Method and device for optimizing path of platooning vehicle, vehicle and storage medium

Abstract

The application relates to the technical field of vehicles, in particular to a path optimization method and device for a following vehicle in a column, apparatus and a storage medium, wherein the method comprises the following steps: obtaining an optimal planning path of a host vehicle in a target area and a historical path of a leading vehicle; determining a first evaluation value of the optimal planning path and a second evaluation value of the historical path according to the target area, the optimal planning path and the historical path; determining the optimal planning path or the historical path as an optimal following path of the host vehicle according to the first evaluation value and the second evaluation value, and controlling the host vehicle to perform a following action based on the optimal following path. Therefore, the problems that the following vehicle usually performs following driving based on the historical trajectory of the leading vehicle in the prior art, the following vehicle is prone to take a shortcut or perform unstable driving, and the safety and stability of the following driving are poor are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a path optimization method, apparatus, vehicle, and storage medium for platooning vehicles. Background Technology

[0002] In platooning scenarios, a typical platoon includes a lead vehicle and one or more following vehicles. The lead vehicle can be driven manually or autonomously, generating a historical trajectory. The following vehicles in the platoon can then drive autonomously based on the lead vehicle's historical trajectory. Therefore, ensuring the stability and safety of platooning has become a pressing issue.

[0003] In related technologies, in order to ensure the stability of convoy driving and maintain a safe distance, the lead vehicle needs to provide more path information. The path information needs to be transmitted between vehicles in the convoy through V2X (vehicle to X) equipment. At the same time, in order to ensure the reliability of transmission, a certain amount of transmission bandwidth usually needs to be reserved.

[0004] However, due to the characteristics of V2X device transmission, the size of data packets is limited. Therefore, whether information compression or decompression sampling is used, the amount of information, such as trajectory data density, may be reduced, resulting in insufficient trajectory points for the following vehicle. Once in complex road conditions such as curves, it is easy to cause the following vehicle to take shortcuts or become unstable when collecting and tracking data, which greatly reduces the safety and reliability of following the vehicle. Summary of the Invention

[0005] This application provides a path optimization method, device, vehicle, and storage medium for platooning vehicles, to solve the problems in related technologies where following vehicles usually follow the historical trajectory of the lead vehicle, which can easily lead to shortcuts or unstable driving, resulting in poor safety and stability of following vehicles.

[0006] The first aspect of this application provides a path optimization method for platooning vehicles, comprising the following steps: obtaining the optimal planned path of the vehicle in a target area and the historical path of the lead vehicle; determining a first evaluation value of the optimal planned path and a second evaluation value of the historical path based on the target area, the optimal planned path, and the historical path; determining the optimal planned path or the historical path as the optimal following path for the vehicle based on the first evaluation value and the second evaluation value, and controlling the vehicle to perform a following action based on the optimal following path.

[0007] Optionally, determining the optimal planned path or the historical path as the optimal following path for the vehicle based on the first evaluation value and the second evaluation value further includes: when the first evaluation value and the second evaluation value are equal, generating the optimal path for the vehicle based on the historical path; otherwise, generating the optimal following path for the vehicle based on the path corresponding to the optimal value among the first evaluation value and the second evaluation value.

[0008] Optionally, determining a first evaluation value for the optimal planning path and a second evaluation value for the historical path based on the target area, the optimal planning path, and the historical path includes: obtaining at least one first actual distance between the optimal planning path and the boundary of the target area, and at least one second actual distance between the historical path and the boundary of the target area; calculating the first evaluation value based on the at least one first actual distance and the target safety distance, and calculating the second evaluation value based on the at least one second actual distance and the target safety distance.

[0009] Optionally, obtaining the optimal planned path of the vehicle within the target area includes: obtaining road information of the vehicle within the target area; performing binary encoding on the road information to generate at least one candidate path; selecting a target path from the at least one candidate path using a genetic algorithm, and smoothing the target path to generate the optimal planned path.

[0010] Optionally, the road information includes road boundaries and lane centerlines. The step of generating at least one candidate path by binary encoding the road information includes: dividing the target area longitudinally into equal parts according to the road boundaries and lane centerlines to obtain multiple path cross-sections; dividing each path cross-section laterally into equal parts according to a preset span to obtain multiple path points; and binary encoding the multiple path points to generate at least one candidate path.

