A Multi-Vehicle Cooperative Lateral and Longitudinal Joint Motion Planning Method and Device Based on Relative Coordinates

Abstract

This application discloses a multi-vehicle cooperative lateral and longitudinal joint motion planning method, device, electronic device, and storage medium based on relative coordinates. The method includes: generating the expected target positions of vehicles in a formation in a unified relative coordinate system based on the lateral and longitudinal motion requirements of the vehicles. These target positions provide input for subsequent multi-vehicle target allocation and relative path planning. This application matches vehicles one-to-one according to their preferred target positions, and then plans the relative motion paths of all vehicles to their target positions in the relative coordinate system. The motion of the vehicles in the relative coordinate system is further projected onto the absolute coordinate system, and the vehicles perform further absolute trajectory planning, including front wheel steering angle control sequences and longitudinal velocity (or acceleration) control sequences. This solves the problem of multi-vehicle cooperative motion planning with different motion requirements.

Description

Technical Field

[0001] This application relates to the field of vehicle cooperative planning technology, and in particular to a multi-vehicle cooperative lateral and longitudinal joint motion planning method, device, electronic device and storage medium based on relative coordinates. Background Technology

[0002] Currently, multi-vehicle cooperative motion planning methods based on absolute coordinates are difficult to avoid vehicle collisions. This is because when multiple vehicles travel forward at the same speed, even if their paths intersect in the geodetic coordinate system, they may not necessarily collide due to the time difference.

[0003] Existing multi-vehicle cooperative motion planning methods based on relative coordinate planning do not clearly explain how to handle different driving needs of vehicles. For example, vehicles may have longitudinal relative position priorities due to the urgency of the task, or lateral lane preferences due to the direction of travel at intersections. These issues urgently need to be addressed. Summary of the Invention

[0004] This application provides a method, device, electronic device, and storage medium for multi-vehicle cooperative lateral and longitudinal joint motion planning based on relative coordinates, in order to solve problems such as multi-vehicle cooperative motion planning with different motion requirements.

[0005] The first aspect of this application provides a multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates, comprising the following steps: generating multiple expected positions of the vehicles in the fleet in a relative coordinate system based on the lateral and longitudinal motion requirements of the vehicles in the fleet; matching a corresponding target position for each vehicle in the expected positions according to the preset allocation requirements of each vehicle in the fleet, and planning a relative path for each vehicle to reach the target position in the relative coordinate system; projecting the relative path to an absolute coordinate system to obtain the absolute trajectory planning of each vehicle, and controlling each vehicle to move according to the absolute trajectory planning.

[0006] Optionally, in one embodiment of this application, generating the expected position of each vehicle in the fleet in a relative coordinate system based on the lateral and longitudinal movement requirements of the fleet vehicles includes: calculating the expected number of vehicles arriving at each lane, and generating the plurality of expected positions in each lane from front to back according to the direction of travel at preset intervals.

[0007] Optionally, in one embodiment of this application, the step of matching a corresponding target location for each vehicle in the expected location according to the preset allocation requirements of each vehicle in the fleet includes: calculating the cost of allocating each vehicle to the plurality of expected target locations, and constructing a cost matrix based on the cost, wherein the cost is infinite when the vehicle is not allowed to be allocated to any target location; and matching a corresponding target location for each vehicle based on the cost matrix and the Hungarian algorithm.

[0008] Optionally, in one embodiment of this application, the step of planning the relative path for each vehicle to reach the target position in the relative coordinate system includes: planning the relative path required for all vehicles to reach the target position using the A* algorithm according to the allocation relationship between the vehicles and the target position, and setting the current path planning result as the root node; calculating the conflict relationship for the vehicles to perform the first step of movement according to the current path planning, wherein the conflict includes multiple vehicles arriving at the same position at the same time, or the paths of multiple vehicles intersecting within the same time period; applying the conflict relationship as a constraint to the conflicting vehicles in sequence, wherein the constraint includes prohibiting the conflicting vehicles from performing a specific action at a specific time, and the constraint applied by the root node will generate a branch as a child node after the root node; for each conflicting branch, based on the currently applied constraint, using the A* algorithm to plan the relative path required for each vehicle to reach the target position, and detecting the conflict relationship, while applying the conflict relationship as a constraint to the conflicting vehicles in sequence, repeating the process multiple times, and generating a conflict tree when the loop termination condition is met; in the conflict tree, the relative path corresponding to the node with the smallest total distance among the non-conflicting nodes is taken as the current optimal relative path.

