CN109885943B - Prediction method and device for driving decision, storage medium and terminal equipment - Google Patents
Prediction method and device for driving decision, storage medium and terminal equipment Download PDFInfo
- Publication number
- CN109885943B CN109885943B CN201910140320.XA CN201910140320A CN109885943B CN 109885943 B CN109885943 B CN 109885943B CN 201910140320 A CN201910140320 A CN 201910140320A CN 109885943 B CN109885943 B CN 109885943B
- Authority
- CN
- China
- Prior art keywords
- accuracy
- motion trail
- prediction
- predicted
- predicted motion
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004422 calculation algorithm Methods 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 3
- 230000015654 memory Effects 0.000 description 23
- 238000004891 communication Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention provides a prediction method, a prediction device, a storage medium and terminal equipment for driving decisions, wherein the method comprises the following steps: acquiring a predicted motion trail and a real motion trail of an obstacle encountered by a vehicle in the running process; calculating the accuracy and/or recall rate of the predicted motion trail according to the obtained predicted motion trail and the real motion trail; and adjusting the driving decision of the vehicle according to the accuracy rate and/or the recall rate. By adopting the method and the device, the accuracy of driving decision can be effectively improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a driving decision prediction method, a driving decision prediction device, a storage medium, and a terminal device.
Background
When the vehicle starts the automatic driving mode to drive, the driver generally does not need to input operation, and the automatic driving vehicle can acquire the positions of other vehicles and obstacles in the driving environment through the sensors mounted on the vehicle, and the positions can be collectively called as sensing data. The awareness data is then used to train a control algorithm for autopilot or to perform autopilot simulation using the awareness data.
Therefore, accurate prediction of the trajectory of obstacles around the vehicle is a necessary condition for the autonomous vehicle to be able to ensure safety and comfort. Such as traffic participants. How to effectively evaluate the prediction effect of the motion trail of the obstacle around the vehicle is a worth discussing. The existing scheme is generally as follows: fitting the predicted motion trail with the real motion trail, and judging the prediction effect of the predicted trail according to the fitting degree. However, the existing scheme only evaluates through fitting degree, and the effect is single.
Disclosure of Invention
The embodiment of the invention provides a prediction method, a prediction device, a storage medium and terminal equipment for driving decisions, which are used for solving or relieving one or more of the technical problems in the prior art.
In a first aspect, an embodiment of the present invention provides a method for predicting a driving decision, including:
acquiring a predicted motion trail and a real motion trail of an obstacle encountered by a vehicle in the running process;
calculating the accuracy and/or recall rate of the predicted motion trail according to the obtained predicted motion trail and the real motion trail; and
and adjusting the driving decision of the vehicle according to the accuracy rate and/or the recall rate.
In one embodiment, the calculating the accuracy and/or recall of the prediction algorithm for predicting the predicted motion trajectory includes:
aiming at each predicted motion track, respectively counting the distance difference between the predicted motion track and the corresponding real motion track at a plurality of set time points;
determining whether the predicted motion trail is predicted accurately according to the distance differences of the plurality of time points; and
and calculating the accuracy and/or recall rate of the predicted motion trail according to the predicted result of each predicted motion trail, the number of the obtained predicted motion trail and the number of the obtained real motion trail.
In one embodiment, the calculating the accuracy and/or recall of the predictive algorithm includes:
counting the number of accurate prediction results according to the prediction results of each prediction motion trail;
taking the ratio of the number of the accurate prediction results to the number of the obtained prediction motion tracks as the accuracy of the prediction motion tracks; and/or
And taking the ratio of the number of the accurate prediction results to the number of the obtained real motion trail as the recall rate of the prediction motion trail.
In one embodiment, the adjusting the driving decision of the vehicle includes:
if the accuracy is greater than a set accuracy threshold, the error range of the driving decision of the vehicle is widened;
if the accuracy is smaller than a set accuracy threshold, tightening an error range of a driving decision of the vehicle; or (b)
And if the recall rate is larger than the accuracy rate, correcting a prediction algorithm for predicting the predicted motion trail, and determining the driving decision of the vehicle by combining the motion trail predicted by the corrected prediction algorithm.
