CN-117167152-B - Throttle control method and device for automatic driving vehicle, vehicle and medium

CN117167152BCN 117167152 BCN117167152 BCN 117167152BCN-117167152-B

Abstract

The invention discloses an accelerator control method, device, vehicle and medium for an automatic driving vehicle, wherein the method comprises the steps of obtaining environmental information around the vehicle, determining a driving environment of the vehicle from a driving environment database of a pre-established data set according to the environmental information, determining a first control strategy corresponding to the driving environment in a first functional logic set of the data set, controlling the vehicle to run based on the first control strategy, obtaining first vehicle data of the vehicle after executing the first control strategy, inputting the first vehicle data into a set machine learning frame for training to obtain a second functional logic set, determining a second control strategy corresponding to the driving environment in the second functional logic set, and determining a target control strategy for controlling the accelerator of the vehicle according to the first control strategy and the second control strategy. The method can solve the problem of inaccurate throttle control and ensure driving safety.

Inventors

WU ZHENGYU
WEI WANGLING
WANG CHENG
DING CONGCONG
SUN CHUAN
LI HAORAN
XU LIN
TIAN LIANGYU
ZHENG SIFA
XU SHUCAI
FENG BIN
ZHANG TINGYANG

Assignees

清华大学苏州汽车研究院（相城）

Dates

Publication Date: 20260512
Application Date: 20230831

Claims (6)

1. A throttle control method of an automatically driven vehicle, comprising: Acquiring environmental information around a vehicle, and determining the driving environment of the vehicle from a driving environment database of a pre-created data set according to the environmental information; determining a first control strategy corresponding to the driving environment in a first functional logic set of the data set; Controlling the vehicle to run based on the first control strategy, and acquiring first vehicle data of the vehicle after the first control strategy is executed; inputting the first vehicle data into a set machine learning framework for training to obtain a second functional logic set; Determining a second control strategy corresponding to the driving environment in the second functional logic set; Determining a target control strategy for vehicle throttle control according to the first control strategy and the second control strategy, wherein the target control strategy comprises the following steps: comparing the first control strategy with the second control strategy to determine a first evaluation score, wherein the first evaluation score characterizes the similarity of the first control strategy and the second control strategy; Combining the first control strategy and the second control strategy to obtain the target control strategy under the condition that the first evaluation score is larger than a first preset threshold value; The step of, when the first evaluation score is equal to or less than a first preset threshold value,: The second vehicle data represents the data related to the second function logic set, and the second vehicle data comprises the data obtained in the process of generating a second control strategy based on the second function logic set and the data obtained in the process of comparing the second control strategy with the first control strategy; determining a third control strategy corresponding to the driving environment in the third functional logic set; Determining the target control strategy according to the first control strategy, the second control strategy and the third control strategy comprises the following steps: Comparing the first control strategy, the second control strategy and the third control strategy to determine three second evaluation scores, wherein the three second evaluation scores respectively comprise the similarity of the first control strategy and the third control strategy, the similarity of the second control strategy and the third control strategy, and the similarity of the first control strategy, the second control strategy and the third control strategy; Combining the first control strategy, the second control strategy and the third control strategy to obtain the target control strategy under the condition that the second evaluation scores of at least two items are larger than the first preset threshold value; And under the condition that at least two second evaluation scores are smaller than or equal to the first preset threshold value, third vehicle data are input to the set machine learning framework for training to obtain a fourth functional logic set, the third vehicle data represent data related to the third functional logic set, a fourth control strategy corresponding to the driving environment is determined in the fourth functional logic set, the fourth control strategy is determined to be the target control strategy, and the fourth control strategy is used for controlling the vehicle to run in a safe state.
2. The method according to claim 1, wherein the determining the driving environment of the vehicle in the stored driving environment database according to the environment information comprises: Comparing the environment information with the driving environment stored in the driving environment database to determine a corresponding probability value, wherein the probability value represents the matching probability of the environment information and the corresponding driving environment; and determining the corresponding driving environment as the driving environment of the vehicle when the probability value is larger than a second set threshold value.
3. The method according to claim 1, wherein the method further comprises: And uploading the first vehicle data to a cloud server to learn the first vehicle data and vehicle data uploaded by other vehicles.
4. An accelerator control apparatus for an automatically driven vehicle, comprising: The first determining module is used for acquiring environmental information around the vehicle and determining the driving environment of the vehicle from a driving environment database of a pre-created data set according to the environmental information; The second determining module is used for determining a first control strategy corresponding to the driving environment in a first functional logic set of the data set; The acquisition module is used for controlling the vehicle to run based on the first control strategy and acquiring first vehicle data of the vehicle after the first control strategy is executed; the training module is used for inputting the first vehicle data into a set machine learning framework for training to obtain a second functional logic set; A third determining module, configured to determine a second control policy corresponding to the driving environment in the second functional logic set; A fourth determining module, configured to determine a target control strategy for vehicle throttle control according to the first control strategy and the second control strategy, including: comparing the first control strategy with the second control strategy to determine a first evaluation score, wherein the first evaluation score characterizes the similarity of the first control strategy and the second control strategy; Combining the first control strategy and the second control strategy to obtain the target control strategy under the condition that the first evaluation score is larger than a first preset threshold value; The step of, when the first evaluation score is equal to or less than a first preset threshold value,: The second vehicle data represents the data related to the second function logic set, and the second vehicle data comprises the data obtained in the process of generating a second control strategy based on the second function logic set and the data obtained in the process of comparing the second control strategy with the first control strategy; determining a third control strategy corresponding to the driving environment in the third functional logic set; Determining the target control strategy according to the first control strategy, the second control strategy and the third control strategy comprises the following steps: Comparing the first control strategy, the second control strategy and the third control strategy to determine three second evaluation scores, wherein the three second evaluation scores respectively comprise the similarity of the first control strategy and the third control strategy, the similarity of the second control strategy and the third control strategy, and the similarity of the first control strategy, the second control strategy and the third control strategy; Combining the first control strategy, the second control strategy and the third control strategy to obtain the target control strategy under the condition that the second evaluation scores of at least two items are larger than the first preset threshold value; And under the condition that at least two second evaluation scores are smaller than or equal to the first preset threshold value, third vehicle data are input to the set machine learning framework for training to obtain a fourth functional logic set, the third vehicle data represent data related to the third functional logic set, a fourth control strategy corresponding to the driving environment is determined in the fourth functional logic set, the fourth control strategy is determined to be the target control strategy, and the fourth control strategy is used for controlling the vehicle to run in a safe state.
5. An autonomous vehicle comprising a memory and a processor, said memory having a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 3 when the computer program is executed.
6. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 3.

