KR20170053799A - Apparatus and method for providing the safety of autonomous driving vehicle - Google Patents

Abstract

Disclosed is a method for providing stability in an apparatus for providing safety of an autonomous vehicle including an interface unit, a dangerous situation sensing unit, a dangerous situation alarm unit, and an operation pattern learning unit. The method of providing safety of an autonomous vehicle includes receiving driver information, calling an operation pattern according to the driver information, detecting a dangerous situation based on the degree of similarity with the called operation pattern, , Receiving the input of the driver for the dangerous situation, and updating the driving pattern of the driver by collecting data on the automobile on which the driver is driving and analyzing the collected data .

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an autonomous driving vehicle,

An embodiment according to the concept of the present invention relates to an apparatus and method for providing safety of an autonomous vehicle, and more particularly to an apparatus and method for providing safety of an autonomous vehicle, To a safety mode in which an automatic mode can be changed to a manual mode in accordance with an instruction from a user.

This patent discloses a technique for detecting a dangerous situation that may occur in a vehicle Internet (IoT) environment equipped with an autonomous navigation system.

With the recent convergence of ICT (Information and Communication Technology) technology in vehicles, the Connected Car environment where vehicles are connected to the external network has been commercialized, and automobiles equipped with autonomous traveling systems that are moving by themselves are being commercialized . The automobile industry expects autonomous vehicles to be commercialized by 2020. 'Lane Departure Warning System (LDWS)', 'Lane Maintenance Support System (LKAS)', 'Back Side Warning System' (BSD), 'Automobile Emergency Vehicle Brake system (AEB) '.

On May 14, 2015, the Korea Automobile Safety Research Institute presented safety and autonomous technology demonstrations to show safety devices such as automobile safety devices, automatic emergency braking devices for passenger cars, lane keeping devices, and technologies related to autonomous driving technology. The automatic safety braking device and the lane keeping support device are reflected as an evaluation item in the 2017 Automobile Safety Evaluation (KNCAP).

Outside of the country, Google unveiled a prototype of autonomous vehicles in December 2014, and showed technology related to autonomous driving at BMW, Benz Volvo at the International Consumer Electronics Show (CES)

This change means that the vehicle is increasingly connected to the outside, and malicious remote control or hacking of such a function is increasing.

Autonomous navigation systems use advanced sensors and high-performance graphics devices to recognize objects around them, most of which use LiDAR sensors. However, the rider system can hack at a low cost of about 60 dollars. Although autonomous navigation is being commercialized in this way, the management of vehicle security is still insufficient.

The technical problem to be solved by the present invention is to detect the dangerous situations that may occur in the Internet (IoT) environment of an autonomous driving vehicle object by comparing the similarity with the existing driving pattern of the driver and provide the driver with the self- And to provide a method and apparatus for providing safety.

A method for providing safety of an autonomous vehicle according to an embodiment of the present invention includes receiving driver information, calling an operation pattern according to the driver information, detecting a dangerous situation based on the similarity with the called operation pattern The method comprising the steps of: providing an alarm for the dangerous situation; receiving an input of a driver for the dangerous situation; and collecting data on the automobile on which the driver is driving and analyzing the collected data, And updating the operation pattern.

Also, an apparatus for providing safety of an autonomous vehicle according to an embodiment of the present invention includes an input device and a display device, and may display a vehicle driving information or a dangerous situation alarm to a driver, or may display driver information or an autonomous driving mode / A risk situation alarm unit for detecting a dangerous situation based on a similarity analysis based on an operation pattern of the driver, a dangerous situation alarm unit for providing an alarm for the dangerous situation when the dangerous situation is detected, An operation pattern learning unit for collecting vehicle-related data for a predetermined period to generate a new operation pattern or updating an existing operation pattern, and a storage unit for storing the driver information and the operation pattern.

A method and apparatus for providing safety of an autonomous vehicle according to an embodiment of the present invention collects information on a vehicle and provides an alarm to a driver when the driver leaves the operation pattern of the driver. It can be judged.

In addition, the safety of the autonomous vehicle can be secured by receiving a dangerous situation alarm through the analysis of the similarity degree of the operation pattern and a driver selection according to the alarm.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In order to more fully understand the drawings recited in the detailed description of the present invention, a detailed description of each drawing is provided.
1 is a functional block diagram of an apparatus for providing safety of an autonomous vehicle according to an embodiment of the present invention.
2 is a flowchart illustrating a method for providing safety of an autonomous vehicle according to an embodiment of the present invention.
FIG. 3 illustrates an interface screen for detecting a dangerous situation and generating a dangerous situation alarm according to an embodiment of the present invention.
FIG. 4 is a table on which vehicle information for dangerous situation detection and driver pattern learning according to an embodiment of the present invention is loaded.