In a second aspect, an embodiment of the present invention provides a prediction apparatus for driving decision, including:
the track acquisition module is used for acquiring the predicted motion track and the real motion track of the obstacle encountered by the vehicle in the running process;
the calculation module is used for calculating the accuracy and/or recall rate of the predicted motion trail according to the acquired predicted motion trail and the real motion trail; and
and the driving decision adjustment module is used for adjusting the driving decision of the vehicle according to the accuracy rate and/or the recall rate.
In one embodiment, the computing module includes:
the distance difference statistics unit is used for respectively counting the distance difference between each predicted motion track and the corresponding real motion track at a plurality of set time points according to each predicted motion track;
the prediction result determining unit is used for determining whether the prediction motion trail is accurate according to the distance differences of the plurality of time points; and
the accuracy rate recall rate calculation unit is used for calculating the accuracy rate and/or recall rate of the predicted motion trail according to the predicted result of each predicted motion trail, the number of the obtained predicted motion trail and the number of the obtained real motion trail.
In one embodiment, the accuracy recall calculation unit includes:
the quantity counting subunit is used for counting the quantity of accurate prediction results according to the prediction results of each prediction motion trail;
the accuracy rate calculating subunit is used for taking the ratio of the number of the accurate prediction results to the number of the obtained prediction motion tracks as the accuracy rate of the prediction motion tracks; and/or
And the recall rate calculating subunit is used for taking the ratio of the number of the accurate prediction results to the number of the obtained real motion tracks as the recall rate of the prediction motion tracks.
In one embodiment, the driving decision adjustment module includes:
an error widening unit, configured to, if the accuracy is greater than a set accuracy threshold, widen an error range of a driving decision of the vehicle;
the error tightening unit is used for tightening the error range of the driving decision of the vehicle if the accuracy is smaller than a set accuracy threshold; or (b)
And the decision determining unit is used for correcting the prediction algorithm if the recall rate is larger than the accuracy rate and determining the driving decision of the vehicle by combining the motion trail predicted by the corrected prediction algorithm.
In a third aspect, an embodiment of the present invention provides a prediction apparatus for driving decision, where the function of the apparatus may be implemented by hardware, or may be implemented by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above.
In one possible design, the prediction structure of the driving decision includes a processor and a memory, where the memory is used for executing the prediction program of the driving decision by the prediction device of the driving decision, and the processor is configured to execute the program stored in the memory. The prediction device of the driving decision may further comprise a communication interface, and the prediction device for the driving decision is in communication with other devices or a communication network.
In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, including computer software instructions for use by a prediction apparatus for driving decisions, where the computer software instructions include a program for executing the prediction method for driving decisions.
Any one of the technical schemes has the following advantages or beneficial effects:
according to the embodiment of the invention, the accuracy and recall rate of the prediction algorithm can be determined by using the predicted motion trail and the real motion trail, and then the driving decision of the vehicle is adjusted according to the accuracy and recall rate, so that the accuracy of the driving decision can be effectively improved. And the effect of prediction can be evaluated from two dimensions of accuracy and recall.
The foregoing summary is for the purpose of the specification only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will become apparent by reference to the drawings and the following detailed description.
Drawings
In the drawings, the same reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily drawn to scale. It is appreciated that these drawings depict only some embodiments according to the disclosure and are not therefore to be considered limiting of its scope.
Fig. 1 is a flow chart of an embodiment of a prediction method for driving decisions provided by the present invention.
FIG. 2 is a flow chart of one embodiment of a process for calculating accuracy and recall provided by the present invention.
FIG. 3 is a flow chart of one embodiment of a process for calculating accuracy and recall provided by the present invention.
Fig. 4 is a schematic structural diagram of an embodiment of a prediction apparatus for driving decision provided by the present invention.
Fig. 5 is a schematic structural diagram of an embodiment of a terminal device provided by the present invention.
Detailed Description
Hereinafter, only certain exemplary embodiments are briefly described. As will be recognized by those of skill in the pertinent art, the described embodiments may be modified in various different ways without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive.