[0011] A second aspect of this application provides a path optimization device for platooning vehicles, comprising: an acquisition module for acquiring the optimal planned path of the vehicle in a target area and the historical path of the lead vehicle; an evaluation module for determining a first evaluation value of the optimal planned path and a second evaluation value of the historical path based on the target area, the optimal planned path, and the historical path; and a control module for determining the optimal planned path or the historical path as the optimal following path for the vehicle based on the first evaluation value and the second evaluation value, and controlling the vehicle to perform a following action based on the optimal following path.

[0012] Optionally, the acquisition module is configured to: acquire road information of the vehicle within the target area; perform binary encoding on the road information to generate at least one candidate path; select a target path from the at least one candidate path using a genetic algorithm, and perform smoothing processing on the target path to generate the optimal planned path.

[0013] Optionally, the evaluation module is configured to: obtain at least one first actual distance between the optimal planned path and the boundary of the target area, and at least one second actual distance between the historical path and the boundary of the target area; calculate the first evaluation value based on the at least one first actual distance and the target safety distance, and calculate the second evaluation value based on the at least one second actual distance and the target safety distance.

[0014] Optionally, the control module is configured to: generate the optimal path for the vehicle based on the historical path when the first evaluation value and the second evaluation value are equal; otherwise, generate the optimal following path for the vehicle based on the path corresponding to the optimal value among the first evaluation value and the second evaluation value.

[0015] Optionally, the road information includes road boundaries and lane centerlines, and the acquisition module is further configured to: longitudinally divide the target area into multiple path sections according to the road boundaries and lane centerlines; laterally divide each path section into multiple path points according to a preset span; and binary encode the multiple path points to generate at least one candidate path.

[0016] A third aspect of this application provides a vehicle, 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 implement the path optimization method for platooning vehicles as described in the above embodiments.

[0017] 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 implement the path optimization method for platooning vehicles as described in the above embodiments.

[0018] Therefore, this application has at least the following beneficial effects:

[0019] Because the following vehicles have self-planning capabilities when driving in convoy, they can jointly determine an optimal route based on their own planned path and the lead vehicle's historical path. This avoids the limitations of relying solely on the lead vehicle's historical path, effectively preventing shortcuts or unstable swaying during automatic following, significantly improving the safety and stability of convoy driving and enhancing the user experience. This solves the technical problems in related technologies where following vehicles typically rely on the lead vehicle's historical trajectory, easily leading to shortcuts or unstable swaying, resulting in poor safety and stability during convoy driving.

[0020] 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

[0021] 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:

[0022] Figure 1 This is a flowchart of a path optimization method for platooning vehicles according to an embodiment of this application;

[0023] Figure 2 This is a flowchart illustrating the workflow provided according to an embodiment of this application;

[0024] Figure 3 This is a schematic diagram illustrating the use of a genetic algorithm to find the optimal solution according to an embodiment of this application.

[0025] Figure 4 This is an example diagram of a path optimization device for platooning vehicles provided according to an embodiment of this application;

[0026] Figure 5 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0027] 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.

[0028] When autonomous vehicles perform obstacle avoidance, lane changing, and overtaking maneuvers, they need to plan the desired driving path within a 100-meter radius of their current position to smoothly navigate around obstacles and maintain an appropriate safety distance. Therefore, path planning needs to consider two important factors: the real-time performance of the planning algorithm and the smoothness of the output path. Related technologies can be based on an EM (Expectation-Maximum) iterative algorithm, employing a two-level EM dynamic and static obstacle projection state grid occupancy strategy. Safety and passenger experience are achieved through a combination of multi-lane, path speed iteration, traffic rules, and decision-making. The planning evaluation criteria are safety and comfort. In other aspects, when using path planning, obstacles and roads are segmented into grids and occupancy areas to provide a passable area for path planning. For autonomous vehicles traveling in a convoy, the lead vehicle (usually driven by a human) typically generates a trajectory based on its own driving path and broadcasts it to the following vehicles via V2X equipment. The following vehicles then decode the trajectory information to complete autonomous driving trajectory tracking. Therefore, the path planning task during convoy driving is mainly performed by the lead vehicle, while the following vehicles drive according to the received path without performing additional path planning.