[0009] Optionally, in one embodiment of this application, controlling the vehicle to move according to the absolute trajectory plan includes: generating a front wheel steering angle control sequence and a longitudinal speed or acceleration control sequence for the vehicle based on the absolute trajectory plan; and controlling the vehicle based on the front wheel steering angle control sequence and the longitudinal speed or acceleration control sequence.

[0010] A second aspect of this application provides a multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates, comprising: a generation module, configured to generate multiple expected positions of the vehicles in the fleet in a relative coordinate system based on the lateral and longitudinal motion requirements of the vehicles in the fleet; a matching module, configured to match a corresponding target position for each vehicle in the expected positions according to the preset allocation requirements of each vehicle in the fleet, and plan a relative path for each vehicle to reach the target position in the relative coordinate system; and a control module, configured to project the relative path to an absolute coordinate system to obtain an absolute trajectory plan for each vehicle, and control each vehicle to move according to the absolute trajectory plan.

[0011] Optionally, in one embodiment of this application, the matching module is specifically used to: calculate the cost of assigning each vehicle to the plurality of expected target locations, and construct a cost matrix based on the cost, wherein the cost is infinite when the vehicle is not allowed to be assigned to any target location; match a corresponding target location for each vehicle based on the cost matrix and the Hungarian algorithm; the step of planning the relative path for each vehicle to reach the target location in the relative coordinate system includes: planning the relative path required for all vehicles to reach the target location using the A* algorithm based on the allocation relationship between the vehicle and the target location, and setting the current path planning result as the root node; calculating the conflict relationship of the vehicle performing the first step of movement according to the current path planning, wherein the conflict includes multiple vehicles When multiple vehicles arrive at the same location at the same time, or when their paths intersect within the same time period, the conflict relationship is applied as a constraint to each vehicle in sequence. This constraint includes prohibiting the vehicles from performing specific actions at a specific time. The constraint applied by the root node will become a child node, creating a branch after the root node. For each conflicting branch, based on the currently applied constraints, the A* algorithm is used to plan the relative path required for each vehicle to reach the target location, and the conflict relationship is detected. Simultaneously, the conflict relationship is applied as a constraint to each vehicle in sequence. This process is repeated multiple times, and a conflict tree is generated when the loop termination condition is met. In the conflict tree, the relative path corresponding to the node with the smallest total distance among the non-conflicting nodes is taken as the current optimal relative path.

[0012] Optionally, in one embodiment of this application, controlling the vehicle to move according to the absolute trajectory plan includes: generating a front wheel steering angle control sequence and a longitudinal speed or acceleration control sequence for the vehicle based on the absolute trajectory plan; and controlling the vehicle based on the front wheel steering angle control sequence and the longitudinal speed or acceleration control sequence.

[0013] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates as described in the above embodiments.

[0014] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to perform the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates as described in the above embodiments.

[0015] Therefore, this application has at least the following beneficial effects:

[0016] By employing a multi-vehicle motion planning method based on relative coordinates, the perspective of vehicle motion planning and conflict resolution is shifted from an absolute coordinate system to a relative coordinate system that follows vehicle movement. First, the relative motion paths of the vehicles are planned. Then, the planned coordinate points are projected onto the absolute coordinate system, and the vehicles are controlled to continuously pass through designated waypoints within a specified time. This comprehensively considers the combined lateral and longitudinal motion requirements of the vehicles, controlling them to reach the desired relative positions while avoiding collisions. It achieves longitudinal sequential positioning and lateral lane distribution. Thus, it solves the problem of multi-vehicle cooperative motion planning with different motion requirements.

[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0019] Figure 1 This is a flowchart of a multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates provided in an embodiment of this application;

[0020] Figure 2 This is a schematic diagram of a conflict tree structure provided according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the initial and target positions of a vehicle according to an embodiment of this application;

[0022] Figure 4 This is a schematic diagram of the vehicle relative path planning result provided according to an embodiment of this application;

[0023] Figure 5 This is an example diagram of a multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates according to an embodiment of this application;

[0024] Figure 6 A schematic diagram of the structure of the electronic device provided in the application embodiment.

