Networked autonomous vehicle trajectory planning method based on artificial potential field method

Abstract

The invention provides a networked autonomous vehicle trajectory planning method based on an artificial potential field method, and the method comprises the following steps: S1, constructing an artificial potential field according to the basic condition and traffic condition of an expressway, and enabling the artificial potential field to comprise a target point gravitational potential field generated by the position and speed of a target point; a dynamic environment vehicle repulsive force potential field is generated according to the dynamic environment vehicle position and speed; a road boundary repulsive force potential field is generated by the road boundary; s2, according to the artificial potential field, a resultant force of the controlled vehicle in the potential field is calculated to generate a vehicle initial track, and the initial track is smoothed; and S3, the state information of the controlled vehicle after smoothing processing is fed back to the controller, closed-loop control is formed by combining real-time data of the environment vehicle, and the vehicle track is dynamically adjusted. Through the method, the traffic operation efficiency is effectively improved, the vehicle delay is reduced, and a positive effect on reducing carbon emission is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic control, and particularly to a trajectory planning method for connected autonomous vehicles based on the artificial potential field method. Background Art

[0002] With the rapid development of China's economy and technology, people have higher demands for the convenience, efficiency, and safety of travel. With the sharp increase in the number of vehicles, problems such as traffic congestion and traffic accidents have become increasingly serious. To solve the above problems, expressways have gradually become the key facilities for big cities to relieve traffic pressure. Although expressways can relieve some traffic pressure, due to the insufficient passing capacity in the weaving section during peak periods, expressways still present normal traffic congestion, frequent accidents, and environmental pollution problems.

[0003] The development of intelligent connected technology has brought revolutionary changes to the field of traffic control. Through the intelligent information exchange and sharing between vehicles and vehicles, and between vehicles and infrastructure, more refined and intelligent traffic management can be achieved. In this context, the research and development of intelligent connected traffic control systems have become the focus and key points in the field of traffic engineering, and have also brought new solutions to the traffic control problems in the expressway weaving section. Among them, trajectory-level traffic collaborative control is an effective way to relieve traffic congestion in the weaving section, improve road safety, and reduce environmental pollution.

[0004] However, there are many challenges in existing intelligent connected traffic control systems, including: 1) Insufficient research on trajectory-level traffic collaborative control. Current research mostly focuses on the macroscopic behavior of vehicles, such as traffic flow control and congestion management, while there is relatively little in-depth research on the specific driving trajectories and spatio-temporal collaboration of individual vehicles; 2) Restrictions of traditional lane division on autonomous vehicles: The integration of autonomous vehicles requires rethinking traditional lane division and traffic rules. Lanes may no longer be fixed, but can be dynamically adjusted according to traffic conditions to improve the flexibility and efficiency of the road; 3) Diversity of traffic scenarios and driving behaviors: Most existing traffic control studies are based on specific traffic scenarios, or only conduct trajectory planning for connected autonomous vehicles from a single dimension; 4) Limited dynamic application of the artificial potential field method: In a dynamic environment, the influence of speed needs to be considered. Therefore, the movement of obstacles makes path planning more complex. It is necessary to improve the artificial potential field method so that it can respond to environmental changes in real time and provide safe and efficient paths for vehicles. Summary of the Invention

[0005] The purpose of the present invention is to provide a trajectory planning method for intelligent connected autonomous vehicles that can take into account the influence of various factors on vehicle driving, so as to improve the traffic operation efficiency in the expressway weaving section, reduce delays, and achieve environmental protection goals.