[0029] In platooning, whether the lead vehicle is manually or autonomously driven, it provides a passable trajectory (driving path) for the following vehicles. To ensure the stability of platooning and maintain a safe following distance, the lead vehicle needs to provide more path information. This additional planning information needs to be transmitted between vehicles in the platoon via V2X devices. To ensure transmission reliability, a certain amount of bandwidth needs to be reserved, thus limiting the size of data packets. Therefore, whether information compression or decompression sampling is used, it may reduce the amount of information, such as trajectory data density. This can lead to insufficient trajectory points when the following vehicle is tracking the trajectory, causing vehicles to "cut corners" on curves or become unstable. Furthermore, due to the influence of the safe distance between platooning vehicles and their own length, coupled with environmental interference, delays or intermittent interruptions in information transmission are inevitable. Moreover, the path traveled by the lead vehicle may no longer be suitable for the following vehicle to continue following after specific changes in traffic conditions behind it. Therefore, the following vehicles need to participate in the driving path planning themselves and form a global planning and feedback mechanism with the lead vehicle to adapt to more complex platooning scenarios.

[0030] The following description, with reference to the accompanying drawings, outlines a method, apparatus, vehicle, and storage medium for optimizing the path of platooning vehicles according to embodiments of this application.

[0031] Specifically, Figure 1 This is a flowchart illustrating a path optimization method for platooning vehicles provided in an embodiment of this application.

[0032] like Figure 1 As shown, the path optimization method for this convoy of following vehicles includes the following steps:

[0033] In step S101, the optimal planned path of the vehicle within the target area and the historical path of the lead vehicle are obtained.

[0034] The historical route of the lead vehicle refers to the route that the lead vehicle has already traveled; the target area can be understood as the passable space of this lane.

[0035] It is understood that during convoy driving, the following vehicles in this embodiment of the application have self-planning capabilities, enabling them to plan their own routes. Thus, the following vehicles in this embodiment of the application can obtain two selectable routes when driving alongside other vehicles: the route planned by the vehicle itself and the historical route of the lead vehicle.

[0036] The embodiments of this application can obtain the optimal planned path of the vehicle in the target area through at least one method, without making specific limitations thereto.

[0037] As one possible implementation, the steps of obtaining the optimal planned path of the vehicle in the target area in this application embodiment may include: obtaining road information of the vehicle in the target area; performing binary encoding on the road information to generate at least one candidate path; selecting the target path from the at least one candidate path through a genetic algorithm, and smoothing the target path to generate the optimal planned path.

[0038] The road information includes information such as road boundaries and lane centerlines.

[0039] It is understood that embodiments of this application can obtain lane line information and an obstacle list of the current lane from the perception system of the currently following vehicle, and construct a target area, such as... Figure 2 As shown, if the constructed target area meets the passage conditions, then path candidates and target area boundaries are established, and the reference trajectory is sampled and a preset candidate path is generated using binary encoding. At the same time, an evaluation model for the candidate path is established, and the candidate path is optimized using a genetic algorithm.

[0040] Therefore, the application embodiment can optimize the process from the global path, avoiding the possibility of local path optimization; at the same time, the application embodiment adopts binary encoding and explicit optimization method, so that the arbitrary driving process of the platoon vehicles is controllable and calibrated and adjustable, with greater flexibility, without the need for larger operating space and higher computing power, and it is easy to realize real-time path planning and scheme implementation.

[0041] The following sections will elaborate on candidate path preparation and follow-up path optimization, as detailed below:

[0042] In this embodiment of the application, generating at least one candidate path by binary encoding based on road information includes: dividing the target area longitudinally into equal parts according to the road boundary and the lane centerline to obtain multiple path sections; dividing each path section laterally into equal parts according to a preset span to obtain multiple path points; and binary encoding the multiple path points to generate at least one candidate path.

[0043] It is understood that the embodiments of this application can perform image processing and semantic segmentation processing to generate road boundaries and lane centerlines as path reference benchmarks. For example, the embodiments of this application can establish curves for path segmentation in the Flexner coordinate system with road boundaries and lane centerlines as reference benchmarks, and then perform longitudinal equal division within a certain perception distance in front of the vehicle; wherein, the number of equal divisions is used as the length of individual genes (path sections), and each segmented section is laterally divided with a certain span as gene alternatives (path points).

