Path planning method and device, equipment and storage medium

Abstract

This invention relates to the field of data processing technology and discloses a path planning method, apparatus, device, and storage medium. The method includes: constructing several joint defense lines based on the location information of the target convoy and the location information of competing convoys, and determining the target joint defense line from among the joint defense lines; assigning roles to the target convoy based on the target joint defense line, and determining the first type of vehicles and the second type of vehicles in the target convoy; obtaining the first vehicle path plan corresponding to the first type of vehicle, and obtaining the second vehicle path plan corresponding to the second type of vehicle. This invention determines the first type of vehicles and the second type of vehicles in the target convoy based on the target joint defense line, and obtains the first vehicle path plan used to instruct the first type of vehicles to travel, and the second vehicle path plan used to instruct the second type of vehicles to travel, solving the technical problem in the prior art where the reliability of the planned path is low due to the many uncertainties that arise when vehicles are driving in the actual competition environment.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a path planning method, apparatus, device, and storage medium. Background Technology

[0002] In recent years, autonomous driving technology has developed rapidly and made great progress. With the increasing demand for intelligent driving vehicles in complex real-world environments, autonomous vehicle racing competitions have attracted more and more attention. Most existing racing strategies employ trajectory-following control methods under obstacle avoidance constraints. The side that can plan a shorter route and travel at a higher speed is likely to win the race. However, due to uncertainties such as collisions and obstacles encountered by vehicles in real-world racing environments, the reliability of the planned driving paths is relatively low.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a path planning method, apparatus, device, and storage medium, which aims to solve the technical problem that the reliability of planned paths is low due to the many uncertainties that occur when vehicles are driving in actual competition environments.

[0005] To achieve the above objectives, the present invention provides a path planning method, the path planning method comprising:

[0006] Determine the location information of the target fleet and the competing fleets based on the current route planning data;

[0007] Based on the target vehicle location information and the competing vehicle location information, several joint defense lines are constructed, and the target joint defense line is determined from each joint defense line;

[0008] Based on the target joint defense line, the target convoy is assigned roles, and the first and second categories of vehicles in the target convoy are determined.

[0009] A first vehicle route plan is determined for the first type of vehicle, and a second vehicle route plan is determined for the second type of vehicle. The first vehicle route plan is used to instruct the first type of vehicle to travel, and the second vehicle route plan is used to instruct the second type of vehicle to travel.

[0010] Optionally, the step of constructing several joint defense lines based on the target convoy location information and the competing convoy location information, and determining the target joint defense line from among the joint defense lines, includes:

[0011] Based on the target vehicle's location information and the competing vehicle's location information, several joint defense lines are constructed using the Apollonius circle model.

[0012] Based on the Apollonius circle model, establish the defense line equations corresponding to each joint defense line;

[0013] The target joint defense line is determined from each joint defense line according to the defense line equation.

[0014] Optionally, before the step of determining the target joint defense line from the joint defense lines based on the defense line equation, the method further includes:

[0015] Obtain the number of vehicles corresponding to the target low-speed vehicles in each of the joint defense lines;

[0016] A defense line optimization function is constructed based on the number of vehicles and a preset cost coefficient matrix;

[0017] The step of determining the target joint defense line from the joint defense lines according to the defense line equation includes:

[0018] The target joint defense line is determined from each joint defense line based on the defense line equation and the defense line optimization function.

[0019] Optionally, the step of determining the first vehicle route planning corresponding to the first type of vehicle includes:

[0020] Based on the forward motion target corresponding to the first type of vehicle, path planning is performed on the first type of vehicle to obtain the first type of vehicle optimization function;

[0021] The first vehicle path planning corresponding to the first type of vehicle is determined by the first type of vehicle optimization function.

[0022] Optionally, the step of performing path planning for the first type of vehicles based on the forward motion target corresponding to the first type of vehicles to obtain the optimization function for the first type of vehicles includes:

[0023] Obtain the driving direction of the first type of vehicle, and the vehicle distance between the foreground moving target corresponding to the first type of vehicle and the first type of vehicle;

[0024] Based on the driving direction and the distance to the vehicle, path planning is performed on the first type of vehicle to obtain the first type of vehicle optimization function.

[0025] Optionally, the step of determining the second vehicle route planning corresponding to the second type of vehicle includes:

[0026] Based on the defensive game objective corresponding to the second type of vehicle, path planning is performed on the second type of vehicle to obtain the optimization function of the second type of vehicle.

[0027] The second vehicle path planning corresponding to the second type of vehicle is determined by the second type of vehicle optimization function.

[0028] Optionally, the step of determining the second vehicle path planning corresponding to the second type of vehicle through the second type of vehicle optimization function includes:

[0029] The second type of vehicle is used to predict the target strategy of the defender in the game within the prediction time.

[0030] The defensive strategy of the second type of vehicle within the predicted time period is determined based on the game objective strategy and the optimization function of the second type of vehicle.

[0031] The Nash equilibrium point is determined based on the game objective strategy and the defender strategy, and the second vehicle path planning corresponding to the second type of vehicle is determined through the Nash equilibrium point.

[0032] Furthermore, to achieve the above objectives, the present invention also proposes a path planning device, the device comprising:

[0033] The information determination module is used to determine the location information of the target vehicle fleet and the competing vehicle fleet based on the current route planning data.

[0034] The defense line determination module is used to construct several joint defense lines based on the target vehicle convoy location information and the competing vehicle convoy location information, and to determine the target joint defense line from each joint defense line;

[0035] The role assignment module is used to assign roles to the target convoy based on the target joint defense line, and to determine the first type of vehicles and the second type of vehicles in the target convoy;

[0036] The route planning module is used to determine the first vehicle route plan corresponding to the first type of vehicle and the second vehicle route plan corresponding to the second type of vehicle. The first vehicle route plan is used to instruct the first type of vehicle to travel, and the second vehicle route plan is used to instruct the second type of vehicle to travel.

[0037] Furthermore, to achieve the above objectives, the present invention also proposes a path planning device, the device comprising: a memory, a processor, and a path planning program stored in the memory and executable on the processor, the path planning program being configured to implement the steps of the path planning method as described above.

[0038] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a path planning program, which, when executed by a processor, implements the steps of the path planning method described above.

