CN-122009235-A - Vehicle control method, device, medium, electronic equipment and vehicle

CN122009235ACN 122009235 ACN122009235 ACN 122009235ACN-122009235-A

Abstract

The disclosure belongs to the technical field of vehicle control, and relates to a vehicle control method, a device, a medium, electronic equipment and a vehicle. The method comprises the steps of collecting environment audio of a current vehicle in a driving process, carrying out recognition and positioning processing on the environment audio to obtain a current recognition result, wherein the environment audio comprises an alarm prompt sound of a special vehicle, the special vehicle sends out the alarm prompt sound when the special vehicle is used for executing a specific task, the current recognition result comprises one or more of a vehicle type of the special vehicle, a movement trend of the special vehicle and azimuth information of the special vehicle relative to the current vehicle, and an execution element of the current vehicle is controlled according to the current recognition result. According to the method and the device, the intelligent perception and analysis are carried out on the environmental audio by utilizing an artificial intelligence technology, the implementation complexity and the additional hardware cost of the system are reduced, the robustness and the practicability under complex road conditions are improved, the effect that the automatic control executing element realizes avoiding of the special vehicle is achieved, and the effective decision information is provided.

Inventors

CHEN FANGYUE
LIU KAI
WANG PENG
HU JINBO
LUO ZHENBO
CHEN ZHAOBO
XING YUEFENG
WANG YUJUN
YAN ZHIYONG

Assignees

小米汽车科技有限公司
小米科技(武汉)有限公司
北京小米移动软件有限公司
北京小米松果电子有限公司

Dates

Publication Date: 20260512
Application Date: 20260304

Claims (17)