[0044] It should be noted that the embodiments of this application can use the lane centerline as the baseline for sampling; if lane changing or overtaking is considered, a four-digit two-dimensional coding method can be added to encode the sampling points, thereby improving the adaptability of path optimization and enhancing the user experience. The specific application shall prevail, and no specific limitation is made.

[0045] For example, suppose that individual 1 in this embodiment of the application is 101110101011000011 = 565303, and the lateral sampling unit in this embodiment of the application is 0.5 meters. Then, 565303 represents the sampling point offsets as follows: 2.5m, 3.0m, 2.5m, 1.5m, 0m, and 1.5m. In this case, individual 1 can represent path 1. Similarly, in the complete mapping relationship, suppose there exists individual 2 001100000101110101 = 1 40565 indicates that the sampling point offsets are 0.5m, 2.0m, 0m, 2.5m, 3.0m, and 2.5m, which can represent path 2; there is an individual 100101101101010010 = 455522, which indicates that the sampling point offsets are 2.0m, 2.5m, 2.5m, 1.0m, and 1.0m, which can represent path 3, and so on; that is, each individual is a candidate path to be selected in the algorithm.

[0046] In this embodiment, a genetic algorithm can be applied to select the current path from candidate paths. The objective function of the evaluation model can be min(f(uc,ua,us)), which takes the minimum safe distance uc, minimum yaw rate ua, and shortest path us as boundary constraints. Here, uc considers both following distance and obstacle avoidance distance, while us represents the curve length of the path. The assimilation rate (i.e., the proportion of identical genes in an individual) and the probability of mutation or crossover can be specifically set according to actual conditions. For example, in this embodiment, the assimilation rate can be set to 95%, and the probability of mutation or crossover can be randomly selected between 0.6 and 0.95. This embodiment also needs to limit the number of evolutionary iterations.

[0047] It should be noted that the embodiments of this application can use at least one genetic algorithm to select a target path from at least one candidate path. For example, the embodiments of this application can use a genetic algorithm that searches for the optimal solution by simulating the natural evolution process to optimize the path.

[0048] Specifically, the process of using a genetic algorithm to find the optimal solution in the embodiments of this application can be illustrated as follows: Figure 3 As shown, this algorithm can find the optimal solution by encoding the possible global solutions of the problem. For example, binary encoding, floating-point encoding, and symbolic encoding can be used. After encoding, these solution options become genetic individuals (genes) in the genetic algorithm and participate in the evolutionary cycle of individuals. Through the inheritance, optimization evaluation and replacement of individuals, and crossover or mutation according to a certain probability, a new population is generated, completing one evolution, and proceeding to the next generation of inheritance and mutation update process until the optimal combination of individuals (global optimal solution) is evolved, that is, all or most individuals are assimilated.

[0049] In step S102, based on the target area, the optimal planning path, and the historical path, the first evaluation value of the optimal planning path and the second evaluation value of the historical path are determined.

[0050] It is understandable that after the following vehicle has completed the selection of its own optimal path, it has two path options: the historical path from the lead vehicle and the best path selected by the following vehicle. Therefore, in this embodiment of the application, the optimal path can be selected by calculating the evaluation value of each path.

[0051] In this embodiment of the application, determining a first evaluation value of the optimal planning path and a second evaluation value of the historical path based on the target area, the optimal planning path, and the historical path includes: obtaining at least one first actual distance between the optimal planning path and the boundary of the target area, and at least one second actual distance between the historical path and the boundary of the target area; calculating a first evaluation value based on at least one first actual distance and a target safety distance, and calculating a second evaluation value based on at least one second actual distance and a target safety distance.

[0052] It is understood that the embodiments of this application can determine the evaluation value of each path based on the actual distance between each path and the boundary of the target area. For example, the average value of the ratio between the actual distance and the target safe distance can be used as the evaluation value, and those skilled in the art can set it according to the actual situation, without making specific limitations. Taking the calculation of the ratio as an example, the lower the ratio, the closer to the boundary and the worse the safety. Therefore, the embodiments of this application can set that the smaller the ratio, the lower the evaluation value, etc. For example, the target safe distance can be set to 2m. If the first actual distance is 1m and the second actual distance is 0.5m, then the first evaluation value is calculated to be 0.5 and the second evaluation value is 0.25. Since the first evaluation value is greater than the second evaluation value, it can be determined that the optimal planned path of this vehicle is better than the historical path.

