , a communication device 304 and an input/output interface 305 . These pieces of hardware are connected to each other via signal lines.
  • a processor 301 is an IC that performs arithmetic processing and controls other hardware.
  • processor 301 is a CPU.
  • Memory 302 is a volatile or non-volatile storage device. Memory 302 is also referred to as main storage or main memory.
  • memory 302 is RAM.
  • the data stored in the memory 302 is saved in the auxiliary storage device 303 as required.
  • Auxiliary storage device 303 is a non-volatile storage device.
  • the auxiliary storage device 303 is ROM, HDD or flash memory. Data stored in the auxiliary storage device 303 is loaded into the memory 302 as required.
  • Communication device 304 is a receiver and transmitter.
  • communication device 304 is a communication chip or NIC.
  • the input/output interface 305 is a port to which an input device and an output device are connected.
  • the input/output interface 305 is a USB terminal
  • the input device is a keyboard and mouse
  • the output device is a display.
  • Input/output of the design support device 300 is performed using the input/output interface 305 .
  • the design support device 300 includes elements such as a rule system construction unit 311 , a conversion unit 312 , a false transition detection unit 313 , a transition system construction unit 314 , an underived rule detection unit 315 and a display unit 316 . These elements are implemented in software.
  • Auxiliary storage device 303 contains a design support program for causing a computer to function as a rule system construction unit 311, a conversion unit 312, a false transition detection unit 313, a transition system construction unit 314, an underived rule detection unit 315, and a display unit 316. remembered.
  • the design support program is loaded into memory 302 and executed by processor 301 .
  • the auxiliary storage device 303 further stores an OS. At least part of the OS is loaded into memory 302 and executed by processor 301 .
  • the processor 301 executes the design support program while executing the OS.
  • Input/output data of the design support program are stored in the storage unit 390 .
  • Memory 302 functions as storage unit 390 .
  • a storage device such as the auxiliary storage device 303 , a register within the processor 301 and a cache memory within the processor 301 may function as the storage unit 390 instead of or together with the memory 302 .
  • the design support device 300 may include multiple processors that substitute for the processor 301 .
  • the design support program can be recorded (stored) in a computer-readable manner on a non-volatile recording medium such as an optical disc or flash memory.
  • FIG. 6 shows the functional configuration of the design support device 300. As shown in FIG. Arrows in the figure indicate the flow of data or the flow of processing. State transition graph 291 and rule set 292 are stored in storage unit 390 . The operation of each element of the design support device 300 will be described later.
  • the operation procedure of the design support device 300 corresponds to the design support method. Further, the operation procedure of the design support device 300 corresponds to the procedure of processing by the design support program.
  • a design support method (transition) will be described based on FIG.
  • a design support method (transition) is a method for displaying false transitions.
  • step S ⁇ b>301 the rule system construction unit 311 constructs a logical system of the rule set 292 .
  • the construction method is the same as the method in step S110 of the first embodiment.
  • step S ⁇ b>302 the conversion unit 312 selects one unselected state transition from the state transition graph 291 .
  • Steps S303 to S305 are executed for the state transition selected in step S302.
  • step S303 the conversion unit 312 converts the state transition into a logical expression.
  • the conversion method is the same as the method in step S140 of the first embodiment.
  • step S ⁇ b>304 the false transition detection unit 313 determines whether the state transition logical expression contradicts the logical system of the rule set 292 .
  • the determination method is the same as the method in step S150 of the first embodiment.
  • step S305 If the state transition logic formula conflicts with the logic system of rule set 292, processing proceeds to step S305. If the state transition formula is consistent with the logical system of rule set 292, processing proceeds to step S306.
  • a state transition corresponding to a logical expression that contradicts the logical system of the rule set 292 is called a "false transition”.
  • step S305 the display unit 316 displays the false transition on the display.
  • a false transition corresponds to a state transition that violates the law.
  • step S ⁇ b>306 the conversion unit 312 determines whether there is an unselected state transition in the state transition graph 291 . If there is an unselected state transition in state transition graph 291, the process proceeds to step S302. If there are no unselected state transitions in state transition graph 291, the process ends.
  • a design support method (rule) will be described based on FIG.
  • the design support method (rule) is a method for displaying non-derived rules, which will be described later.
  • step S311 the conversion unit 312 converts each state transition in the state transition graph 291 into a logical expression.
  • the conversion method is the same as the method in step S140 of the first embodiment. If each state transition in state transition graph 291 has already been converted into a logical expression, step S311 is unnecessary.
  • step S ⁇ b>312 the transition system building unit 314 builds a logical system of multiple logical formulas for multiple logical formulas corresponding to multiple state transitions in the state transition graph 291 .
  • the constructed logic system is called the logic system of the state transition graph 291 .
  • the method of constructing the logical system of state transition graph 291 is the same as the method of constructing the logical system of rule set 292 .
  • step S313 the underived rule detection unit 315 selects one unselected traffic rule from the rule set 292.
  • Steps S314 and S315 are executed for the traffic rule selected in step S313.
  • step S ⁇ b>314 the underived rule detection unit 315 determines whether the logic formula of the traffic rule is derived from the logic system of the state transition graph 291 . If the logic formula of the traffic rule is not derived from the logic system of the state transition graph 291, it is considered that there is a traffic rule that is not expressed in the state transition graph 291.
  • the underived rule detection unit 315 determines whether or not the logical formula A can be derived in the logical system L by solving the satisfiability problem of L&P and ⁇ (L&P).
  • the non-derivation rule detection unit 315 may make the determination by other methods.
  • step S316 If the logical expression of the traffic rule is derived from the logical system of state transition graph 291, the process proceeds to step S316. If the logical formula of the traffic rule is not derived from the logical system of state transition graph 291, the process proceeds to step S315.
  • a traffic rule corresponding to a logical expression that is not derived from the logical system of the state transition graph 291 is called an "underived rule”.
  • step S315 the display unit 316 displays the non-derivation rule on the display.
  • a non-derived rule corresponds to a traffic rule that is not guaranteed by the state transition graph 291 .
  • step S ⁇ b>316 the underived rule detection unit 315 determines whether there is an unselected traffic rule in the rule set 292 . If there is an unselected traffic rule in rule set 292, the process proceeds to step S313. If there are no unselected traffic rules in rule set 292, the process ends.
  • the rule system builder 311 may add to the logical system of the rule set 292 a logical expression indicating that two or more states of the autonomous vehicle 100 cannot be true at the same time.
  • the transition system construction unit 314 may add to the logic system of the state transition graph 291 a logical expression indicating that two or more states of the autonomous vehicle 100 do not become true at the same time.
  • Embodiment 2 can be used by the designer of the state transition graph 291 to judge whether the state transition graph 291 is good or bad, and to redesign the state transition graph 291 if necessary.
  • Embodiment 2 can be used by the designer of the ruleset 292 to judge whether the ruleset 292 is good or bad, and to redesign the ruleset 292 if necessary.
  • the design support device 300 displays state transitions (false transitions) that violate the rule set 292 and traffic rules that are not secured by the state transition graph 291 (underived rules).
  • the display of underived rules informs the designer of possible missing state transitions. This allows the designer to design the state transition graph 291 to comply with the rule set 292 .
  • the action determining device 200 includes processing circuitry 209 .
  • the processing circuit 209 is hardware that implements the updating unit 211 , the rule system building unit 212 , the converting unit 213 , the false transition detecting unit 214 , the false transition removing unit 215 , and the action determining unit 216 .
  • the processing circuitry 209 may be dedicated hardware, or may be the processor 201 that executes programs stored in the memory 202 .
  • processing circuitry 209 may be, for example, a single circuit, multiple circuits, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.
  • ASIC is an abbreviation for Application Specific Integrated Circuit.
  • FPGA is an abbreviation for Field Programmable Gate Array.
  • the action determination device 200 may include a plurality of processing circuits that substitute for the processing circuit 209.
  • processing circuit 209 some functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.
  • the functions of the behavior determination device 200 can be realized by hardware, software, firmware, or a combination thereof.
  • the hardware configuration of the design support device 300 will be described based on FIG.
  • the design support device 300 has a processing circuit 309 .
  • the processing circuit 309 is hardware that realizes the rule system construction unit 311 , the conversion unit 312 , the false transition detection unit 313 , the transition system construction unit 314 , the underived rule detection unit 315 , and the display unit 316 .
  • the processing circuit 309 may be dedicated hardware, or may be the processor 301 that executes a program stored in the memory 302 .
  • the processing circuit 309 is dedicated hardware, the processing circuit 309 is, for example, a single circuit, multiple circuits, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.
  • the design support device 300 may include a plurality of processing circuits that substitute for the processing circuit 309.
  • processing circuit 309 some functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.
  • the functions of the design support device 300 can be realized by hardware, software, firmware, or a combination thereof.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

In this invention, a rule system construction unit (212) constructs a logical system of a rule set, which is a set of traffic rules expressed by logical expressions. A conversion unit (213) converts, into a logical expression, each state transition in a state transition graph that represents the plurality of state transitions for the plurality of states of an autonomous vehicle. A false transition detection unit (214) determines whether the logical expression of each of the state transitions in the state transition graph contradicts the logical system of the rule set. A false transition removal unit (215) removes the state transition corresponding to each logical expression determined to be contradictory from the state transition graph as a false transition. A behavior determination unit (216) determines the behavior of the autonomous vehicle using the state transition graph after the false transition is removed.

Description

行動決定装置、行動決定方法、行動決定プログラム、設計支援装置、設計支援方法および設計支援プログラムAction decision device, action decision method, action decision program, design support device, design support method, and design support program

　本開示は、自動運転車の行動を決定するための技術に関するものである。 This disclosure relates to technology for determining the behavior of self-driving cars.