[0006] To achieve the above object, the present invention proposes a trajectory planning method for a connected autonomous vehicle based on the artificial potential field method, including the following steps: S1: Construct an artificial potential field according to the basic situation and traffic conditions of the expressway, including: The target point gravitational potential field generated by the position and speed of the target point; The repulsive potential field of dynamic environment vehicles generated by the position and speed of dynamic environment vehicles; The road boundary repulsive potential field generated by the road boundary; S2: According to the artificial potential field, generate an initial vehicle trajectory by calculating the resultant force (force condition) of the controlled vehicle in the potential field, and smooth the initial trajectory to reduce trajectory fluctuations; S3: Feed back the state of the controlled vehicle after smoothing processing information to the controller, form a closed-loop control in combination with the real-time data of environmental vehicles, and dynamically adjust the vehicle trajectory. Among them, is the centroid position of the controlled vehicle; is the speed of the controlled vehicle; a c represents the acceleration of the controlled vehicle, which is determined by the resultant force F / m of the controlled vehicle, and m can take the mass of a standard car, which can be 1.5t.

[0007] Furthermore, the basic situation of the expressway includes the construction of the expressway road boundary and the position of static obstacles on the expressway, and the traffic conditions include the real-time position and real-time speed of environmental vehicles. The application scenario of the present invention is a fully connected autonomous driving situation, and the road is a road structure with only width and no road division, and the lanes are not fixed, so the vehicle runs freely in the horizontal and vertical two-dimensional space without being affected by lane division.

[0008] Furthermore, in step S1, the basic situation and traffic conditions of the expressway include the gravitational potential field generated by the target point position and speed, the repulsive potential field generated by the dynamic environment vehicle position and speed, and the repulsive potential field generated by the road boundary.

[0009] Furthermore, in step S1, the construction method of the target point gravitational potential field is: based on the relative position difference and relative speed difference of the controlled vehicle and the target node, the target point attraction potential field can be regarded as being generated by the points in the merging area moving along the target lane at a restricted speed. Define the target point gravitational potential field function as: ; Among them, is the centroid position of the controlled vehicle; is the position of the target node; is the speed of the controlled vehicle; is the speed of the target node, taking the speed limit of the expressway; are the Euclidean distances of the relative position and relative speed respectively, and their expressions are: ; ; In the expression, and are the gain coefficients of the position and speed gravity of the target point respectively.

[0010] Furthermore, the gravity function corresponding to the gravity potential field function of the target point is the direction in which the potential field drops fastest, that is ; where is used to make the controlled vehicle track the position of the target node, is used to make the controlled vehicle track the speed of the target node, is the gravity function corresponding to the gravity potential field function of the target point, which represents the direction in which the gravity potential field function drops fastest and the maximum change rate at this point; represents the negative gradient of the gravity potential field.

[0011] Furthermore, in step S1, the construction method of the repulsive potential field of the dynamic environment vehicle is: based on the relative position and relative speed between the controlled vehicle and the i-th environment vehicle, determine the repulsive potential field function of the dynamic environment vehicle as: ; ; where and are the position and speed of the i-th environment vehicle, and are the repulsive gain coefficients of the position and speed of the environment vehicle respectively, is the maximum action range of the environment vehicle; The repulsive potential field generated by the i-th environment vehicle on the controlled vehicle; ): that is , representing the vector difference between the position of the controlled vehicle and the position of the i-th vehicle; : that is , representing the vector difference between the speed of the i-th vehicle and the speed of the i-th vehicle.

[0012] Furthermore, in the repulsive potential field function of the dynamic environment vehicle: When ; When When ; When When ; When When ; The repulsive force function corresponding to the repulsive force potential field of the dynamic environment vehicle is: ; Wherein, : The repulsive force potential field generated by the speed of the i-th environmental vehicle on the controlled vehicle; The repulsive force potential field generated by the position of on the controlled vehicle; The negative gradient of the repulsive force potential field of the i-th environmental vehicle on the controlled vehicle; The repulsive force generated by the position of the i-th environmental vehicle on the controlled vehicle, which represents The direction of the fastest descent and the maximum rate of change at this point; : The repulsive force generated by the i-th environmental vehicle on the controlled vehicle, representing The direction of the fastest descent and the maximum rate of change at this point; The repulsive force generated by the speed of the i-th environmental vehicle on the controlled vehicle, representing The direction of the fastest descent and the maximum rate of change at this point.

