CN112373485A - Decision planning method for automatic driving vehicle considering interactive game - Google Patents

Decision planning method for automatic driving vehicle considering interactive game Download PDF

Info

Publication number
CN112373485A
CN112373485A CN202011209224.5A CN202011209224A CN112373485A CN 112373485 A CN112373485 A CN 112373485A CN 202011209224 A CN202011209224 A CN 202011209224A CN 112373485 A CN112373485 A CN 112373485A
Authority
CN
China
Prior art keywords
vehicle
surrounding
surrounding vehicles
game
vehicles
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.)
Pending
Application number
CN202011209224.5A
Other languages
Chinese (zh)
Inventor
徐灿
赵万忠
李琳
刘津强
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.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
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 Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202011209224.5A priority Critical patent/CN112373485A/en
Publication of CN112373485A publication Critical patent/CN112373485A/en
Pending 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
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/10—Path keeping
    • 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
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • 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
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B60W2050/0031—Mathematical model of the vehicle

Abstract

The invention discloses an automatic driving vehicle decision planning method considering interactive game, which comprises the following steps: acquiring relative position and relative speed information of surrounding vehicles in real time; local track prediction is carried out on surrounding vehicles based on a vehicle kinematic model; establishing an interactive game model of the self vehicle and surrounding vehicles by a Nash game method; determining joint optimal driving behaviors by using a disadvantage elimination strategy and a Nash equilibrium method; and planning a corresponding track according to the determined optimal driving behavior of the self-vehicle, and outputting the corresponding track to a control execution module of the vehicle. According to the invention, after the motion information of the surrounding vehicles is acquired by the sensors, the motion of the surrounding vehicles is predicted by utilizing the vehicle kinematics model, and the interactive game with the surrounding vehicles is fully considered.

Description

Decision planning method for automatic driving vehicle considering interactive game
Technical Field
The invention belongs to the technical field of vehicle active safety, and particularly relates to an automatic driving vehicle decision planning method considering interactive game.
Background
In recent years, traffic accidents, traffic jams and other problems are troubling people to go out, and therefore, companies such as hundredths and Huayi in China research the automatic driving technology of vehicles to solve the problems encountered by the existing human drivers to go out. Autonomous taxis have been pushed in the sand, for example, hundreds of degrees, to speed the process of landing autonomous vehicles. However, when the automatic driving vehicle runs on a complex traffic road with human drivers, it is still difficult to realize good interactive cooperation, so that the automatic driving system is not agile and flexible enough.
The interactive game of the automatically driven vehicle and the surrounding vehicles mainly exists in the working conditions of lane changing and overtaking of the surrounding vehicles, vehicle gathering and lane merging, turning at intersections and the like. Under the working conditions, the driving track of the self vehicle collides with surrounding vehicles, and existing research mainly aims to ensure the safety of the vehicle and adopts a conservative method to avoid the surrounding vehicles, but the running efficiency of the self vehicle is sacrificed in the process, and meanwhile, the normal running of the rear vehicle is influenced because the running of the self vehicle is conservative. Therefore, a decision planning method capable of taking the interactive game between the automatic driving vehicle and the surrounding vehicles into consideration is needed at present, so that the automatic driving can keep safe and efficient driving in a multi-vehicle traffic environment, and the passing efficiency of the whole traffic system is improved by cooperating with the surrounding vehicles.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide an automatic driving vehicle decision planning method considering interactive game so as to solve the problem that the driving style is too conservative and the vehicle-vehicle interaction is rarely considered in the prior art; according to the method, after the motion information of the surrounding vehicles is acquired through the sensors, the motion of the surrounding vehicles is predicted by utilizing the vehicle kinematic model, the interactive game with the surrounding vehicles is fully considered, and the optimal driving behavior of the self vehicle is further obtained.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention discloses an automatic driving vehicle decision planning method considering interactive game, which comprises the following steps:
1) acquiring relative position and relative speed information of surrounding vehicles in real time;
2) local track prediction is carried out on surrounding vehicles based on a vehicle kinematic model;
3) establishing an interactive game model of the self vehicle and surrounding vehicles by a Nash game method;
4) determining joint optimal driving behaviors by using a disadvantage elimination strategy and a Nash equilibrium method;
5) and planning a corresponding track according to the determined optimal driving behavior of the self-vehicle, and outputting the corresponding track to a control execution module of the vehicle.
Further, the local trajectory prediction of the surrounding vehicle based on the kinematic model in the step 2) specifically includes:
21) the kinematic equation for the acceleration of the vehicle to the vehicle state is established as follows:
Figure BDA0002758104730000021
in the formula (I), the compound is shown in the specification,
Figure BDA0002758104730000022
respectively corresponding tangential acceleration and normal acceleration of the vehicle;
Figure BDA0002758104730000023
the vehicle state is respectively longitudinal position, lateral position, speed and yaw angle information;
22) establishing constraints corresponding to the predicted track at the current time t and the final time t + Np;
at the current time t, the surrounding vehicle motion information perceived by the vehicle comprises:
Figure BDA0002758104730000024
wherein, Δ st,ΔltThe relative longitudinal position and the relative transverse position of the surrounding vehicle and the self vehicle are respectively;
Figure BDA0002758104730000025
the corresponding speed and acceleration of the surrounding vehicle respectively;
Figure BDA0002758104730000026
for surrounding vehiclesA relative yaw rate to the host vehicle;
Figure BDA0002758104730000027
respectively the yaw angular velocity and the yaw angular acceleration of the surrounding vehicles;
the motion information of the surrounding vehicle at the current time t is expressed as follows:
Figure BDA0002758104730000028
wherein the content of the first and second substances,
Figure BDA0002758104730000029
respectively the longitudinal and transverse positions of the surrounding vehicle,
Figure BDA00027581047300000210
as is the yaw angle of the surrounding vehicle,
Figure BDA00027581047300000211
tangential and normal accelerations of the surrounding vehicle, respectively;
for the final time t + Np of the predicted trajectory, the corresponding lateral velocity and acceleration will be 0, with the following specific constraints:
Figure BDA00027581047300000212
wherein the content of the first and second substances,
Figure BDA00027581047300000213
the lateral speed corresponding to the peripheral vehicle at the final moment of the predicted track is obtained;
23) for the lateral position of the vehicle, there are 5 constraints at the current time t and the final time t + Np, fitting with a 4 th order polynomial as follows:
Figure BDA0002758104730000031
wherein, aiFitting parameters of the lateral track are represented by i, wherein i is 0-4;
for the longitudinal position, a 3 rd order polynomial is fitted according to the 4 constraints at the current time t and the final time t + Np as follows:
Figure BDA0002758104730000032
wherein, bjFitting parameters of the longitudinal track, wherein j is 0-3;
therefore, a local track corresponding to the surrounding vehicle in a future time domain [ t, t + Np ] is obtained.
Further, the step 3) specifically includes:
31) when a vehicle exists around the self vehicle, the game vehicle is the vehicle existing in the self vehicle; when a plurality of vehicles exist around, if interactive games are considered at the same time, the calculated amount is too large when the optimal driving behavior is solved, and the vehicle with the largest risk degree around is selected as a game vehicle;
32) when the own vehicle and the surrounding vehicles make decisions at each moment, the driving behaviors of accelerating, decelerating or changing lanes are executed, and the action sets A and B of the own vehicle and the surrounding vehicles are as follows:
A＝{A1,A2,A3,A4,A5}；B＝{B1,B2,B3,B4,B5}
in the formula, A1,A2,A3,A4,A5Respectively performing acceleration, left lane changing, deceleration, right lane changing and motion maintaining behaviors of the bicycle; b is1,B2,B3,B4,B5Acceleration, left lane change, deceleration, right lane change and motion maintenance behaviors of surrounding vehicles are respectively performed;
bicycle A5The track corresponding to the action is the track predicted in the step 2), and the corresponding target end point is as follows: a. the5＝(st+Np,lt+Np) To maintain the motion A in motion5As a reference, a left lane and a right lane A are obtained2,A4The end points of the corresponding local trajectories are as follows:
Figure BDA0002758104730000033
in the formula IupAnd ldownThe lateral positions of the central lines of the two adjacent lanes corresponding to the surrounding vehicles are respectively obtained through lane line recognition sensors;
corresponding acceleration action A1And a deceleration action A3Is in the lateral position of5And the longitudinal position is obtained according to the acceleration and deceleration performance of the vehicle, and the longitudinal position is specifically as follows:
Figure BDA0002758104730000041
where Np is the local trajectory planning time domain, aeIs the corresponding maximum acceleration of the vehicle during normal running, deThe maximum deceleration corresponding to the normal running of the vehicle;
the candidate terminal corresponding to each action of the surrounding vehicles is obtained by the method, so that an interactive game model of the vehicle and the surrounding vehicles is obtained;
33) and obtaining profits of the two vehicles taking corresponding actions through corresponding benefit functions according to the action sets corresponding to the two game vehicles and the corresponding local track terminal points, and establishing a corresponding game matrix G.
Further, the step 4) specifically includes:
41) for the game matrix G obtained in the step 33), a low-dimensionality game matrix is obtained or the optimal driving behaviors of two game vehicles are directly obtained by removing the disadvantage strategy;
42) for a low-dimensional game matrix, a corresponding Nash equilibrium solution is obtained through a Lemke-Howson (Nash equilibrium solving algorithm) algorithm, specifically, the probability that two vehicles take corresponding actions is as follows:
Figure BDA0002758104730000042
in the formula, PeSelecting probability of each action, P, for the vehiclesSelecting the probability of each action for surrounding vehicles;
obtaining the optimal driving behavior A obtained after the interactive game of the vehicle and the surrounding vehicles according to the probability of each action*And B*The specific corresponding local track end points are as follows:
Figure BDA0002758104730000043
wherein k is 1 to 5.
Further, the step 5) specifically includes: according to the optimal driving behavior A of the self-vehicle*And planning a corresponding local track of the self-vehicle by using a polynomial fitting method, and inputting the local track into a control execution module of the vehicle to perform track tracking execution.
The invention has the beneficial effects that:
compared with the existing decision planning method, the interactive game process with surrounding vehicles is fully considered, the collaborative planning with the surrounding vehicles can be realized, and the traffic efficiency of the whole traffic system is ensured to be improved.
Drawings
FIG. 1 is a schematic diagram of the method of the present invention.
Fig. 2 is a schematic diagram of an interactive game model of a self vehicle and surrounding vehicles.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention.
Referring to fig. 1, the decision planning method for an automatic driving vehicle considering interactive game according to the present invention includes the following steps:
1) acquiring relative position and relative speed information of surrounding vehicles in real time;
11) the motion information of the vehicle and surrounding vehicles can be obtained through the vehicle-mounted GPS, the inertial measurement unit IMU, the laser radar, the millimeter wave radar and the camera.
2) The method comprises the following steps of predicting local tracks of surrounding vehicles based on a vehicle kinematic model, wherein the method specifically comprises the following steps:
21) the kinematic equation for the acceleration of the vehicle to the vehicle state is established as follows:
Figure BDA0002758104730000051
in the formula (I), the compound is shown in the specification,
Figure BDA0002758104730000052
respectively corresponding tangential acceleration and normal acceleration of the vehicle;
Figure BDA0002758104730000053
the vehicle state is respectively longitudinal position, lateral position, speed and yaw angle information;
22) establishing constraints corresponding to the predicted track at the current time t and the final time t + Np;
at the current time t, the surrounding vehicle motion information perceived by the vehicle comprises:
Figure BDA0002758104730000054
wherein, Δ st,ΔltThe relative longitudinal position and the relative transverse position of the surrounding vehicle and the self vehicle are respectively;
Figure BDA0002758104730000055
the corresponding speed and acceleration of the surrounding vehicle respectively;
Figure BDA0002758104730000056
the relative yaw velocity of the surrounding vehicle and the own vehicle;
Figure BDA0002758104730000057
respectively the yaw angular velocity and the yaw angular acceleration of the surrounding vehicles;
the motion information of the surrounding vehicle at the current time t is expressed as follows:
Figure BDA0002758104730000058
wherein the content of the first and second substances,
Figure BDA0002758104730000059
respectively the longitudinal and transverse positions of the surrounding vehicle,
Figure BDA00027581047300000510
as is the yaw angle of the surrounding vehicle,
Figure BDA00027581047300000511
tangential and normal accelerations of the surrounding vehicle, respectively;
for the final time t + Np of the predicted trajectory, the corresponding lateral velocity and acceleration will be 0, with the following specific constraints:
Figure BDA00027581047300000512
wherein the content of the first and second substances,
Figure BDA0002758104730000061
the lateral speed corresponding to the peripheral vehicle at the final moment of the predicted track is obtained;
23) for the lateral position of the vehicle, there are 5 constraints at the current time t and the final time t + Np, fitting with a 4 th order polynomial as follows:
Figure BDA0002758104730000062
wherein, aiFitting parameters of the lateral track are represented by i, wherein i is 0-4;
for the longitudinal position, a 3 rd order polynomial is fitted according to the 4 constraints at the current time t and the final time t + Np as follows:
Figure BDA0002758104730000063
wherein, bjFitting parameters of the longitudinal track, wherein j is 0-3;
therefore, a local track corresponding to the surrounding vehicle in a future time domain [ t, t + Np ] is obtained.
3) An interactive game model of the bicycle and surrounding vehicles is established through a Nash game method, as shown in FIG. 2, the specific steps are as follows:
31) when a vehicle exists around the self vehicle, the game vehicle is the vehicle existing in the self vehicle; when a plurality of vehicles exist around, if interactive games are considered at the same time, the calculated amount is too large when the optimal driving behavior is solved, and the vehicle with the largest risk degree around is selected as a game vehicle;
32) when the own vehicle and the surrounding vehicles make decisions at each moment, the driving behaviors of accelerating, decelerating or changing lanes are executed, and the action sets A and B of the own vehicle and the surrounding vehicles are as follows:
A＝{A1,A2,A3,A4,A5}；B＝{B1,B2,B3,B4,B5}
in the formula, A1,A2,A3,A4,A5Respectively performing acceleration, left lane changing, deceleration, right lane changing and motion maintaining behaviors of the bicycle; b is1,B2,B3,B4,B5Acceleration, left lane change, deceleration, right lane change and motion maintenance behaviors of surrounding vehicles are respectively performed;
bicycle A5The track corresponding to the action is the track predicted in the step 2), and the corresponding target end point is as follows: a. the5＝(st+Np,lt+Np) To maintain the motion A in motion5As a reference, a left lane and a right lane A are obtained2,A4The end points of the corresponding local trajectories are as follows:
Figure BDA0002758104730000071
in the formula IupAnd ldownThe lateral positions of the central lines of the two adjacent lanes corresponding to the surrounding vehicles are respectively obtained through lane line recognition sensors;
corresponding acceleration action A1And a deceleration action A3Is in the lateral position of5And the longitudinal position is obtained according to the acceleration and deceleration performance of the vehicle, and the longitudinal position is specifically as follows:
Figure BDA0002758104730000072
where Np is the local trajectory planning time domain, aeIs the corresponding maximum acceleration of the vehicle during normal running, deThe maximum deceleration corresponding to the normal running of the vehicle;
the candidate terminal corresponding to each action of the surrounding vehicles is obtained by the method, so that an interactive game model of the vehicle and the surrounding vehicles is obtained;
33) according to the action sets corresponding to the two game vehicles and the corresponding local track end points, profits of the two vehicles for taking corresponding actions are obtained through corresponding gain functions, and specifically, corresponding game matrixes G can be established according to safety, high efficiency, energy-saving type and other indexes corresponding to the local tracks.
4) Determining joint optimal driving behaviors by using a disadvantage elimination strategy and a Nash equilibrium method;
41) for the game matrix G obtained in the step 33), a low-dimensionality game matrix is obtained or the optimal driving behaviors of two game vehicles are directly obtained by removing the disadvantage strategy;
42) for a low-dimensional game matrix, a corresponding Nash equilibrium solution is obtained through a Lemke-Howson algorithm, specifically, the probability that two cars take corresponding actions is as follows:
Figure BDA0002758104730000073
in the formula, PeSelecting probability of each action, P, for the vehiclesSelecting the probability of each action for surrounding vehicles;
obtaining the optimal driving behavior A obtained after the interactive game of the vehicle and the surrounding vehicles according to the probability of each action*And B*The specific corresponding local track end points are as follows:
Figure BDA0002758104730000074
wherein k is 1 to 5.
5) According to the optimal driving behavior A of the self-vehicle*And (4) corresponding end point constraint, planning a corresponding local track of the self-vehicle by utilizing a polynomial fitting method, and inputting the local track into a control execution module of the vehicle to perform track tracking execution.
51) Specifically, the behavior A can be restricted according to the state of the vehicle corresponding to the current time t and the final time t + Np*Solving local trajectory equations(s) with determined position constraintst,lt)；
For lateral, at the end of the time the vehicle is stable, the corresponding lateral velocity and acceleration are both 0 and can be expressed as follows using a 4 th order polynomial:
Figure BDA0002758104730000081
wherein, cmFitting parameters of the planned lateral trajectory, wherein m is 0-4;
for the longitudinal direction, the velocity of the local trajectory at the final time is unknown, the acceleration is 0, and the following can be expressed by using a 3-degree polynomial:
Figure BDA0002758104730000082
wherein d isnFitting parameters of the planned lateral trajectory, wherein n is 0-3;
thereby obtaining the corresponding local track of the self-vehicle.
While the invention has been described in terms of its preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims (4)

1. An automatic driving vehicle decision planning method considering interactive game is characterized by comprising the following steps:
1) acquiring relative position and relative speed information of surrounding vehicles in real time;
2) local track prediction is carried out on surrounding vehicles based on a vehicle kinematic model;
3) establishing an interactive game model of the self vehicle and surrounding vehicles by a Nash game method;
4) determining joint optimal driving behaviors by using a disadvantage elimination strategy and a Nash equilibrium method;
5) and planning a corresponding track according to the determined optimal driving behavior of the self-vehicle.
2. The interactive game-based decision planning method for the automatic driving vehicle according to claim 1, wherein the predicting local trajectories of the surrounding vehicles based on the kinematic model in the step 2) specifically comprises:
21) the kinematic equation for the acceleration of the vehicle to the vehicle state is established as follows:
Figure FDA0002758104720000011
in the formula (I), the compound is shown in the specification,
Figure FDA0002758104720000012
respectively corresponding tangential acceleration and normal acceleration of the vehicle; st,lt,vt,
Figure FDA0002758104720000013
The vehicle state is respectively longitudinal position, lateral position, speed and yaw angle information;
22) establishing constraints corresponding to the predicted track at the current time t and the final time t + Np;
at the current time t, the surrounding vehicle motion information perceived by the vehicle comprises:
Figure FDA0002758104720000014
wherein, Δ st,ΔltThe relative longitudinal position and the relative transverse position of the surrounding vehicle and the self vehicle are respectively;
Figure FDA0002758104720000015
the corresponding speed and acceleration of the surrounding vehicle respectively;
Figure FDA0002758104720000016
the relative yaw velocity of the surrounding vehicle and the own vehicle;
Figure FDA0002758104720000017
respectively the yaw angular velocity and the yaw angular acceleration of the surrounding vehicles;
the motion information of the surrounding vehicle at the current time t is expressed as follows:
Figure FDA0002758104720000018
wherein the content of the first and second substances,
Figure FDA0002758104720000019
respectively the longitudinal and transverse positions of the surrounding vehicle,
Figure FDA00027581047200000110
as is the yaw angle of the surrounding vehicle,
Figure FDA00027581047200000111
tangential and normal accelerations of the surrounding vehicle, respectively;
for the final time t + Np of the predicted trajectory, the corresponding lateral velocity and acceleration will be 0, with the following specific constraints:
Figure FDA0002758104720000021
wherein the content of the first and second substances,
Figure FDA0002758104720000022
the lateral speed corresponding to the peripheral vehicle at the final moment of the predicted track is obtained;
23) for the lateral position of the vehicle, there are 5 constraints at the current time t and the final time t + Np, fitting with a 4 th order polynomial as follows:
Figure FDA0002758104720000023
wherein, aiFitting parameters of the lateral track are represented by i, wherein i is 0-4;
for the longitudinal position, a 3 rd order polynomial is fitted according to the 4 constraints at the current time t and the final time t + Np as follows:
Figure FDA0002758104720000024
in the formula, bjFitting parameters of the longitudinal track, wherein j is 0-3;
therefore, a local track corresponding to the surrounding vehicle in a future time domain [ t, t + Np ] is obtained.
3. The interactive game-based decision planning method for automated driving vehicles according to claim 1, wherein the step 3) specifically comprises:
31) when a vehicle exists around the self vehicle, the game vehicle is the vehicle existing in the self vehicle; when a plurality of vehicles exist around, if interactive games are considered at the same time, the calculated amount is too large when the optimal driving behavior is solved, and the vehicle with the largest risk degree around is selected as a game vehicle;
32) when the own vehicle and the surrounding vehicles make decisions at each moment, the driving behaviors of accelerating, decelerating or changing lanes are executed, and the action sets A and B of the own vehicle and the surrounding vehicles are as follows:
A＝{A1,A2,A3,A4,A5}；B＝{B1,B2,B3,B4,B5}
in the formula, A1,A2,A3,A4,A5Respectively performing acceleration, left lane changing, deceleration, right lane changing and motion maintaining behaviors of the bicycle; b is1,B2,B3,B4,B5Acceleration, left lane change, deceleration, right lane change and motion maintenance behaviors of surrounding vehicles are respectively performed;
bicycle A5The track corresponding to the action is the track predicted in the step 2), and the corresponding target end point is as follows:
Figure FDA0002758104720000035
with movement holding action A5As a reference, a left lane and a right lane A are obtained2,A4The end points of the corresponding local trajectories are as follows:
Figure FDA0002758104720000031
in the formula IupAnd ldownThe lateral positions of the central lines of the two adjacent lanes corresponding to the surrounding vehicles are respectively obtained through lane line recognition sensors;
corresponding acceleration action A1And a deceleration action A3Is in the lateral position of5And the longitudinal position is obtained according to the acceleration and deceleration performance of the vehicle, and the longitudinal position is specifically as follows:
Figure FDA0002758104720000032
where Np is the local trajectory planning time domain, aeIs the corresponding maximum acceleration of the vehicle during normal running, deThe maximum deceleration corresponding to the normal running of the vehicle;
obtaining candidate end points corresponding to all actions of surrounding vehicles by the method in the step 32), so as to obtain an interactive game model of the vehicle and the surrounding vehicles;
33) and obtaining profits of the two vehicles taking corresponding actions through corresponding benefit functions according to the action sets corresponding to the two game vehicles and the corresponding local track terminal points, and establishing a corresponding game matrix G.
4. The interactive game-based decision planning method for autonomous vehicles according to claim 3, wherein the step 4) comprises:
41) for the game matrix G obtained in the step 33), a low-dimensionality game matrix is obtained or the optimal driving behaviors of two game vehicles are directly obtained by removing the disadvantage strategy;
42) for a low-dimensional game matrix, a corresponding Nash equilibrium solution is obtained through a Lemke-Howson algorithm, specifically, the probability that two cars take corresponding actions is as follows:
Figure FDA0002758104720000033
in the formula, PeSelecting probability of each action, P, for the vehiclesSelecting the probability of each action for surrounding vehicles;
obtaining the optimal driving behavior A obtained after the interactive game of the vehicle and the surrounding vehicles according to the probability of each action*And B*The specific corresponding local track end points are as follows:
Figure FDA0002758104720000034
wherein k is 1 to 5.
CN202011209224.5A 2020-11-03 2020-11-03 Decision planning method for automatic driving vehicle considering interactive game Pending CN112373485A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011209224.5A CN112373485A (en) 2020-11-03 2020-11-03 Decision planning method for automatic driving vehicle considering interactive game

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011209224.5A CN112373485A (en) 2020-11-03 2020-11-03 Decision planning method for automatic driving vehicle considering interactive game

Publications (1)

Publication Number Publication Date
CN112373485A true CN112373485A (en) 2021-02-19

Family

ID=74577937

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011209224.5A Pending CN112373485A (en) 2020-11-03 2020-11-03 Decision planning method for automatic driving vehicle considering interactive game

Country Status (1)

Country Link
CN (1) CN112373485A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112874509A (en) * 2021-03-03 2021-06-01 知行汽车科技（苏州）有限公司 Intelligent driver model IDM-based trajectory planning method and device and storage medium
CN113076897A (en) * 2021-04-09 2021-07-06 广州机械科学研究院有限公司 Game dynamic driving safety measurement and control method and regulation and control terminal of intelligent networked automobile
CN113306558A (en) * 2021-07-30 2021-08-27 北京理工大学 Lane changing decision method and system based on lane changing interaction intention
CN113928338A (en) * 2021-10-08 2022-01-14 南京航空航天大学 Longitudinal and transverse coupling intelligent vehicle track planning method and system
CN113963535A (en) * 2021-09-30 2022-01-21 华为技术有限公司 Driving decision determination method and device and electronic equipment storage medium
CN114084155A (en) * 2021-11-15 2022-02-25 清华大学 Predictive intelligent automobile decision control method and device, vehicle and storage medium
CN114162144A (en) * 2022-01-06 2022-03-11 苏州挚途科技有限公司 Automatic driving decision method and device and electronic equipment
WO2022227827A1 (en) * 2021-04-26 2022-11-03 华为技术有限公司 Decision-making method and apparatus and vehicle
WO2022246802A1 (en) * 2021-05-28 2022-12-01 华为技术有限公司 Driving strategy determination method and apparatus, device, and vehicle
WO2023155041A1 (en) * 2022-02-15 2023-08-24 华为技术有限公司 Intelligent driving method, device, and vehicle comprising said device
WO2024036580A1 (en) * 2022-08-18 2024-02-22 华为技术有限公司 Movement path planning method and apparatus and intelligent driving device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110298131A (en) * 2019-07-05 2019-10-01 西南交通大学 Automatic Pilot lane-change decision model method for building up under a kind of mixing driving environment
WO2020079074A2 (en) * 2018-10-16 2020-04-23 Five AI Limited Autonomous vehicle planning
CN111267846A (en) * 2020-02-11 2020-06-12 南京航空航天大学 Game theory-based peripheral vehicle interaction behavior prediction method
CN111338335A (en) * 2019-12-31 2020-06-26 清华大学 Vehicle local track planning method under structured road scene

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020079074A2 (en) * 2018-10-16 2020-04-23 Five AI Limited Autonomous vehicle planning
CN110298131A (en) * 2019-07-05 2019-10-01 西南交通大学 Automatic Pilot lane-change decision model method for building up under a kind of mixing driving environment
CN111338335A (en) * 2019-12-31 2020-06-26 清华大学 Vehicle local track planning method under structured road scene
CN111267846A (en) * 2020-02-11 2020-06-12 南京航空航天大学 Game theory-based peripheral vehicle interaction behavior prediction method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CAN XU , WANZHONG ZHAO , LIN LI , QINGYUN CHEN, DENGMING KUANG,: "A Nash Q-Learning Based Motion Decision", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 *
邢德鑫等: "基于自适应容积粒子滤波的车辆状态估计", 《南京航空航天大学学报》 *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112874509A (en) * 2021-03-03 2021-06-01 知行汽车科技（苏州）有限公司 Intelligent driver model IDM-based trajectory planning method and device and storage medium
CN113076897A (en) * 2021-04-09 2021-07-06 广州机械科学研究院有限公司 Game dynamic driving safety measurement and control method and regulation and control terminal of intelligent networked automobile
WO2022227827A1 (en) * 2021-04-26 2022-11-03 华为技术有限公司 Decision-making method and apparatus and vehicle
WO2022246802A1 (en) * 2021-05-28 2022-12-01 华为技术有限公司 Driving strategy determination method and apparatus, device, and vehicle
CN113306558A (en) * 2021-07-30 2021-08-27 北京理工大学 Lane changing decision method and system based on lane changing interaction intention
CN113963535A (en) * 2021-09-30 2022-01-21 华为技术有限公司 Driving decision determination method and device and electronic equipment storage medium
CN113928338A (en) * 2021-10-08 2022-01-14 南京航空航天大学 Longitudinal and transverse coupling intelligent vehicle track planning method and system
CN114084155B (en) * 2021-11-15 2023-10-20 清华大学 Predictive intelligent automobile decision control method and device, automobile and storage medium
CN114084155A (en) * 2021-11-15 2022-02-25 清华大学 Predictive intelligent automobile decision control method and device, vehicle and storage medium
CN114162144A (en) * 2022-01-06 2022-03-11 苏州挚途科技有限公司 Automatic driving decision method and device and electronic equipment
CN114162144B (en) * 2022-01-06 2024-02-02 苏州挚途科技有限公司 Automatic driving decision method and device and electronic equipment
WO2023155041A1 (en) * 2022-02-15 2023-08-24 华为技术有限公司 Intelligent driving method, device, and vehicle comprising said device
WO2024036580A1 (en) * 2022-08-18 2024-02-22 华为技术有限公司 Movement path planning method and apparatus and intelligent driving device

Similar Documents

Publication Publication Date Title
CN112373485A (en) Decision planning method for automatic driving vehicle considering interactive game
CN109669461B (en) Decision-making system for automatically driving vehicle under complex working condition and track planning method thereof
CN109501799B (en) Dynamic path planning method under condition of Internet of vehicles
CN108256233B (en) Intelligent vehicle trajectory planning and tracking method and system based on driver style
CN107264531B (en) The autonomous lane-change of intelligent vehicle is overtaken other vehicles motion planning method in a kind of semi-structure environment
CN113291308B (en) Vehicle self-learning lane-changing decision-making system and method considering driving behavior characteristics
CN108919795B (en) Automatic driving automobile lane change decision method and device
CN111071249B (en) Unmanned vehicle emergency steering obstacle avoidance method based on obstacle motion prediction
US20190113919A1 (en) Controlling an autonomous vehicle using smart control architecture selection
EP4230964A1 (en) Navigation based on vehicle activity
CN102541061B (en) Micro intelligent vehicle based on visual and auditory information
CN110293970B (en) Driving control method and device for automatic driving automobile and automobile
CN111681452B (en) Unmanned vehicle dynamic lane change track planning method based on Frenet coordinate system
CN105857306A (en) Vehicle autonomous parking path programming method used for multiple parking scenes
CN112249008B (en) Unmanned automobile early warning method aiming at complex dynamic environment
CN112644486B (en) Intelligent vehicle obstacle avoidance trajectory planning method based on driving safety field
CN105151043A (en) Emergency avoidance system and method for unmanned automobile
CN111696339B (en) Car following control method and system for automatic driving fleet and car
CN110239547A (en) Controller of vehicle, control method for vehicle and storage medium
CN110239542A (en) Controller of vehicle, control method for vehicle and storage medium
CN110239546A (en) Controller of vehicle, control method for vehicle and storage medium
JP2016215790A (en) Lane change plan generating device, lane change plan generating method
CN110320916A (en) Consider the autonomous driving vehicle method for planning track and system of occupant's impression
CN115523934A (en) Vehicle track prediction method and system based on deep learning
CN111103882A (en) Autonomous following control method for unmanned electric vehicle

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210219

WD01 Invention patent application deemed withdrawn after publication