　従来、自動運転車の行動決定技術が提案されている。
　例えば、特許文献１は、次にとるべき自車の状態を算出する技術を開示している。この技術では、まず、自車の状態とセンサの観測値が取得される。センサの観測値は他車の運動情報に相当する。そして、自車の状態遷移グラフと自車および他車の運動モデルを用いて、次にとるべき自車の状態が算出される。
　状態遷移グラフは、自車の状態間の遷移の集合である。例えば、状態遷移グラフの一部は、状態「交差点に接近」から状態「交差点前で停止」への遷移とその遷移の条件「赤信号または黄色信号である」を示す。 Conventionally, behavior determination techniques for self-driving cars have been proposed.
For example, Patent Literature 1 discloses a technique for calculating the state of the own vehicle to be taken next. In this technique, first, the state of the own vehicle and the observed values of the sensors are obtained. Observed values of the sensors correspond to motion information of other vehicles. Then, using the state transition graph of the own vehicle and the motion models of the own vehicle and other vehicles, the state of the own vehicle to be taken next is calculated.
A state transition graph is a set of transitions between states of the vehicle. For example, a portion of the state transition graph shows the transition from the state "approaching the intersection" to the state "stop before the intersection" and the condition of the transition "the light is red or yellow".

米国特許出願公開第２０１９／０３９１５８０号明細書U.S. Patent Application Publication No. 2019/0391580

　自動運転車は交通法規を守る必要がある。
　従来技術においては、交通法規に違反しない状態遷移グラフを設計する必要がある。しかし、人間が膨大かつ詳細に記述された法規を網羅的に把握しながら辻褄のあう状態遷移グラフを設計することは困難である。 Self-driving cars must obey traffic laws.
In the prior art, it is necessary to design a state transition graph that does not violate traffic regulations. However, it is difficult for humans to design a consistent state transition graph while comprehensively grasping the laws and regulations described in great detail.

　本開示は、交通法規の順守を担保しながら自動運転車の行動を決定できるようにすることを目的とする。 The purpose of this disclosure is to enable the behavior of self-driving cars to be determined while ensuring compliance with traffic laws.

　本開示の行動決定装置は、
　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築するルール体系構築部と、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換部と、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定する偽遷移検出部と、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を偽遷移として前記状態遷移グラフから除去する偽遷移除去部と、
　各偽遷移が除去された後の前記状態遷移グラフを用いて、前記自動運転車の行動を決定する行動決定部と、を備える。 The behavior decision device of the present disclosure includes:
a rule system building unit that refers to a rule set, which is a set of traffic rules expressed by logical formulas, and builds a logical system of the rule set;
A conversion unit that refers to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converts the state transition into a logical expression for each state transition in the state transition graph;
a false transition detector that determines, for each state transition in the state transition graph, whether the logical expression of the state transition contradicts the logical system of the rule set;
a false transition removal unit for removing from the state transition graph as a false transition a state transition corresponding to each logical expression determined to be inconsistent with the logical system of the rule set;
and a behavior determination unit that determines behavior of the automatic driving vehicle using the state transition graph after each false transition is removed.

　本開示によれば、状態遷移グラフがルールセットに基づいて修正され、自動運転車の行動が修正された状態遷移グラフを用いて決定される。そのため、交通法規の順守を担保しながら自動運転車の行動を決定することが可能となる。 According to the present disclosure, the state transition graph is modified based on the rule set, and the behavior of the autonomous vehicle is determined using the modified state transition graph. Therefore, it is possible to determine the behavior of the autonomous vehicle while ensuring compliance with traffic laws.

実施の形態１における自動運転車１００の構成図。1 is a configuration diagram of an automatic driving vehicle 100 according to Embodiment 1. FIG. 実施の形態１における行動決定装置２００の構成図。1 is a configuration diagram of an action determining device 200 according to Embodiment 1. FIG. 実施の形態１における自動運転システム１１０の機能構成図。1 is a functional configuration diagram of an automatic driving system 110 according to Embodiment 1. FIG. 実施の形態１における行動決定方法のフローチャート。4 is a flowchart of a behavior determination method according to Embodiment 1; 実施の形態２における設計支援装置３００の構成図。FIG. 3 is a configuration diagram of a design support device 300 according to Embodiment 2; 実施の形態２における設計支援装置３００の機能構成図。FIG. 5 is a functional configuration diagram of a design support device 300 according to Embodiment 2; 実施の形態２における設計支援方法（遷移）のフローチャート。10 is a flowchart of a design support method (transition) according to Embodiment 2; 実施の形態２における設計支援方法（ルール）のフローチャート。10 is a flowchart of a design support method (rule) according to Embodiment 2; 実施の形態１における行動決定装置２００のハードウェア構成図。FIG. 2 is a hardware configuration diagram of the action determining device 200 according to the first embodiment; FIG. 実施の形態２における設計支援装置３００のハードウェア構成図。FIG. 2 is a hardware configuration diagram of a design support device 300 according to Embodiment 2;

　実施の形態および図面において、同じ要素または対応する要素には同じ符号を付している。説明した要素と同じ符号が付された要素の説明は適宜に省略または簡略化する。図中の矢印はデータの流れ又は処理の流れを主に示している。 In the embodiments and drawings, the same or corresponding elements are denoted by the same reference numerals. Descriptions of elements having the same reference numerals as those described will be omitted or simplified as appropriate. Arrows in the figure mainly indicate the flow of data or the flow of processing.

　実施の形態１．
　自動運転車１００の行動を決定する形態について、図１から図４に基づいて説明する。 Embodiment 1.
A mode for determining the behavior of the automatic driving vehicle 100 will be described based on FIGS. 1 to 4. FIG.

＊＊＊構成の説明＊＊＊
　図１に基づいて、自動運転車１００の構成を説明する。
　自動運転車１００は、自動運転機能を有する自動車である。 *** Configuration description ***
The configuration of the automatic driving vehicle 100 will be described based on FIG.
The automatic driving vehicle 100 is a vehicle having an automatic driving function.

　自動運転車１００は、自動運転システム１１０を備える。
　自動運転システム１１０は、自動運転を実現するためのシステムである。 An autonomous vehicle 100 includes an autonomous driving system 110 .
The automatic driving system 110 is a system for realizing automatic driving.

　自動運転システム１１０は、センサ群１１１と、情報取得装置１１２と、行動決定装置２００と、自動運転装置１１３と、を備える。 The automatic driving system 110 includes a sensor group 111, an information acquisition device 112, a behavior determination device 200, and an automatic driving device 113.

　センサ群１１１は、自動運転車１００に設けられる１つ以上のセンサである。
　具体的には、センサ群１１１は、自車情報を取得するための１つ以上のセンサ（第１センサ群）と、他車情報を取得するための１つ以上のセンサ（第２センサ群）と、を含む。
　自車情報の具体例は、自動運転車１００（自車）の位置情報および速度情報である。第１センサ群の具体例は、衛星測位システムの受信機および速度計である。
　他車情報の具体例は、自動運転車１００の周辺に位置する各自動車（他車）の位置情報である。第２センサ群のセンサの具体例は、可視カメラまたはミリ波レーダである。 The sensor group 111 is one or more sensors provided in the automatic driving vehicle 100 .
Specifically, the sensor group 111 includes one or more sensors (first sensor group) for acquiring own vehicle information and one or more sensors (second sensor group) for acquiring other vehicle information. and including.
A specific example of the own vehicle information is position information and speed information of the self-driving vehicle 100 (own vehicle). Examples of the first sensor group are satellite positioning system receivers and speedometers.
A specific example of the other vehicle information is position information of each automobile (other vehicle) located around the autonomous vehicle 100 . Specific examples of the sensors of the second sensor group are visible cameras or millimeter wave radars.

　情報取得装置１１２は、センサ群１１１を利用して自車情報と他車情報を取得するコンピュータである。
　例えば、衛星測位システムの受信機が自動運転車１００の位置を測位し、情報取得装置１１２は衛星測位システムの受信機から自動運転車１００の位置情報を取得する。
　例えば、可視カメラが、自動運転車１００の周辺を撮影して画像データを生成する。画像データは、自動運転車１００の周辺が映った画像を表す。そして、情報取得装置１１２は、可視カメラから画像データを取得し、画像データを処理して自動運転車１００に対する各他車の相対位置を算出し、各他車の相対位置を示す位置情報を生成する。
　例えば、ミリ波レーダが、自動運転車１００に対する各他車の相対方向および相対距離を算出する。そして、情報取得装置１１２は、ミリ波レーダから各他車の相対方向および相対距離を取得し、各他車の相対方向および相対距離に基づいて自動運転車１００に対する各他車の相対位置を算出し、各他車の相対位置を示す位置情報を生成する。 The information acquisition device 112 is a computer that acquires own vehicle information and other vehicle information using the sensor group 111 .
For example, the receiver of the satellite positioning system measures the position of the automatic driving vehicle 100, and the information acquisition device 112 acquires the position information of the automatic driving vehicle 100 from the receiver of the satellite positioning system.
For example, a visible camera captures the surroundings of the autonomous vehicle 100 to generate image data. The image data represents an image showing the surroundings of the automatic driving vehicle 100 . Then, the information acquisition device 112 acquires image data from the visible camera, processes the image data, calculates the relative position of each other vehicle with respect to the autonomous vehicle 100, and generates position information indicating the relative position of each other vehicle. do.
For example, a millimeter wave radar calculates the relative direction and relative distance of each other vehicle with respect to the self-driving vehicle 100 . Then, the information acquisition device 112 acquires the relative direction and relative distance of each other vehicle from the millimeter wave radar, and calculates the relative position of each other vehicle with respect to the self-driving vehicle 100 based on the relative direction and relative distance of each other vehicle. and generate position information indicating the relative position of each other vehicle.

　行動決定装置２００は、自車情報および他車情報などに基づいて自動運転車１００の行動を決定するコンピュータである。
　例えば、自動運転車１００の行動は、加減速および操舵などである。 The behavior determination device 200 is a computer that determines the behavior of the self-driving vehicle 100 based on own vehicle information, other vehicle information, and the like.
For example, actions of the automatic driving vehicle 100 include acceleration/deceleration and steering.

　自動運転装置１１３は、行動決定装置２００によって決定された行動にしたがって自動運転車１００を制御することによって自動運転を行うコンピュータである。 The automatic driving device 113 is a computer that performs automatic driving by controlling the automatic driving vehicle 100 according to the behavior determined by the behavior determination device 200.