[0053] In practical applications, the target area can refer to the three-dimensional area surrounded by obstacles around the vehicle, including platooned vehicles. Therefore, in this embodiment, the two paths can be re-evaluated based on the safe distance between the target area where the following vehicle is currently located and the boundary of the vehicle. Max(g(uc)) is taken as the evaluation objective function to obtain the first evaluation value and the second evaluation value.

[0054] In step S103, the optimal planned path or historical path is determined as the optimal following path of the vehicle based on the first evaluation value and the second evaluation value, and the vehicle is controlled to perform the following action based on the optimal following path.

[0055] It is understood that, after evaluating each path, the best path can be determined as the final optimal path. This overcomes the limitations of the lead vehicle providing the path and the follower vehicle tracking the trajectory, thus forming an efficient path optimization and collaborative feedback planning strategy.

[0056] In this embodiment of the application, determining the optimal planned path or historical path as the optimal following path of the vehicle based on the first evaluation value and the second evaluation value further includes: when the first evaluation value and the second evaluation value are equal, generating the optimal path of the vehicle based on the historical path; otherwise, generating the optimal following path of the vehicle based on the path corresponding to the optimal value among the first evaluation value and the second evaluation value.

[0057] The optimal value can be understood as the evaluation value corresponding to the optimal path among the optimal planned path and the historical paths. It can be determined according to the calculation method of the evaluation value. For example, when the evaluation value is the average of the ratio between the actual distance between the path and the boundary of the target area and the target safe distance, the optimal value can be the maximum value; when the evaluation value is the average of the ratio between the target safe distance and the actual distance, the optimal value can be the minimum value, etc., without specific limitations.

[0058] It is understood that when the obtained evaluation values ​​are equal, it can be understood that the historical path and the optimal planned path of this application embodiment are the same path, and the historical path is the optimal path planning selection of the current vehicle. Therefore, this application embodiment can generate the optimal path of the vehicle based on the historical path and perform the following action based on the path. Similarly, when the evaluation values ​​are not equal, it can be understood that the historical path and the optimal planned path of this application embodiment are different paths. At this time, this application embodiment can generate the optimal following path of the vehicle based on the path corresponding to the optimal value of the first evaluation value and the second evaluation value, as shown in the above embodiment, and perform the following action based on the path.

[0059] The path optimization method for platooning vehicles according to this application will be described below through a specific embodiment, such as... Figure 2 As shown, the specific steps are as follows:

[0060] (1) Candidate path preparation

[0061] This application embodiment can obtain lane line information and an obstacle list of the current lane from the current following vehicle perception system, and establish path candidates and target area boundaries. Specifically, as Figure 2 As shown, in this embodiment, the system can first receive a list of lane lines and obstacles from the perception system, then construct the path boundary and divide it into equal parts horizontally and vertically to construct the target area. If the space is determined to be passable, the system proceeds to the next step, which will not be elaborated here. If the space is determined to be impassable, the system repeats the above steps until it becomes passable. This embodiment can also receive the trajectory of the navigator vehicle at the same time.

[0062] (2) Following vehicle path optimization

[0063] In this embodiment, a reference trajectory can be sampled, then candidate paths can be preset using binary encoding, an evaluation model for the candidate paths can be established, a genetic algorithm can be used to optimize the candidate paths, and a fitting algorithm can be used to smooth the candidate paths.

[0064] Specifically, such as Figure 2As shown, after determining that the path is passable, this embodiment of the application can create path candidates. First, the population is initialized, and then the individuals are updated. At this time, it is determined whether the obtained result meets the error requirement. If it does, the current best path of the vehicle can be output. If it does not, each individual, i.e. each path, is evaluated, and crossover and mutation are calculated with equal probability. Then, the step of updating individuals is returned to update, and the loop is repeated until the current best path of the vehicle can be output.