It is to be understood that the specific structural or functional description of embodiments of the present invention disclosed herein is for illustrative purposes only and is not intended to limit the scope of the inventive concept But may be embodied in many different forms and is not limited to the embodiments set forth herein.

The embodiments according to the concept of the present invention can make various changes and can take various forms, so that the embodiments are illustrated in the drawings and described in detail herein. It should be understood, however, that it is not intended to limit the embodiments according to the concepts of the present invention to the particular forms disclosed, but includes all modifications, equivalents, or alternatives falling within the spirit and scope of the invention.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises" or "having" and the like are used to specify that there are features, numbers, steps, operations, elements, parts or combinations thereof described herein, But do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning of the context in the relevant art and, unless explicitly defined herein, are to be interpreted as ideal or overly formal Do not.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings attached hereto.

Hereinafter, an apparatus for providing safety of an autonomous vehicle according to an embodiment of the present invention will be described in detail with reference to FIG.

1 is a functional block diagram of an apparatus 100 for providing safety of an autonomous vehicle according to an embodiment of the present invention.

Referring to FIG. 1, an apparatus 100 for providing safety of an autonomous vehicle includes an interface unit 110, a dangerous situation sensing unit 120, a dangerous situation alarm unit 130, an operation pattern learning unit 140, 180, and a control unit 190.

As used herein, the term "minus" may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the '-section' may mean a logical unit of a predetermined code and a hardware resource to be executed by the predetermined code, and does not necessarily mean a physically connected code or a kind of hardware.

The interface unit 100 includes an input device or a display device, and displays information to the user of the safety-providing device 100 of the autonomous vehicle or inputs information from the user.

The driver can input driver information, for example, through the interface unit 110, or can select the automatic driving mode or the manual driving mode.

The dangerous situation sensing unit 120 monitors the driver's operation pattern and senses a dangerous situation. For example, if the driver's registered operation pattern is compared with the similarity of the data currently collected, if the threshold value is exceeded, it is detected as a dangerous situation. At this time, if the registered operation pattern of the driver does not exist, it is possible to compare the default value preset for the car with the similarity of the data currently collected.

The danger status alarm unit 130 may display an alert window through the interface unit 110. [ In addition, a driver can immediately recognize a dangerous situation by generating a beep or generating vibration on a car seat or the like.

The operation pattern learning unit 140 may collect data of the vehicle for a predetermined period of time and generate an operation pattern. If the initial value of the operation pattern is not set, the operation pattern learning unit 140 collects the vehicle running information of at least one driver before the vehicle is sold, for a predetermined period (for example, about 3 to 6 months) The default value of the operation pattern can be set. Next, when there is no registered operation pattern for a specific driver, for example, in the case of a driver who newly purchases the vehicle and drives the vehicle, the operation pattern learning unit 140 sets the operation pattern default value The driving pattern information of the driver can be collected and the driving pattern for the driver can be registered by updating the driving pattern default value. Next, in the case of the driver having the registered operation pattern, the operation pattern learning unit 140 may collect the vehicle driving information of the driver for the registered driving pattern, and update the registered driving pattern. At this time, the operation pattern may be automatically updated according to a preset cycle, or the update timing may be specified by the driver or the manager.

The storage unit 180 includes a driver information storage unit for storing information related to the driver, for example, driver identification information or a driver operation pattern. The storage unit 180 may include a program memory and a data memory. The program memory may store a program for controlling the operation of the safety providing apparatus 100, for example, an application for providing safety of the autonomous driving vehicle. Data generated during the execution of the programs may be stored in the data memory.

The control unit 190 controls the overall operation of the safety-providing device 100 of the autonomous vehicle. That is, the operation of the interface unit 110, the dangerous situation sensing unit 120, the dangerous situation alarm unit 130, the operation pattern learning unit 140, and the storage unit 180 can be controlled. In particular, the control unit 190 can execute an application for providing safety of the autonomous vehicle.

Hereinafter, a safety providing method of an autonomous vehicle using the safety providing apparatus of an autonomous vehicle according to an embodiment of the present invention will be described in detail with reference to FIG. 2 to FIG.

FIG. 2 is a flowchart for explaining a safety providing method of an autonomous vehicle using the safety providing apparatus of the autonomous vehicle shown in FIG. 1. FIG. 3 is a flowchart illustrating a method of detecting a dangerous situation according to an embodiment of the present invention, FIG. 4 is an exemplary table in which vehicle information for dangerous situation detection and driver pattern learning is loaded according to an embodiment of the present invention. Referring to FIG.