Description

Throttle control method and device for automatic driving vehicle, vehicle and medium Technical Field The invention relates to the technical field of automatic driving, in particular to an accelerator control method and device for an automatic driving vehicle, the vehicle and a medium. Background In the related art, throttle control of an automatic driving vehicle is a very important part of an automatic driving system, mainly relates to three aspects of environment perception, decision planning and control, and in the aspect of decision planning, a target detection and classification algorithm based on deep learning and a path planning algorithm based on machine learning can automatically judge road conditions under different driving scenes, select a verified driving route and generate a corresponding throttle control command, so that automatic intelligent throttle adjustment is realized, however, in complex traffic scenes, accurate control of a throttle of the vehicle is difficult to realize, and thus stable and safe driving of the vehicle is difficult to ensure. Disclosure of Invention In view of the foregoing, it is desirable to provide a throttle control method, device, vehicle, and medium for an autonomous vehicle that can accurately control the throttle of the vehicle. A throttle control method of an autonomous vehicle, comprising the steps of: Acquiring environmental information around a vehicle, and determining the driving environment of the vehicle from a driving environment database of a pre-created data set according to the environmental information; determining a first control strategy corresponding to the driving environment in a first functional logic set of the data set; Controlling the vehicle to run based on the first control strategy, and acquiring first vehicle data of the vehicle after the first control strategy is executed; inputting the first vehicle data into a set machine learning framework for training to obtain a second functional logic set; Determining a second control strategy corresponding to the driving environment in the second functional logic set; And determining a target control strategy for controlling the accelerator of the vehicle according to the first control strategy and the second control strategy. A throttle control apparatus for an autonomous vehicle, comprising: The first determining module is used for acquiring environmental information around the vehicle and determining the driving environment of the vehicle from a driving environment database of a pre-created data set according to the environmental information; The second determining module is used for determining a first control strategy corresponding to the driving environment in a first functional logic set of the data set; The acquisition module is used for controlling the vehicle to run based on the first control strategy and acquiring first vehicle data of the vehicle after the first control strategy is executed; the training module is used for inputting the first vehicle data into a set machine learning framework for training to obtain a second functional logic set; A third determining module, configured to determine a second control policy corresponding to the driving environment in the second functional logic set; And the fourth determining module is used for determining a target control strategy for controlling the accelerator of the vehicle according to the first control strategy and the second control strategy. An autonomous vehicle comprising a memory storing a computer program and a processor implementing the steps of the above method for throttle control of an autonomous vehicle when the processor executes the computer program. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the throttle control method of an autonomous vehicle described above. According to the accelerator control method, the accelerator control device, the vehicle and the medium for the automatic driving vehicle, the driving environment of the vehicle is determined according to the environmental information around the vehicle, the corresponding first control strategy is determined according to the driving environment of the vehicle and the first functional logic set, the first vehicle data of the first control strategy is executed by the vehicle to learn, the second functional logic set is obtained, and the second control strategy is determined by utilizing the second functional logic set, so that the accelerator of the vehicle is controlled through the first control strategy and the second control strategy, the accelerator control strategy can be generated in an effective and safe mode according to the current driving situation, and the efficiency and the accuracy of accelerator control are improved. Drawings FIG. 1 is a schematic diagram of a system architecture for throttle control of an autonomous vehicle in one embodiment; FIG. 2 is a flow