[0065] (3) Optimal path selection

[0066] Based on the results of the above steps, this application embodiment can again evaluate the overall drivable area boundary of the platoon, calculate (g(uc)), and take the larger path to determine whether to select the optimized path of the autonomous vehicle or accept the path sent by the lead vehicle.

[0067] Specifically, such as Figure 2 As shown, in this embodiment of the application, after outputting the current best path of the autonomous vehicle and receiving the trajectory of the navigator vehicle, the feasible boundary is evaluated, (g(uc)) is calculated, and the calculation results of the two are compared. If the autonomous vehicle's planning is more optimized, the autonomous vehicle's path is output as the optimal path and executed, and the workflow ends. If the navigator vehicle's path planning is more optimized, the navigator vehicle's path is output as the optimal path and executed, and the workflow ends.

[0068] The path optimization method for platooning vehicles proposed in the embodiments of this application enables the following vehicles to have the ability to self-plan their driving trajectory when driving in a platoon. It can determine an optimal driving path based on the planned path of the vehicle itself and the historical path of the lead vehicle, avoiding the limitations of following a vehicle based solely on the historical path of the lead vehicle. It effectively avoids the phenomenon of taking shortcuts or swaying and instability when automatically following a vehicle, greatly improving the safety and stability of following a vehicle and enhancing the user experience.

[0069] Next, referring to the accompanying drawings, a path optimization device for platooning vehicles according to an embodiment of this application is described.

[0070] Figure 4 This is a block diagram of a path optimization device for platooning vehicles according to an embodiment of this application.

[0071] like Figure 4 As shown, the path optimization device 10 for the convoy following vehicles includes: an acquisition module 100, an evaluation module 200, and a control module 300.

[0072] The acquisition module 100 is used to acquire the optimal planned path of the vehicle in the target area and the historical path of the lead vehicle; the evaluation module 200 is used to determine the first evaluation value of the optimal planned path and the second evaluation value of the historical path based on the target area, the optimal planned path and the historical path; the control module 300 is used to determine the optimal planned path or the historical path as the optimal following path of the vehicle based on the first evaluation value and the second evaluation value, and control the vehicle to perform the following action based on the optimal following path.

[0073] In this embodiment of the application, the acquisition module 100 is used to: acquire road information of the vehicle in the target area; perform binary encoding on the road information to generate at least one candidate path; select the target path from the at least one candidate path through a genetic algorithm, and perform smoothing processing on the target path to generate the optimal planned path.

[0074] In this embodiment of the application, the evaluation module 200 is used to: obtain at least one first actual distance between the optimal planned path and the boundary of the target area, and at least one second actual distance between the historical path and the boundary of the target area; calculate a first evaluation value based on at least one first actual distance and the target safety distance, and calculate a second evaluation value based on at least one second actual distance and the target safety distance.

[0075] In this embodiment of the application, the control module 300 is used to: generate the optimal path for the vehicle based on the historical path when the first evaluation value and the second evaluation value are equal; otherwise, generate the optimal following path for the vehicle based on the path corresponding to the optimal value among the first evaluation value and the second evaluation value.

[0076] In this embodiment of the application, the road information includes the road boundary and the lane centerline. The acquisition module 100 is further used to: divide the target area longitudinally into equal parts according to the road boundary and the lane centerline to obtain multiple path sections; divide each path section laterally into equal parts according to a preset span to obtain multiple path points; and encode the multiple path points in binary to generate at least one candidate path.

[0077] It should be noted that the foregoing explanation of the path optimization method embodiment for platooning vehicles also applies to the path optimization device for platooning vehicles in this embodiment, and will not be repeated here.

[0078] The path optimization device for platooning vehicles proposed in the embodiments of this application enables the following vehicles to have the ability to self-plan their driving trajectory when driving in a platoon. It can determine an optimal driving path based on the planned path of the vehicle itself and the historical path of the lead vehicle, avoiding the limitations of following a vehicle based solely on the historical path of the lead vehicle. It effectively avoids the phenomenon of taking shortcuts or swaying and instability when automatically following a vehicle, greatly improving the safety and stability of following a vehicle and enhancing the user experience.

[0079] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0080] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0081] When the processor 502 executes the program, it implements the path optimization method for queuing vehicles provided in the above embodiments.

[0082] Furthermore, the vehicle also includes:

[0083] Communication interface 503 is used for communication between memory 501 and processor 502.

[0084] The memory 501 is used to store computer programs that can run on the processor 502.

[0085] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0086] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0087] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0088] Processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0089] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described path optimization method for queuing vehicles.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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 (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0094] 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 path optimization method for platooning vehicles, characterized in that, Includes the following steps: Obtain the optimal planned path for this vehicle and the historical path of the lead vehicle within the target area; Based on the target area, the optimal planning path, and the historical path, determine the first evaluation value of the optimal planning path and the second evaluation value of the historical path; as well as The optimal planned path or the historical path is determined as the optimal following path for the vehicle based on the first evaluation value and the second evaluation value, and the vehicle is controlled to perform a following action based on the optimal following path.

2. The method according to claim 1, characterized in that, The step of determining the optimal planned path or the historical path as the optimal following path for the vehicle based on the first evaluation value and the second evaluation value further includes: When the first evaluation value and the second evaluation value are equal, the optimal path for the vehicle is generated based on the historical path; otherwise, the optimal following path for the vehicle is generated based on the path corresponding to the optimal value among the first evaluation value and the second evaluation value.

3. The method according to claim 1, characterized in that, The step of determining a first evaluation value for the optimal planning path and a second evaluation value for the historical path based on the target area, the optimal planning path, and the historical path includes: Obtain at least one first actual distance between the optimal planned path and the boundary of the target area, and at least one second actual distance between the historical path and the boundary of the target area; The first evaluation value is calculated based on the at least one first actual distance and the target safe distance, and the second evaluation value is calculated based on the at least one second actual distance and the target safe distance.

4. The method according to any one of claims 1-3, characterized in that, The step of obtaining the optimal planned path for this vehicle within the target area includes: Obtain the road information of the vehicle within the target area; Based on the road information, binary encoding is performed to generate at least one candidate path; The target path is selected from the at least one candidate path using a genetic algorithm, and the target path is smoothed to generate the optimal planned path.

5. The method according to claim 4, characterized in that, The road information includes road boundaries and lane centerlines. The step of generating at least one candidate path by binary encoding the road information includes: The target area is longitudinally divided into multiple path sections based on the road boundary and the lane centerline. Each path section is divided horizontally into equal parts according to a preset span to obtain multiple path points; The multiple path points are binary encoded to generate at least one candidate path.

6. A path optimization device for platooning vehicles, characterized in that, include: The acquisition module is used to obtain the optimal planned path of this vehicle and the historical path of the lead vehicle within the target area; The evaluation module is used to determine a first evaluation value of the optimal planning path and a second evaluation value of the historical path based on the target area, the optimal planning path, and the historical path. as well as The control module determines the optimal planned path or the historical path as the optimal following path for the vehicle based on the first evaluation value and the second evaluation value, and controls the vehicle to perform a following action based on the optimal following path.

7. The apparatus according to claim 6, characterized in that, The acquisition module is used to: acquire road information of the vehicle in the target area; perform binary encoding on the road information to generate at least one candidate path; select a target path from the at least one candidate path using a genetic algorithm, and perform smoothing processing on the target path to generate the optimal planned path; The evaluation module is further configured to: obtain at least one first actual distance between the optimal planning path and the boundary of the target area, and at least one second actual distance between the historical path and the boundary of the target area; calculate the first evaluation value based on the at least one first actual distance and the target safety distance, and calculate the second evaluation value based on the at least one second actual distance and the target safety distance; The control module is further configured to: when the first evaluation value and the second evaluation value are equal, generate the optimal path of the vehicle based on the historical path; otherwise, generate the optimal following path of the vehicle based on the path corresponding to the optimal value among the first evaluation value and the second evaluation value.

8. The apparatus according to claim 7, characterized in that, The road information includes road boundaries and lane centerlines. The acquisition module is further configured to: divide the target area longitudinally into equal parts according to the road boundaries and lane centerlines to obtain multiple path sections; divide each path section laterally into equal parts according to a preset span to obtain multiple path points; and encode the multiple path points in binary to generate at least one candidate path.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the path optimization method for platooning vehicles as described in any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the path optimization method for platooning vehicles as described in any one of claims 1-5.

Images