[0025] Explanation of reference numerals in the attached diagram: Generation module-100, Matching module-200, Control module-300, Memory-601, Processor-602, Communication interface-603. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0027] The following describes a multi-vehicle cooperative lateral and longitudinal joint motion planning method, apparatus, electronic device, and storage medium based on relative coordinates according to embodiments of this application, with reference to the accompanying drawings. Addressing the problems mentioned in the background art, this application provides a multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates. In this method, based on the lateral and longitudinal motion requirements of vehicles, the longitudinal direction considers the relative position requirements due to different vehicle task priorities, and the lateral direction considers the lane occupancy requirements of vehicles near intersections or ramp entrances / exits. The expected target positions of vehicles in the formation are uniformly generated in a relative coordinate system. Vehicles with the same requirements (i.e., the same longitudinal task priority and the same lateral lane occupancy requirements) will generate multiple target positions, and the allocation relationship between these vehicles and target positions can be arbitrarily interchanged. The target positions generated in the relative coordinate system provide input for subsequent multi-vehicle target allocation and relative path planning. Simultaneously, this application matches vehicles one-to-one according to their preferred target positions, and then plans the relative motion paths of all vehicles to their target positions in the relative coordinate system. This relative path refers to a continuous sequence of relative coordinate points for each vehicle, ensuring that no collisions occur between multiple vehicles. The vehicle's motion in the relative coordinate system is further projected onto the absolute coordinate system, allowing the vehicle to perform further absolute trajectory planning, including front wheel steering angle control sequences and longitudinal velocity (or acceleration) control sequences. This solves the problem of multi-vehicle cooperative motion planning with different motion requirements.

[0028] Specifically, Figure 1 This is a flowchart of a multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates provided in an embodiment of this application.

[0029] like Figure 1 As shown, the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates includes the following steps:

[0030] In step S101, based on the lateral and longitudinal movement requirements of the fleet vehicles, multiple expected positions of the fleet vehicles are generated in the relative coordinate system.

[0031] It should be noted that the embodiments of this application take into account the overall requirements of the combined lateral and longitudinal movement of vehicles, and uniformly generate the expected target position of vehicles in the formation in a relative coordinate system. Among them, in terms of lateral and longitudinal movement requirements, the longitudinal direction considers the relative position requirements of front and rear due to different vehicle task priorities, and the lateral direction considers the lane occupancy requirements of vehicles near intersections or ramp entrances and exits.

[0032] Understandably, vehicles may have the same needs. Vehicles with the same needs (meaning the same longitudinal task priority and the same lateral lane occupancy requirements) will generate multiple target locations, and the allocation relationship between these vehicles and target locations can be arbitrarily interchanged. The target locations generated in the relative coordinate system provide input for subsequent multi-vehicle target allocation and relative path planning.

[0033] Optionally, in one embodiment of this application, the expected position of each vehicle in the fleet is generated in a relative coordinate system based on the lateral and longitudinal movement requirements of the fleet vehicles, including: calculating the expected number of vehicles arriving at each lane, and generating multiple expected positions in each lane from front to back according to the direction of travel at preset intervals.

[0034] Specifically, in the embodiments of this application, the expected target positions of vehicles in a convoy are uniformly generated in a relative coordinate system based on the lateral and longitudinal movement requirements of the vehicles. For example, firstly, the cloud establishes a relative coordinate system for the movement of vehicles in a normally moving convoy, and plans the movement of vehicles in the relative coordinate system. The relative coordinate system moves forward with the vehicles, keeping the relative coordinates of vehicles moving at a constant speed unchanged. In the relative coordinate system, the vehicle movement plane is discretized into an equidistant grid to determine the coordinate position of the vehicle in the aforementioned relative coordinate system, thereby performing subsequent path and trajectory planning. If a vehicle in the convoy wants to turn at the intersection to the left ahead, the cloud calculates that only this vehicle has the expectation of turning forward. Before turning, the vehicle needs to change lanes sequentially to reach the left-turn lane to make the left turn. Therefore, the cloud generates multiple expected positions in the lanes it needs to travel in during the lane change process, from front to back according to the direction of travel, at preset intervals, such as 3 meters. Thus, the vehicle can travel to the corresponding target position to make the left turn. The selection of the corresponding target position is described in detail below.

[0035] In step S102, according to the preset allocation requirements of each vehicle in the fleet, a corresponding target position is matched for each vehicle in the expected position, and the relative path for each vehicle to reach the target position is planned in the relative coordinate system.