[0039] This invention discloses a method for determining the location information of the target team and competing teams based on current path planning data; constructing several joint defense lines based on the target team and competing team location information, and determining the target joint defense line from each joint defense line; assigning roles to the target team based on the target joint defense line, and determining the first type of vehicles and the second type of vehicles in the target team; obtaining the first vehicle path plan corresponding to the first type of vehicle, and obtaining the second vehicle path plan corresponding to the second type of vehicle, wherein the first vehicle path plan is used to instruct the first type of vehicle to drive, and the second vehicle path plan is used to instruct the second type of vehicle to drive; compared with the existing technology where the reliability of the driving path planned by the trajectory following control method under obstacle avoidance constraints is low, this invention solves the technical problem of low path reliability in the existing technology due to the many uncertainties that exist when vehicles drive in the actual competition environment. This is because the target team and competing team location information are used to construct joint defense lines, and the first type of vehicles and the second type of vehicles in the target team are determined based on the target joint defense line in each joint defense line, and finally the first vehicle path plan used to instruct the first type of vehicle to drive, and the second vehicle path plan used to instruct the second type of vehicle to drive. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the path planning device for the hardware operating environment involved in the embodiments of the present invention.

[0041] Figure 2 This is a flowchart illustrating the first embodiment of the path planning method of the present invention;

[0042] Figure 3 This is a schematic diagram of the competition track in the first embodiment of the path planning method of the present invention;

[0043] Figure 4 This is a schematic diagram of the construction of a joint defense line in the first embodiment of the path planning method of the present invention;

[0044] Figure 5 This is a schematic diagram of the shortest route to the defense line in the first embodiment of the path planning method of the present invention;

[0045] Figure 6 This is a flowchart illustrating the second embodiment of the path planning method of the present invention;

[0046] Figure 7 This is a flowchart illustrating the third embodiment of the path planning method of the present invention;

[0047] Figure 8 This is a schematic diagram of the overall process of vehicle racing in the path planning method of the present invention;

[0048] Figure 9 This is a statistical chart of experimental results in the third embodiment of the path planning method of the present invention;

[0049] Figure 10 This is a non-cooperative MPC race situation diagram in the third embodiment of the path planning method of the present invention;

[0050] Figure 11 The third embodiment of the path planning method of the present invention includes a competition framework and a competition situation diagram for the team.

[0051] Figure 12 This is a competition framework diagram for a multi-member team in the third embodiment of the path planning method of the present invention;

[0052] Figure 13 This is a structural block diagram of the first embodiment of the path planning device of the present invention.

[0053] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0054] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0055] Reference Figure 1 , Figure 1 This is a schematic diagram of the path planning device structure of the hardware operating environment involved in the embodiments of the present invention.

[0056] like Figure 1As shown, the path planning device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0057] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the path planning device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0058] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a path planning program.

[0059] exist Figure 1 In the path planning device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the path planning device of the present invention can be set in the path planning device, and the path planning device calls the path planning program stored in the memory 1005 through the processor 1001 and executes the path planning method provided in the embodiment of the present invention.

[0060] This invention provides a path planning method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the path planning method of the present invention.

[0061] In this embodiment, the path planning method includes the following steps:

[0062] Step S10: Determine the location information of the target vehicle team and the competing vehicle teams based on the current route planning data.

[0063] It should be noted that the execution subject of the method in this embodiment can be a path planning device for planning the driving path of vehicles traveling on the lane, or other path planning systems that can achieve the same or similar functions and include such a path planning device. Here, the path planning methods provided in this embodiment and the following embodiments will be specifically described using a path planning system (hereinafter referred to as the system).

[0064] It should be understood that in real-world vehicle racing scenarios, the competition between vehicles is non-cooperative, with vehicles exhibiting a variety of intentional actions such as pushing, overtaking, and blocking. Therefore, this solution can incorporate game theory. If a team can cooperate and engage in appropriate adversarial physical interactions with its opponents, then even if the team is slower, it has a chance to defeat a faster opponent if it has a numerical advantage. Specifically, this solution can use a distributed strategy for path planning for autonomous vehicles to demonstrate behaviors such as avoidance, overtaking, blocking, and threats, thereby helping teams with numerical advantages but speed disadvantages to win the race.

[0065] Understandably, this solution can be applied to racing competitions of any autonomous vehicle, and has a relatively low maximum speed (v). E A group of N (N≥2) vehicles (i\in\{1,2,…,N\}=\mathcal{N}) and a vehicle with a higher maximum speed (v P The autonomous vehicles compete against each other under the following conditions: 1) There are collision avoidance safety constraints between the vehicles, and the underlying motion control systems of all autonomous vehicles will strictly follow the safety settings; 2) All vehicles are required to complete the race on a regular one-way track without any forks; 3) Victory condition: the team to which a vehicle belongs wins as soon as any one of its vehicles reaches the finish line; 4) All cars will move forward at maximum speed without external constraints, and the upper bound of the speed of the two teams satisfies 0 < λ = v. P / v E <1.

[0066] It should be noted that the aforementioned current path planning data can be the data required for vehicle path planning. In this embodiment, the current path planning information may include: the data information of the vehicle's current racing lane, and the position information of the target team and competing teams. Specifically, the racing lane data information may include the total length and width of the lane, etc., which are not limited in this embodiment.

[0067] It should be understood that the aforementioned target team position information can be the position information of all vehicles in the target team within the race track; correspondingly, the aforementioned competing team position information can be the position information of all vehicles in the target team's opposing teams within the race track. The target team can be a team with a numerical advantage but a speed disadvantage; the competing teams can be the target team's rival teams. This embodiment plans the routes for vehicles in the target team with a numerical advantage but a speed disadvantage, enabling any vehicle in the target team to reach the finish line first and win the race.

[0068] Understandably, referring to Figure 3 , Figure 3 This is a schematic diagram of the race track in the first embodiment of the path planning method of the present invention. Figure 3 As shown, in this embodiment, the lane centerline can be defined as τ: [0, l τ →R 2 , l τ This is the total length of the track, and the track width is 2ω. τ The position of the vehicle in the lane is denoted as p. i =[x i ,y i ] T ∈R 2 Then the progress of the track centerline at a certain position can be expressed as:

[0069]

[0070] In practice, before planning the route for the vehicles, the user can input the total length and width of the current race lane, as well as the position information of all vehicles in the target team and the competing teams in the current race lane. Thus, when the system plans the route for the vehicles, it can obtain the current route planning data information pre-input by the user and obtain the position information of the target team and the competing teams based on the current route planning data information.