1. A vehicle control method characterized by comprising: Collecting environment audio of a current vehicle in a running process, and carrying out recognition positioning processing on the environment audio to obtain a current recognition result, wherein the environment audio comprises an alarm prompt tone of a special vehicle, the special vehicle is a special vehicle which sends the alarm prompt tone when a specific task is executed, and the current recognition result comprises one or more of a vehicle type of the special vehicle, a movement trend of the special vehicle and azimuth information of the special vehicle relative to the current vehicle; And controlling an executive component of the current vehicle according to the current identification result.
2. The vehicle control method according to claim 1, wherein the identifying and positioning the environmental audio to obtain the current identification result includes: Performing discrimination processing on the environmental audio to obtain discrimination results; based on the discrimination result, carrying out noise reduction treatment on the environmental audio to obtain noise-reduced environmental audio; and carrying out recognition positioning processing on the noise-reduced environmental audio to obtain a current recognition result.
3. The vehicle control method according to claim 2, characterized in that the performing the discrimination processing on the environmental audio to obtain a discrimination result includes: measuring the sound pressure level of the environmental audio, and determining the distance between the current vehicle and the special vehicle according to the sound pressure level; and determining that the current recognition result of the environmental audio is valid based on the fact that the distance meets a preset condition.
4. The vehicle control method according to claim 2, characterized in that the noise reduction processing of the environmental audio to obtain the noise-reduced environmental audio includes: and inputting the environmental audio into a preset deep learning model to obtain the noise-reduced environmental audio.
5. The vehicle control method according to claim 4, characterized in that before the input of the environmental audio into a preset deep learning model, the method further comprises: a first audio sample is obtained, and is subjected to type recognition processing to obtain a classification result, wherein the first audio sample comprises an alarm sample and a noise sample, and the classification result characterizes the first audio sample as the alarm sample or the noise sample; Acquiring a second audio sample, and determining the alarm sample in the second audio sample according to the classification result, wherein the second audio sample is a sample obtained by mixing the alarm sample and the noise sample; and determining a first loss function according to the alarm sample and the second audio sample, and training by using the first loss function to obtain the preset deep learning model.
6. The vehicle control method according to claim 2, wherein the performing the recognition positioning process on the noise-reduced environmental audio to obtain the current recognition result includes: performing feature extraction processing on the noise-reduced environmental audio to obtain audio features; and carrying out coding processing on the audio features to obtain a current identification result.
7. The vehicle control method according to claim 6, wherein the encoding the audio feature to obtain the current recognition result includes: The audio feature is input to an encoder to output the vehicle type using a first activation function of the encoder and the motion trend and the orientation information using a second activation function of the encoder.
8. The vehicle control method according to claim 1, characterized in that the controlling the actuator of the current vehicle according to the current recognition result includes: Acquiring other recognition results corresponding to the current recognition result, wherein the other recognition results are determined at adjacent time of the current recognition result; And determining a target recognition result according to the current recognition result and the other recognition results, and controlling an executing element of the current vehicle according to the target recognition result.
9. The vehicle control method according to claim 1, characterized in that the controlling the actuator of the current vehicle according to the current recognition result includes any one of: In a first driving mode of the current vehicle, controlling a display screen of the current vehicle to display early warning prompt information according to the current recognition result, wherein the early warning prompt information is used for prompting attention to avoid the special vehicle; Controlling the steering wheel of the current vehicle to vibrate according to the current recognition result in a first driving mode of the current vehicle so as to prompt attention to avoid the special vehicle; and in the first driving mode of the current vehicle, controlling a loudspeaker of the current vehicle to play an early warning prompt tone according to the current recognition result, wherein the early warning prompt tone is used for prompting attention to avoid the special vehicle.
10. The vehicle control method according to claim 1, characterized in that the controlling the actuator of the current vehicle according to the current recognition result includes any one of: in a second driving mode of the current vehicle, controlling an accelerator pedal of the current vehicle to reduce speed according to the current recognition result so as to avoid the proprietary vehicle; in a second driving mode of the current vehicle, controlling a steering wheel and a car lamp of the current vehicle to change lanes according to the current recognition result so as to avoid the special vehicle; In a second driving mode of the current vehicle, controlling a display screen of the current vehicle to display early warning prompt information according to the current recognition result, wherein the early warning prompt information is used for prompting attention to avoid the special vehicle; And in the second driving mode of the current vehicle, controlling a loudspeaker of the current vehicle to play an early warning prompt tone according to the current recognition result, wherein the early warning prompt tone is used for prompting attention to avoid the special vehicle.
11. A vehicle control apparatus characterized by comprising: The system comprises an audio acquisition module, a control module and a control module, wherein the audio acquisition module is configured to acquire environmental audio of a current vehicle in a driving process, and perform identification positioning processing on the environmental audio to obtain a current identification result, the environmental audio comprises an alarm prompt sound of a special vehicle, the special vehicle is a special vehicle which sends the alarm prompt sound when a specific task is executed, and the current identification result comprises one or more of a vehicle type of the special vehicle, a movement trend of the special vehicle and azimuth information of the special vehicle relative to the current vehicle; And the element control module is configured to control an execution element of the current vehicle according to the current identification result.
12. The vehicle control device of claim 11, wherein the audio acquisition module is configured to: Performing discrimination processing on the environmental audio to obtain discrimination results; based on the discrimination result, carrying out noise reduction treatment on the environmental audio to obtain noise-reduced environmental audio; and carrying out recognition positioning processing on the noise-reduced environmental audio to obtain a current recognition result.
13. The vehicle control apparatus of claim 11, wherein the element control module is configured to: In a first driving mode of the current vehicle, controlling a display screen of the current vehicle to display early warning prompt information according to the current recognition result, wherein the early warning prompt information is used for prompting attention to avoid the special vehicle; Controlling the steering wheel of the current vehicle to vibrate according to the current recognition result in a first driving mode of the current vehicle so as to prompt attention to avoid the special vehicle; and in the first driving mode of the current vehicle, controlling a loudspeaker of the current vehicle to play an early warning prompt tone according to the current recognition result, wherein the early warning prompt tone is used for prompting attention to avoid the special vehicle.
14. The vehicle control apparatus of claim 11, wherein the element control module is configured to: in a second driving mode of the current vehicle, controlling an accelerator pedal of the current vehicle to reduce speed according to the current recognition result so as to avoid the proprietary vehicle; in a second driving mode of the current vehicle, controlling a steering wheel and a car lamp of the current vehicle to change lanes according to the current recognition result so as to avoid the special vehicle; In a second driving mode of the current vehicle, controlling a display screen of the current vehicle to display early warning prompt information according to the current recognition result, wherein the early warning prompt information is used for prompting attention to avoid the special vehicle; And in the second driving mode of the current vehicle, controlling a loudspeaker of the current vehicle to play an early warning prompt tone according to the current recognition result, wherein the early warning prompt tone is used for prompting attention to avoid the special vehicle.
15. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the steps of the method of any of claims 1 to 10.
16. An electronic device, comprising: A memory having a computer program stored thereon; A processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1 to 10.
17. A vehicle, characterized by comprising: A processor; A memory for storing processor-executable instructions; Wherein the processor is configured to execute executable instructions stored in the memory to implement the steps of the vehicle control method of any one of claims 1-10.