[0013] Furthermore, in step S1, the construction method of the road boundary repulsive force potential field function of the road boundary repulsive force potential field is: through the Euclidean distance between the controlled vehicle and the road boundary and the maximum action distance range of the repulsive force generated by the road boundary on the controlled vehicle, determine the road boundary repulsive force potential field function, that is: ; Wherein, is the road boundary repulsive force gain coefficient; represents the point on the road boundary closest to the position of the controlled vehicle, that is, the intersection point of the perpendicular line from the position of the controlled vehicle to the road boundary; is 1 / 2 of the road width, that is, only when the controlled vehicle is located on the road center line is it considered not to be affected by the road boundary repulsive force; The repulsive force potential field generated by the road boundary on the controlled vehicle.

[0014] Furthermore, the repulsive force function corresponding to the road boundary repulsive force potential field function is: ; Wherein, The repulsive force generated by the road boundary on the controlled vehicle, which represents the direction of the fastest decline and the maximum change rate at this point.

[0015] Furthermore, in step S2, the method for generating the initial trajectory includes: obtaining the force condition of the controlled vehicle on a continuous time series by using the artificial potential field method, and according to the kinematic relationship to plan the path for the vehicle, determining the initial position, target position of the vehicle and the positions of obstacles in the environment, using the superposition of the gravitational field and the repulsive field to form the total potential field, obtaining the total force field received by the controlled vehicle according to the total potential field gradient descent method and the predetermined speed model, and updating the vehicle position to generate a continuous trajectory; using the locally weighted regression algorithm to smooth the generated trajectory; among them, the kinematic relationship where a is the acceleration in kinematics, which represents the acceleration of the controlled vehicle here; is the first derivative of the velocity in kinematics; is the second derivative of the position in kinematics.

[0016] Furthermore, the specific method for smoothing the generated trajectory by using the locally weighted regression algorithm is: 1) Determine the local neighborhood: For the given point of the obtained trajectory data, it is first necessary to determine the local neighborhood, select the bandwidth to determine that the neighborhood contains the data points with the closest distance , where n is the total number of trajectories, and the set of data points in the neighborhood is set as , where

[0017] is the k-th point in the neighborhood. (The basis for the selection of α is that it can balance the capture of local trends and the retention of the characteristics of the original trajectory to a certain extent, which can effectively smooth the trajectory without over-smoothing). 2) Calculate the weights: For each point in the neighborhood , use the weight function to calculate its weight relative to , and select the Tricube weight function for calculation, = , that is, the maximum distance from the points in the neighborhood to , where refers to the point to be smoothed and optimized for the trajectory position in the trajectory smoothing process; refers to the maximum distance from all data points in the local neighborhood to the target point ; Refers to the local area neighborhood Within, all data points To the target point The maximum value of the distance. (Reason for choosing the Tricube weight function: Compared with some other weight functions, the cubic weight function performs moderately in suppressing the influence of distant points and highlighting the role of nearby points. It will not cause the attenuation of the weight to be too drastic or slow, thus being able to provide a more reasonable weight distribution for local weighted regression.).

[0018] 3) Local weighted regression: Within the neighborhood Perform weighted linear regression to estimate The corresponding smoothed value ; Use the linear model Where Is the error term, and it is necessary to minimize the weighted sum of squared errors: ; ; .

[0019] It can be obtained And The value of, and the smoothed value Can be calculated. Then traverse each point of the original trajectory Repeat the above steps to obtain the smoothed trajectory .