[0071] Step S20: Construct several joint defense lines based on the target vehicle location information and the competing vehicle location information, and determine the target joint defense line from each joint defense line.

[0072] It should be noted that the aforementioned joint defense line can be a defensive line formed by vehicles in the target convoy to defend against vehicles in the competing convoy. Accordingly, the aforementioned target joint defense line can be the best defensive line among all joint defense lines. The evaluation criterion for defensive performance can be proximity; for example, the closer the joint defense line is to the competing convoy, the better its defensive performance.

[0073] It should be understood that this plan can determine multiple different joint defense lines composed of different numbers of vehicles based on the positions between the target convoy and the competing convoy, and select the target joint defense line with the optimal defense form from these joint defense lines.

[0074] Furthermore, to make the constructed joint defense line more reasonable, step S20 may include:

[0075] Step S201: Based on the target vehicle location information and the competing vehicle location information, construct several joint defense lines using the Apollonius circle model.

[0076] It should be noted that the Apollonius circle model mentioned above can be a model of a point on a plane whose difference in distance to two known points is equal to a constant value (such as an ellipse, hyperbola, and parabola).

[0077] Step S202: Establish the defense line equations corresponding to each joint defense line based on the Apollonius circle model.

[0078] It should be understood that the above defense line equations can be the equation expressions corresponding to each joint defense line. In practical applications, since the joint defense line formed by the vehicles in the target convoy may have multiple segments, the defense line equations corresponding to the joint defense lines may also have multiple expressions. In this embodiment, the defense line equations corresponding to each joint defense line can be established based on the Apollonius circle model.

[0079] Understandably, referring to Figure 4 , Figure 4 This is a schematic diagram illustrating the construction of a joint defense line in the first embodiment of the path planning method of the present invention. (See diagram below.) Figure 4 As shown, for two intelligent agents (equivalent to vehicles) P (such as...) Figure 4 (small circles in the middle) and E (such as) Figure 4 The small squares in the middle can be located respectively. Figure 4 P(x) P y P ) and E(x E y E In this context, P can be any of the remaining vehicles in the target convoy excluding those forming a defensive line, and E can be any vehicle in the competing convoy. The maximum speeds of P and E are v0 and v1 respectively. P and v E , λ=v P / v E There exists a Center (e.g.) Figure 4 (the five-pointed star in the middle) A circle with radius \mathcal{A} (e.g.) Figure 4As shown by the dashed line, this allows agents P and E to simultaneously reach any point on the circumference when they both start moving at maximum speed in a certain direction, meaning the faster agent can reach the area outside circle A earlier, while the slower agent can reach the area inside circle A earlier. Therefore, this embodiment can utilize this characteristic of a chase-and-escape game to construct a defense line.

[0080] Specifically, this scheme can draw a target line [M, N] perpendicular to the centerline in front of all vehicles (e.g., ...). Figure 4 (The target line in the middle). Let there be a point Q(x) on the target line. Q y Q If the time difference between points P and E reaching point Q is given by the payoff function, then the payoff function is:

[0081]

[0082] There exists a point Q0 such that G1 is monotonically decreasing on [M, Q0] and monotonically increasing on [Q0, N], and Q0 can be a point Q0 at... Figure 4 The x-coordinate on the coordinate axis.

[0083] The goal of this scheme is to enable P to capture E, meaning P can reach the target line before E, i.e., for any position Q, G_1(Q)>=0. This requires the entire target line segment to lie within the Apollonius circle formed by points P and E. Specifically, for a fixed point P, there exists a set of moving points E such that line segment MN lies exactly within the Apollonius circle formed by points P and E. The curve formed by this set of moving points is the aforementioned defensive line. If point E is located inside the defensive line, then at least one endpoint of the target line segment lies outside the Apollonius circle, and point E can reach this endpoint before point P, resulting in a failed defense. Mathematically, the defensive line can be divided into two segments:

[0084]

[0085]

[0086] in, yes and The x-coordinate of the intersection point, l represents the length of line segment MN.

[0087] Secondly, consider the scenario where two low-speed vehicles jointly defend against a high-speed vehicle. The two low-speed vehicles, P1 and P2, work together to prevent the high-speed vehicle E from reaching the target line first. This requires that the interiors of the two Apollonius circles formed by P1, P2, and E contain all points on the target line segment [M, N]. Figure 4Let Q_c be the intersection of the two Apollonius circles on the target line. This point is the only capture point that the two low-speed vehicles can reach simultaneously. That is, the position of Q_c must satisfy the relationship ||Q c -P1||2=||Q c -P2||2. For high-speed vehicles E, M, N, and Q_c naturally become the most vulnerable points in the defense. Therefore, for two fixed points P1 and P2, there exists a set of moving points E such that line segment MN lies exactly within the two Apollonius circles formed by P1, P2, and E, and the two Apollonius circles intersect at a point Qc on the target line [M, N]. This is a critical state, and the curve formed by this set of moving points is the defensive line. Mathematically, as... Figure 4 As shown in the diagram, the defensive line can be divided into three sections:

[0088]

[0089]

[0090]

[0091] in, It is a target point that two low-speed vehicles can reach simultaneously. yes and The x-coordinate of the intersection point, yes and The x-coordinate of the intersection point, l1 represents the length of line segment MQ_c, and l2 represents the length of line segment Q_cN.

[0092] Finally, extending this to a joint defense line composed of N low-speed vehicles, the target line segment can be divided into N smaller segments, and its defense line equation can be divided into N+1 segments, namely:

[0093]

[0094]

[0095]

[0096] Where n∈(1,N).

[0097] It should be noted that without coordinated defense, in a one-on-one situation, the high-speed vehicle would almost certainly win the race unless the starting position difference was too large. Compared to single-vehicle defense, multi-vehicle defense expands the defensible area because, in multi-vehicle coordinated defense, each vehicle in the target team forming the coordinated defense line can be responsible for a small segment of the target line, which we call a kind of swarm intelligence.