　図２に基づいて、行動決定装置２００の構成を説明する。
　行動決定装置２００は、プロセッサ２０１とメモリ２０２と補助記憶装置２０３と入出力インタフェース２０４といったハードウェアを備えるコンピュータである。これらのハードウェアは、信号線を介して互いに接続されている。 The configuration of the behavior determination device 200 will be described based on FIG.
The action determination device 200 is a computer including hardware such as a processor 201 , a memory 202 , an auxiliary storage device 203 and an input/output interface 204 . These pieces of hardware are connected to each other via signal lines.

　プロセッサ２０１は、演算処理を行うＩＣであり、他のハードウェアを制御する。例えば、プロセッサ２０１はＣＰＵである。
　ＩＣは、Ｉｎｔｅｇｒａｔｅｄ　Ｃｉｒｃｕｉｔの略称である。
　ＣＰＵは、Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔの略称である。 A processor 201 is an IC that performs arithmetic processing and controls other hardware. For example, processor 201 is a CPU.
IC is an abbreviation for Integrated Circuit.
CPU is an abbreviation for Central Processing Unit.

　メモリ２０２は揮発性または不揮発性の記憶装置である。メモリ２０２は、主記憶装置またはメインメモリとも呼ばれる。例えば、メモリ２０２はＲＡＭである。メモリ２０２に記憶されたデータは必要に応じて補助記憶装置２０３に保存される。
　ＲＡＭは、Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙの略称である。 Memory 202 is a volatile or non-volatile storage device. Memory 202 is also referred to as main storage or main memory. For example, memory 202 is RAM. The data stored in memory 202 is saved in auxiliary storage device 203 as needed.
RAM is an abbreviation for Random Access Memory.

　補助記憶装置２０３は不揮発性の記憶装置である。例えば、補助記憶装置２０３は、ＲＯＭ、ＨＤＤまたはフラッシュメモリである。補助記憶装置２０３に記憶されたデータは必要に応じてメモリ２０２にロードされる。
　ＲＯＭは、Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙの略称である。
　ＨＤＤは、Ｈａｒｄ　Ｄｉｓｋ　Ｄｒｉｖｅの略称である。 Auxiliary storage device 203 is a non-volatile storage device. For example, the auxiliary storage device 203 is ROM, HDD or flash memory. Data stored in the auxiliary storage device 203 is loaded into the memory 202 as required.
ROM is an abbreviation for Read Only Memory.
HDD is an abbreviation for Hard Disk Drive.

　入出力インタフェース２０４は、データの入出力に用いられるインタフェースである。例えば、入出力インタフェース２０４は、各種のポートである。 The input/output interface 204 is an interface used for data input/output. For example, input/output interfaces 204 are various ports.

　行動決定装置２００は、更新部２１１とルール体系構築部２１２と変換部２１３と偽遷移検出部２１４と偽遷移除去部２１５と行動決定部２１６といった要素を備える。これらの要素はソフトウェアで実現される。 The behavior determination device 200 includes elements such as an update unit 211, a rule system construction unit 212, a conversion unit 213, a false transition detection unit 214, a false transition removal unit 215, and an action determination unit 216. These elements are implemented in software.

　補助記憶装置２０３には、更新部２１１とルール体系構築部２１２と変換部２１３と偽遷移検出部２１４と偽遷移除去部２１５と行動決定部２１６としてコンピュータを機能させるための行動決定プログラムが記憶されている。行動決定プログラムは、メモリ２０２にロードされて、プロセッサ２０１によって実行される。
　補助記憶装置２０３には、さらに、ＯＳが記憶されている。ＯＳの少なくとも一部は、メモリ２０２にロードされて、プロセッサ２０１によって実行される。
　プロセッサ２０１は、ＯＳを実行しながら、行動決定プログラムを実行する。
　ＯＳは、Ｏｐｅｒａｔｉｎｇ　Ｓｙｓｔｅｍの略称である。 The auxiliary storage device 203 stores an action determination program for causing the computer to function as an update unit 211, a rule system construction unit 212, a conversion unit 213, a false transition detection unit 214, a false transition removal unit 215, and an action determination unit 216. ing. The action determination program is loaded into memory 202 and executed by processor 201 .
The auxiliary storage device 203 further stores an OS. At least part of the OS is loaded into memory 202 and executed by processor 201 .
The processor 201 executes the action determination program while executing the OS.
OS is an abbreviation for Operating System.

　行動決定プログラムの入出力データは記憶部２９０に記憶される。
　メモリ２０２は記憶部２９０として機能する。但し、補助記憶装置２０３、プロセッサ２０１内のレジスタおよびプロセッサ２０１内のキャッシュメモリなどの記憶装置が、メモリ２０２の代わりに、又は、メモリ２０２と共に、記憶部２９０として機能してもよい。 Input/output data of the action determination program are stored in the storage unit 290 .
Memory 202 functions as storage unit 290 . However, a storage device such as the auxiliary storage device 203 , a register within the processor 201 and a cache memory within the processor 201 may function as the storage unit 290 instead of or together with the memory 202 .

　行動決定装置２００は、プロセッサ２０１を代替する複数のプロセッサを備えてもよい。 The behavior determination device 200 may include multiple processors that substitute for the processor 201 .

　行動決定プログラムは、光ディスクまたはフラッシュメモリ等の不揮発性の記録媒体にコンピュータ読み取り可能に記録（格納）することができる。 The action determination program can be computer-readable (stored) in a non-volatile recording medium such as an optical disc or flash memory.

　図３に、自動運転システム１１０の機能構成を示す。図中の矢印はデータの流れ又は処理の流れを示している。
　行動決定装置２００の要素（２２１～２２６）の動作およびデータ（２９１、２９２）の内容について後述する。 FIG. 3 shows the functional configuration of the automatic driving system 110. As shown in FIG. Arrows in the figure indicate the flow of data or the flow of processing.
The operations of the elements (221 to 226) of the action determining device 200 and the contents of the data (291, 292) will be described later.

＊＊＊動作の説明＊＊＊
　行動決定装置２００の動作の手順は行動決定方法に相当する。また、行動決定装置２００の動作の手順は行動決定プログラムによる処理の手順に相当する。 ***Description of operation***
The procedure of operation of the behavior determination device 200 corresponds to the behavior determination method. Further, the procedure of operation of the behavior determination device 200 corresponds to the procedure of processing by the behavior determination program.

　図４に基づいて、行動決定方法を説明する。
　ステップＳ１１０において、ルール体系構築部２１２は、ルールセット２９２を参照し、ルールセット２９２の論理体系を構築する。
　ルールセット２９２は、論理式で表現された交通ルールの集合であり、記憶部２９０に記憶される。
　交通ルールは、運転において順守すべき法規ルールである。但し、交通ルールは、順守すべきものであれば法規ルール以外のルールであってもよい。 Based on FIG. 4, the action determination method will be described.
In step S<b>110 , the rule system construction unit 212 constructs a logical system of the rule set 292 by referring to the rule set 292 .
The rule set 292 is a set of traffic rules expressed by logical formulas and stored in the storage section 290 .
Traffic rules are legal rules to be observed in driving. However, the traffic rules may be rules other than legal rules as long as they should be complied with.

　例えば、交通ルールは以下のように論理式で表現される。
　「信号機の現示が赤信号である」という命題記号を「ａ」とする。
　「信号機の現示が黄信号である」という命題記号を「ｂ」とする。
　「交差点に進入する」という命題記号を「ｃ」とする。
　「赤信号または黄信号のときは交差点に進入してはいけない」という交通ルールは、次のような論理式で表現される。「｜」は論理和を意味する。「＾」は否定を意味する。
　（ａ｜ｂ）－＞＾ｃ
　但し、論理体系の構築が可能であれば、交通ルールは他の表現方法で表現されてもよい。 For example, a traffic rule is expressed by a logical expression as follows.
Let 'a' be the propositional symbol 'a traffic light is red'.
Let 'b' be the propositional symbol that 'the traffic light is yellow'.
Let “c” be the propositional symbol “enter the intersection”.
The traffic rule "do not enter the intersection when the light is red or yellow" is expressed by the following logical expression. "|" means a logical sum. "^" means negation.
(a|b)->^c
However, traffic rules may be expressed in other ways as long as a logical system can be constructed.

　例えば、ルールセット２９２の論理体系は以下のように構築される。
　ルールセット２９２が交通ルールＡと交通ルールＢと交通ルールＣから成る。この場合、ルールセット２９２の論理体系は以下のように表される。
　Ａ＆Ｂ＆Ｃ
　但し、後述する偽遷移の検出が可能であれば、ルールセット２９２の論理体系は他の構築方法で構築されてもよい。 For example, the logic of rule set 292 is constructed as follows.
A rule set 292 consists of traffic rule A, traffic rule B and traffic rule C. In this case, the logic of rule set 292 is expressed as follows.
A&B&C
However, the logic system of the rule set 292 may be constructed by other construction methods as long as it is possible to detect false transitions, which will be described later.

　ステップＳ１２０において、更新部２１１は、自車情報および他車情報に基づいて状態遷移グラフ２９１を更新する。
　状態遷移グラフ２９１は、自動運転車１００の複数の状態について複数の状態遷移を表すグラフのデータであり、記憶部２９０に記憶される。
　状態遷移は状態間の遷移を意味する。例えば、状態遷移グラフ２９１において、各状態遷移は２つのノードとエッジで表される。各ノードは状態を表す。エッジは遷移の向きと遷移の条件とを表す。 In step S120, the update unit 211 updates the state transition graph 291 based on the own vehicle information and the other vehicle information.
The state transition graph 291 is graph data representing a plurality of state transitions for a plurality of states of the autonomous vehicle 100 and is stored in the storage unit 290 .
State transition means transition between states. For example, in state transition graph 291, each state transition is represented by two nodes and an edge. Each node represents a state. Edges represent transition directions and transition conditions.

　具体的には、更新部２１１は、自車情報および他車情報に基づいて各種情報を算出し、算出した各種情報に基づいて状態遷移グラフ２９１を更新する。
　状態遷移グラフ２９１は任意の方法で更新して構わない。
　また、ステップＳ１２０が省略されても構わない。つまり、状態遷移グラフ２９１が自車情報および他車情報に基づいて更新されなくてもよい。 Specifically, the updating unit 211 calculates various information based on the host vehicle information and the other vehicle information, and updates the state transition graph 291 based on the calculated various information.
State transition graph 291 may be updated in any manner.
Also, step S120 may be omitted. That is, the state transition graph 291 does not have to be updated based on own vehicle information and other vehicle information.

