CN-122015891-A - Vehicle path planning method, vehicle and readable storage medium

CN122015891ACN 122015891 ACN122015891 ACN 122015891ACN-122015891-A

Abstract

The embodiment of the application provides a vehicle path planning method, a vehicle and a readable storage medium, which comprise the steps of obtaining an initial occupation grid and an initial occupation probability corresponding to the initial occupation grid, carrying out grey image conversion on the initial occupation grid based on the initial occupation probability, a pixel gray value mapping relation and a zero copy conversion method to obtain an initial gray image, determining an obstacle area in the initial gray image based on an adaptive threshold value, carrying out optimization processing on the obstacle area based on a vehicle dynamic parameter and a confidence weighting filter mechanism to obtain a target gray image, converting the target gray image into the target occupation grid through the zero copy conversion method, converting a pixel gray value of the target gray image into the target occupation probability of the target occupation grid through the pixel gray value mapping relation, and planning a running path of the vehicle based on the target occupation grid and the target occupation probability, thereby solving the technical problem of lower accuracy when identifying the obstacle in the related technology.

Inventors

SHAN WANCHAO
LIN JIANFEI
ZHOU JIAN

Assignees

奇瑞汽车股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. A vehicle path planning method, comprising: Acquiring an initial occupation grid and initial occupation probability corresponding to the initial occupation grid, wherein the initial occupation probability is used for representing the probability of the barrier existing in the initial occupation grid; Converting the gray image of the initial occupied grid based on the initial occupied probability, the pixel gray value mapping relation and a zero copy conversion method to obtain an initial gray image, wherein the zero copy conversion method is used for mutually converting the occupied grid and the gray image based on a memory address mapping relation; Determining an obstacle region in the initial gray image based on an adaptive threshold; Optimizing the obstacle region based on the vehicle dynamic parameters and the confidence weighting filtering mechanism to obtain a target gray level image; Converting the target gray image into a target occupation grid through the zero copy conversion method, and converting the pixel gray value of the target gray image into the target occupation probability of the target occupation grid through the pixel gray value mapping relation; And planning the driving path of the vehicle based on the target occupation grid and the target occupation probability.
2. The method according to claim 1, wherein the method further comprises: acquiring a reference threshold, a vehicle speed, a sensor noise variance and a driving environment dynamic index, wherein the reference threshold is used for being used as an adjustment initial value of the self-adaptive threshold, the sensor noise variance is used for measuring the fluctuation degree of sensor data, and the driving environment dynamic index is used for measuring the transient change degree of the current driving environment; The adaptive threshold is obtained by weighted summation of the reference threshold, the vehicle speed, the sensor noise variance, the driving environment dynamic index, and the local probability gradient of the initial occupancy probability.
3. The method of claim 1, wherein said performing a graying image conversion on said initial occupancy grid based on said initial occupancy probability, pixel gray value mapping relation, and zero-copy conversion method to obtain an initial gray image comprises: Determining a pixel gray value corresponding to the initial occupation probability according to the initial occupation probability and the pixel gray value mapping relation; and converting the initial occupation grid according to the pixel gray value and the zero copy conversion method to obtain the initial gray image.
4. A method according to claim 3, wherein said determining an obstacle region in the initial gray image based on an adaptive threshold comprises: Dividing the initial gray image into a plurality of regions based on the pixel gray values; in response to the pixel grayscale value of any one of the regions being greater than or equal to the adaptive threshold, determining the region where the pixel grayscale value is greater than or equal to the adaptive threshold as the obstacle region.
5. The method of claim 4, wherein the vehicle dynamics parameters include vehicle width, vehicle speed, and turning radius, and wherein the optimizing the obstacle region based on the vehicle dynamics parameters and the confidence weighting filter mechanism includes: Determining a first obstacle boundary in the obstacle region based on a morphological operation kernel, wherein a size and shape of the morphological operation kernel is adjusted in real time based on the vehicle width, the vehicle speed, and the turning radius; determining a plurality of the obstacle regions and areas of the obstacle regions based on the first obstacle boundary; Removing areas with the area smaller than a first preset area threshold value from the plurality of barrier areas to obtain a first barrier area; Screening the first obstacle region through the confidence weighting filtering mechanism, and reserving a second obstacle region with confidence greater than a preset confidence threshold in the first obstacle region; and further optimizing the second obstacle region to obtain the target gray level image.
6. The method of claim 5, wherein the further optimizing the second obstacle region to obtain the target gray scale image comprises: removing the area, smaller than a second preset area threshold, in the second obstacle area to obtain a third obstacle area, wherein the second preset area threshold is smaller than the first preset area threshold; extracting a second obstacle boundary in the third obstacle region based on the morphological operation core; Performing complement correction on the irregular boundary and the discontinuous boundary in the second barrier boundary based on a contour interpolation method to obtain a third barrier boundary; determining a fourth obstacle region based on the third obstacle boundary; and determining the target gray scale image according to the fourth obstacle region and a non-obstacle region, wherein the pixel gray scale value of the non-obstacle region is smaller than the adaptive threshold.
7. The method of claim 1, wherein planning the travel path of the vehicle based on the target occupancy grid and the target occupancy probability comprises: Determining an obstacle grid and a non-obstacle grid in the target occupation grid based on the target occupation probability, wherein the obstacle grid is used for representing grid units with obstacles, and the non-obstacle grid is used for representing grid units without obstacles; Identifying the barrier grids and the non-barrier grids to obtain a drivable area; And planning the driving path of the vehicle according to the driving area.
8. A vehicle, characterized by comprising: A memory storing an executable program; A processor for executing the executable program, wherein the executable program when run on the processor performs the vehicle path planning method of any one of the preceding claims 1 to 7.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program, wherein the computer program is arranged to perform the vehicle path planning method according to any of the preceding claims 1 to 7 when run on a computer or processor.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the vehicle path planning method as claimed in any one of the preceding claims 1 to 7.