[0020] Note: The subscript j represents the index of the specific data point currently being processed or calculating the smoothed value. Subscript i: Used when determining The local neighborhood of, and is used to represent the index of other points within the neighborhood; Represents The local neighborhood The k-th point within; here Is the index of the point within the neighborhood, which is selected from the index i of the original data point, and the value range of i is from 1 to n; —The intercept term of the linear model, representing the offset on the y-axis during linear fitting; —The slope term of the linear model, reflecting the rate of influence of the independent variable x on the dependent variable y; —The k-th point within the neighborhood Relative to the target point The weight of, used for weighted regression, reflecting the degree of influence of the point on the regression estimate; ; —The neighborhood The k-th point inside The corresponding original dependent variable data; — The weighted sum of squared errors, which is used to measure the fitting effect of the linear model on the data within the neighborhood, and the optimal one is determined by minimizing it ; — The estimated value of the intercept term obtained after minimizing the weighted sum of squared errors ; — The estimated value of the slope term obtained after minimizing the weighted sum of squared errors ; — The target point The smoothed value obtained after local weighted regression of the target point, which is the output result after trajectory smoothing processing.

[0021] Furthermore, in step S3, the implementation manner of the closed-loop control is as follows: Obtain the state information of the controlled vehicle after trajectory generation and smoothing processing, including the position and speed of the controlled vehicle; Feed back the real-time position and speed information of the controlled vehicle to the controller, and at the same time enable the controller to obtain the environmental vehicle information, combine the dynamic data of the environmental vehicle, update the artificial potential field parameters periodically and re-plan the trajectory, so as to adjust and optimize the subsequent vehicle trajectory according to the overall traffic conditions.

[0022] Compared with the prior art, the advantages of the present invention are as follows: By constructing a reasonable artificial potential field model and considering the influence of various factors on vehicle driving, the present invention can effectively improve the traffic operation efficiency, reduce vehicle delays, reduce carbon emissions, has environmental protection, and has a positive effect on alleviating traffic congestion in the weaving area of the expressway and enhancing road safety. Brief Description of the Drawings

[0023] Figure 1 It is a flow chart of a method for trajectory planning of a connected autonomous vehicle based on the artificial potential field method of the present invention; Figure 2 It is a spatial distribution diagram of the gravitational potential field of the target point in an embodiment of the present invention; Figure 3 It is a spatial distribution diagram of the repulsive potential field of the road boundary in an embodiment of the present invention; Figure 4 It is the spatial distribution of the combined field of the gravitational potential field of the target point, the repulsive potential field of the dynamic environmental vehicle, and the repulsive potential field of the road boundary in an embodiment of the present invention; Figure 5 It is the trajectory generation process of the controlled vehicle trajectory under the action of the artificial potential field and the trajectory smoothing effect of the local weighted regression algorithm on the trajectory in an embodiment of the present invention. Detailed Implementation Manner

[0024] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be further described below.

[0025] The trajectory planning method for a connected and autonomous vehicle based on the artificial potential field method in this embodiment is as Figure 1 shown and includes the following steps: S1: According to the basic situation of the expressway (including the construction of the expressway road boundary and the position of static obstacles on the expressway) and the traffic situation (including the real-time position and real-time speed of environmental vehicles), construct an artificial potential field, including: 1) The gravitational potential field of the target point generated according to the relative position difference and relative speed difference between the controlled vehicle and the target node; In this embodiment, the construction method of the gravitational potential field of the target point is: based on the relative position difference and relative speed difference between the controlled vehicle and the target node, the gravitational potential field of the target point can be regarded as being generated by the points in the merging area moving along the target lane at a restricted speed. Define the gravitational potential field function of the target point as: ; where, is the centroid position of the controlled vehicle; is the position of the target node; is the speed of the controlled vehicle; is the speed of the target node, taking the restricted speed of the expressway; are the Euclidean distances of the relative position and relative speed respectively; , are the gain coefficients of the position and speed gravitation of the target point respectively.