　ステップＳ１３０において、変換部２１３は、状態遷移グラフ２９１から、未選択の状態遷移を１つ選択する。 In step S130, the conversion unit 213 selects one unselected state transition from the state transition graph 291.

　ステップＳ１４０からステップＳ１６０は、ステップＳ１３０で選択された状態遷移に対して実行される。 Steps S140 to S160 are executed for the state transition selected in step S130.

　ステップＳ１４０において、変換部２１３は、状態遷移を論理式に変換する。 In step S140, the conversion unit 213 converts the state transition into a logical expression.

　例えば、状態遷移は以下のように論理式で表現される。
　遷移元の状態が「ｓ１」である。遷移先の状態が「ｓ２」である。遷移の条件が「ｃ１」且つ「ｃ２または＾ｃ３」である。この場合、状態遷移は次のような論理式で表現される。
　（ｓ１＆（ｃ１＆（ｃ２｜＾ｃ３）））－＞ｓ２
　但し、後述する偽遷移の検出が可能であれば、状態遷移は他の変換方法で変換されてもよい。 For example, a state transition is represented by a logical expression as follows.
The transition source state is "s1". The transition destination state is "s2". The transition conditions are "c1" and "c2 or ^c3". In this case, the state transition is expressed by the following logical expression.
(s1&(c1&(c2|^c3)))->s2
However, the state transition may be converted by another conversion method as long as it is possible to detect a false transition, which will be described later.

　ステップＳ１５０において、偽遷移検出部２１４は、状態遷移の論理式がルールセット２９２の論理体系に対して矛盾するか判定する。
　状態遷移の論理式がルールセット２９２の論理体系に対して矛盾する場合、状態遷移がルールセット２９２に違反すると考えられる。 In step S<b>150 , the false transition detection unit 214 determines whether the state transition logical expression contradicts the logical system of the rule set 292 .
A state transition is considered to violate rule set 292 if the state transition's formula contradicts the logic of rule set 292 .

　例えば、偽遷移検出部２１４は、Ｌ＆Ｐの充足可能性問題を解くことによって、論理体系Ｌにおいて論理式Ａが恒偽であるか否かを判定する。
　但し、偽遷移検出部２１４は他の方法で判定を行ってもよい。 For example, the false transition detector 214 determines whether the logical formula A is true or false in the logical system L by solving the L&P satisfiability problem.
However, the false transition detection unit 214 may make determination by other methods.

　状態遷移の論理式がルールセット２９２の論理体系に対して矛盾する場合、処理はステップＳ１６０に進む。
　状態遷移の論理式がルールセット２９２の論理体系に対して矛盾しない場合、処理はステップＳ１７０に進む。 If the state transition logic is inconsistent with the logic of rule set 292, processing proceeds to step S160.
If the state transition formula is consistent with the logical system of rule set 292, processing proceeds to step S170.

　ルールセット２９２の論理体系に対して矛盾すると判定された論理式に対応する状態遷移を「偽遷移」と称する。 A state transition corresponding to a logical expression determined to be inconsistent with the logical system of the rule set 292 is called a "false transition".

　ステップＳ１６０において、偽遷移除去部２１５は、偽遷移を状態遷移グラフ２９１から一時的に除去する。
　偽遷移の一時的な除去は、偽遷移が自動運転車１００の次の行動の決定に考慮されないようにすることを意味する。 In step S<b>160 , the false transition removal unit 215 temporarily removes false transitions from the state transition graph 291 .
Temporarily removing false transitions means preventing false transitions from being considered in determining the next action of the autonomous vehicle 100 .

　ステップＳ１７０において、変換部２１３は、状態遷移グラフ２９１の中に未選択の状態遷移があるか判定する。
　状態遷移グラフ２９１の中に未選択の状態遷移がある場合、処理はステップＳ１３０に進む。
　状態遷移グラフ２９１の中に未選択の状態遷移がない場合、処理はステップＳ１８０に進む。 In step S<b>170 , the conversion unit 213 determines whether there is an unselected state transition in the state transition graph 291 .
If there is an unselected state transition in state transition graph 291, the process proceeds to step S130.
If there is no unselected state transition in state transition graph 291, the process proceeds to step S180.

　ステップＳ１８０において、行動決定部２１６は、各偽遷移が除去された後の状態遷移グラフ２９１を用いて、自動運転車１００の次の行動を決定する。 In step S180, the action determination unit 216 determines the next action of the self-driving vehicle 100 using the state transition graph 291 after each false transition is removed.

　具体的には、行動決定部２１６は、状態遷移グラフ２９１と自車情報と他車情報とに基づいて、自動運転車１００の次の行動を以下のように決定する。
　まず、行動決定部２１６は、状態遷移グラフ２９１から自動運転車１００の現在の状態と一致する状態（遷移元の状態）を選択し、選択した状態の遷移先となる１つ以上の状態（遷移先の状態）を状態遷移グラフ２９１から抽出する。
　次に、行動決定部２１６は、自車情報と他車情報と自動運転車１００の運動モデルとに基づいて、１つ以上の遷移先の状態から１つの遷移先の状態を自動運転車１００の次の状態に決定する。例えば、自動運転車１００の次の状態は、特許文献１に記載の方法で決定される。
　そして、行動決定部２１６は、自動運転車１００の現在の状態と自動運転車１００の次の状態とに基づいて、自動運転車１００の次の行動を決定する。自動運転車１００の次の行動は任意の方法で決定される。 Specifically, the behavior determination unit 216 determines the next behavior of the self-driving vehicle 100 based on the state transition graph 291, the own vehicle information, and the other vehicle information as follows.
First, the action determination unit 216 selects a state (transition source state) that matches the current state of the automatic driving vehicle 100 from the state transition graph 291, and selects one or more states (transition destination) that are transition destinations of the selected state. previous state) is extracted from the state transition graph 291 .
Next, the action determination unit 216 determines one transition destination state from one or more transition destination states of the autonomous vehicle 100 based on the own vehicle information, the other vehicle information, and the motion model of the autonomous vehicle 100. Decide on the next state. For example, the next state of the self-driving vehicle 100 is determined by the method described in Patent Document 1.
Then, the action determination unit 216 determines the next action of the autonomous vehicle 100 based on the current state of the autonomous vehicle 100 and the next state of the autonomous vehicle 100 . The next action of autonomous vehicle 100 is determined in any manner.

＊＊＊実施例の説明＊＊＊
　ルール体系構築部２１２は、センサ群１１１によって取得される動的な環境情報をルールセット２９２の論理体系に反映してもよい。
　動的な環境情報の具体例は、天気を示す天気情報または時刻を示す時刻情報である。例えば、センサ群１１１は、天気情報を受信する受信機と時刻情報を受信する受信機とを含む。
　具体的には、動的な環境情報は動的な条件として交通ルールに反映される。例えば、時刻情報は「ｘｘ時以降は通行禁止」のように交通ルールに反映される。また、天気情報は「霧が出ているときはｙｙしなければならない」のように交通ルールに反映される。 ***Description of Examples***
The rule system construction unit 212 may reflect dynamic environment information acquired by the sensor group 111 in the logical system of the rule set 292 .
A specific example of dynamic environmental information is weather information indicating the weather or time information indicating the time. For example, the sensor group 111 includes a receiver that receives weather information and a receiver that receives time information.
Specifically, dynamic environmental information is reflected in traffic rules as dynamic conditions. For example, the time information is reflected in traffic rules such as "no traffic after xx o'clock". In addition, weather information is reflected in traffic rules such as "you must drive when it is foggy".

　ルール体系構築部２１２は、自動運転車１００の２つ以上の状態が同時に真にならないことを示す論理式をルールセット２９２の論理体系に追加してもよい。 The rule system construction unit 212 may add to the logical system of the rule set 292 a logical expression indicating that two or more states of the self-driving vehicle 100 are not true at the same time.

＊＊＊実施の形態１の効果＊＊＊
　行動決定装置２００は、以下のようにルールセット２９２の順守を担保することができる。
　行動決定装置２００は、ルールセット２９２に違反しない状態遷移のみから成る状態遷移グラフ２９１を用いて自動運転車１００の行動を決定する。つまり、行動決定装置２００は、ルールセット２９２に違反しない行動を決定することができる． *** Effect of Embodiment 1 ***
Behavior decision device 200 can ensure compliance with rule set 292 as follows.
The behavior determination device 200 determines the behavior of the self-driving vehicle 100 using a state transition graph 291 consisting only of state transitions that do not violate the rule set 292 . In other words, the behavior determination device 200 can determine behavior that does not violate the rule set 292 .

　行動決定装置２００は、ルールセット２９２を用いた論理推論によって、ルールセット２９２を満たすように状態遷移グラフ２９１を修正する。
　自動運転車１００の行動の決定には、特許文献１に記載の行動決定アルゴリズムをそのまま利用することができる。特許文献１に記載の行動決定アルゴリズムは運動モデルに密に紐づいている。
　一般に法規ルールのセットは膨大かつ詳細に記述されている。そのため、法規ルールのセットの全てを把握し、法規ルールのセットの全てと辻褄が合う状態遷移グラフを人手で作成することは困難である。実施の形態１では状態遷移グラフ２９１がルールセット２９２に基づいて修正されるため、作成者はルールセット２９２を意識することなく状態遷移グラフ２９１を作成することができる。
　法規ルールの表現および適用は、厳密である必要があり、論理式による表現および論理的な推論と相性がよい。また、法規ルールを１つずつ検証するだけでなく、法規ルールの再帰的な組み合わせによって成立しうる複合ルールについても担保する必要がある。そのため、自動運転車１００の行動の決定には、実施の形態１のように論理推論による判定が適している。 The action determination device 200 modifies the state transition graph 291 so as to satisfy the rule set 292 by logical reasoning using the rule set 292 .
For determining the behavior of the automatic driving vehicle 100, the behavior determination algorithm described in Patent Literature 1 can be used as it is. The action determination algorithm described in Patent Document 1 is closely tied to the motion model.
Generally, the set of legal rules is extensive and detailed. Therefore, it is difficult to grasp all legal rule sets and manually create a state transition graph that is consistent with all legal rule sets. Since the state transition graph 291 is modified based on the rule set 292 in the first embodiment, the creator can create the state transition graph 291 without being aware of the rule set 292 .
The expression and application of statutory rules need to be strict and are compatible with expression by logical formulas and logical reasoning. In addition, it is necessary not only to verify legal rules one by one, but also to secure compound rules that can be established by recursively combining legal rules. Therefore, determination based on logical inference as in the first embodiment is suitable for determining the behavior of the self-driving vehicle 100 .