Referring to fig. 1, an embodiment of the present invention provides a prediction method for driving decisions. The present embodiment may be performed by a motor vehicle including: two-wheeled motor vehicles such as electric bicycles and motorcycles, motor vehicles with four wheels such as electric, hybrid or gasoline, and traffic equipment such as airplanes and ships. The present embodiment may include steps S100 to S400 as follows:
s100, obtaining a predicted motion trail and a real motion trail of an obstacle encountered by the vehicle in the running process.
In this embodiment, the obstacle may include a traffic participant such as a vehicle, a pedestrian, a bicycle, etc., a traffic street lamp, a static building, etc. The predicted motion trail may predict a motion trail of the obstacle during traveling through a prediction algorithm. For example, parameters such as the position, speed, and appearance of an external obstacle are sensed by a sensor of the vehicle. The prediction algorithm then uses these parameters to construct the motion profile of the obstacle. The real motion trail refers to the real trail of the obstacle motion in the driving environment, and the real motion trail of each obstacle can be constructed by acquiring GPS positioning data of each obstacle through a GPS system.
And S200, calculating the accuracy and/or recall rate of the predicted motion trail according to the acquired predicted motion trail and the actual motion trail.
The accuracy rate indicates the accuracy degree of the predicted motion trail relative to all the predicted motion trail, and the recall rate indicates the accuracy degree of the predicted motion trail relative to all the real motion trail. In this embodiment, the predicted motion trajectory and the actual motion trajectory predicted do not necessarily coincide. For example, there are 12 motion trajectories predicted during running of the vehicle, whereas there are only 10 motion trajectories actually determined by the GPS system. Then the recall may be described for the probability that a more accurate trajectory is predicted to be determined relative to the true motion trajectory.
S300, adjusting the driving decision of the vehicle according to the accuracy and/or recall rate.
In some embodiments, the accuracy may be utilized to adjust the error range of the algorithm for deciding the driving decisions of the vehicle, and improve the rationality of the driving decisions.
Specifically, if the accuracy of the predicted motion trajectory is greater than the set accuracy threshold, the error range of the driving decision of the vehicle is widened. And if the accuracy of the predicted motion trail is smaller than the set accuracy threshold, tightening the error range of the driving decision of the vehicle.
For example, assuming an accuracy threshold of 95% and if the accuracy of the predictive algorithm is 98%, it is indicated that the traffic participant is traveling substantially along the predicted trajectory with little error, the error range of the driving decision may not be adjusted or relaxed. For example, the original error range is ±2%, and the error range is adjusted to ±5% after being relaxed. So that the selectivity of driving decision can be larger. If the accuracy of the prediction algorithm is 93%, the fact that the track error of the traffic participant in running is large is indicated, and the host vehicle can tighten or correct the prediction algorithm to avoid accidents so as to improve the safety of driving decisions.
In some embodiments, accuracy or recall may be utilized to determine whether the predictive algorithm requires modification. And then predicting the motion trail again by using the corrected prediction algorithm, and adjusting the driving decision of the vehicle by using the newly predicted motion trail.
Specifically, if the recall rate of the predicted motion trail is greater than the accuracy rate, correcting the prediction algorithm for predicting the motion trail, and determining the driving decision of the vehicle by combining the motion trail predicted by the corrected prediction algorithm.
Illustratively, if the recall rate of the prediction algorithm is 90%, but the accuracy rate is 80%, at this time, the number of predicted motion trajectories is higher than the number of real motion trajectories, and the accuracy rate is lower than the accuracy rate threshold value by 95%. If the driving decision is carried out by continuing to use the current data, the safety accident can be caused. Therefore, the prediction algorithm is modified in order to improve the accuracy and safety of the subsequent decisions. And then the new prediction algorithm predicts the motion trail of the obstacle again, and makes a driving decision by using the new predicted motion trail.
In some embodiments, referring to fig. 2, the process of calculating the accuracy rate and the recall rate in step S200 may include steps S210 to S230 as follows:
s210, for each predicted motion trail, respectively counting the distance difference between the predicted motion trail and the corresponding real motion trail at the moment according to a plurality of set moment.
S220, determining whether the predicted motion trail is predicted accurately according to the distance differences of the plurality of time points.
