CN-117270515-B - Route optimization method and device for queuing following vehicles, vehicles and storage medium

CN117270515BCN 117270515 BCN117270515 BCN 117270515BCN-117270515-B

Abstract

The application relates to the technical field of vehicles, in particular to a method, a device, equipment and a storage medium for optimizing a path of a train following vehicle, wherein the method comprises the steps of obtaining an optimal planning path of a vehicle in a target area and a history path of a pilot vehicle; and determining the optimal planned path or the historical path as the optimal following path of the vehicle according to the first evaluation value and the second evaluation value, and controlling the vehicle to execute following action based on the optimal following path. Therefore, the problems that in the related art, the following vehicle usually carries out following vehicle running based on the history track of the piloted vehicle, the phenomenon of short-distance reading or unstable running swing easily occurs, the following vehicle running safety and stability are poor and the like are solved.

Inventors

SHI XIAOWU
JIN DAPENG
WANG NING

Assignees

北汽福田汽车股份有限公司

Dates

Publication Date: 20260512
Application Date: 20220613

Claims (10)

1. A method of path optimization for queuing following vehicles, comprising the steps of: acquiring an optimal planning path of the vehicle in a target area and a historical path of a pilot vehicle; Determining a first evaluation value of the optimal planned path and a second evaluation value of the historical path according to the target area, the optimal planned path and the historical path, and And determining the optimal planned path or the historical path as an optimal following path of the vehicle according to the first evaluation value and the second evaluation value, and controlling the vehicle to execute following action based on the optimal following path.
2. The method of claim 1, wherein the determining that the optimal planned path or the historical path is the optimal following path of the host vehicle according to the first evaluation value and the second evaluation value further comprises: And when the first evaluation value and the second evaluation value are equal, generating an optimal path of the vehicle according to the historical path, and otherwise, generating an optimal following path of the vehicle according to a path corresponding to the optimal value in the first evaluation value and the second evaluation value.
3. The method of claim 1, wherein the determining the first evaluation value of the optimal planned path and the second evaluation value of the historical path from the target area, the optimal planned path, and the historical path comprises: acquiring 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 according to the at least one first actual distance and the target safety distance, and the second evaluation value is calculated according to the at least one second actual distance and the target safety distance.
4. A method according to any one of claims 1-3, wherein said obtaining an optimal planned path of the host vehicle in the target area comprises: Acquiring road information of the vehicle in a target area; binary coding is carried out according to the road information, and at least one candidate path is generated; And selecting a target path from the at least one candidate path through a genetic algorithm, and performing smoothing processing on the target path to generate the optimal planning path.
5. The method of claim 4, wherein the roadway information includes roadway boundaries and lane centerlines, wherein the binary encoding based on the roadway information generates at least one candidate path comprising: Longitudinally equally dividing the target area according to the road boundary and the lane center line to obtain a plurality of path sections; Performing transverse equal division on each path section according to a preset span to obtain a plurality of path points; and binary coding is carried out on the plurality of path points, and at least one candidate path is generated.
6. A path optimizing apparatus that queues following vehicles, characterized by comprising: The acquisition module is used for acquiring an optimal planning path of the vehicle in the target area and a history path of the pilot vehicle; An evaluation module for determining a first evaluation value of the optimal planned path and a second evaluation value of the historical path according to the target area, the optimal planned path and the historical path, and The control module determines the optimal planned path or the historical path to be the optimal following path of the vehicle according to the first evaluation value and the second evaluation value, and controls the vehicle to execute following action based on the optimal following path.
7. The apparatus of claim 6, wherein the device comprises a plurality of sensors, The acquisition module is used for acquiring road information of the vehicle in a target area, performing binary coding according to the road information to generate at least one candidate path, selecting a target path from the at least one candidate path through a genetic algorithm, and performing smoothing treatment on the target path to generate the optimal planning path; the evaluation module is further used for acquiring 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 to obtain the first evaluation value according to the at least one first actual distance and the target safety distance, and calculating to obtain the second evaluation value according to the at least one second actual distance and the target safety distance; The control module is further configured to generate an optimal path of the host vehicle according to the historical path when the first evaluation value and the second evaluation value are equal, and otherwise, generate an optimal following path of the host vehicle according to a path corresponding to the optimal value in the first evaluation value and the second evaluation value.
8. The apparatus of claim 7, wherein the roadway information comprises a roadway boundary and a lane centerline, and wherein the acquisition module is further configured to divide the target area longitudinally and equally according to the roadway boundary and the lane centerline to obtain a plurality of path sections, divide each path section transversely and equally according to a preset span to obtain a plurality of path points, and binary encode the plurality of path points to generate at least one candidate path.
9. A vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the path optimization method of queuing follower vehicles of any one of claims 1-5.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for implementing a path optimization method of a train-following vehicle according to any one of claims 1 to 5.