Description

Vehicle path planning method, vehicle and readable storage medium Technical Field The embodiment of the application relates to the technical field of automatic driving, in particular to a vehicle path planning method, a vehicle and a readable storage medium. Background In the technical field of automatic driving, accurate obstacle recognition and map construction are one of key links for realizing intelligent driving. However, the conventional rule-based or statistic-based processing method is poor in calculation efficiency and real-time data processing capability, so that the problem of low accuracy in identifying obstacles in the prior art exists. There is currently no good solution to the above problems. Disclosure of Invention The embodiment of the application provides a vehicle path planning method, a vehicle and a readable storage medium, which are used for at least solving the technical problem of lower accuracy in identifying obstacles in the related art. According to one aspect of the embodiment of the application, a vehicle path planning method is provided, which comprises the steps of obtaining an initial occupation grid and initial occupation probability corresponding to the initial occupation grid, wherein the initial occupation probability is used for representing the probability that an obstacle exists in the initial occupation grid, carrying out grey-scale image conversion on the initial occupation grid based on the initial occupation probability, a pixel grey value mapping relation and a zero copy conversion method to obtain an initial grey-scale image, wherein the zero copy conversion method is used for carrying out mutual conversion on the occupation grid and the grey-scale image based on a memory address mapping relation, determining an obstacle area in the initial grey-scale image based on an adaptive threshold, carrying out optimization processing on the obstacle area based on a vehicle dynamic parameter and a confidence weighting filter mechanism to obtain a target grey-scale image, converting the target grey-scale image into the target occupation grid through the zero copy conversion method, and converting the pixel grey value of the target grey-scale image into the target occupation probability of the target occupation grid through the pixel grey-scale value mapping relation, and planning the running path of the vehicle based on the target occupation grid and the target occupation probability. Further, the vehicle path planning method further comprises the steps of obtaining a reference threshold value, a vehicle speed, a sensor noise variance and a driving environment dynamic index, wherein the reference threshold value is used for being used as an adjustment initial value of the self-adaptive threshold value, the sensor noise variance is used for measuring the fluctuation degree of sensor data, the driving environment dynamic index is used for measuring the transient change degree of the current driving environment, and the self-adaptive threshold value is obtained through weighting and summing the reference threshold value, the vehicle speed, the sensor noise variance, the driving environment dynamic index and the local probability gradient of initial occupation probability. Further, the method for converting the gray image of the initial occupation grid based on the initial occupation probability, the pixel gray value mapping relation and the zero copy conversion method comprises the steps of determining a pixel gray value corresponding to the initial occupation probability according to the initial occupation probability and the pixel gray value mapping relation, and converting the initial occupation grid according to the pixel gray value and the zero copy conversion method to obtain the initial gray image. Further, determining an obstacle region in the initial gray image based on the adaptive threshold includes dividing the initial gray image into a plurality of regions based on the pixel gray values, and determining a region having a pixel gray value greater than or equal to the adaptive threshold as the obstacle region in response to the pixel gray value of any one region being greater than or equal to the adaptive threshold. The method comprises the steps of determining a first obstacle boundary in an obstacle area based on a morphological operation core, adjusting the size and shape of the morphological operation core in real time based on the vehicle width, the vehicle speed and the turning radius, determining a plurality of obstacle areas and areas of the obstacle areas based on the first obstacle boundary, removing areas of the plurality of obstacle areas, the areas of which are smaller than a first preset area threshold value, to obtain a first obstacle area, screening the first obstacle area through the confidence weighting filtering mechanism, reserving a second obstacle area, the confidence of which is larger than the preset confidence threshold value, in the first o