[0098] Step S203: Determine the target joint defense line from the joint defense lines according to the defense line equation.

[0099] It should be understood that after obtaining the defense line equations corresponding to each joint defense line, the shortest distance between vehicles in the competing convoy and all joint defense lines can be calculated based on the defense line equations, and the target joint defense line can be determined from each joint defense line based on the distance. Specifically, in this embodiment, the joint defense line closest to the vehicles in the competing convoy can be determined as the target joint defense line.

[0100] Understandably, referring to Figure 5 , Figure 5 This is a schematic diagram of the shortest route to the defense line in the first embodiment of the path planning method of the present invention. Figure 5 As shown, Figure 5 In It can represent a joint defense line; 'c' represents a defense line. Competing vehicle E in the middle of the competing teams j In this scheme, the closest point can be represented by 'c' to indicate the degree of danger of the opponent breaking through the defense line; Representing c and E j The distance between them, i.e., the defensive line Competing vehicle E j The shortest distance between them. For fast-moving vehicles outside the defensive line, this embodiment can use the following formula to calculate their distance from the defensive line:

[0101]

[0102]

[0103] The distance between each joint defense line and a competing vehicle traveling at high speed outside the defense line can be calculated using the above formula, thus allowing the target joint defense line to be identified from among the joint defense lines.

[0104] Furthermore, since the distances of the defense lines formed by different numbers and combinations are different, in order to improve the flexibility and reliability of determining the target joint defense line, before step S203, the method further includes: obtaining the number of vehicles corresponding to the target low-speed vehicles in each joint defense line; constructing a defense line optimization function based on the number of vehicles and a preset cost coefficient matrix; correspondingly, step S203 includes: determining the target joint defense line from each joint defense line according to the defense line equation and the defense line optimization function.

[0105] It should be noted that the aforementioned target low-speed vehicles can be vehicles used to build joint defense lines.

[0106] It should be understood that the aforementioned preset cost coefficient matrix can be a matrix composed of cost coefficients.

[0107] It is understandable that the above defense optimization function can be used to select the most suitable defense from all joint defense lines.

[0108] Specifically, the defense optimization function in this embodiment can be:

[0109]

[0110] Here, k can represent the number of vehicles that make up the joint defense line. A represents the possible combinations of k vehicles selected from a convoy of M vehicles. k It can be the preset cost coefficient matrix, p k The position of the vehicles forming the joint defense line, τ(p) k ) can be the progress of the track centerline corresponding to the position of the vehicle forming the joint defense line, and D can be the distance between the joint defense line and the competing vehicle in the competing team. In this embodiment, the distance can be calculated by the defense line equation corresponding to the joint defense line.

[0111] It should be understood that the first term of the aforementioned defense line optimization function allows more high-speed vehicles located outside the defense line to travel further and more effectively, thus ensuring the quality of defense. The second term of the defense line optimization function can be a progress loss cost, designed to prevent all low-speed vehicles from defending and ignoring their own chance of reaching the destination. The combination of vehicles added to the defense line construction will receive the defense reward of the first term of the optimization function, while correspondingly suffering the progress loss penalty of the second term. Thus, under this trade-off, the most suitable target joint defense line can be selected from all joint defense lines.

[0112] In its implementation, the system can obtain the position information of all vehicles in both the target and competing convoys based on their location information. Using this position information, it constructs several interconnected defensive lines within the target convoy using the Apollonius circle model. Then, it establishes the corresponding defense line equations for each interconnected defensive line based on the Apollonius circle model. After establishing the defense line equations, the number of vehicles corresponding to each interconnected defensive line can be obtained. A defense line optimization function is then constructed based on the number of vehicles and the cost coefficient matrix. This allows the system to select the most suitable target interconnected defensive line from all interconnected defensive lines based on the defense line equations and the optimization function. Selecting the target interconnected defensive line through the defense line optimization function is more reliable and appropriate than directly selecting it based on the distance between the defensive line and competing vehicles.

[0113] Step S30: Assign roles to the target convoy based on the target joint defense line, and determine the first type of vehicles and the second type of vehicles in the target convoy.

[0114] It should be noted that assigning roles to the target fleet means classifying all vehicles in the target fleet as Class 1 vehicles and Class 2 vehicles.

[0115] It should be understood that the first type of vehicles mentioned above can be vehicles in the target convoy that do not constitute the target joint defense line; correspondingly, the second type of vehicles mentioned above can be vehicles in the target convoy that constitute the target joint defense line.

[0116] In practical applications, after identifying the target joint defense line from all joint defense lines, the vehicles that construct the target joint defense line can be identified and designated as Category II vehicles, while the remaining vehicles that have not constructed the target joint defense line are designated as Category I vehicles.

[0117] Step S40: Determine the first vehicle route plan corresponding to the first type of vehicle and determine the second vehicle route plan corresponding to the second type of vehicle. The first vehicle route plan is used to instruct the first type of vehicle to travel, and the second vehicle route plan is used to instruct the second type of vehicle to travel.

[0118] It is understood that the aforementioned first vehicle route planning can be a route planned by the system for the first type of vehicle to indicate the travel of the first type of vehicle; correspondingly, the aforementioned second vehicle route planning can be a route planned by the system for the second type of vehicle to indicate the travel of the second type of vehicle.

[0119] In its implementation, the system can determine the driving path of the first vehicle corresponding to the first vehicle based on the first vehicle path planning of the first vehicle. When the target team and the competing vehicles are competing, the first vehicle can drive directly according to the first vehicle driving path, while the second vehicle can interact with the high-speed vehicles in the competing team according to its corresponding second vehicle path planning in order to try to block the high-speed vehicles and increase the winning probability of the first vehicle.