S230, calculating the accuracy and/or recall rate of the predicted motion trail according to the predicted result of each predicted motion trail, the number of the obtained predicted motion trail and the number of the obtained real motion trail.
For example, the distance differences between the predicted motion trajectories and the corresponding real motion trajectories at the respective time points of the 1 st second, the 4 th second, and the 9 th second may be calculated. For example: the distance difference at 1 st second was 1.8m, the distance difference at 4 th second was 1.4m, and the distance difference at 9 th second was 1.7m. If the distance difference is less than 1.5m, the prediction of the predicted trajectory is considered accurate. If the distance difference is greater than or equal to 1.5m, the prediction of the predicted trajectory is considered inaccurate. The number of distance differences of more than or equal to 1.5m at a plurality of moments of the predicted motion trajectory can be counted. If the number is greater than the set threshold, the predicted motion trajectory may be considered accurate. If the number is less than the set threshold, this predicted motion trajectory may be considered to be mispredicted.
In some embodiments, the accuracy and recall of the motion trail of the type can be calculated according to the type of the obstacle, and then the driving decision of the vehicle can be adjusted according to the accuracy and recall of the type of the prediction algorithm. For example, the classification adjustment prediction algorithm re-predicts the motion trail of the obstacle of the corresponding classification, and then makes a driving decision by using the new predicted motion trail of the obstacle of each classification.
For example, the movement trajectories are classified by pedestrians, vehicles, and bicycles, respectively. Then, the accuracy and recall rate of predicting the motion trail of the pedestrian, the accuracy and recall rate of predicting the motion trail of the motor vehicle, and the accuracy and recall rate of predicting the motion trail of the bicycle are calculated, respectively. And then, according to the accuracy and recall rate determined by the three categories, respectively adjusting the predicted motion trail according to the respective requirements, and then, carrying out driving decision.
In some embodiments, referring to fig. 3, in the above step S230, calculating the accuracy and recall of the predicted motion trajectory may include steps S232 to S236 as follows:
s232, counting the number of accurate prediction results according to the prediction results of each prediction motion trail.
S234, the ratio of the number of accurate prediction results to the number of the obtained prediction motion tracks is used as the accuracy of the prediction motion tracks.
S236, taking the ratio of the number of accurate prediction results to the number of the obtained real motion tracks as the recall rate of the prediction motion tracks.
For example, if there are 10 real trajectories during this driving, 12 predicted motion trajectories are predicted by a prediction algorithm. If 6 predicted motion trajectories exist in the 12 predicted trajectories through the judgment of the above embodiment, the predicted motion trajectories are considered to be accurate, the accuracy is 6 divided by 12 and equal to 50%, and the recall is 6 divided by 10 and equal to 60%.
Referring to fig. 4, an embodiment of the present invention provides a prediction apparatus for driving decision, including:
the track acquisition module 100 is used for acquiring a predicted motion track and a real motion track of an obstacle encountered by the vehicle in the driving process;
the calculation module 200 is configured to calculate an accuracy rate and/or a recall rate of the predicted motion trail according to the obtained predicted motion trail and the actual motion trail; and
and the driving decision adjustment module 300 is configured to adjust a driving decision of the vehicle according to the accuracy rate and/or the recall rate.
In one embodiment, the computing module 200 includes:
the distance difference statistics unit is used for respectively counting the distance difference between each predicted motion track and the corresponding real motion track at a plurality of set time points according to each predicted motion track;
the prediction result determining unit is used for determining whether the prediction motion trail is accurate according to the distance differences of the plurality of time points; and
the accuracy rate recall rate calculation unit is used for calculating the accuracy rate and/or recall rate of the predicted motion trail according to the predicted result of each predicted motion trail, the number of the obtained predicted motion trail and the number of the obtained real motion trail.
In one embodiment, the accuracy recall calculation unit includes:
the quantity counting subunit is used for counting the quantity of accurate prediction results according to the prediction results of each prediction motion trail;
the accuracy rate calculating subunit is used for taking the ratio of the number of the accurate prediction results to the number of the obtained prediction motion tracks as the accuracy rate of the prediction motion tracks; and/or
And the recall rate calculating subunit is used for taking the ratio of the number of the accurate prediction results to the number of the obtained real motion tracks as the recall rate of the prediction motion tracks.