[0026] The gravitational function corresponding to this gravitational potential field function of the target point is the direction in which the potential field drops fastest, that is: ; where, is used to make the controlled vehicle track the position of the target node, is used to make the controlled vehicle track the speed of the target node, is the gravitational function corresponding to the gravitational potential field function of the target point, which represents the direction in which the gravitational potential field function drops fastest and the maximum change rate at this point; represents the negative gradient of the gravitational potential field.

[0027] As Figure 2The spatial distribution of the gravitational potential field of the target point shown. From the lateral position, longitudinal position, and gravitational potential field distribution of the expressway in the figure, it can be seen that the greater the distance between the controlled vehicle and the target point, the greater the potential energy value of the controlled vehicle; the smaller the distance, the smaller the potential energy value of the controlled object; the greater the speed difference, the greater the potential energy value of the controlled vehicle.

[0028] 2) The repulsive potential field of the dynamic environment vehicle generated based on the relative position and relative speed of the controlled vehicle and the dynamic environment vehicle; In this embodiment, the specific construction method of the repulsive potential field of the dynamic environment vehicle in step S1 is: based on the relative position and relative speed of the controlled vehicle and the i-th environmental vehicle, the repulsive potential field function of the dynamic environment vehicle is determined as: ; ; where 、 are the position and speed of the i-th environmental vehicle, 、 are the repulsive gain coefficients of the environmental vehicle position and speed respectively, is the maximum action range of the environmental vehicle; The repulsive potential field generated by the i-th environmental vehicle on the controlled vehicle; ): that is , representing the vector difference between the position of the controlled vehicle and the position of the i-th vehicle; : that is , representing the vector difference between the speed of the i-th vehicle and the speed of the i-th vehicle.

[0029] In this dynamic environment vehicle repulsive potential field function: When ; When at that time, ; When at that time, ; When at that time, ; The repulsive force function corresponding to this dynamic environment vehicle repulsive potential field function is: ; where The repulsive potential field generated by the speed of the i-th environmental vehicle on the controlled vehicle; The repulsive potential field generated by the position of the i-th environmental vehicle on the controlled vehicle; The negative gradient of the repulsive potential field of the i-th environmental vehicle on the controlled vehicle; The repulsive force generated by the position of the i-th environmental vehicle on the controlled vehicle, which represents The direction of the steepest descent and the maximum rate of change at this point; Represents the repulsive force generated by the i-th environmental vehicle on the controlled vehicle, representing The direction of the steepest descent and the maximum rate of change at this point; The repulsive force generated by the speed of the i-th environmental vehicle on the controlled vehicle, representing The direction of the steepest descent and the maximum rate of change at this point.

[0030] As Figure 4 shown, it is the spatial distribution of the combined field of the gravitational potential field of the target point, the repulsive potential field of the dynamic environmental vehicle, and the repulsive potential field of the road boundary. The potential field increases in each area close to the obstacle and the road boundary; the potential field decreases close to the target point and increases far from the target point. The controlled vehicle will choose to move forward in the direction of the route with the steepest potential field descent.

[0031] When , it indicates that the relative position vector and relative velocity vector of the controlled vehicle and the environmental vehicle are less than 90°, that is, the relative velocity will increase the risk of collision; When , it indicates that the relative position vector and relative velocity vector of the controlled vehicle and the environmental vehicle are greater than 90°, that is, the relative velocity will reduce the risk of collision.

[0032] 3) The road boundary repulsive potential field generated according to the Euclidean distance between the controlled vehicle and the road boundary; In this embodiment, the construction method of the road boundary repulsive potential field function in step S1 is: through the Euclidean distance between the controlled vehicle and the road boundary and the maximum action range of the road boundary generating repulsive force on the controlled vehicle to determine the road boundary repulsive potential field function, that is: ; Among them, is the road boundary repulsive gain coefficient; represents the point on the road boundary closest to the position of the controlled vehicle, that is, the intersection point of the perpendicular line from the position of the controlled vehicle to the road boundary; is 1 / 2 of the road width, that is, it is considered that the controlled vehicle is not affected by the road boundary repulsive force only when it is located on the road center line; The repulsive potential field generated by the road boundary on the controlled vehicle.