[0120] This embodiment discloses a method for determining the location information of the target vehicle team and the competing vehicle teams based on current path planning data; constructing several joint defense lines based on the target vehicle team location information and the competing vehicle team location information, and determining the target joint defense line from each joint defense line; assigning roles to the target vehicle team based on the target joint defense line, and determining the first type of vehicles and the second type of vehicles in the target vehicle team; obtaining the first vehicle path plan corresponding to the first type of vehicle, and obtaining the second vehicle path plan corresponding to the second type of vehicle, where the first vehicle path plan is used to instruct the first type of vehicle to drive, and the second vehicle path plan is used to instruct the second type of vehicle to drive; compared with the existing technology where the driving path planned by the trajectory following control method under obstacle avoidance constraints has low reliability, this embodiment solves the technical problem of low path reliability in the existing technology due to the many uncertainties that exist when vehicles drive in the actual competition environment, because it constructs joint defense lines based on the target vehicle team location information and the competing vehicle team location information, and determines the first type of vehicles and the second type of vehicles in the target vehicle team based on the target joint defense line in each joint defense line, and finally obtains the first vehicle path plan used to instruct the first type of vehicle to drive, and the second vehicle path plan used to instruct the second type of vehicle to drive.

[0121] refer to Figure 6 , Figure 6 This is a flowchart illustrating the second embodiment of the path planning method of the present invention.

[0122] Based on the first embodiment described above, in order to improve the rationality of the route planning for the first type of vehicle, in this embodiment, the step of determining the route planning for the first type of vehicle includes:

[0123] Step S411: Based on the forward motion target corresponding to the first type of vehicle, perform path planning for the first type of vehicle to obtain the first type of vehicle optimization function.

[0124] It should be noted that the aforementioned target of the forward movement can be the vehicle closest to the finish line in the competing team, or all vehicles located ahead of the first-class vehicles.

[0125] It should be understood that the aforementioned optimization function for the first type of vehicle can be a function used to optimize the driving path corresponding to the first type of vehicle.

[0126] It is understood that step S411 may specifically include: obtaining the driving direction of the first type of vehicle and the vehicle distance between the forward moving target corresponding to the first type of vehicle and the first type of vehicle; performing path planning for the first type of vehicle based on the driving direction and the vehicle distance to obtain the first type of vehicle optimization function corresponding to the first type of vehicle.

[0127] It should be understood that the aforementioned driving direction is the direction in which the first type of vehicle is currently traveling on the track.

[0128] It is understandable that the aforementioned vehicle distance refers to the distance between the moving target and the first type of vehicle.

[0129] It should be noted that regardless of whether the first type of vehicle is in a leading or lagging position within the competing vehicle convoy, its driving objective is to overtake the vehicle in front. Therefore, the optimization function for the first type of vehicle can be:

[0130]

[0131] Where, θ i This can be an optimization variable, representing the driving direction of the first type of vehicle i; p(θ) i ) represents the first type of vehicle i in θ i The position that p(θ) will reach in the next moment when traveling in the downward direction. i )=p±v P *T, where T can be the predicted time step, i.e., the furthest position that the first type of vehicle can travel; s i (p(θ i )) indicates that in p(θ) i This position corresponds to the location on the entire track; d ij β represents the distance between vehicle i and vehicle j (i.e., the forward moving target); β is a weighting coefficient.

[0132] It is understandable that the position is not directly used as the optimized output in this embodiment because the forward will default to driving at the maximum speed according to the dynamics, and the driving direction can facilitate the design of the dynamics controller.

[0133] It should be noted that the first term of the above-mentioned first type of vehicle optimization function is used to ensure that the leading vehicle will try its best to sprint forward. This term not only makes the leading slow vehicle try its best to maintain its lead, but also makes the lagging slow vehicle catch up. The second term is used to ensure that the vehicle maintains a wider distance from other vehicles while sprinting to prevent blocking situations. This term not only prevents the leading slow vehicles from affecting each other, but also prevents the lagging slow vehicles from being too affected by the defensive line formed by their teammates.

[0134] Step S412: Determine the first vehicle path plan corresponding to the first type of vehicle through the first type of vehicle optimization function.

[0135] In its implementation, the system can obtain the driving direction θ of the first type of vehicle. i And the vehicle distance d between the forward moving target corresponding to the first type of vehicle and the first type of vehicle. ij In addition, it is also possible to obtain the first type of vehicle i at θi The position p(θ) that will be reached in the next moment when traveling in the downward direction. i ), p(θ i The corresponding position s on the track i (p(θ i The first type of vehicle optimization function can be determined based on the predicted time step T, and the first type of vehicle path planning can be determined by the first type of vehicle optimization function.

[0136] This embodiment performs path planning for the first type of vehicle based on the driving direction of the first type of vehicle and the distance between the target vehicle and the first type of vehicle, obtains the optimization function of the first type of vehicle, and determines the path planning of the first type of vehicle through the optimization function, thereby making the planned driving path of the first type of vehicle more reasonable and thus increasing the probability of the target vehicle winning.

[0137] refer to Figure 7 , Figure 7 This is a flowchart illustrating the third embodiment of the path planning method of the present invention.

[0138] Based on the above embodiments, in order to improve the rationality of the route planning for the second type of vehicle, in this embodiment, the step of determining the route planning for the second type of vehicle includes:

[0139] Step S421: Based on the defensive game objective corresponding to the second type of vehicle, perform path planning for the second type of vehicle to obtain the optimization function for the second type of vehicle.

[0140] It should be noted that the target of the aforementioned defender game can be any vehicle in the competing teams.

[0141] It should be understood that the above-mentioned second type of vehicle optimization function can be a function used to optimize the driving path corresponding to the second type of vehicle.

[0142] Step S422: Determine the second vehicle path planning corresponding to the second type of vehicle through the second type of vehicle optimization function.

[0143] Further, step S422 includes: predicting the game objective strategy of the defender in the prediction time using the second type of vehicle; determining the defender strategy of the second type of vehicle in the prediction time based on the game objective strategy and the optimization function of the second type of vehicle; determining the Nash equilibrium point based on the game objective strategy and the defender strategy, and determining the second vehicle path planning corresponding to the second type of vehicle through the Nash equilibrium point.

[0144] It is understood that in this embodiment, the above-mentioned prediction time is the prediction time step T, and there can be 0 steps in the prediction time step T; correspondingly, the above-mentioned game objective strategy can be the set of positions of the defender game objective in the next 0 steps within the prediction time T, wherein the game objective strategy is the decision variable of the second type of vehicle optimization function.

[0145] It should be noted that the Nash equilibrium point mentioned above can be the equilibrium point reached in the game between the second type of vehicle and the defender, where both the second type of vehicle and the defender know each other's equilibrium strategy and neither party can change its own strategy to increase its own benefit.