　実施の形態２．
　状態遷移グラフ２９１およびルールセット２９２の設計を支援する形態について、主に実施の形態１と異なる点を図５から図８に基づいて説明する。 Embodiment 2.
A mode for supporting the design of state transition graph 291 and rule set 292 will be described mainly with reference to FIGS. 5 to 8 for differences from the first embodiment.

＊＊＊構成の説明＊＊＊
　図５に基づいて、設計支援装置３００の構成を説明する。
　設計支援装置３００は、プロセッサ３０１とメモリ３０２と補助記憶装置３０３と通信装置３０４と入出力インタフェース３０５といったハードウェアを備えるコンピュータである。これらのハードウェアは、信号線を介して互いに接続されている。 *** Configuration description ***
The configuration of the design support device 300 will be described based on FIG.
The design support device 300 is a computer having hardware such as a processor 301 , a memory 302 , an auxiliary storage device 303 , a communication device 304 and an input/output interface 305 . These pieces of hardware are connected to each other via signal lines.

　プロセッサ３０１は、演算処理を行うＩＣであり、他のハードウェアを制御する。例えば、プロセッサ３０１はＣＰＵである。
　メモリ３０２は揮発性または不揮発性の記憶装置である。メモリ３０２は、主記憶装置またはメインメモリとも呼ばれる。例えば、メモリ３０２はＲＡＭである。メモリ３０２に記憶されたデータは必要に応じて補助記憶装置３０３に保存される。
　補助記憶装置３０３は不揮発性の記憶装置である。例えば、補助記憶装置３０３は、ＲＯＭ、ＨＤＤまたはフラッシュメモリである。補助記憶装置３０３に記憶されたデータは必要に応じてメモリ３０２にロードされる。
　通信装置３０４はレシーバ及びトランスミッタである。例えば、通信装置３０４は通信チップまたはＮＩＣである。設計支援装置３００の通信は通信装置３０４を用いて行われる。
　入出力インタフェース３０５は、入力装置および出力装置が接続されるポートである。例えば、入出力インタフェース３０５はＵＳＢ端子であり、入力装置はキーボードおよびマウスであり、出力装置はディスプレイである。設計支援装置３００の入出力は入出力インタフェース３０５を用いて行われる。 A processor 301 is an IC that performs arithmetic processing and controls other hardware. For example, processor 301 is a CPU.
Memory 302 is a volatile or non-volatile storage device. Memory 302 is also referred to as main storage or main memory. For example, memory 302 is RAM. The data stored in the memory 302 is saved in the auxiliary storage device 303 as required.
Auxiliary storage device 303 is a non-volatile storage device. For example, the auxiliary storage device 303 is ROM, HDD or flash memory. Data stored in the auxiliary storage device 303 is loaded into the memory 302 as required.
Communication device 304 is a receiver and transmitter. For example, communication device 304 is a communication chip or NIC. Communication of the design support device 300 is performed using the communication device 304 .
The input/output interface 305 is a port to which an input device and an output device are connected. For example, the input/output interface 305 is a USB terminal, the input device is a keyboard and mouse, and the output device is a display. Input/output of the design support device 300 is performed using the input/output interface 305 .

　設計支援装置３００は、ルール体系構築部３１１と変換部３１２と偽遷移検出部３１３と遷移体系構築部３１４と不導出ルール検出部３１５と表示部３１６といった要素を備える。これらの要素はソフトウェアで実現される。 The design support device 300 includes elements such as a rule system construction unit 311 , a conversion unit 312 , a false transition detection unit 313 , a transition system construction unit 314 , an underived rule detection unit 315 and a display unit 316 . These elements are implemented in software.

　補助記憶装置３０３には、ルール体系構築部３１１と変換部３１２と偽遷移検出部３１３と遷移体系構築部３１４と不導出ルール検出部３１５と表示部３１６としてコンピュータを機能させるための設計支援プログラムが記憶されている。設計支援プログラムは、メモリ３０２にロードされて、プロセッサ３０１によって実行される。
　補助記憶装置３０３には、さらに、ＯＳが記憶されている。ＯＳの少なくとも一部は、メモリ３０２にロードされて、プロセッサ３０１によって実行される。
　プロセッサ３０１は、ＯＳを実行しながら、設計支援プログラムを実行する。 Auxiliary storage device 303 contains a design support program for causing a computer to function as a rule system construction unit 311, a conversion unit 312, a false transition detection unit 313, a transition system construction unit 314, an underived rule detection unit 315, and a display unit 316. remembered. The design support program is loaded into memory 302 and executed by processor 301 .
The auxiliary storage device 303 further stores an OS. At least part of the OS is loaded into memory 302 and executed by processor 301 .
The processor 301 executes the design support program while executing the OS.

　設計支援プログラムの入出力データは記憶部３９０に記憶される。
　メモリ３０２は記憶部３９０として機能する。但し、補助記憶装置３０３、プロセッサ３０１内のレジスタおよびプロセッサ３０１内のキャッシュメモリなどの記憶装置が、メモリ３０２の代わりに、又は、メモリ３０２と共に、記憶部３９０として機能してもよい。 Input/output data of the design support program are stored in the storage unit 390 .
Memory 302 functions as storage unit 390 . However, a storage device such as the auxiliary storage device 303 , a register within the processor 301 and a cache memory within the processor 301 may function as the storage unit 390 instead of or together with the memory 302 .

　設計支援装置３００は、プロセッサ３０１を代替する複数のプロセッサを備えてもよい。 The design support device 300 may include multiple processors that substitute for the processor 301 .

　設計支援プログラムは、光ディスクまたはフラッシュメモリ等の不揮発性の記録媒体にコンピュータ読み取り可能に記録（格納）することができる。 The design support program can be recorded (stored) in a computer-readable manner on a non-volatile recording medium such as an optical disc or flash memory.

　図６に、設計支援装置３００の機能構成を示す。図中の矢印はデータの流れ又は処理の流れを示している。
　状態遷移グラフ２９１およびルールセット２９２は、記憶部３９０に記憶される。
　設計支援装置３００の各要素の動作について後述する。 FIG. 6 shows the functional configuration of the design support device 300. As shown in FIG. Arrows in the figure indicate the flow of data or the flow of processing.
State transition graph 291 and rule set 292 are stored in storage unit 390 .
The operation of each element of the design support device 300 will be described later.

＊＊＊動作の説明＊＊＊
　設計支援装置３００の動作の手順は設計支援方法に相当する。また、設計支援装置３００の動作の手順は設計支援プログラムによる処理の手順に相当する。 ***Description of operation***
The operation procedure of the design support device 300 corresponds to the design support method. Further, the operation procedure of the design support device 300 corresponds to the procedure of processing by the design support program.

　図７に基づいて、設計支援方法（遷移）を説明する。
　設計支援方法（遷移）は、偽遷移を表示するための方法である。 A design support method (transition) will be described based on FIG.
A design support method (transition) is a method for displaying false transitions.

　ステップＳ３０１において、ルール体系構築部３１１は、ルールセット２９２の論理体系を構築する。
　構築方法は、実施の形態１のステップＳ１１０における方法と同じである。 In step S<b>301 , the rule system construction unit 311 constructs a logical system of the rule set 292 .
The construction method is the same as the method in step S110 of the first embodiment.

　ステップＳ３０２において、変換部３１２は、状態遷移グラフ２９１から、未選択の状態遷移を１つ選択する。 In step S<b>302 , the conversion unit 312 selects one unselected state transition from the state transition graph 291 .

　ステップＳ３０３からステップＳ３０５は、ステップＳ３０２で選択された状態遷移に対して実行される。 Steps S303 to S305 are executed for the state transition selected in step S302.

　ステップＳ３０３において、変換部３１２は、状態遷移を論理式に変換する。
　変換方法は、実施の形態１のステップＳ１４０における方法と同じである。 In step S303, the conversion unit 312 converts the state transition into a logical expression.
The conversion method is the same as the method in step S140 of the first embodiment.

　ステップＳ３０４において、偽遷移検出部３１３は、状態遷移の論理式がルールセット２９２の論理体系に対して矛盾するか判定する。
　判定方法は、実施の形態１のステップＳ１５０における方法と同じである。 In step S<b>304 , the false transition detection unit 313 determines whether the state transition logical expression contradicts the logical system of the rule set 292 .
The determination method is the same as the method in step S150 of the first embodiment.

　状態遷移の論理式がルールセット２９２の論理体系に対して矛盾する場合、処理はステップＳ３０５に進む。
　状態遷移の論理式がルールセット２９２の論理体系に対して矛盾しない場合、処理はステップＳ３０６に進む。 If the state transition logic formula conflicts with the logic system of rule set 292, processing proceeds to step S305.
If the state transition formula is consistent with the logical system of rule set 292, processing proceeds to step S306.

　ルールセット２９２の論理体系に対して矛盾する論理式に対応する状態遷移を「偽遷移」と称する。 A state transition corresponding to a logical expression that contradicts the logical system of the rule set 292 is called a "false transition".

　ステップＳ３０５において、表示部３１６は、偽遷移をディスプレイに表示する。
　偽遷移は、法規に違反する状態遷移に相当する。 In step S305, the display unit 316 displays the false transition on the display.
A false transition corresponds to a state transition that violates the law.