The present invention can largely be divided into an information collecting step and a dangerous situation sensing step. The driver recognizes a dangerous situation on the basis of the driver pattern information, and automatically sets the automatic mode (autonomous driving mode) Mode (manual operation mode), thereby ensuring safety.

First, a method of setting a default value of an operation pattern for providing safety of an autonomous vehicle according to an embodiment of the present invention will be described.

First, data related to the autonomous vehicle is collected for a predetermined period of time. For example, the information collected is shown in [Table 1] below. The data collection period can be from about 3 months to 6 months.

Fuel Consumption (mcc) Long Term Fuel Balance Bank 1 (%) Flywheel torque (Nm) Wheel speed - Front left (km / h) Road slope (%) Excel position (%) Engine speed (rpm) Torque conversion coefficient (Nm) Wheel speed - rear right (km / h) Lateral acceleration (m / s2) Throttle Position (%) Engine Torque - After Calibration (%) Standard torque ratio Wheel speed - Front right (km / h) Steering wheel rotation speed (˚ / s) Short-term fuel correction bank 1 (%) Friction torque (%) Ignition angle delay request -TCU (°) Wheel speed - rear left (km / h) Steering wheel angle (°) Suction air pressure (kPa) Flywheel torque - after adjustment (Nm) Engine torque limit request -TCU (Nm) Torque Converter Turbine Speed - Before Filtering Fuel pressure (kPa) Excel Position - Filtering Value (%) Current ignition timing (°) Engine speed increase request -TCU (%) Check clutch operation Engine torque - Minimum indication (%) Throttle Position - Absolute Value (%) Engine coolant temperature (° C) Target Engine Speed - Lockup Module (rpm) Converter clutch Current gear Engine pressure holding time (Min) Engine idling Target speed (rpm) Preheat plug control request Gear selection Brake switch Fuel cutback Engine torque (%) Compressor operation Vehicle speed (km / h) Longitudinal acceleration (m / s2) Engine fuel cut-off Calculated load value (%) Torque converter speed (rpm)

Next, the collected data is analyzed to set a default value of the operation pattern. It is also possible to further reflect variables such as season or weather to the default value.

FIG. 2 is a flowchart illustrating a method for providing safety of an autonomous vehicle using the safety providing apparatus of the autonomous vehicle shown in FIG. 1. FIG. According to one embodiment, a method for providing safety of an autonomous vehicle may be provided through an application, particularly a navigation application, and the collected information may be stored in a storage of the application to monitor basic information of the vehicle in real time.

First, the control unit 190 of the safety providing apparatus 100 may execute an application for providing safety of the autonomous driving deviation.

Next, driver information such as driver identification information is received through the interface unit 110 (S100). At this time, the driver identification information may be a driver name, a driver alias, or a driver ID.

Next, it is determined whether the received driver information is a driver registered with an operation pattern (S200).

If the driver is not registered with the operation pattern, the driver information is newly registered and the default value is called (S320). The new driver information is stored in the storage unit 180 and the interface unit 110 notifies that the registration of the driver information is completed. At this time, the default value may be a value set by collecting vehicle driving information of at least one driver for a predetermined period (for example, about 3 months to 6 months) before the vehicle is marketed.

If the operation pattern is the registered driver, the registered operation pattern information is retrieved (S310).

Although not shown in the drawings, the method may further include adjusting a called operation pattern according to an internal factor or an external factor with respect to the called operation pattern.

Next, the operation pattern is monitored and a dangerous situation is sensed (S400, see Figs. 3 (a) and 3 (b)). For example, it is possible to monitor whether or not an operation pattern different from the called operation pattern occurs. Specifically, in the case of an initially registered driver, a dangerous situation is detected when an operation pattern different from the called default is generated, and in the case of a registered driver, a dangerous situation is detected when an operation pattern different from the previously registered operation pattern occurs . That is, the operation pattern or default according to the existing driving habit compares the previous data with the current data to the normal range of the corresponding driver and detects the dangerous condition when the threshold is exceeded. At this time, the critical range may be preset by the administrator or the driver, and preferably, the critical range may be 95% to 98% under the statistical technique.

Next, when a dangerous situation is detected, for example, when an operation pattern different from the called operation pattern occurs, a dangerous situation occurrence alarm is generated (S500, see FIG. For example, if a sudden sudden break, a handle breaks, or overspeeds, it is detected as a dangerous situation and an alert window is displayed to switch to manual mode (manual operation mode) or to maintain automatic mode (autonomous mode) The driver can select whether to do so. In addition, it can generate a beep warning of a dangerous situation so that it can react immediately.