[0036] Based on the lateral and longitudinal movement requirements of the convoy vehicles, multiple expected positions of the vehicles are obtained. According to the target position preferences of each vehicle in the convoy, a corresponding target position is matched for each vehicle among the expected positions. Then, the relative movement paths of all vehicles to their target positions are planned in a relative coordinate system.

[0037] It should be noted that the path refers to planning how each vehicle arrives at a specified location at a specified time. Only the coordinates of the time and location are restricted, but the process of the vehicle moving between multiple coordinates is not restricted. It is guaranteed that as long as the vehicle moves continuously between multiple locations according to the given requirements, no collision will occur.

[0038] Optionally, in one embodiment of this application, matching a corresponding target location for each vehicle in the expected locations according to the preset allocation requirements of each vehicle in the fleet includes: calculating the cost of allocating each vehicle to multiple expected target locations, and constructing a cost matrix based on the cost, wherein the cost is infinite when a vehicle is not allowed to be allocated to any target location; and matching a corresponding target location for each vehicle based on the cost matrix and the Hungarian algorithm.

[0039] Specifically, embodiments of this application employ an improved Hungarian algorithm to match vehicles with target locations, the steps of which include:

[0040] Step 1: Define the cost matrix, which is the cost of assigning each vehicle to each target. Considering the allocation preference between vehicles and target locations (some vehicles can be assigned to a certain target, while others cannot), the allocation cost of vehicles and targets that cannot be matched is defined as infinite.

[0041] Step 2: Use the standard Hungarian algorithm to match multiple vehicle targets. The infinite matching cost set here will prevent vehicles from being matched with certain targets, since the total cost value is infinite.

[0042] For example, suppose the defined cost matrix is ​​C = [c i,j The value in the i-th row and j-th column represents the cost of assigning vehicle i to target j. An assignment matrix A = [a...] needs to be calculated. i,j The expression is defined as follows: If the element in the i-th row and j-th column is 1, it means vehicle i has been assigned to target j; if it is 0, it means vehicle i has not been assigned. This actually involves solving a mathematical integer programming problem, as follows:

[0043]

[0044]

[0045]

[0046]

[0047] It should be noted that the task of the above target allocation algorithm is to find a one-to-one allocation relationship that minimizes the sum of allocation costs between the assigned vehicles and the targets. The Hungarian algorithm and the simplex algorithm can both be used to solve the above target allocation problem; the specific method can be determined by those skilled in the art based on the actual situation, and no specific limitations are made here.

[0048] Then, the relative motion paths of all vehicles to their target positions are planned in the relative coordinate system. This relative path refers to a continuous sequence of relative coordinate points for each vehicle, and ensures that no collisions occur between multiple vehicles.

[0049] Specifically, in one embodiment of this application, the main steps of planning the relative path for each vehicle to reach the target location in a relative coordinate system include:

[0050] Step 1: After determining the allocation relationship between vehicles and targets, without considering collisions, use the A* algorithm to plan the relative paths required for all vehicles to reach the target location. The path planning result at this time is the root node.

[0051] Step 2: Calculate the conflicts that occur when all vehicles move in the first step. This conflict refers to multiple vehicles arriving at the same position at the same time, or multiple vehicles' paths intersecting within the same time period.

[0052] Step 3: Apply the conflicts detected in Step 2 as constraints to the conflicting vehicles sequentially. Each constraint prohibits a vehicle from performing a certain action at a given time. This resolves a conflict because one of the conflicting vehicles is prohibited from engaging in the conflicting action, while the other vehicle maintains its original planned path. Constraints applied by the root node will create a branch as a child node following the root node.

[0053] Step 4: For each branch where there is still a conflict, continue to use the A* algorithm to plan the relative path required to reach the target position for each vehicle while only considering the constraints currently applied. Continue to detect conflicts and continue to apply the constraints to the conflicting vehicles in the current node. In this way, the new path planning result will be used as the child node of the constrained node to continue to expand the conflict tree.

[0054] Step 5: Repeat Step 4 until the computation time reaches the specified maximum computation time, or there are no more conflicting nodes in the conflict tree. At this point, the relative path corresponding to the node with the smallest total distance among all conflict-free nodes is the optimal path obtained so far.

[0055] For example, an example of a conflict tree is as follows: Figure 2 As shown, the root node is numbered 0 and has no constraints, but there are two conflicts. These two constraints are transformed into two constraints and applied to the root node, resulting in two child nodes. The two child nodes have constraints 1 and 2 respectively. After planning for the child node of constraint 1, two new conflicts are generated, namely conflict 4 and conflict 5. These two conflicts are then applied to node 1, generating two child nodes of node 1. In addition to inheriting the existing constraints of node 1, these child nodes also transform conflict 4 and conflict 5 into constraints 4 and 5 respectively. In child node 3, which is constrained by constraints 1 and 4, there are no new conflicts in its path planning result, that is, a conflict-free relative path planning result is found. Other conflicting nodes will continue to transform conflicts into constraints and generate child nodes until a conflict-free child node is generated.

[0056] In step S103, the relative path is projected onto the absolute coordinate system to obtain the absolute trajectory plan for each vehicle, and each vehicle is controlled to move according to the absolute trajectory plan.

[0057] After obtaining the key point coordinates provided by cloud computing, the relative coordinates are projected onto the absolute coordinates, and the actual movement trajectory of the vehicle is planned on the vehicle side according to the location of the coordinate points and the required arrival time.

[0058] It should be noted that the trajectory refers to the speed and front wheel steering angle control inputs required to ensure that the vehicle continuously reaches the specified position at a specified time after the above path planning is completed.

[0059] In the embodiments of this application, controlling the vehicle to move according to the absolute trajectory planning includes: the motion of the vehicle in the relative coordinate system is further projected into the absolute coordinate system, the vehicle performs further absolute trajectory planning accordingly, generates a front wheel steering angle control sequence and a longitudinal speed or acceleration control sequence based on the absolute trajectory planning, and controls the vehicle according to the front wheel steering angle control sequence and the longitudinal speed or acceleration control sequence.

[0060] For example, a feasible trajectory planning method is to first connect the absolute coordinate points using a Bézier curve, then use a proportional-integral-derivative controller to control the lateral steering input of the vehicle, use the length of the Bézier curve to represent the vehicle's travel distance, and solve for the vehicle's longitudinal control input based on the optimal control method with fixed initial and final states.

[0061] like Figure 3 As shown, it displays the current relative position of a vehicle and the relative position of a target. The black circles represent unoccupied coordinates in the relative coordinate system, which the vehicle can move to during its movement. The path planning result is as follows: Figure 4 As shown, the vehicle goes through three steps to adjust from the current state to the target state.

[0062] It is important to note that in the above results, some vehicles appear to be moving backward. This is because the planning is carried out in a relative coordinate system, and the relative coordinate system moves forward together with the group of vehicles. The backward movement of the vehicles in the relative coordinate system is actually deceleration in the absolute coordinate system, which does not violate the rules of vehicle motion.

[0063] The multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates proposed in this application generates multiple expected positions of vehicles in a convoy in a relative coordinate system based on the lateral and longitudinal motion requirements of the vehicles. According to the preset allocation requirements of each vehicle in the convoy, a corresponding target position is matched for each vehicle among the expected positions, and a relative path for each vehicle to reach the target position is planned in the relative coordinate system. The relative path is projected onto an absolute coordinate system to obtain the absolute trajectory planning for each vehicle, and each vehicle is controlled to move according to the absolute trajectory planning. This comprehensively considers the lateral and longitudinal joint motion requirements of the vehicles, controlling the vehicles to reach the desired relative positions while avoiding vehicle collisions, thus achieving longitudinal sequential positioning and lateral lane distribution.

[0064] Next, referring to the accompanying drawings, a multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates, according to an embodiment of this application, is described.

[0065] Figure 5 This is a block diagram of a multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates according to an embodiment of this application.

[0066] like Figure 5 As shown, the multi-vehicle collaborative lateral and longitudinal joint motion planning device 10 based on relative coordinates includes: a generation module 100, a matching module 200, and a control module 300.

[0067] The generation module 100 is used to generate multiple expected positions of vehicles in the fleet in a relative coordinate system based on the lateral and longitudinal movement requirements of the vehicles in the fleet; the matching module 200 is used to match a corresponding target position for each vehicle in the expected positions according to the preset allocation requirements of each vehicle in the fleet, and to plan the relative path of each vehicle to the target position in the relative coordinate system; the control module 300 is used to project the relative path to the absolute coordinate system to obtain the absolute trajectory planning of each vehicle, and control each vehicle to move according to the absolute trajectory planning.

[0068] Optionally, in one embodiment of this application, the generation module 100 is specifically used to calculate the expected number of vehicles arriving at each lane and generate multiple expected positions in each lane from front to back according to the direction of travel at preset intervals.

[0069] Optionally, in one embodiment of this application, matching a corresponding target location for each vehicle in the expected locations according to the preset allocation requirements of each vehicle in the fleet includes: calculating the cost of allocating each vehicle to multiple expected target locations, and constructing a cost matrix based on the cost, wherein the cost is infinite when a vehicle is not allowed to be allocated to any target location; and matching a corresponding target location for each vehicle based on the cost matrix and the Hungarian algorithm.

[0070] Optionally, in one embodiment of this application, planning the relative path for each vehicle to reach the target location in a relative coordinate system includes: planning the relative paths required for all vehicles to reach the target location using the A* algorithm based on the allocation relationship between vehicles and target locations, and setting the current path planning result as the root node; calculating the conflict relationship for vehicles to perform the first step of movement according to the current path planning, where conflicts include multiple vehicles arriving at the same location at the same time, or the paths of multiple vehicles intersecting within the same time period; applying the conflict relationship as constraints to the conflicting vehicles in sequence, where constraints include prohibiting the conflicting vehicles from performing specific actions at a specific time, and the constraints applied by the root node will generate a branch as a child node after the root node; for each conflicting branch, based on the currently applied constraints, using the A* algorithm to plan the relative path required for each vehicle to reach the target location, and detecting conflict relationships, while applying the conflict relationship as constraints to the conflicting vehicles in sequence, repeating the process multiple times, and generating a conflict tree when the loop termination condition is met; in the conflict tree, the relative path corresponding to the node with the smallest total distance among the non-conflicting nodes is taken as the current optimal relative path.

[0071] Optionally, in one embodiment of this application, controlling the vehicle to move according to an absolute trajectory plan includes: generating a front wheel steering angle control sequence and a longitudinal speed or acceleration control sequence based on the absolute trajectory plan; and controlling the vehicle based on the front wheel steering angle control sequence and the longitudinal speed or acceleration control sequence.

[0072] It should be noted that the foregoing explanation of the embodiment of the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates also applies to the multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates in this embodiment, and will not be repeated here.

[0073] The multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates proposed in this application generates multiple expected positions of vehicles in a convoy in a relative coordinate system based on the lateral and longitudinal motion requirements of the vehicles. According to the preset allocation requirements of each vehicle in the convoy, a corresponding target position is matched for each vehicle among the expected positions, and a relative path for each vehicle to reach the target position is planned in the relative coordinate system. The relative path is projected onto an absolute coordinate system to obtain the absolute trajectory planning for each vehicle, and each vehicle is controlled to move according to the absolute trajectory planning. This comprehensively considers the lateral and longitudinal joint motion requirements of the vehicles, controlling the vehicles to reach the desired relative positions while avoiding vehicle collisions, thus achieving longitudinal sequential positioning and lateral lane distribution.

[0074] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0075] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0076] When the processor 602 executes the program, it implements the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates provided in the above embodiments.

[0077] Furthermore, electronic devices also include:

[0078] Communication interface 603 is used for communication between memory 601 and processor 602.

[0079] The memory 601 is used to store computer programs that can run on the processor 602.

[0080] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0081] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0082] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0083] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0084] This embodiment also provides a computer-readable storage medium storing a computer program, characterized in that the program, when executed by a processor, implements the above-described multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates.

[0085] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0086] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0087] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0088] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0089] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates, characterized in that, Includes the following steps: Based on the lateral and longitudinal movement requirements of the fleet vehicles, multiple expected positions of the fleet vehicles are generated in a relative coordinate system. According to the preset allocation requirements of each vehicle in the fleet, a corresponding target position is matched for each vehicle in the expected position, and a relative path for each vehicle to reach the target position is planned in the relative coordinate system; The relative path is projected onto the absolute coordinate system to obtain the absolute trajectory plan for each vehicle, and each vehicle is controlled to move according to the absolute trajectory plan. Planning the relative path for each vehicle to reach the target location in the relative coordinate system includes: Based on the allocation relationship between the vehicles and the target location, the A* algorithm is used to plan the relative paths required for all vehicles to reach the target location, and the current path planning result is set as the root node; Calculate the conflict relationships when the vehicle makes its first step according to the current path plan. The conflict includes multiple vehicles arriving at the same position at the same time, or multiple vehicles' paths intersecting within the same time period. The conflict relationship is applied as a constraint to the conflicting vehicles in sequence. The constraint includes prohibiting the conflicting vehicles from performing a specific action at a specific time. The constraint applied by the root node will generate a branch as a child node after the root node. For each conflicting branch, based on the currently applied constraints, the A* algorithm is used to plan the relative path required to reach the target location for each vehicle, and the conflict relationship is detected. At the same time, the conflict relationship is applied as a constraint to the conflicting vehicles in turn. This process is repeated multiple times, and a conflict tree is generated when the loop termination condition is met. In the conflict tree, the relative path corresponding to the node with the smallest total distance among the conflict-free nodes is taken as the current optimal relative path.

2. The method according to claim 1, characterized in that, The process of generating the expected position of each vehicle in the convoy in a relative coordinate system based on the lateral and longitudinal movement requirements of the convoy vehicles includes: Calculate the expected number of vehicles arriving in each lane, and generate the multiple expected locations in each lane from front to back according to the direction of travel at preset intervals.

3. The method according to claim 1, characterized in that, The step of matching a corresponding target location for each vehicle in the expected location according to the preset allocation requirements of each vehicle in the fleet includes: Calculate the cost of assigning each vehicle to multiple expected target locations, and construct a cost matrix based on the costs, wherein the cost is infinite when the vehicle is not allowed to be assigned to any target location; The target location is matched for each vehicle based on the cost matrix and the Hungarian algorithm.

4. The method according to claim 1, characterized in that, Controlling the vehicle to move according to the absolute trajectory plan includes: The vehicle's front wheel steering angle control sequence and longitudinal speed or acceleration control sequence are generated based on the absolute trajectory planning. The vehicle is controlled according to the front wheel steering angle control sequence and the longitudinal speed or acceleration control sequence.

5. A multi-vehicle cooperative lateral and longitudinal joint motion planning device based on relative coordinates, characterized in that, include: The generation module is used to generate multiple expected positions of the vehicles in the fleet in a relative coordinate system based on the lateral and longitudinal movement requirements of the fleet vehicles. The matching module is used to match a corresponding target position for each vehicle in the expected position according to the preset allocation requirements of each vehicle in the fleet, and to plan the relative path for each vehicle to reach the target position in the relative coordinate system; The control module is used to project the relative path onto the absolute coordinate system to obtain the absolute trajectory plan for each vehicle, and control each vehicle to move according to the absolute trajectory plan; The step of planning the relative path for each vehicle to reach the target location in the relative coordinate system includes: Based on the allocation relationship between the vehicles and the target location, the A* algorithm is used to plan the relative paths required for all vehicles to reach the target location, and the current path planning result is set as the root node; Calculate the conflict relationships when the vehicle makes its first step according to the current path plan. The conflict includes multiple vehicles arriving at the same position at the same time, or multiple vehicles' paths intersecting within the same time period. The conflict relationship is applied as a constraint to the conflicting vehicles in sequence. The constraint includes prohibiting the conflicting vehicles from performing a specific action at a specific time. The constraint applied by the root node will generate a branch as a child node after the root node. For each conflicting branch, based on the currently applied constraints, the A* algorithm is used to plan the relative path required to reach the target location for each vehicle, and the conflict relationship is detected. At the same time, the conflict relationship is applied as a constraint to the conflicting vehicles in turn. This process is repeated multiple times, and a conflict tree is generated when the loop termination condition is met. In the conflict tree, the relative path corresponding to the node with the smallest total distance among the conflict-free nodes is taken as the current optimal relative path.

6. The apparatus according to claim 5, characterized in that, The matching module is specifically used for, Calculate the cost of assigning each vehicle to multiple expected target locations, and construct a cost matrix based on the costs, wherein the cost is infinite when the vehicle is not allowed to be assigned to any target location; The target location is matched for each vehicle based on the cost matrix and the Hungarian algorithm.

7. The apparatus according to claim 6, characterized in that, Controlling the vehicle to move according to the absolute trajectory plan includes: The vehicle's front wheel steering angle control sequence and longitudinal speed or acceleration control sequence are generated based on the absolute trajectory planning. The vehicle is controlled according to the front wheel steering angle control sequence and the longitudinal speed or acceleration control sequence.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates as described in any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the multi-vehicle cooperative lateral and longitudinal joint motion planning method based on relative coordinates as described in any one of claims 1-4.

Images