　ステップＳ３０６において、変換部３１２は、状態遷移グラフ２９１の中に未選択の状態遷移があるか判定する。
　状態遷移グラフ２９１の中に未選択の状態遷移がある場合、処理はステップＳ３０２に進む。
　状態遷移グラフ２９１の中に未選択の状態遷移がない場合、処理は終了する。 In step S<b>306 , the conversion unit 312 determines whether there is an unselected state transition in the state transition graph 291 .
If there is an unselected state transition in state transition graph 291, the process proceeds to step S302.
If there are no unselected state transitions in state transition graph 291, the process ends.

　図８に基づいて、設計支援方法（ルール）を説明する。
　設計支援方法（ルール）は、後述する不導出ルールを表示するための方法である。 A design support method (rule) will be described based on FIG.
The design support method (rule) is a method for displaying non-derived rules, which will be described later.

　ステップＳ３１１において、変換部３１２は、状態遷移グラフ２９１の中の状態遷移ごとに、状態遷移を論理式に変換する。
　変換方法は、実施の形態１のステップＳ１４０における方法と同じである。
　状態遷移グラフ２９１の中の各状態遷移が既に論理式に変換されている場合、ステップＳ３１１は不要である。 In step S311, the conversion unit 312 converts each state transition in the state transition graph 291 into a logical expression.
The conversion method is the same as the method in step S140 of the first embodiment.
If each state transition in state transition graph 291 has already been converted into a logical expression, step S311 is unnecessary.

　ステップＳ３１２において、遷移体系構築部３１４は、状態遷移グラフ２９１の中の複数の状態遷移に対応する複数の論理式について、複数の論理式の論理体系を構築する。
　構築される論理体系を状態遷移グラフ２９１の論理体系と称する。
　状態遷移グラフ２９１の論理体系を構築する方法は、ルールセット２９２の論理体系を構築する方法と同じである。 In step S<b>312 , the transition system building unit 314 builds a logical system of multiple logical formulas for multiple logical formulas corresponding to multiple state transitions in the state transition graph 291 .
The constructed logic system is called the logic system of the state transition graph 291 .
The method of constructing the logical system of state transition graph 291 is the same as the method of constructing the logical system of rule set 292 .

　ステップＳ３１３において、不導出ルール検出部３１５は、ルールセット２９２から、未選択の交通ルールを１つ選択する。 In step S313, the underived rule detection unit 315 selects one unselected traffic rule from the rule set 292.

　ステップＳ３１４およびステップＳ３１５は、ステップＳ３１３で選択された交通ルールに対して実行される。 Steps S314 and S315 are executed for the traffic rule selected in step S313.

　ステップＳ３１４において、不導出ルール検出部３１５は、交通ルールの論理式が状態遷移グラフ２９１の論理体系から導出されるか判定する。
　交通ルールの論理式が状態遷移グラフ２９１の論理体系から導出されない場合、状態遷移グラフ２９１で表現されていない交通ルールがあると考えられる。 In step S<b>314 , the underived rule detection unit 315 determines whether the logic formula of the traffic rule is derived from the logic system of the state transition graph 291 .
If the logic formula of the traffic rule is not derived from the logic system of the state transition graph 291, it is considered that there is a traffic rule that is not expressed in the state transition graph 291.

　例えば、不導出ルール検出部３１５は、Ｌ＆Ｐおよび＾（Ｌ＆Ｐ）の充足可能性問題を解くことによって、論理体系Ｌにおいて論理式Ａが導出可能であるか否かを判定する。
　但し、不導出ルール検出部３１５は他の方法で判定を行ってもよい。 For example, the underived rule detection unit 315 determines whether or not the logical formula A can be derived in the logical system L by solving the satisfiability problem of L&P and ^(L&P).
However, the non-derivation rule detection unit 315 may make the determination by other methods.

　交通ルールの論理式が状態遷移グラフ２９１の論理体系から導出される場合、処理はステップＳ３１６に進む。
　交通ルールの論理式が状態遷移グラフ２９１の論理体系から導出されない場合、処理はステップＳ３１５に進む。 If the logical expression of the traffic rule is derived from the logical system of state transition graph 291, the process proceeds to step S316.
If the logical formula of the traffic rule is not derived from the logical system of state transition graph 291, the process proceeds to step S315.

　状態遷移グラフ２９１の論理体系から導出されない論理式に対応する交通ルールを「不導出ルール」と称する。 A traffic rule corresponding to a logical expression that is not derived from the logical system of the state transition graph 291 is called an "underived rule".

　ステップＳ３１５において、表示部３１６は、不導出ルールをディスプレイに表示する。
　不導出ルールは、状態遷移グラフ２９１で担保されていない交通ルールに相当する。 In step S315, the display unit 316 displays the non-derivation rule on the display.
A non-derived rule corresponds to a traffic rule that is not guaranteed by the state transition graph 291 .

　ステップＳ３１６において、不導出ルール検出部３１５は、ルールセット２９２の中に未選択の交通ルールがあるか判定する。
　ルールセット２９２の中に未選択の交通ルールがある場合、処理はステップＳ３１３に進む。
　ルールセット２９２の中に未選択の交通ルールがない場合、処理は終了する。 In step S<b>316 , the underived rule detection unit 315 determines whether there is an unselected traffic rule in the rule set 292 .
If there is an unselected traffic rule in rule set 292, the process proceeds to step S313.
If there are no unselected traffic rules in rule set 292, the process ends.

＊＊＊実施例の説明＊＊＊
　ルール体系構築部３１１は、自動運転車１００の２つ以上の状態が同時に真にならないことを示す論理式をルールセット２９２の論理体系に追加してもよい。 ***Description of Examples***
The rule system builder 311 may add to the logical system of the rule set 292 a logical expression indicating that two or more states of the autonomous vehicle 100 cannot be true at the same time.

　遷移体系構築部３１４は、自動運転車１００の２つ以上の状態が同時に真にならないことを示す論理式を状態遷移グラフ２９１の論理体系に追加してもよい。 The transition system construction unit 314 may add to the logic system of the state transition graph 291 a logical expression indicating that two or more states of the autonomous vehicle 100 do not become true at the same time.

＊＊＊実施の形態２の効果＊＊＊
　実施の形態２は、状態遷移グラフ２９１の設計者が、状態遷移グラフ２９１の良し悪しを判断し、必要があれば状態遷移グラフ２９１を再設計するために、利用することができる。
　実施の形態２は、ルールセット２９２の設計者が、ルールセット２９２の良し悪しを判断し、必要があればルールセット２９２を再設計するために、利用することができる。 *** Effect of Embodiment 2 ***
Embodiment 2 can be used by the designer of the state transition graph 291 to judge whether the state transition graph 291 is good or bad, and to redesign the state transition graph 291 if necessary.
Embodiment 2 can be used by the designer of the ruleset 292 to judge whether the ruleset 292 is good or bad, and to redesign the ruleset 292 if necessary.

　設計支援装置３００は、ルールセット２９２に違反する状態遷移（偽遷移）、及び、状態遷移グラフ２９１で担保されていない交通ルール（不導出ルール）を表示する。不導出ルールの表示は、状態遷移が不足している可能性を設計者に知らせる。
　これにより、設計者は、ルールセット２９２を順守するための状態遷移グラフ２９１を設計することができる。 The design support device 300 displays state transitions (false transitions) that violate the rule set 292 and traffic rules that are not secured by the state transition graph 291 (underived rules). The display of underived rules informs the designer of possible missing state transitions.
This allows the designer to design the state transition graph 291 to comply with the rule set 292 .

＊＊＊実施の形態の補足＊＊＊
　図９に基づいて、行動決定装置２００のハードウェア構成を説明する。
　行動決定装置２００は処理回路２０９を備える。
　処理回路２０９は、更新部２１１とルール体系構築部２１２と変換部２１３と偽遷移検出部２１４と偽遷移除去部２１５と行動決定部２１６とを実現するハードウェアである。
　処理回路２０９は、専用のハードウェアであってもよいし、メモリ２０２に格納されるプログラムを実行するプロセッサ２０１であってもよい。 *** Supplement to the embodiment ***
The hardware configuration of the behavior determination device 200 will be described based on FIG.
The action determining device 200 includes processing circuitry 209 .
The processing circuit 209 is hardware that implements the updating unit 211 , the rule system building unit 212 , the converting unit 213 , the false transition detecting unit 214 , the false transition removing unit 215 , and the action determining unit 216 .
The processing circuitry 209 may be dedicated hardware, or may be the processor 201 that executes programs stored in the memory 202 .

　処理回路２０９が専用のハードウェアである場合、処理回路２０９は、例えば、単一回路、複合回路、プログラム化したプロセッサ、並列プログラム化したプロセッサ、ＡＳＩＣ、ＦＰＧＡまたはこれらの組み合わせである。
　ＡＳＩＣは、Ａｐｐｌｉｃａｔｉｏｎ　Ｓｐｅｃｉｆｉｃ　Ｉｎｔｅｇｒａｔｅｄ　Ｃｉｒｃｕｉｔの略称である。
　ＦＰＧＡは、Ｆｉｅｌｄ　Ｐｒｏｇｒａｍｍａｂｌｅ　Ｇａｔｅ　Ａｒｒａｙの略称である。 If processing circuitry 209 is dedicated hardware, processing circuitry 209 may be, for example, a single circuit, multiple circuits, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.
ASIC is an abbreviation for Application Specific Integrated Circuit.
FPGA is an abbreviation for Field Programmable Gate Array.

　行動決定装置２００は、処理回路２０９を代替する複数の処理回路を備えてもよい。 The action determination device 200 may include a plurality of processing circuits that substitute for the processing circuit 209.

　処理回路２０９において、一部の機能が専用のハードウェアで実現されて、残りの機能がソフトウェアまたはファームウェアで実現されてもよい。 In the processing circuit 209, some functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.

　このように、行動決定装置２００の機能はハードウェア、ソフトウェア、ファームウェアまたはこれらの組み合わせで実現することができる。 In this way, the functions of the behavior determination device 200 can be realized by hardware, software, firmware, or a combination thereof.