In one embodiment, the driving decision adjustment module 300 includes:
an error widening unit, configured to, if the accuracy is greater than a set accuracy threshold, widen an error range of a driving decision of the vehicle;
the error tightening unit is used for tightening the error range of the driving decision of the vehicle if the accuracy is smaller than a set accuracy threshold; or (b)
And the decision determining unit is used for correcting the prediction algorithm if the recall rate is larger than the accuracy rate and determining the driving decision of the vehicle by combining the motion trail predicted by the corrected prediction algorithm.
The functions of the device can be realized by hardware, and also can be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above.
In one possible design, the prediction structure of the driving decision includes a processor and a memory, where the prediction device for the driving decision executes the prediction program of the driving decision in the first aspect, and the processor is configured to execute the program stored in the memory. The prediction device of the driving decision may further comprise a communication interface, and the prediction device for the driving decision is in communication with other devices or a communication network.
The embodiment of the invention also provides a prediction terminal device for driving decision, as shown in fig. 5, the device comprises: memory 21 and processor 22, and memory 21 stores a computer program that is executable on processor 22. The processor 22 implements the prediction method of driving decisions in the above embodiment when executing a computer program. The number of memories 21 and processors 22 may be one or more.
The apparatus further comprises:
a communication interface 23 for communication between the processor 22 and an external device.
The memory 21 may include a high-speed RAM memory or may further include a non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 21, the processor 22 and the communication interface 23 are implemented independently, the memory 21, the processor 22 and the communication interface 23 may be connected to each other and perform communication with each other through a bus. The bus may be an industry standard architecture (ISA, industry Standard Architecture) bus, a peripheral component interconnect (PCI, peripheral Component) bus, or an extended industry standard architecture (EISA, extended Industry Standard Component) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 21, the processor 22 and the communication interface 23 are integrated on a chip, the memory 21, the processor 22 and the communication interface 23 may communicate with each other through internal interfaces.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
The computer readable medium of the embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the two. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include at least the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
In an embodiment of the invention, the computer readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with computer readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, input method, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, radio Frequency (RF), and the like, or any suitable combination of the foregoing.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or part of the steps carried out in the method of the above-described embodiments are programs that can be implemented by means of a program to instruct related hardware, and the programs can be stored in a computer readable storage medium, and the programs, when executed, include one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product. The storage medium may be a read-only memory, a magnetic disk or optical disk, etc.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that various modifications and substitutions are possible within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The prediction method for the driving decision is characterized by comprising the following steps of:
the method comprises the steps of obtaining a predicted motion trail and a real motion trail of an obstacle encountered by a vehicle in the running process, wherein the position, the speed and the appearance shape parameters of the obstacle outside are sensed through a sensor of the vehicle, the prediction algorithm utilizes the parameters to construct the motion trail of the obstacle, the real motion trail refers to the real motion trail of the obstacle in the running environment, and the GPS positioning data of each obstacle is obtained through a GPS system to construct the real motion trail of each obstacle;
calculating the accuracy and/or recall rate of the predicted motion trail according to the obtained predicted motion trail and the actual motion trail, wherein the accuracy represents the accuracy of the predicted motion trail relative to all the predicted motion trail, and the recall rate represents the accuracy of the predicted motion trail relative to all the actual motion trail; and
and adjusting the error range of a driving decision algorithm of the vehicle according to the accuracy rate and/or the recall rate.
2. The method of claim 1, wherein the calculating predicts an accuracy and/or recall of the predicted motion profile, comprising:
aiming at each predicted motion track, respectively counting the distance difference between the predicted motion track and the corresponding real motion track at a plurality of set time points;
determining whether the predicted motion trail is predicted accurately according to the distance differences of the plurality of time points; and
and calculating the accuracy and/or recall rate of the predicted motion trail according to the predicted result of each predicted motion trail, the number of the obtained predicted motion trail and the number of the obtained real motion trail.