Next, the driver's input on the dangerous situation is received from the driver (S600). For example, you can receive operator input on whether to keep the automatic mode or switch to manual mode. If the driver is in an emergency, unlike the existing driving pattern, speeding up is not a dangerous situation. Therefore, the automatic mode is maintained. However, when the vehicle is in the hacking state, it can be switched to the manual mode to secure safety. In other words, when the vehicle is running in the automatic mode, it is possible to secure the safety of the driver by switching manually when a dangerous situation occurs.

Next, the driver collects data related to the vehicle (S700). The driver's driving habits can collect data by day, month, year, and season (up to one year). It is also possible to collect the input information of the driver for the dangerous situation alarm and the like. The collected data can be loaded into an on-car android-based navigation application, and a loaded example is shown in FIG.

Next, the collected operation information is learned and the existing operation pattern setting value is updated (S800). The update period can be set by the administrator or the driver, and can be automatically updated according to the set period. It is also possible to update manually by the driver.

Some steps shown in FIG. 2, for example, a vehicle information collecting step, and the like may be performed in a different order.

With the commercialization of self-propelled vehicles, many automobile industries are developing, but safety management of autonomous vehicles is insufficient. Hacking techniques using these vulnerabilities have appeared, and the safety of autonomous vehicles is not guaranteed. The apparatus and method for improving the stability of an autonomous vehicle according to the present invention can provide safety to an autonomous vehicle by allowing a user to recognize a dangerous situation at the time of autonomous driving and to judge the dangerous situation.

The safety providing method of the above-described autonomous vehicle may be a program that can be executed by a computer, and the program may be recorded on a computer-readable recording medium, and the program may be provided through a network .

Examples of the recording medium include a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a CDROM, an optical medium such as a DVD, a magneto-optical medium such as a floptical disk magneto-optical media, and hardware devices that are specially configured to store and execute programs such as ROM, RAM, flash memory, and the like. In addition, the recording medium may be distributed and distributed to a network-connected computer system so that a computer-readable instruction set can be stored and executed in a distributed manner.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

100: safety safety device for autonomous vehicle
110: interface unit 120: dangerous situation detection unit
130: Risk alarm unit 140: Operation pattern learning unit
180: storage unit 190: control unit

Claims (8)

A method for providing safety of an autonomous vehicle,
Receiving driver information;
Calling an operation pattern according to the driver information;
Detecting a dangerous situation based on the called operation pattern and a degree of similarity;
Providing an alarm for the risk condition;
Receiving an input of a driver for the risk condition alarm; And
And collecting data on the vehicle traveling by the driver and analyzing the collected data to update the driving pattern of the driver. The method according to claim 1,
The step of calling the operation pattern
If a registered operation pattern does not exist for the driver information, a default value of the operation pattern is called,
Wherein the registered operation pattern is called when there is a registered operation pattern for the driver information. 3. The method of claim 2,
The operation pattern default value
Collecting vehicle-related data according to driving of at least one driver for a predetermined period of time, and analyzing and collecting the collected data. The method according to claim 1,
The step of detecting the dangerous situation includes:
Analyzing the similarity between the called operation pattern and the vehicle-related data with respect to the current driving, and detecting the dangerous situation when the degree of similarity is lower than a lower limit threshold or higher than an upper limit threshold. 5. The method of claim 4,
Wherein the lower limit threshold is 95% and the upper limit threshold is 98%. The method according to claim 1,
The step of providing an alarm for the risk situation comprises:
And displaying an alarm window for selecting whether to maintain the autonomous mode or switch to the manual operation mode,
Wherein the step of receiving an input of a driver for the dangerous situation comprises:
And receiving a selection of whether to maintain the autonomous mode or switch to the manual operation mode. A computer-readable recording medium storing a program for providing a safety of an autonomous vehicle for executing the method of any one of claims 1 to 6 in a computer. An interface unit including an input device and a display device and displaying the vehicle driving information or the dangerous situation alarm to the driver or receiving the driver information or the autonomous driving mode / manual driving mode selection from the driver;
A danger detection unit for detecting a dangerous situation through a similarity analysis based on the driving pattern of the driver;
A danger alarm unit for providing an alarm for the dangerous situation when the dangerous situation is detected;
An operation pattern learning unit for collecting vehicle-related data for a predetermined period to generate a new operation pattern or update an existing operation pattern; And
And a storage unit for storing the driver information and the operation pattern.

Images