Description

Route optimization method and device for queuing following vehicles, vehicles and storage medium Technical Field The present application relates to the field of vehicle technologies, and in particular, to a method and apparatus for optimizing a path of a train-following vehicle, a vehicle, and a storage medium. Background In an application scenario of the train running, a pilot vehicle and one or more following vehicles are generally included, where the pilot vehicle may use manual driving or automatic driving, and generates a historical track of the vehicle running, and the following vehicles in the train may automatically drive according to the historical track of the pilot vehicle. Therefore, how to ensure stability and safety of the train operation is a major issue. In the related art, in order to ensure the stability of the train running and maintain the safe distance between the vehicles, the pilot vehicle is required to provide more path information, the path information is required to be transmitted between the trains through a V2X (vehicle to outside information exchange) device, and meanwhile, in order to ensure the reliability of transmission, a certain transmission bandwidth is generally required to be reserved. However, because the size of the data packet is limited due to the transmission characteristics of the V2X device, the information quantity, such as track data density, can be reduced no matter the information is compressed or decompressed and sampled, so that the track point of the following vehicle is insufficient, once the following vehicle is in a complex road condition such as a curve, the phenomenon of short-distance reading or unstable form swing of the following vehicle is easily caused when the following vehicle carries out gathering and tracking, and the safety and reliability of the following vehicle are greatly reduced. Disclosure of Invention The application provides a path optimization method, a path optimization device, a vehicle and a storage medium for queuing following vehicles, and aims to solve the problems that in the related art, following vehicles usually carry out following running based on a history track of a piloted vehicle, the phenomenon of short-distance reading or unstable running swing easily occurs, and the following running safety and stability are poor. An embodiment of a first aspect of the application provides a path optimization method for a train-following vehicle, which comprises the following steps of obtaining an optimal planning path of a vehicle in a target area and a history path of a pilot vehicle, determining a first evaluation value of the optimal planning path and a second evaluation value of the history path according to the target area, the optimal planning path and the history path, determining the optimal planning path or the history path as the optimal following path of the vehicle according to the first evaluation value and the second evaluation value, and controlling the vehicle to execute following action based on the optimal following path. Optionally, the determining that the optimal planned path or the historical path is the optimal following path of the vehicle according to the first evaluation value and the second evaluation value further includes generating an optimal path of the vehicle according to the historical path when the first evaluation value and the second evaluation value are equal, otherwise generating an optimal following path of the vehicle according to a path corresponding to an optimal value in the first evaluation value and the second evaluation value. Optionally, the determining the first evaluation value of the optimal planning path and the second evaluation value of the historical path according to the target area, the optimal planning path and the historical path comprises 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 according to the at least one first actual distance and the target safety distance, and calculating the second evaluation value according to the at least one second actual distance and the target safety distance. The method comprises the steps of obtaining road information of a vehicle in a target area, binary encoding according to the road information to generate at least one candidate path, selecting a target path from the at least one candidate path through a genetic algorithm, and smoothing the target path to generate the optimal planning path. Optionally, the road information comprises a road boundary and a lane center line, the binary encoding is performed according to the road information to generate at least one candidate path, the method comprises the steps of longitudinally equally dividing the target area according to the road boundary and the lane center line to obtain a