[0146] It should be understood that for the second type of vehicle i, i∈B, as a member of the defense line organizer, its driving goal, from the perspective of defense line construction, is to arrive at the interception point on the target line segment before the opponent's vehicle. However, the target line segment is merely a virtual target depicted for defense line construction. From a defensive perspective, its fundamental goal is still to find ways (such as using collision avoidance constraints) to reduce the opponent's vehicle's track progress. Therefore, the following optimization function for the second type of vehicle, which has both forward motivation and blocking aggression, can be designed:

[0147]

[0148] Among them, decision variables It can be the set of positions of the second type of vehicle i in the next o steps within the prediction time T, that is, the strategy of the second type of vehicle i (the above game objective strategy); This indicates that vehicle i of the second class adopts a game-theoretic objective strategy. The track progress at step 0; Indicates that competing vehicle j follows the defensive strategy θ i The optimal strategy will be adopted next. The track progress at step 0; α ij It is a weighting factor that represents the strength of the aggressive blocking intention of the second type of vehicle i against the competing vehicle, and can adapt to changes in the environment.

[0149] Understandably, the first term of the second type of vehicle optimization function ensures that the defender is still trying to finish the game; the second term helps the defender slow down the opponent's progress as much as possible, which is achieved by using collision avoidance to reduce the opponent's progress by approximately ||p. i -p j ||>d0 is the product of the game iteration, and the specific process may include: 1) Initializing the current initial position p of all intelligent vehicles. i p j ;2) The strategy of the defender i to predict the opponent vehicle j's next move within the predicted field of view T. j 3) The defenders, based on the predicted strategy θ j Based on the above optimization function, formulate its own strategy θ for the next o-step within the prediction horizon T.j 4) Repeat steps two and three, at which point the opposing sides will converge to a Nash equilibrium; 5) Set the Nash equilibrium point... As the optimal decision and execute it.

[0150] It should be understood that the second vehicle's path planning strategy does not directly adopt the interception strategy used during defense line construction. This is because the decision-making layer for constructing the defense line obtains the role allocation result under the worst-case scenario. However, the actual opponent's strategy may be more direct and short-sighted. Therefore, path planning needs to make local adjustments based on the opponent's real-time position. Furthermore, since each second-class vehicle in this embodiment can independently calculate its own optimization function and make decisions, the computation of the entire racing method is distributed.

[0151] Specifically, the system can perform path planning for the second type of vehicles based on the defensive game objective corresponding to the second type of vehicles, obtain the optimization function of the second type of vehicles, predict the game objective strategy of the defensive game objective within the prediction time through the second type of vehicles, and then determine the defensive strategy of the second type of vehicles within the prediction time. This allows the Nash equilibrium point between the second type of vehicles and the defensive game objective to be obtained based on the game objective strategy and the defensive strategy. The Nash equilibrium point is then used as the optimal decision and executed, that is, the path planning for the second type of vehicles is determined through the Nash equilibrium point.

[0152] In the specific implementation, refer to Figure 8 , Figure 8 This is a schematic diagram of the overall process of vehicle racing in the path planning method of this invention. Figure 8 As shown, before the target vehicle and the competing vehicle engage in the race, relevant personnel can input the data information of the racing lane, the target team's position information, and the competing team's information (i.e., enemy and friendly positions) into the system. At this time, the system can determine whether any vehicle has reached the finish line based on this information. If not, it can determine the shortest distance between each joint defense line and the competing vehicle based on the defense line equations corresponding to several constructed joint defense lines, and determine the optimal function of the defense line based on the shortest distance. Based on the optimal function of the defense line, the target joint defense line can be determined from all joint defense lines. Then, the target joint defense line can be used to assign roles to all vehicles in the target team, classifying them as forward vehicles (i.e., first-class vehicles) and rear guard vehicles (i.e., second-class vehicles). After the assignment is completed, path planning can be performed for the first-class vehicles based on the forward movement objective, and path planning can be performed for the second-class vehicles based on the rear guard game objective. Then, the first-class vehicles can directly perform path planning according to the path prediction control of the first-class vehicles. The second-class vehicles interact with the high-speed vehicles in the competing team to obtain the Nash equilibrium solution of the path planning game, in order to try to block the high-speed vehicles and increase the winning probability of the first-class vehicles.

[0153] It should be noted that this scheme uses five low-speed vehicles (equivalent to the target team) and one high-speed vehicle (equivalent to the competing team) to complete an autonomous driving racing competition on a specified map track. During the race, the low-speed vehicle teams will cooperate; slightly ahead low-speed vehicles will form a defensive line, approaching the high-speed vehicle to create obstruction and force it to slow down. Meanwhile, the other low-speed vehicles will try their best to move forward to finish the race faster and win. To demonstrate the effectiveness of the proposed path planning method, three sets of experiments were conducted, each repeated 100 times and the results were statistically analyzed. Furthermore, to fully illustrate the generalizability of the results, the initial position layout settings may differ for each experiment.

[0154] Specifically, in Experiment 1: all vehicles made no collaborative decisions and instead used only MPC (Model Predictive Control) to reach the finish line. (Refer to...) Figure 9 , Figure 9 This is a statistical chart of experimental results in the third embodiment of the path planning method of the present invention. The statistical results of Experiment 1 are as follows: Figure 9 As shown, high-speed vehicles have a 90% chance of winning, while low-speed vehicles win only when they have a significant advantage in the initial layout. (Refer to...) Figure 10 , Figure 10 This is a non-cooperative MPC race situation diagram in the third embodiment of the path planning method of the present invention. Figure 10 The image shows the positions and speeds of vehicles 0i (V≤0.8), 1j (V≤0.6), 2k (V≤0.6), 3z (V≤0.6), 4u (V≤0.6), and 5v (V≤0.6) on the track. As can be seen from the image, without teamwork, on a long track, high-speed vehicles will almost certainly be able to overtake and win due to their speed advantage.

[0155] Experiment 2: Teams of low-speed vehicles used our competition framework for collaborative decision-making, but the team size was small, with a ratio of less than 5:1 to the number of high-speed vehicles. Statistical results are as follows: Figure 9 As shown, the winning probability of the low-speed vehicle team has increased, but because the track has many curves and long straights, high-speed vehicles still have a certain probability of overtaking the low-speed vehicles ahead and gaining the lead. (Refer to...) Figure 11 , Figure 11 In the third embodiment of the path planning method of the present invention, the team has a competition framework and a competition situation diagram. Figure 11The figure shows the positions of Vehicle 0i (V≤0.9), Vehicle 2j (V≤0.6), and Vehicle 3k (V≤0.6) on the track, as well as their corresponding speeds. As can be seen from the figure, the path planning method proposed in this scheme generates rich interactive behaviors between low-speed teams and between low-speed teams and high-speed vehicles. This is beneficial and effective for the manifestation of swarm intelligence and successfully restricts the behavior of high-speed vehicles.

[0156] Experiment 3: Low-speed vehicle teams collaborated and made decisions using our competition framework, with a relatively large team size and a ratio of more than 5:1 between low-speed and high-speed vehicles. Statistical results are as follows: Figure 9 As shown, the winning probability of the low-speed vehicle team increases significantly, reaching 90%. High-speed vehicles are almost unable to break through the defenses formed by low-speed vehicles, and are frequently forced to slow down during the race, ultimately losing the competition. (Refer to...) Figure 12 , Figure 12 This is a competition framework diagram for a multi-member team in the third embodiment of the path planning method of the present invention. Figure 12 The experiment demonstrates the positions and speeds of vehicles 0i (V≤0.8), 1j (V≤0.6), 2k (V≤0.6), 3z (V≤0.6), 4u (V≤0.6), and 5v (V≤0.6) on the track. By comparing with the previous two sets of experiments, the effectiveness of the path planning method proposed in this study is demonstrated. This is a clear manifestation of swarm intelligence and has rich application value in scenarios requiring team collaboration.

[0157] This embodiment performs path planning for the second type of vehicle based on the defensive game objective corresponding to the second type of vehicle, obtains the optimization function of the second type of vehicle, and predicts the game objective strategy of the defensive game objective within the prediction time using the second type of vehicle. Then, based on the game objective strategy and the optimization function of the second type of vehicle, the defensive strategy of the second type of vehicle within the prediction time is determined. This allows the Nash equilibrium point to be determined based on the game objective strategy and the defensive strategy, and the path planning of the second type of vehicle can be determined through the Nash equilibrium point. As a result, the planned driving path of the second type of vehicle is more reasonable, thereby increasing the probability of the target vehicle winning.

[0158] Furthermore, embodiments of the present invention also propose a storage medium storing a path planning program, which, when executed by a processor, implements the steps of the path planning method described above.

[0159] Reference Figure 13 , Figure 13 This is a structural block diagram of the first embodiment of the path planning device of the present invention.

[0160] like Figure 13 As shown, the path planning device proposed in this embodiment of the invention includes:

[0161] The information determination module 501 is used to determine the location information of the target vehicle fleet and the location information of the competing vehicle fleet based on the current route planning data.

[0162] The defense line determination module 502 is used to construct several joint defense lines based on the target vehicle convoy location information and the competing vehicle convoy location information, and to determine the target joint defense line from each joint defense line;

[0163] The role assignment module 503 is used to assign roles to the target convoy based on the target joint defense line, and to determine the first type of vehicles and the second type of vehicles in the target convoy.

[0164] The route planning module 504 is used to determine the first vehicle route plan corresponding to the first type of vehicle and the second vehicle route plan corresponding to the second type of vehicle. The first vehicle route plan is used to instruct the first type of vehicle to travel, and the second vehicle route plan is used to instruct the second type of vehicle to travel.

[0165] Furthermore, the defense line determination module 502 is also used to construct several joint defense lines based on the target vehicle position information and the competing vehicle position information using the Apollonius circle model; establish defense line equations corresponding to each joint defense line based on the Apollonius circle model; and determine the target joint defense line from the joint defense lines according to the defense line equations.

[0166] Furthermore, the defense line determination module 502 is also used to obtain the number of vehicles corresponding to the target low-speed vehicles in each joint defense line; construct a defense line optimization function based on the number of vehicles and a preset cost coefficient matrix; and determine the target joint defense line from each joint defense line according to the defense line equation and the defense line optimization function.

[0167] This embodiment of the path planning device discloses determining the target team's position information and the competing team's position information based on current path planning data; constructing several joint defense lines based on the target team's position information and the competing team's position information, and determining the target joint defense line from each joint defense line; assigning roles to the target team based on the target joint defense line, and determining the first type of vehicles and the second type of vehicles in the target team; obtaining the first vehicle path plan corresponding to the first type of vehicle, and obtaining the second vehicle path plan corresponding to the second type of vehicle, the first vehicle path plan is used to instruct the first type of vehicle to drive, and the second vehicle path plan is used to instruct the second type of vehicle to drive; compared with the existing technology where the driving path planned by the trajectory following control method under obstacle avoidance constraints in the competition strategy has low reliability, this embodiment constructs joint defense lines based on the target team's position information and the competing team's position information, and determines the first type of vehicles and the second type of vehicles in the target team based on the target joint defense line in each joint defense line, and finally obtains the first vehicle path plan used to instruct the first type of vehicle to drive, and the second vehicle path plan used to instruct the second type of vehicle to drive, thereby solving the technical problem in the prior art where the planned path has low reliability due to many uncertainties when vehicles drive in the actual competition environment.

[0168] Based on the first embodiment of the path planning device of the present invention described above, a second embodiment of the path planning device of the present invention is proposed.

[0169] In this embodiment, the path planning module 504 is further configured to perform path planning for the first type of vehicle based on the forward motion target corresponding to the first type of vehicle, and obtain the first type of vehicle optimization function corresponding to the first type of vehicle; and determine the first vehicle path planning corresponding to the first type of vehicle through the first type of vehicle optimization function.

[0170] Furthermore, the path planning module 504 is also used to obtain the driving direction of the first type of vehicle and the vehicle distance between the forward moving target corresponding to the first type of vehicle and the first type of vehicle; perform path planning for the first type of vehicle based on the driving direction and the vehicle distance to obtain the first type of vehicle optimization function corresponding to the first type of vehicle.

[0171] This embodiment performs path planning for the first type of vehicle based on the driving direction of the first type of vehicle and the distance between the target vehicle and the first type of vehicle, obtains the optimization function of the first type of vehicle, and determines the path planning of the first type of vehicle through the optimization function, thereby making the planned driving path of the first type of vehicle more reasonable and thus increasing the probability of the target vehicle winning.

[0172] Based on the above embodiments, a third embodiment of the path planning device of the present invention is proposed.

[0173] In this embodiment, the path planning module 504 is further configured to perform path planning for the second type of vehicles based on the defensive game objective corresponding to the second type of vehicles, and obtain the second type of vehicle optimization function corresponding to the second type of vehicles; and determine the second vehicle path planning corresponding to the second type of vehicles through the second type of vehicle optimization function.

[0174] Furthermore, the path planning module 504 is also used to predict the game objective strategy of the defender in the prediction time using the second type of vehicle; determine the defender strategy of the second type of vehicle in the prediction time based on the game objective strategy and the optimization function of the second type of vehicle; determine the Nash equilibrium point based on the game objective strategy and the defender strategy, and determine the second vehicle path planning corresponding to the second type of vehicle through the Nash equilibrium point.

[0175] This embodiment performs path planning for the second type of vehicle based on the defensive game objective corresponding to the second type of vehicle, obtains the optimization function of the second type of vehicle, and predicts the game objective strategy of the defensive game objective within the prediction time using the second type of vehicle. Then, based on the game objective strategy and the optimization function of the second type of vehicle, the defensive strategy of the second type of vehicle within the prediction time is determined. This allows the Nash equilibrium point to be determined based on the game objective strategy and the defensive strategy, and the path planning of the second type of vehicle can be determined through the Nash equilibrium point. As a result, the planned driving path of the second type of vehicle is more reasonable, thereby increasing the probability of the target vehicle winning.

[0176] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0177] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0178] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0179] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A path planning method, characterized in that, The path planning method includes: Determine the location information of the target fleet and the competing fleets based on the current route planning data; Based on the target vehicle location information and the competing vehicle location information, several joint defense lines are constructed, and the target joint defense line is determined from each joint defense line; Based on the target joint defense line, the target convoy is assigned roles, and the first and second categories of vehicles in the target convoy are determined. A first vehicle route plan is determined for the first type of vehicle, and a second vehicle route plan is determined for the second type of vehicle. The first vehicle route plan is used to instruct the first type of vehicle to travel, and the second vehicle route plan is used to instruct the second type of vehicle to travel. The step of constructing several joint defense lines based on the target vehicle location information and the competing vehicle location information, and determining the target joint defense line from each joint defense line, includes: Based on the target vehicle's location information and the competing vehicle's location information, several joint defense lines are constructed using the Apollonius circle model. Based on the Apollonius circle model, establish the defense line equations corresponding to each joint defense line; Obtain the number of vehicles corresponding to the target low-speed vehicles in each of the joint defense lines; A defense line optimization function is constructed based on the number of vehicles and a preset cost coefficient matrix; The target joint defense line is determined from each joint defense line based on the defense line equation and the defense line optimization function.

2. The path planning method as described in claim 1, characterized in that, The step of determining the first vehicle route planning corresponding to the first type of vehicle includes: Based on the forward motion target corresponding to the first type of vehicle, path planning is performed on the first type of vehicle to obtain the first type of vehicle optimization function; The first vehicle path planning corresponding to the first type of vehicle is determined by the first type of vehicle optimization function.

3. The path planning method as described in claim 2, characterized in that, The step of performing path planning for the first type of vehicles based on the forward motion target corresponding to the first type of vehicles, and obtaining the optimization function for the first type of vehicles, includes: Obtain the driving direction of the first type of vehicle, and the vehicle distance between the foreground moving target corresponding to the first type of vehicle and the first type of vehicle; Based on the driving direction and the distance to the vehicle, path planning is performed on the first type of vehicle to obtain the first type of vehicle optimization function.

4. The path planning method as described in claim 1, characterized in that, The step of determining the second vehicle route planning corresponding to the second type of vehicle includes: Based on the defensive game objective corresponding to the second type of vehicle, path planning is performed on the second type of vehicle to obtain the optimization function of the second type of vehicle. The second vehicle path planning corresponding to the second type of vehicle is determined by the second type of vehicle optimization function.

5. The path planning method as described in claim 4, characterized in that, The step of determining the second vehicle path planning corresponding to the second type of vehicle through the second type of vehicle optimization function includes: The second type of vehicle is used to predict the target strategy of the defender in the game within the prediction time. The defensive strategy of the second type of vehicle within the predicted time period is determined based on the game objective strategy and the optimization function of the second type of vehicle. The Nash equilibrium point is determined based on the game objective strategy and the defender strategy, and the second vehicle path planning corresponding to the second type of vehicle is determined through the Nash equilibrium point.

6. A path planning device, characterized in that, The device includes: The information determination module is used to determine the location information of the target vehicle fleet and the competing vehicle fleet based on the current route planning data. The defense line determination module is used to construct several joint defense lines based on the target vehicle convoy location information and the competing vehicle convoy location information, and to determine the target joint defense line from each joint defense line; The role assignment module is used to assign roles to the target convoy based on the target joint defense line, and to determine the first type of vehicles and the second type of vehicles in the target convoy; The route planning module is used to determine the first vehicle route plan corresponding to the first type of vehicle and the second vehicle route plan corresponding to the second type of vehicle. The first vehicle route plan is used to instruct the first type of vehicle to travel, and the second vehicle route plan is used to instruct the second type of vehicle to travel. The defense line determination module is further configured to: construct several joint defense lines based on the target convoy location information and the competing convoy location information using the Apollonius circle model; establish defense line equations corresponding to each joint defense line based on the Apollonius circle model; obtain the number of vehicles corresponding to target low-speed vehicles in each joint defense line; construct a defense line optimization function based on the number of vehicles and a preset cost coefficient matrix; and determine the target joint defense line from each joint defense line according to the defense line equations and the defense line optimization function.

7. A path planning device, characterized in that, The device includes: a memory, a processor, and a path planning program stored in the memory and executable on the processor, the path planning program being configured to implement the steps of the path planning method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a path planning program, which, when executed by a processor, implements the steps of the path planning method as described in any one of claims 1 to 5.

Images