　図１０に基づいて、設計支援装置３００のハードウェア構成を説明する。
　設計支援装置３００は処理回路３０９を備える。
　処理回路３０９は、ルール体系構築部３１１と変換部３１２と偽遷移検出部３１３と遷移体系構築部３１４と不導出ルール検出部３１５と表示部３１６とを実現するハードウェアである。
　処理回路３０９は、専用のハードウェアであってもよいし、メモリ３０２に格納されるプログラムを実行するプロセッサ３０１であってもよい。 The hardware configuration of the design support device 300 will be described based on FIG.
The design support device 300 has a processing circuit 309 .
The processing circuit 309 is hardware that realizes the rule system construction unit 311 , the conversion unit 312 , the false transition detection unit 313 , the transition system construction unit 314 , the underived rule detection unit 315 , and the display unit 316 .
The processing circuit 309 may be dedicated hardware, or may be the processor 301 that executes a program stored in the memory 302 .

　処理回路３０９が専用のハードウェアである場合、処理回路３０９は、例えば、単一回路、複合回路、プログラム化したプロセッサ、並列プログラム化したプロセッサ、ＡＳＩＣ、ＦＰＧＡまたはこれらの組み合わせである。 If the processing circuit 309 is dedicated hardware, the processing circuit 309 is, for example, a single circuit, multiple circuits, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

　設計支援装置３００は、処理回路３０９を代替する複数の処理回路を備えてもよい。 The design support device 300 may include a plurality of processing circuits that substitute for the processing circuit 309.

　処理回路３０９において、一部の機能が専用のハードウェアで実現されて、残りの機能がソフトウェアまたはファームウェアで実現されてもよい。 In the processing circuit 309, some functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.

　このように、設計支援装置３００の機能はハードウェア、ソフトウェア、ファームウェアまたはこれらの組み合わせで実現することができる。 In this way, the functions of the design support device 300 can be realized by hardware, software, firmware, or a combination thereof.

　各実施の形態は、好ましい形態の例示であり、本開示の技術的範囲を制限することを意図するものではない。各実施の形態は、部分的に実施してもよいし、他の形態と組み合わせて実施してもよい。フローチャート等を用いて説明した手順は、適宜に変更してもよい。 Each embodiment is an example of a preferred form and is not intended to limit the technical scope of the present disclosure. Each embodiment may be implemented partially or in combination with other embodiments. The procedures described using flowcharts and the like may be changed as appropriate.

　行動決定装置２００と設計支援装置３００とのそれぞれの要素である「部」は、「処理」、「工程」、「回路」または「サーキットリ」と読み替えてもよい。 "Units", which are elements of the action determination device 200 and the design support device 300, may be read as "processing", "process", "circuit" or "circuitry".

　１００　自動運転車、１１０　自動運転システム、１１１　センサ群、１１２　情報取得装置、１１３　自動運転装置、２００　行動決定装置、２０１　プロセッサ、２０２　メモリ、２０３　補助記憶装置、２０４　入出力インタフェース、２０９　処理回路、２１１　更新部、２１２　ルール体系構築部、２１３　変換部、２１４　偽遷移検出部、２１５　偽遷移除去部、２１６　行動決定部、２９０　記憶部、２９１　状態遷移グラフ、２９２　ルールセット、３００　設計支援装置、３０１　プロセッサ、３０２　メモリ、３０３　補助記憶装置、３０４　通信装置、３０５　入出力インタフェース、３０９　処理回路、３１１　ルール体系構築部、３１２　変換部、３１３　偽遷移検出部、３１４　遷移体系構築部、３１５　不導出ルール検出部、３１６　表示部、３９０　記憶部。 100 self-driving car, 110 self-driving system, 111 sensor group, 112 information acquisition device, 113 self-driving device, 200 behavior decision device, 201 processor, 202 memory, 203 auxiliary storage device, 204 input/output interface, 209 processing circuit, 211 Update unit 212 Rule system construction unit 213 Conversion unit 214 False transition detection unit 215 False transition removal unit 216 Action determination unit 290 Storage unit 291 State transition graph 292 Rule set 300 Design support device 301 Processor , 302 memory, 303 auxiliary storage device, 304 communication device, 305 input/output interface, 309 processing circuit, 311 rule system construction unit, 312 conversion unit, 313 false transition detection unit, 314 transition system construction unit, 315 underived rule detection unit , 316 display unit, 390 storage unit.

Claims (15)

　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築するルール体系構築部と、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換部と、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定する偽遷移検出部と、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を偽遷移として前記状態遷移グラフから除去する偽遷移除去部と、
　各偽遷移が除去された後の前記状態遷移グラフを用いて、前記自動運転車の行動を決定する行動決定部と、
を備える行動決定装置。 a rule system building unit that refers to a rule set, which is a set of traffic rules expressed by logical formulas, and builds a logical system of the rule set;
A conversion unit that refers to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converts the state transition into a logical expression for each state transition in the state transition graph;
a false transition detector that determines, for each state transition in the state transition graph, whether the logical expression of the state transition contradicts the logical system of the rule set;
a false transition removal unit for removing from the state transition graph as a false transition a state transition corresponding to each logical expression determined to be inconsistent with the logical system of the rule set;
A behavior determination unit that determines the behavior of the automatic driving vehicle using the state transition graph after each false transition is removed;
A behavior decision device comprising: 　前記ルール体系構築部は、前記自動運転車に設けられるセンサによって取得される動的な環境情報を前記ルールセットの前記論理体系に反映する
請求項１に記載の行動決定装置。 The behavior determination device according to claim 1, wherein the rule system construction unit reflects dynamic environment information acquired by sensors provided in the automatic driving vehicle in the logical system of the rule set. 　前記ルール体系構築部は、前記自動運転車の２つ以上の状態が同時に真にならないことを示す論理式を前記ルールセットの前記論理体系に追加する
請求項１または請求項２に記載の行動決定装置。 3. The action determination according to claim 1 or claim 2, wherein the rule system construction unit adds to the logical system of the rule set a logical expression indicating that two or more states of the automatic driving vehicle are not true at the same time. Device. 　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築し、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換し、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定し、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を偽遷移として前記状態遷移グラフから除去し、
　各偽遷移が除去された後の前記状態遷移グラフを用いて、前記自動運転車の行動を決定する
行動決定方法。 referring to a rule set, which is a set of traffic rules expressed by logical formulas, constructing a logical system of the rule set;
referring to a state transition graph representing a plurality of state transitions for a plurality of states of an autonomous vehicle, converting the state transition into a logical expression for each state transition in the state transition graph;
determining, for each state transition in the state transition graph, whether the formula for the state transition contradicts the logic system of the rule set;
removing state transitions corresponding to each logical expression determined to be inconsistent with the logical system of the rule set from the state transition graph as false transitions;
A behavior determination method for determining the behavior of the autonomous vehicle using the state transition graph after each false transition has been removed. 　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築するルール体系構築処理と、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換処理と、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定する偽遷移検出処理と、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を偽遷移として前記状態遷移グラフから除去する偽遷移除去処理と、
　各偽遷移が除去された後の前記状態遷移グラフを用いて、前記自動運転車の行動を決定する行動決定処理と、
をコンピュータに実行させるための行動決定プログラム。 A rule system building process for building a logical system of the rule set by referring to a rule set, which is a set of traffic rules expressed by logical expressions;
A conversion process of referring to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converting the state transition into a logical expression for each state transition in the state transition graph;
false transition detection processing for determining, for each state transition in the state transition graph, whether the logical expression of the state transition contradicts the logical system of the rule set;
False transition removal processing for removing from the state transition graph as a false transition a state transition corresponding to each logical expression determined to be inconsistent with the logical system of the rule set;
An action determination process for determining the action of the automatic driving vehicle using the state transition graph after each false transition is removed;
Action decision program for causing a computer to execute 　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換部と、
　前記複数の状態遷移に対応する複数の論理式の論理体系を前記状態遷移グラフの論理体系として構築する遷移体系構築部と、
　論理式で表現された交通ルールの集合であるルールセットの中の交通ルールごとに、前記交通ルールの前記論理式が前記状態遷移グラフの前記論理体系から導出されるか判定する不導出ルール検出部と、
　前記状態遷移グラフの前記論理体系から導出されないと判定された論理式に対応する交通ルールを表示する表示部と、
を備える設計支援装置。 A conversion unit that refers to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converts the state transition into a logical expression for each state transition in the state transition graph;
a transition system building unit that builds a logic system of a plurality of logical expressions corresponding to the plurality of state transitions as a logic system of the state transition graph;
An underived rule detection unit that determines whether the logical formula of the traffic rule is derived from the logical system of the state transition graph for each traffic rule in a rule set that is a set of traffic rules expressed by logical formulas. When,
a display unit for displaying a traffic rule corresponding to a logical expression determined not to be derived from the logical system of the state transition graph;
A design support device comprising: 　前記遷移体系構築部は、前記自動運転車の２つ以上の状態が同時に真にならないことを示す論理式を前記状態遷移グラフの前記論理体系に追加する
請求項６に記載の設計支援装置。 7. The design support device according to claim 6, wherein the transition system construction unit adds a logical expression indicating that two or more states of the automatic driving vehicle do not simultaneously become true to the logical system of the state transition graph. 　前記設計支援装置は、
　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築するルール体系構築部と、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式と前記ルールセットの前記論理体系とを用いて、前記状態遷移が前記ルールセットに対して矛盾するか判定する偽遷移検出部と、を備え
　前記表示部は、前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を表示する
請求項６または請求項７に記載の設計支援装置。 The design support device is
a rule system building unit that refers to a rule set, which is a set of traffic rules expressed by logical formulas, and builds a logical system of the rule set;
False transition detection for each state transition in the state transition graph, using the formula for the state transition and the logical system for the rule set to determine if the state transition conflicts with the rule set. 8. The design support device according to claim 6, wherein said display unit displays state transitions corresponding to each logical expression determined to be inconsistent with said logical system of said rule set. 　前記ルール体系構築部は、前記自動運転車の２つ以上の状態が同時に真にならないことを示す論理式を前記ルールセットの前記論理体系に追加する
請求項８に記載の設計支援装置。 9. The design support device according to claim 8, wherein the rule system construction unit adds to the logical system of the rule set a logical expression indicating that two or more states of the automatic driving vehicle cannot be true at the same time. 　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換し、
　前記複数の状態遷移に対応する複数の論理式の論理体系を前記状態遷移グラフの論理体系として構築し、
　論理式で表現された交通ルールの集合であるルールセットの中の交通ルールごとに、前記交通ルールの前記論理式が前記状態遷移グラフの前記論理体系から導出されるか判定し、
　前記状態遷移グラフの前記論理体系から導出されないと判定された論理式に対応する交通ルールを表示する
設計支援方法。 referring to a state transition graph representing a plurality of state transitions for a plurality of states of an autonomous vehicle, converting the state transition into a logical expression for each state transition in the state transition graph;
constructing a logical system of a plurality of logical expressions corresponding to the plurality of state transitions as a logical system of the state transition graph;
determining whether the logical formula of the traffic rule is derived from the logical system of the state transition graph for each traffic rule in a rule set, which is a set of traffic rules expressed by logical formulas;
A design support method for displaying a traffic rule corresponding to a logical expression determined not to be derived from the logical system of the state transition graph. 　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換処理と、
　前記複数の状態遷移に対応する複数の論理式の論理体系を前記状態遷移グラフの論理体系として構築する遷移体系構築処理と、
　論理式で表現された交通ルールの集合であるルールセットの中の交通ルールごとに、前記交通ルールの前記論理式が前記状態遷移グラフの前記論理体系から導出されるか判定する不導出ルール検出処理と、
　前記状態遷移グラフの前記論理体系から導出されないと判定された論理式に対応する交通ルールを表示する表示処理と、
をコンピュータに実行させるための設計支援プログラム。 A conversion process of referring to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converting the state transition into a logical expression for each state transition in the state transition graph;
a transition system construction process for constructing a logic system of a plurality of logical expressions corresponding to the plurality of state transitions as a logic system of the state transition graph;
Underived rule detection processing for determining whether the logical formula of the traffic rule is derived from the logical system of the state transition graph for each traffic rule in a rule set, which is a set of traffic rules expressed by logical formulas. When,
a display process for displaying a traffic rule corresponding to a logical expression determined not to be derived from the logical system of the state transition graph;
A design support program that allows a computer to execute 　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築するルール体系構築部と、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換部と、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定する偽遷移検出部と、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を表示する表示部と、
を備える設計支援装置。 a rule system building unit that refers to a rule set, which is a set of traffic rules expressed by logical formulas, and builds a logical system of the rule set;
A conversion unit that refers to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converts the state transition into a logical expression for each state transition in the state transition graph;
a false transition detector that determines, for each state transition in the state transition graph, whether the logical expression of the state transition contradicts the logical system of the rule set;
a display unit that displays state transitions corresponding to each logical expression determined to be inconsistent with the logical system of the rule set;
A design support device comprising: 　前記ルール体系構築部は、前記自動運転車の２つ以上の状態が同時に真にならないことを示す論理式を前記ルールセットの前記論理体系に追加する
請求項１２に記載の設計支援装置。 13. The design support device according to claim 12, wherein the rule system construction unit adds to the logical system of the rule set a logical expression indicating that two or more states of the automatic driving vehicle cannot be true at the same time. 　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築し、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換し、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定し、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を表示する
設計支援方法。 referring to a rule set, which is a set of traffic rules expressed by logical formulas, constructing a logical system of the rule set;
referring to a state transition graph representing a plurality of state transitions for a plurality of states of an autonomous vehicle, converting the state transition into a logical expression for each state transition in the state transition graph;
determining, for each state transition in the state transition graph, whether the formula for the state transition contradicts the logic system of the rule set;
A design support method for displaying state transitions corresponding to each logical expression determined to be inconsistent with the logical system of the rule set. 　論理式で表現された交通ルールの集合であるルールセットを参照し、前記ルールセットの論理体系を構築するルール体系構築処理と、
　自動運転車の複数の状態について複数の状態遷移を表す状態遷移グラフを参照し、前記状態遷移グラフの中の状態遷移ごとに前記状態遷移を論理式に変換する変換処理と、
　前記状態遷移グラフの中の状態遷移ごとに、前記状態遷移の前記論理式が前記ルールセットの前記論理体系に対して矛盾するか判定する偽遷移検出処理と、
　前記ルールセットの前記論理体系に対して矛盾すると判定された各論理式に対応する状態遷移を表示する表示処理と、
をコンピュータに実行させるための設計支援プログラム。 A rule system building process for building a logical system of the rule set by referring to a rule set, which is a set of traffic rules expressed by logical expressions;
A conversion process of referring to a state transition graph representing a plurality of state transitions for a plurality of states of an automatic driving vehicle and converting the state transition into a logical expression for each state transition in the state transition graph;
false transition detection processing for determining, for each state transition in the state transition graph, whether the logical expression of the state transition contradicts the logical system of the rule set;
a display process for displaying state transitions corresponding to each logical expression determined to be inconsistent with the logical system of the rule set;
A design support program that allows a computer to execute
PCT/JP2021/018495 2021-05-14 2021-05-14 Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program Ceased WO2022239250A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2021/018495 WO2022239250A1 (en) 2021-05-14 2021-05-14 Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program
JP2023519246A JP7350216B2 (en) 2021-05-14 2021-05-14 Design support device, design support method, and design support program
DE112021007256.0T DE112021007256B4 (en) 2021-05-14 2021-05-14 DESIGN ASSISTANT FACILITY, DESIGN ASSISTANT PROCESS, AND DESIGN ASSISTANT PROGRAM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/018495 WO2022239250A1 (en) 2021-05-14 2021-05-14 Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program