3. The method of claim 2, wherein the calculating the accuracy and/or recall of the predicted motion profile comprises:
counting the number of accurate prediction results according to the prediction results of each prediction motion trail;
taking the ratio of the number of the accurate prediction results to the number of the obtained prediction motion tracks as the accuracy of the prediction motion tracks; and/or
And taking the ratio of the number of the accurate prediction results to the number of the obtained real motion trail as the recall rate of the prediction motion trail.
4. The method of claim 1, wherein said adjusting the error range of the vehicle's driving decision algorithm comprises:
if the accuracy is greater than a set accuracy threshold, the error range of the driving decision of the vehicle is widened;
if the accuracy is smaller than a set accuracy threshold, tightening an error range of a driving decision of the vehicle; or (b)
And if the recall rate is larger than the accuracy rate, correcting a prediction algorithm for predicting the predicted motion trail, and determining the driving decision of the vehicle by combining the motion trail predicted by the corrected prediction algorithm.
5. A prediction device for driving decisions, comprising:
the track acquisition module is used for acquiring a predicted motion track and a real motion track of an obstacle encountered by a vehicle in the running process, wherein the position, the speed and the appearance shape parameters of the obstacle outside are sensed through a sensor of the vehicle, the prediction algorithm utilizes the parameters to construct the motion track of the obstacle, the real motion track refers to the real track of the obstacle motion in the running environment, and the GPS positioning data of each obstacle is acquired through a GPS system to construct the real motion track of each obstacle;
the calculation module is used for calculating the accuracy and/or recall rate of the predicted motion trail according to the obtained predicted motion trail and the actual motion trail, wherein the accuracy represents the accuracy of the predicted motion trail relative to all the predicted motion trail, and the recall rate represents the accuracy of the predicted motion trail relative to all the actual motion trail; and
and the driving decision adjustment module is used for adjusting the error range of the driving decision algorithm of the vehicle according to the accuracy rate and/or the recall rate.
6. The apparatus of claim 5, wherein the computing module comprises:
the distance difference statistics unit is used for respectively counting the distance difference between each predicted motion track and the corresponding real motion track at a plurality of set time points according to each predicted motion track;
the prediction result determining unit is used for determining whether the prediction motion trail is accurate according to the distance differences of the plurality of time points; and
the accuracy rate recall rate calculation unit is used for calculating the accuracy rate and/or recall rate of the predicted motion trail according to the predicted result of each predicted motion trail, the number of the obtained predicted motion trail and the number of the obtained real motion trail.
7. The apparatus of claim 6, wherein the accuracy recall calculation unit comprises:
the quantity counting subunit is used for counting the quantity of accurate prediction results according to the prediction results of each prediction motion trail;
the accuracy rate calculating subunit is used for taking the ratio of the number of the accurate prediction results to the number of the obtained prediction motion tracks as the accuracy rate of the prediction motion tracks; and/or
And the recall rate calculating subunit is used for taking the ratio of the number of the accurate prediction results to the number of the obtained real motion tracks as the recall rate of the prediction motion tracks.
8. The apparatus of claim 5, wherein the driving decision adjustment module comprises:
an error widening unit, configured to, if the accuracy is greater than a set accuracy threshold, widen an error range of a driving decision of the vehicle;
the error tightening unit is used for tightening the error range of the driving decision of the vehicle if the accuracy is smaller than a set accuracy threshold; or (b)
And the decision determining unit is used for correcting a prediction algorithm for predicting the predicted motion trail if the recall rate is larger than the accuracy rate, and determining the driving decision of the vehicle by combining the motion trail predicted by the corrected prediction algorithm.
9. A prediction terminal device for implementing driving decisions, wherein the terminal device comprises:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-4.
10. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910140320.XA CN109885943B (en) | 2019-02-26 | 2019-02-26 | Prediction method and device for driving decision, storage medium and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910140320.XA CN109885943B (en) | 2019-02-26 | 2019-02-26 | Prediction method and device for driving decision, storage medium and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109885943A CN109885943A (en) | 2019-06-14 |
| CN109885943B true CN109885943B (en) | 2023-05-16 |
Family
ID=66929277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910140320.XA Active CN109885943B (en) | 2019-02-26 | 2019-02-26 | Prediction method and device for driving decision, storage medium and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109885943B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444438B (en) * | 2020-03-24 | 2023-09-01 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for determining quasi-recall rate of recall strategy |
| CN112017171B (en) * | 2020-08-27 | 2021-10-26 | 四川云从天府人工智能科技有限公司 | Image processing index evaluation method, system, equipment and medium |
| CN115071703B (en) * | 2022-06-16 | 2025-08-19 | 阿波罗智能技术(北京)有限公司 | Cross-track intention prediction method and device, electronic equipment and automatic driving automobile |
| CN115507867B (en) * | 2022-08-16 | 2025-08-01 | 福思(杭州)智能科技有限公司 | Target track prediction method, device, electronic device and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4062353B1 (en) * | 2006-11-10 | 2008-03-19 | トヨタ自動車株式会社 | Obstacle course prediction method, apparatus, and program |
| US9878710B2 (en) * | 2015-05-04 | 2018-01-30 | Honda Research Institute Europe Gmbh | Method for improving performance of a method for computationally predicting a future state of a target object, driver assistance system, vehicle including such driver assistance system and respective program storage medium and program |
| CN106203667B (en) * | 2015-05-06 | 2019-12-10 | 北京千方信息科技集团有限公司 | bus arrival information evaluation method and device |
| CN106020203B (en) * | 2016-07-15 | 2020-09-29 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling unmanned vehicle |
| US10324469B2 (en) * | 2017-03-28 | 2019-06-18 | Mitsubishi Electric Research Laboratories, Inc. | System and method for controlling motion of vehicle in shared environment |
| JP6419242B2 (en) * | 2017-03-28 | 2018-11-07 | 康二 蓮井 | Moving distance measuring device, moving distance measuring method, and moving distance measuring program |
| JP6558393B2 (en) * | 2017-04-06 | 2019-08-14 | トヨタ自動車株式会社 | Course setting device and course setting method |
| CN109164785B (en) * | 2018-08-24 | 2019-08-30 | 百度在线网络技术（北京）有限公司 | Emulation test method, device, equipment and the storage medium of automatic driving vehicle |
-
2019
- 2019-02-26 CN CN201910140320.XA patent/CN109885943B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 张金旺 ; 章永进 ; 徐友春 ; .基于概率统计的车辆运动轨迹预测方法.军事交通学院学报.2017,(第08期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109885943A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
| CN109885943B (en) | Prediction method and device for driving decision, storage medium and terminal equipment | |
| CN113267199B (en) | Method and device for planning driving track | |
| CN113297881B (en) | Target detection method and related device | |
| CN111469847B (en) | A method and system for lane change path planning | |
| EP3608635A1 (en) | Positioning system | |
| CN112550285B (en) | Method and device for determining collision distance, storage medium and electronic equipment | |
| AU2024200010B2 (en) | Vehicle Safety Control Method And Apparatus, Electronic Device, And Storage Medium | |
| CN114120684A (en) | Vehicle driving assistance system, method and corresponding readable storage medium | |
| CN113386738A (en) | Risk early warning system, method and storage medium | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| JP5682302B2 (en) | Traveling road estimation device, method and program | |
| JP7120170B2 (en) | Lane estimation device | |
| CN109849934B (en) | Track processing method and device, storage medium and terminal equipment | |
| US12024177B2 (en) | Sensor abnormality estimation device | |
| EP4209854B1 (en) | Overtaking planning method and apparatus, and storage medium | |
| CN118907122A (en) | Control method, device, vehicle and medium for speed curve re-planning | |
| CN115465295B (en) | Method and device for predicting future track of intersection vehicle, vehicle and storage medium | |
| CN116985801A (en) | Method and device for controlling vehicle speed of vehicle in self-adaptive cruising curve | |
| CN117104128A (en) | Steering lamp control method and device, vehicle controller, vehicle and storage medium | |
| US11816903B2 (en) | Method for determining a type of parking space | |
| KR20180058436A (en) | Apparatus and method for classifying object | |
| JP7294978B2 (en) | Traveling direction estimation device and object tracking device | |
| KR20240000952A (en) | Method and device for identifying an object | |
| JP6173714B2 (en) | In-vehicle device, position correction method thereof, and position correction program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |