A vehicle behavior modeling method based on social forces
Through the vehicle behavior modeling method based on social forces, vehicle behavior is divided into free driving, follow-up driving and lane-changing modes, and the vehicle movement state is described using specific mechanical formulas, which solves the problem of large computing power consumption and low simulation accuracy in the existing technology. The problem of this problem realizes fast and efficient vehicle behavior modeling and simulation testing.
Patent Information
- Application Number
- CN202210458347.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-27
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-04-27
AI Technical Summary
The existing vehicle behavior modeling methods consume a lot of computing power in simulation tests, which is difficult to meet the needs of rapid testing, and the simulation accuracy is low, making it impossible to effectively evaluate the safety of autonomous vehicles in normal traffic environments.
Using a vehicle behavior modeling method based on social forces, the vehicle behavior is divided into three modes: free driving, follow-up driving and lane change. By separating longitudinal and transverse modules, specific mechanical formulas are used to describe the motion state of the vehicle in different modes. , including self-driving force, collision avoidance resistance, lane line retention force and damping force, to achieve more accurate vehicle behavior modeling.
This method reduces vehicle behavior model parameters, improves running speed, is suitable for large-scale simulation, can quickly obtain vehicle behavior models of different styles, and improves modeling accuracy through parameter optimization, and is suitable for intelligent driving vehicle simulation testing.
Smart Images

Figure CN114781064B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of vehicle behavior modeling, and in particular relates to a vehicle behavior modeling method based on social forces. Background Art
[0002] With the continuous development of computer technology, especially artificial intelligence technology, more and more new technologies are being introduced into the automotive field and used in the development of assisted driving or autonomous driving technology. However, due to the constraints of realistic conditions, conducting real vehicle tests to prove that the vehicle is safe and controllable is an economically and time-consuming solution. Therefore, more and more algorithm verification work requires a large number of simulation experiments before real vehicle tests can be carried out. In the process of simulating autonomous driving vehicles, one test method is to put the vehicle under test in a realistic traffic environment and record the frequency of traffic accidents, so as to evaluate whether it can ensure safety in a normal traffic environment.
[0003] In order to establish a realistic traffic environment, vehicle behavior modeling is of great importance. The current mainstream method is to use vehicle dynamics models and complex decision-making methods to establish vehicle behavior models, which requires a lot of computing power and is difficult to meet the needs of rapid testing. As a model originally used for behavior, the social force model has been used by some researchers for the behavior modeling of vehicles and non-motor vehicles. One of the advantages of the social force model is that it has low requirements for examples and does not require complex vehicle dynamics model geometry to complete the simulation of vehicle behavior, but the simulation accuracy is generally low. Therefore, the field of intelligent driving vehicle simulation testing needs a more accurate vehicle behavior modeling method based on social forces. Summary of the invention
[0004] The main purpose of the present invention is to provide a vehicle behavior modeling method based on social forces, which divides vehicle behavior into three behavior modes: free driving, following vehicle driving, and lane changing. In the free driving mode, the vehicle is subject to the self-driving force generated to achieve the optimal speed in the longitudinal direction; and is subject to the lane line holding force from the lane lines on both sides and the center line damping force from the center line of the lane in the lateral direction. In the following vehicle driving mode, a longitudinal collision avoidance resistance generated to avoid collision with the front vehicle is added on the basis of the free driving mode. In the lane changing mode, the lateral movement of the vehicle is divided into two stages, one is the stage of approaching the middle lane line, that is, the front lane changing stage, and the stage after crossing the middle lane line, that is, the rear lane changing stage. In the front lane changing stage, the vehicle travels in the free driving mode or the following vehicle mode in the longitudinal direction; and is subject to resistance from the middle lane line, attraction from the center line of the target lane, and attraction from the front and rear vehicles on the target lane in the lateral direction.
[0005] To achieve the above objectives, the present invention provides a vehicle behavior modeling method based on social forces, which is used for vehicle behavior modeling and includes the following steps:
[0006] Step S1: dividing the vehicle behavior into a lateral module and a longitudinal module, the lateral module includes a lane-changing mode and a non-lane-changing mode and the longitudinal module includes a free driving mode and a vehicle-following driving mode;
[0007] Step S1.1: In the free driving mode, the vehicle is subjected to a self-driving force generated to achieve an optimal speed in the longitudinal direction, and is subjected to a lane keeping force from lane lines on both sides and a centerline damping force from the centerline of the lane in the lateral direction;
[0008] Step S1.2: In the following driving mode, the vehicle is longitudinally subjected to the self-driving force generated to achieve the optimal speed and the (longitudinal) collision avoidance resistance generated to avoid collision with the vehicle ahead, and laterally subjected to the lane line holding force from the lane lines on both sides and the center line damping force from the center line of the lane;
[0009] Step S1.3: In the lane-changing mode, the lateral movement of the vehicle is divided into two stages, one is the front lane-changing stage approaching the middle lane line, and the other is the rear lane-changing stage after crossing the middle lane line. In the front lane-changing stage, the vehicle travels longitudinally in a free driving mode or a following mode, and the vehicle is laterally subjected to resistance from the middle lane line, attraction from the center line of the target lane, and attraction from the front and rear vehicles in the target lane.
[0010] As a further preferred technical solution of the above technical solution, in step S1.1, in the free driving mode, the self-driving force formula generated by the vehicle to achieve the optimal driving speed is:
[0011]
[0012] In the formula, represents the self-driving force of vehicle i, is the optimal driving speed, m i is the mass of vehicle i, is the current longitudinal velocity of vehicle i, is the longitudinal driving reaction time of vehicle i, x represents the longitudinal direction, t represents the time, is a unit vector pointing in the longitudinal direction of the vehicle.
[0013] As a further preferred technical solution of the above technical solution, in step S1.2, in the following driving mode, there is another vehicle j in front of the vehicle, and the vehicle j in front of the same lane line will generate longitudinal collision avoidance resistance to vehicle i, and the formula is:
[0014]
[0015] In the formula, is the longitudinal collision avoidance force that vehicle j will generate on vehicle i, m iis the mass of vehicle i, is the gain coefficient, is the headway between vehicle i and vehicle j, that is, the distance between the head of vehicle j and the parking space of vehicle i, is the sensitivity coefficient, e represents the exponential function, is the unit vector of vehicle j and vehicle i in the direction of the lane line;
[0016] The resultant force on the vehicle in the longitudinal direction is:
[0017]
[0018] As a further preferred technical solution of the above technical solution, in step S1.3, in the lane change driving mode, the force applied to the vehicle in the lateral direction includes the lane change resistance from the lane line l2 between the current lane l1 and the target lane. Attraction from the center line cl2 of the target lane The attraction force of the preceding vehicle in the target lane from the preceding vehicle k located longitudinally ahead and traveling in the target lane and the target lane rear vehicle attraction force from the rear vehicle h located longitudinally behind and traveling in the target lane The expressions are:
[0019]
[0020] In the formula, is the gain coefficient, is the distance between lane line l2 and the geometric center of vehicle i, is the sensitivity coefficient, is the unit vector pointing from lane line l2 to the geometric center of vehicle i, lc represents the lane change mode;
[0021]
[0022] In the formula, is the gain coefficient, is the distance between the target lane centerline cl2 and the geometric center of vehicle i, is the sensitivity coefficient, is the unit vector pointing from the geometric center of vehicle i to the center line of the target lane cl2;
[0023]
[0024] In the formula, is the gain coefficient, is the headway time between vehicle i and the vehicle k in front of the target lane in the direction of the lane line, is the sensitivity coefficient, is the unit vector from the geometric center of vehicle i to the center line lc2 of the target lane where vehicle k is located;
[0025]
[0026] In the formula, is the gain coefficient, is the headway time between the vehicle h and vehicle i in the target lane in the direction of the lane line, is the sensitivity coefficient, is the unit vector pointing from the geometric center of vehicle i to the center line of the target lane cl2;
[0027] Therefore, the lateral force on the vehicle in the lane-changing driving mode is:
[0028]
[0029] The switching condition between the free driving mode and the following driving mode is whether there is a vehicle j in front of the vehicle i.
[0030] As a further preferred technical solution of the above technical solution, the switching conditions between the lane changing mode and the non-lane changing mode include:
[0031] a. The longitudinal force after changing lanes exceeds a certain threshold value compared to the longitudinal force before changing lanes. (in is the threshold value);
[0032] b. There is no adjacent vehicle in the target lane. An adjacent vehicle refers to a vehicle traveling side by side with vehicle i.
[0033] c. The collision time ttc between the front vehicle k and the rear vehicle h in the target lane and vehicle i is less than a certain threshold ttc thre , the calculation formula of ttc is:
[0034]
[0035] In the formula, r x Indicates the distance between the front and rear vehicles. and are the longitudinal velocities of the rear and front vehicles, respectively.
[0036] As a further preferred technical solution of the above technical solution, in the free driving mode, the following driving mode or the later stage of the lane changing mode, the vehicle i is subjected to the lane keeping force from the lane lines on both sides of the current lane. and and the damping force from the center line lc of the lane in which vehicle i is traveling The expression is:
[0037]
[0038]
[0039] In the formula, represents the lane keeping force from the left lane line of the lane where vehicle i is traveling, represents the lane keeping force from the right lane line of the lane where vehicle i is traveling, and are gain coefficients and and are the lateral distances between the left and right lane lines of the lane where vehicle i is traveling and the geometric center of vehicle i, and are the unit vectors pointing from the left and right lane lines of the lane where vehicle i is traveling to the geometric center of vehicle i;
[0040]
[0041] Where c is the damping coefficient, is the lateral speed of vehicle i, cl represents the center line of the current lane;
[0042] In the later stage of free driving mode, following driving mode or lane changing mode, the longitudinal force acting on vehicle i is:
[0043]
[0044] The switching conditions for the early and late stages of the lane-changing mode are that the geometric center of vehicle i enters the target lane from the original lane.
[0045] To achieve the above objectives, the present invention also relates to an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the vehicle behavior modeling method based on social forces when executing the program.
[0046] To achieve the above objective, a non-transitory computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a vehicle behavior modeling method based on social forces.
[0047] The beneficial effects of the present invention are:
[0048] Compared with traditional methods, this method has fewer parameters for the vehicle behavior model obtained, faster operation speed, and is suitable for large-scale simulation. In addition, different styles of vehicle behavior models can be quickly obtained by modifying relevant parameters, which is easy to use. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 The present invention discloses a road scene diagram of a vehicle behavior modeling method based on social forces.
[0050] Figure 2 It is a parameter optimization trend diagram of a vehicle behavior modeling method based on social forces of the present invention.
[0051] Figure 3 It is a trajectory comparison diagram of a vehicle behavior modeling method based on social forces of the present invention. DETAILED DESCRIPTION
[0052] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.
[0053] In the preferred embodiment of the present invention, those skilled in the art should note that the vehicle and the like involved in the present invention may be regarded as prior art.
[0054] Preferred embodiments.
[0055] The present invention discloses a vehicle behavior modeling method based on social force, which is used for vehicle behavior modeling and includes the following steps:
[0056] Step S1: dividing the vehicle behavior into a lateral module and a longitudinal module, the lateral module includes a lane-changing mode and a non-lane-changing mode and the longitudinal module includes a free driving mode and a vehicle-following driving mode;
[0057] Step S1.1: In the free driving mode, the vehicle is subjected to a self-driving force generated to achieve an optimal speed in the longitudinal direction, and is subjected to a lane keeping force from lane lines on both sides and a centerline damping force from the centerline of the lane in the lateral direction;
[0058] Step S1.2: In the following driving mode, the vehicle is longitudinally subjected to the self-driving force generated to achieve the optimal speed and the (longitudinal) collision avoidance resistance generated to avoid collision with the vehicle ahead, and laterally subjected to the lane line holding force from the lane lines on both sides and the center line damping force from the center line of the lane;
[0059] Step S1.3: In the lane-changing mode, the lateral movement of the vehicle is divided into two stages, one is the front lane-changing stage approaching the middle lane line, and the other is the rear lane-changing stage after crossing the middle lane line. In the front lane-changing stage, the vehicle travels longitudinally in a free driving mode or a following mode, and the vehicle is laterally subjected to resistance from the middle lane line, attraction from the center line of the target lane, and attraction from the front and rear vehicles in the target lane.
[0060] Specifically, in step S1.1, in the free driving mode, the self-driving force formula generated by the vehicle to achieve the optimal driving speed is:
[0061]
[0062] In the formula, represents the self-driving force of vehicle i, is the optimal driving speed, m i is the mass of vehicle i, is the current longitudinal velocity of vehicle i, is the longitudinal driving reaction time of vehicle i, x represents the longitudinal direction, t represents the time, is a unit vector pointing in the longitudinal direction of the vehicle.
[0063] More specifically, in step S1.2, in the following driving mode, there is another vehicle j in front of the vehicle, and the vehicle j in front of the same lane line will generate longitudinal collision avoidance resistance to vehicle i, and the formula is:
[0064]
[0065] In the formula, is the longitudinal collision avoidance force that vehicle j will generate on vehicle i, m i is the mass of vehicle i, is the gain coefficient, is the headway between vehicle i and vehicle j, that is, the distance between the head of vehicle j and the parking space of vehicle i, is the sensitivity coefficient, e represents the exponential function, is the unit vector of vehicle j and vehicle i in the direction of the lane line;
[0066] The resultant force on the vehicle in the longitudinal direction is:
[0067]
[0068] Furthermore, in step S1.3, in the lane-changing driving mode, the lateral force on the vehicle includes the lane-changing resistance from the lane line l2 between the current lane l1 and the target lane. Attraction from the center line cl2 of the target lane The attraction force of the preceding vehicle in the target lane from the preceding vehicle k located longitudinally ahead and traveling in the target lane and the target lane rear vehicle attraction force from the rear vehicle h located longitudinally behind and traveling in the target lane The expressions are:
[0069]
[0070] In the formula, is the gain coefficient, is the distance between lane line l2 and the geometric center of vehicle i, is the sensitivity coefficient, is the unit vector pointing from lane line l2 to the geometric center of vehicle i, lc represents the lane change mode;
[0071]
[0072] In the formula, is the gain coefficient, is the distance between the target lane centerline cl2 and the geometric center of vehicle i, is the sensitivity coefficient, is the unit vector pointing from the geometric center of vehicle i to the center line of the target lane cl2;
[0073]
[0074] In the formula, is the gain coefficient, is the headway time between vehicle i and the vehicle k in front of the target lane in the direction of the lane line, is the sensitivity coefficient, is the unit vector from the geometric center of vehicle i to the center line lc2 of the target lane where vehicle k is located;
[0075]
[0076] In the formula, is the gain coefficient, is the headway time between the vehicle h and vehicle i in the target lane in the direction of the lane line, is the sensitivity coefficient, is the unit vector pointing from the geometric center of vehicle i to the center line of the target lane cl2;
[0077] Therefore, the lateral force on the vehicle in the lane-changing driving mode is:
[0078]
[0079] The switching condition between the free driving mode and the following driving mode is whether there is a vehicle j in front of the vehicle i.
[0080] Furthermore, the switching conditions between the lane changing mode and the non-lane changing mode include:
[0081] a. The longitudinal force after changing lanes exceeds a certain threshold value compared to the longitudinal force before changing lanes. (in is the threshold value);
[0082] b. There is no adjacent vehicle in the target lane. An adjacent vehicle refers to a vehicle traveling side by side with vehicle i.
[0083] c. The collision time ttc between the front vehicle k and the rear vehicle h in the target lane and vehicle i is less than a certain threshold ttc thre , the calculation formula of ttc is:
[0084]
[0085] In the formula, r x Indicates the distance between the front and rear vehicles. and are the longitudinal velocities of the rear and front vehicles, respectively.
[0086] Preferably, in the free driving mode, the following driving mode or the later stage of the lane changing mode, the vehicle i is subjected to the lane keeping force from the lane lines on both sides of the current lane. and and the damping force from the center line lc of the lane in which vehicle i is traveling The expression is:
[0087]
[0088]
[0089] In the formula, represents the lane keeping force from the left lane line of the lane where vehicle i is traveling, represents the lane keeping force from the right lane line of the lane where vehicle i is traveling, and are gain coefficients and and are the lateral distances between the left and right lane lines of the lane where vehicle i is traveling and the geometric center of vehicle i, and are the unit vectors pointing from the left and right lane lines of the lane where vehicle i is traveling to the geometric center of vehicle i;
[0090]
[0091] Where c is the damping coefficient, is the lateral speed of vehicle i, cl represents the center line of the current lane;
[0092] In the later stage of free driving mode, following driving mode or lane changing mode, the longitudinal force acting on vehicle i is:
[0093]
[0094] The switching conditions for the early and late stages of the lane-changing mode are that the geometric center of vehicle i enters the target lane from the original lane.
[0095] In this embodiment, after collecting vehicle driving information on the highway, the vehicle behavior modeling is performed using the method provided by this patent. The particle swarm algorithm is used to adjust the model parameters. The optimized parameters include: c.
[0096] During the parameter setting process, the optimization goal of the algorithm is to minimize the fitness function. The fitness function used in this embodiment is:
[0097]
[0098] Where n is the total amount of trajectory data, Indicates the vertical coordinate value of the frame data in the simulation trajectory. Indicates the ordinate value of the frame data in the real trajectory. Indicates the horizontal coordinate value of the frame data in the simulation trajectory. Indicates the horizontal coordinate value of the frame data in the real trajectory. The k in the formula is a constant greater than 1, which is used to increase the importance of the horizontal coordinate error. In this example, k=10.
[0099] After optimization, it is necessary to calculate the average Euclidean distance between the two trajectories to further determine the accuracy of the model. The average Euclidean distance between the two trajectories is:
[0100]
[0101] The minimum fitness value obtained in this embodiment is 1.2683. The average Euclidean distance between the two trajectories is 0.3026m, indicating that the vehicle behavior modeling method based on social force established by this method has a high modeling accuracy.
[0102] Preferably, the non-lane-changing mode of the present invention is a straight-ahead mode, which is laterally subjected to lane-keeping force from the lane line, and longitudinally subjected to longitudinal collision avoidance force from a leading vehicle if there is one, in addition to longitudinal self-driving force.
[0103] The present invention also discloses an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the vehicle behavior modeling method based on social forces when executing the program.
[0104] The present invention also discloses a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle behavior modeling method based on social forces are implemented.
[0105] It is worth mentioning that the technical features such as vehicles involved in the patent application of this invention should be regarded as prior art. The specific structure, working principle and possible control method and spatial layout method of these technical features can be selected by conventional methods in the field, and should not be regarded as the inventive point of the patent of this invention. The patent of this invention will not be further elaborated.
[0106] For those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A vehicle behavior modeling method based on social forces for vehicle behavior modeling, It is characterized in that The following steps are involved: Step S1: dividing the vehicle behavior into a lateral module and a longitudinal module, the lateral module includes a lane-changing mode and a non-lane-changing mode and the longitudinal module includes a free driving mode and a vehicle-following driving mode; Step S1.1: In the free driving mode, the vehicle is subjected to a self-driving force generated to achieve an optimal speed in the longitudinal direction, and is subjected to a lane keeping force from lane lines on both sides and a centerline damping force from the centerline of the lane in the lateral direction; Step S1.2: In the following driving mode, the vehicle is longitudinally subjected to the self-driving force generated to achieve the optimal speed and the collision avoidance resistance generated to avoid collision with the vehicle in front, and is laterally subjected to the lane line holding force from the lane lines on both sides and the center line damping force from the center line of the lane; Step S1.3: In the lane-changing mode, the lateral movement of the vehicle is divided into two stages, one is the front lane-changing stage approaching the middle lane line, and the other is the rear lane-changing stage after crossing the middle lane line. In the front lane-changing stage, the vehicle travels longitudinally in a free driving mode or a following mode, and the vehicle is laterally subjected to resistance from the middle lane line, attraction from the center line of the target lane, and attraction from the front and rear vehicles in the target lane.
2. A vehicle behavior modeling method based on social forces according to claim 1, It is characterized in that In step S1.1, in the free driving mode, the self-driving force generated by the vehicle to achieve the optimal driving speed is: In the formula, represents the self-driving force of vehicle i, is the optimal driving speed, m i is the mass of vehicle i, is the current longitudinal velocity of vehicle i, is the longitudinal driving reaction time of vehicle i, x represents the longitudinal direction, t represents the time, is a unit vector pointing in the longitudinal direction of the vehicle.
3. A vehicle behavior modeling method based on social forces according to claim 2, It is characterized in that In step S1.2, in the following driving mode, there is another vehicle j in front of the vehicle. The vehicle j in front of the same lane line will generate longitudinal collision avoidance resistance to vehicle i, and the formula is: In the formula, is the longitudinal collision avoidance force that vehicle j will generate on vehicle i, m i is the mass of vehicle i, is the gain coefficient, is the headway between vehicle i and vehicle j, that is, the distance between the head of vehicle j and the parking space of vehicle i, is the sensitivity coefficient, e represents the exponential function, is the unit vector of vehicle j and vehicle i in the direction of the lane line; The resultant force on the vehicle in the longitudinal direction is:
4. A vehicle behavior modeling method based on social forces according to claim 3, It is characterized in that In step S1.3, in the lane-changing driving mode, the lateral force on the vehicle includes the lane-changing resistance from the lane line l2 between the current lane l1 and the target lane. Attraction from the center line cl2 of the target lane The attraction force of the preceding vehicle in the target lane from the preceding vehicle k located longitudinally ahead and traveling in the target lane and the target lane rear vehicle attraction force from the rear vehicle h located longitudinally behind and traveling in the target lane The expressions are: In the formula, is the gain coefficient, is the distance between lane line l2 and the geometric center of vehicle i, is the sensitivity coefficient, is the unit vector pointing from lane line l2 to the geometric center of vehicle i, lc represents the lane change mode; In the formula, is the gain coefficient, is the distance between the target lane centerline cl2 and the geometric center of vehicle i, is the sensitivity coefficient, is the unit vector pointing from the geometric center of vehicle i to the center line of the target lane cl2; In the formula, is the gain coefficient, is the headway time between vehicle i and the vehicle k in front of the target lane in the direction of the lane line, is the sensitivity coefficient, is the unit vector from the geometric center of vehicle i to the center line lc2 of the target lane where vehicle k is located; In the formula, is the gain coefficient, is the headway time between the vehicle h and vehicle i in the target lane in the direction of the lane line, is the sensitivity coefficient, is the unit vector pointing from the geometric center of vehicle i to the center line of the target lane cl2; Therefore, the lateral force on the vehicle in the lane-changing driving mode is: The switching condition between the free driving mode and the following driving mode is whether there is a vehicle j in front of the vehicle i.
5. A vehicle behavior modeling method based on social forces according to claim 4, It is characterized in that The switching conditions between lane-changing mode and non-lane-changing mode include: a. The longitudinal force after changing lanes exceeds a certain threshold value compared to the longitudinal force before changing lanes. b. There is no adjacent vehicle in the target lane. An adjacent vehicle refers to a vehicle traveling side by side with vehicle i. c. The collision time ttc between the front vehicle k and the rear vehicle h in the target lane and vehicle i is less than a certain threshold ttc thre , the calculation formula of ttc is: In the formula, r x Indicates the distance between the front and rear vehicles. and are the longitudinal velocities of the rear and front vehicles, respectively.
6. A vehicle behavior modeling method based on social forces according to claim 5, It is characterized in that In the free driving mode, the following driving mode or the later stage of the lane changing mode, the vehicle i is subjected to the lane keeping force from the lane lines on both sides of the current lane. and and the damping force from the center line lc of the lane in which vehicle i is traveling The expression is: In the formula, represents the lane keeping force from the left lane line of the lane where vehicle i is traveling, represents the lane keeping force from the right lane line of the lane where vehicle i is traveling, and are gain coefficients and and are the lateral distances between the left and right lane lines of the lane where vehicle i is traveling and the geometric center of vehicle i, and are the unit vectors pointing from the left and right lane lines of the lane where vehicle i is traveling to the geometric center of vehicle i; Where c is the damping coefficient, is the lateral speed of vehicle i, cl represents the center line of the current lane; In the later stage of free driving mode, following driving mode or lane changing mode, the longitudinal force acting on vehicle i is: The switching conditions for the early and late stages of the lane-changing mode are that the geometric center of vehicle i enters the target lane from the original lane.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the steps of a vehicle behavior modeling method based on social forces as described in any one of claims 1 to 6 are implemented.
8. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of a vehicle behavior modeling method based on social forces as claimed in any one of claims 1 to 6 are implemented.