Publications (1)

Publication Number Publication Date
WO2022239250A1 true WO2022239250A1 (en) 2022-11-17

Family

ID=84028089

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/018495 Ceased WO2022239250A1 (en) 2021-05-14 2021-05-14 Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program

Country Status (3)

Country Link
JP (1) JP7350216B2 (en)
DE (1) DE112021007256B4 (en)
WO (1) WO2022239250A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019506647A (en) * 2016-12-30 2019-03-07 バイドゥ ユーエスエイ エルエルシーＢａｉｄｕ ＵＳＡ ＬＬＣ Driving method and system for autonomous vehicle based on motion plan
JP2019512824A (en) * 2016-03-23 2019-05-16 ヌートノミー インコーポレイテッド How to simplify vehicle operation and automatic operation
US20190391580A1 (en) * 2018-06-25 2019-12-26 Mitsubishi Electric Research Laboratories, Inc. Systems and Methods for Safe Decision Making of Autonomous Vehicles
US20200026289A1 (en) * 2019-09-28 2020-01-23 Ignacio J. Alvarez Distributed traffic safety consensus
JP2020123259A (en) * 2019-01-31 2020-08-13 株式会社日立ソリューションズ Automatic operation program evaluation system, and automatic operation program evaluation method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2589245B (en) * 2019-06-04 2023-01-25 Motional Ad Llc Autonomous vehicle operation using linear temporal logic
US11650590B2 (en) * 2020-03-26 2023-05-16 Mitsubishi Electric Research Laboratories, Inc. Adaptive optimization of decision making for vehicle control

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019512824A (en) * 2016-03-23 2019-05-16 ヌートノミー インコーポレイテッド How to simplify vehicle operation and automatic operation
JP2019506647A (en) * 2016-12-30 2019-03-07 バイドゥ ユーエスエイ エルエルシーＢａｉｄｕ ＵＳＡ ＬＬＣ Driving method and system for autonomous vehicle based on motion plan
US20190391580A1 (en) * 2018-06-25 2019-12-26 Mitsubishi Electric Research Laboratories, Inc. Systems and Methods for Safe Decision Making of Autonomous Vehicles
JP2020123259A (en) * 2019-01-31 2020-08-13 株式会社日立ソリューションズ Automatic operation program evaluation system, and automatic operation program evaluation method
US20200026289A1 (en) * 2019-09-28 2020-01-23 Ignacio J. Alvarez Distributed traffic safety consensus

Also Published As

Publication number Publication date
JP7350216B2 (en) 2023-09-25
DE112021007256T5 (en) 2024-01-25
JPWO2022239250A1 (en) 2022-11-17
DE112021007256B4 (en) 2025-10-23

Similar Documents

Publication Publication Date Title
JP7702268B2 (en) Using Image Augmentation with Simulated Objects for Training Machine Learning Models in Autonomous Driving Applications
US11829896B2 (en) Uncertainty-based data filtering in a vehicle
CN111506980B (en) Method and device for generating traffic scenes in virtual driving environment
US20210011908A1 (en) Model-based structured data filtering in an autonomous vehicle
CN109032103B (en) Method, device and equipment for testing unmanned vehicle and storage medium
US10755007B2 (en) Mixed reality simulation system for testing vehicle control system designs
CN110796007B (en) Method and computing device for scene recognition
US11962664B1 (en) Context-based data valuation and transmission
CN113535569B (en) Method for determining the control effect of automatic driving
US11577756B2 (en) Detecting out-of-model scenarios for an autonomous vehicle
WO2023037576A1 (en) Vehicle control system and vehicle control method
CN111199088B (en) Method and device for reproducing scene data
JP2020042791A (en) Obstacle distribution simulation method, device, and terminal based on multi-model
CN115480092A (en) Voltage monitoring across multiple frequency ranges in autonomous machine applications
CN116701070A (en) Perform diagnostic operations on the target system
CN109684944B (en) Obstacle detection method, obstacle detection device, computer device, and storage medium
CN115756566B (en) Method and device for avoiding solid line lane change of vehicle
CN111199083A (en) Method and device for reproducing accident data of unmanned vehicle
JP6980128B2 (en) Lane link generator, lane link generator, lane link generator
WO2022239250A1 (en) Behavior determination device, behavior determination method, behavior determination program, design assistance device, design assistance method, and design assistance program
JPWO2021038619A1 (en) Hazard detection device, danger detection method, and danger detection program
US20210012220A1 (en) Rules-based structured data filtering in an autonomous vehicle
US20190243583A1 (en) Conducting forward reasoning in production system
CN109583511B (en) Velocity Fusion Method and Device
US20250283723A1 (en) Vehicle display control device, vehicle display control method, and vehicle display control program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21941980

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023519246

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 112021007256

Country of ref document: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21941980

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 112021007256

Country of ref document: DE