[0033] The repulsive force function corresponding to the road boundary repulsive force potential field function is as follows: ; wherein, denotes the repulsive force generated by the road boundary on the controlled vehicle, representing the direction of the fastest descent and the maximum rate of change at this point.

[0034] As Figure 3 shown in the spatial distribution of the road boundary repulsive force potential field, it can be seen that the greater the distance between the controlled vehicle and the road boundary, the smaller the repulsive force on the controlled vehicle; the smaller the distance, the greater the repulsive force on the controlled vehicle. When the distance between the controlled vehicle and the road boundary exceeds the action distance, the road boundary potential field is 0.

[0035] S2: Based on the constructed artificial potential field, generate the initial trajectory of the vehicle by calculating the resultant force (force condition) of the controlled vehicle in the potential field, and perform smoothing processing on the initial trajectory based on the Loess algorithm to reduce trajectory fluctuations; In this embodiment, the method for generating the initial trajectory includes: obtaining the force condition of the controlled vehicle on a continuous time series by using the artificial potential field method, and according to (a is the acceleration in kinematics, representing the acceleration of the controlled vehicle here; is the first-order derivative of the velocity in kinematics; is the second-order derivative of the position in kinematics), use the kinematic relationship to plan the path of the vehicle, determine the initial position, target position of the vehicle and the positions of obstacles in the environment, form the total potential field by superimposing the gravitational field and the repulsive field, obtain the total force field received by the controlled vehicle according to the total potential field gradient descent method and the predetermined velocity model, and update the vehicle position to generate a continuous trajectory; then use the locally weighted regression algorithm to smooth the generated trajectory to reduce trajectory fluctuations and improve the smoothness of driving and riding comfort. Figure 5 This is a schematic diagram of the trajectory generation process of the controlled vehicle trajectory under the action of the artificial potential field and the smoothing effect of the locally weighted regression algorithm in this embodiment.

[0036] S3: Feed back the state information of the smoothed controlled vehicle to the controller, form a closed-loop control in combination with the real-time data of the environmental vehicles, and dynamically adjust the vehicle trajectory. Among them, the parameters of the artificial potential field in the closed-loop control are updated at fixed time intervals. Since the weaving area of the expressway belongs to the complex environment of urban roads, in order to respond to various dynamic changes in a timely manner, the update frequency is 50Hz.

[0037] In step S3, the specific implementation method of closed-loop control is as follows: Obtain the state information of the controlled vehicle after trajectory generation and smoothing processing, including the position and speed of the controlled vehicle; Feed back the real-time position and speed information of the controlled vehicle to the controller, and at the same time enable the controller to obtain the information of the surrounding vehicles, combine the dynamic data of the surrounding vehicles, periodically update the artificial potential field parameters and re-plan the trajectory, so as to adjust and optimize the subsequent vehicle trajectory according to the overall traffic conditions.

[0038] The simulation traffic control experiment is carried out by the method of this embodiment as follows: 1) Experimental scenario: Build a SUMO simulation road network. This network consists of 6 nodes and 5 edges. The total length of the main road is set to 1200 meters, and the distance between the two ramps is 1000 meters. The maximum speed limit on the main lane is 80 km / h (equivalent to 22.2 m / s), while the speed limit on the ramp is fixed at 40 km / h (equivalent to 11.11 m / s).

[0039] 2) Experimental parameters: The traffic flow setting parameters are 2400 veh / h for the straight line on the main road of the expressway, 1200 veh / h for the ramp merging, and 800 veh / h for the main road exiting. The data from 600 s to 3600 s are obtained by simulation, and the warm-up time data in the first 600 s are removed. Set the output tripinfo file in the SUMO simulation configuration code file to obtain the delay data of the vehicles.

[0040] 3) Set the control group and the experimental group: Control group: Use the lane-changing model LC2013 and the car-following model Krauss in SUMO to simulate the natural traffic flow state, which is hereinafter referred to as no control; Experimental group: Control the simulation program through the Traci interface, including the construction of gravitational and repulsive forces, etc., and ensure that it can correctly interact with SUMO and achieve the expected functions; The other kinematic and dynamic parameters of the two groups are set the same, including the maximum speed of 25 m / s, the maximum acceleration of 2.6 m / s², and the maximum deceleration of 4.5 m / s², and the vehicle body length is set to 5 m.

[0041] 4) Simulation experiment results: Denote the traffic flow path of the main line straight as route1, the traffic flow path from the ramp merging into the main line as route2, and the traffic flow path from the main line exiting as route3. The characteristics of the delay time data of each route are shown in Table 1 below: Table 1:

[0042] From the above experiments, it can be seen that: based on the above weaving section control method, the delay of main road through vehicles is reduced by 31.3%, the delay of main road departing vehicles is reduced by 50.1%, and the delay of ramp merging vehicles is reduced by 39.9%. This result shows that the present invention has remarkable effects in improving the operation efficiency of the weaving section and reducing delays.

[0043] The above are only the preferred embodiments of the present invention and do not impose any limitation on the present invention. Any person skilled in the art, without departing from the scope of the technical solution of the present invention, makes any form of equivalent replacement or modification and other changes to the technical solution and technical content disclosed by the present invention, which are all within the content of the technical solution of the present invention and still fall within the protection scope of the present invention.

Claims

1. A trajectory planning method for a connected autonomous vehicle based on the artificial potential field method, characterized in that It includes the following steps: S1: Construct an artificial potential field according to the basic situation and traffic conditions of the expressway, including: The target point gravitational potential field generated by the position and speed of the target point; The repulsive potential field of dynamic environment vehicles generated by the position and speed of dynamic environment vehicles; The road boundary repulsive potential field generated by the road boundary; S2: According to the artificial potential field, generate the initial trajectory of the vehicle by calculating the resultant force of the controlled vehicle in the potential field, and smooth the initial trajectory; S3: Feed back the state information of the controlled vehicle after smoothing to the controller, form a closed-loop control in combination with the real-time data of the environmental vehicles, and dynamically adjust the vehicle trajectory.

2. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 1, wherein In step S1, the method for constructing the gravitational potential field of the target point is as follows: Based on the relative position difference between the controlled vehicle and the target node and the relative velocity difference , the gravitational potential field function of the target point is defined as: ; where is the position of the center of mass of the controlled vehicle; is the position of the target node; is the velocity of the controlled vehicle; is the velocity of the target node, taking the speed limit of the expressway; are the Euclidean distances of the relative position and the relative velocity respectively, , are the gain coefficients of the gravitational forces of the target point position and velocity respectively.

3. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 2, wherein The gravitational function corresponding to the target point gravitational potential field function is the direction in which the potential field drops fastest, i.e., ; where is used to make the controlled vehicle track the position of the target node, is used to make the controlled vehicle track the speed of the target node, is the gravitational function corresponding to the target point gravitational potential field function, which represents the direction in which the gravitational potential field function drops fastest and the maximum rate of change at this point; is the negative gradient of the gravitational potential field.

4. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 1, characterized in that In step S1, the method for constructing the repulsive potential field of dynamic environment vehicles is as follows: Based on the relative position and relative velocity of the controlled vehicle and the i-th environmental vehicle, the repulsive potential field function of dynamic environment vehicles is determined as: ； ； Among them, , is the position and speed of the i-th environmental vehicle, , are the repulsive gain coefficients of the position and speed of the environmental vehicle respectively, is the maximum action range of the environmental vehicle; : The repulsive potential field generated by the i-th environmental vehicle on the controlled vehicle; ):That is , representing the vector difference between the position of the controlled vehicle and the position of the i-th vehicle; : that is , indicating that the vector difference between the i-th vehicle speed and the i-th vehicle speed is 5. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 4, characterized in that, In the repulsive potential field function of the dynamic environment vehicle: When ; When then ; When then ; When then ; The repulsive force function corresponding to the repulsive potential field function of the dynamic environment vehicle is: ； Among them, : The repulsive force potential field generated by the speed of the i-th environmental vehicle on the controlled vehicle; The repulsive potential field generated by the position of the i-th environmental vehicle on the controlled vehicle; The negative gradient of the repulsive potential field of the i-th environmental vehicle on the controlled vehicle; The repulsive force generated by the position of the i-th environmental vehicle on the controlled vehicle, which represents The direction of the steepest descent and the maximum rate of change at this point; : The repulsive force exerted by the i-th environmental vehicle on the controlled vehicle, representing the direction of the steepest descent and the maximum rate of change at that point; The repulsive force generated by the speed of the i-th environmental vehicle on the controlled vehicle represents The direction of the steepest descent and the maximum rate of change at this point.

6. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 1, wherein In step S1, the method for constructing the road boundary repulsive potential field function of the road boundary repulsive potential field is as follows: by comparing the Euclidean distance between the controlled vehicle and the road boundary and the maximum action range of the road boundary generating repulsive force on the controlled vehicle , construct the road boundary repulsive potential field function: ； Among them, is the repulsive force gain coefficient of the road boundary; The repulsive potential field generated by the road boundary on the controlled vehicle.

7. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 6, characterized in that, The repulsive force function corresponding to the road boundary repulsive potential field function is: ; Among them, refers to the repulsive force generated by the road boundary on the controlled vehicle, which represents the direction of the steepest descent and the maximum rate of change at this point.

8. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 1, wherein In step S2, the method for generating the initial trajectory includes: obtaining the force condition of the controlled vehicle on a continuous time series by using the artificial potential field method, planning a path for the vehicle according to the kinematic relationship of , determining the initial position of the vehicle, the target position, and the positions of obstacles in the environment, forming a total potential field by superimposing the gravitational field and the repulsive field, obtaining the total force field received by the controlled vehicle according to the total potential field gradient descent method and the predetermined speed model, and updating the vehicle position to generate a continuous trajectory; using the locally weighted regression algorithm to smooth the generated trajectory; where a is the acceleration in kinematics, which represents the acceleration of the controlled vehicle here; is the first derivative of the velocity in kinematics; is the second derivative of the position in kinematics.

9. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 8, characterized in that, The specific implementation method of smoothing the generated trajectory by using the locally weighted regression algorithm includes: 1) Determine the local area. Let the set of data points in the neighborhood be , where is the k-th point in the neighborhood. 2) Calculate the weight: For each point within the neighborhood , use the Tricube weight function to calculate its weight relative to , , where = , that is, the maximum distance from the points within the neighborhood to ; where refers to the point in the trajectory smoothing process that indicates the point whose trajectory position needs to be smoothed and optimized; refers to the maximum value of the distances from all data points within the local neighborhood to the target point ; refers to the maximum value of the distances from all data points within the local neighborhood to the target point ; 3) Locally weighted regression: within the neighborhood perform weighted linear regression to estimate the corresponding smoothed value .

10. The trajectory planning method for a connected autonomous vehicle based on the artificial potential field method according to claim 1, wherein In step S3, the implementation method of the closed-loop control is: obtain the state information of the controlled vehicle after trajectory generation and smoothing, including the position and speed of the controlled vehicle; feed back the real-time position and speed information of the controlled vehicle to the controller, and at the same time enable the controller to obtain the environmental vehicle information, combine the dynamic data of the environmental vehicles, periodically update the artificial potential field parameters and re-plan the trajectory, so as to adjust and optimize the subsequent vehicle trajectory according to the overall traffic conditions.

Images