Description

Vehicle control method, device, medium, electronic equipment and vehicle Technical Field The disclosure belongs to the technical field of vehicle control, and particularly relates to a vehicle control method, a vehicle control device, a computer readable storage medium, electronic equipment and a vehicle. Background The related audio processing scheme can only provide extremely poor distance estimation, cannot realize accurate positioning of the azimuth, and is difficult to provide effective information for a driver or an intelligent driving system to decide. Disclosure of Invention To overcome the problems in the related art, the present disclosure provides a vehicle control method, a vehicle control apparatus, a computer-readable storage medium, an electronic device, and a vehicle. According to a first aspect of an embodiment of the present disclosure, there is provided a vehicle control method including: Collecting environment audio of a current vehicle in a running process, and carrying out recognition positioning processing on the environment audio to obtain a current recognition result, wherein the environment audio comprises an alarm prompt tone of a special vehicle, the special vehicle is a special vehicle which sends the alarm prompt tone when a specific task is executed, and the current recognition result comprises one or more of a vehicle type of the special vehicle, a movement trend of the special vehicle and azimuth information of the special vehicle relative to the current vehicle; And controlling an executive component of the current vehicle according to the current identification result. Optionally, the identifying and positioning the environmental audio to obtain a current identifying result includes: Performing discrimination processing on the environmental audio to obtain discrimination results; based on the discrimination result, carrying out noise reduction treatment on the environmental audio to obtain noise-reduced environmental audio; and carrying out recognition positioning processing on the noise-reduced environmental audio to obtain a current recognition result. Optionally, the discriminating processing of the environmental audio to obtain a discriminating result includes: measuring the sound pressure level of the environmental audio, and determining the distance between the current vehicle and the special vehicle according to the sound pressure level; and determining that the current recognition result of the environmental audio is valid based on the fact that the distance meets a preset condition. Optionally, the noise reduction processing is performed on the environmental audio to obtain noise-reduced environmental audio, including: and inputting the environmental audio into a preset deep learning model to obtain the noise-reduced environmental audio. Optionally, before the inputting the environmental audio into a preset deep learning model, the method further includes: a first audio sample is obtained, and is subjected to type recognition processing to obtain a classification result, wherein the first audio sample comprises an alarm sample and a noise sample, and the classification result characterizes the first audio sample as the alarm sample or the noise sample; Acquiring a second audio sample, and determining the alarm sample in the second audio sample according to the classification result, wherein the second audio sample is a sample obtained by mixing the alarm sample and the noise sample; and determining a first loss function according to the alarm sample and the second audio sample, and training by using the first loss function to obtain the preset deep learning model. Optionally, the identifying and positioning the noise-reduced environmental audio to obtain a current identifying result includes: performing feature extraction processing on the noise-reduced environmental audio to obtain audio features; and carrying out coding processing on the audio features to obtain a current identification result. Optionally, the encoding processing of the audio feature to obtain a current recognition result includes: The audio feature is input to an encoder to output the vehicle type using a first activation function of the encoder and the motion trend and the orientation information using a second activation function of the encoder. Optionally, the controlling the actuator of the current vehicle according to the current recognition result includes: Acquiring other recognition results corresponding to the current recognition result, wherein the other recognition results are determined at adjacent time of the current recognition result; And determining a target recognition result according to the current recognition result and the other recognition results, and controlling an executing element of the current vehicle according to the target recognition result. Optionally, the controlling the actuator of the current vehicle according to the current recognition result includes any one