CN-121973679-A - Vehicle control method and device and automobile

CN121973679ACN 121973679 ACN121973679 ACN 121973679ACN-121973679-A

Abstract

The application relates to a vehicle control method, a vehicle control device and an automobile. The method comprises the steps of obtaining multi-mode data of a seat of an automobile and a driver and a passenger located on the seat, obtaining first evaluation information of the seat and second evaluation information of the driver and the passenger based on the multi-mode data, obtaining a current seat comfort value of the seat according to the first evaluation information and the second evaluation information, adjusting current parameters of seat components related to the first evaluation information and the second evaluation information according to the current seat comfort value and a target seat comfort value of the seat to obtain parameters to be adjusted of the seat components, generating an adjustment instruction of the seat according to the parameters to be adjusted, and the adjustment instruction is used for indicating adjustment of the seat components based on the parameters to be adjusted. By adopting the method, the active control effect on the vehicle seat can be improved, so that the comfort of the seat is improved, and the driving safety is also improved.

Inventors

TU CHENGJUN
SHAO YUFEI
ZENG BING
TAN WEI
FU WENJING

Assignees

重庆蓝电汽车科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260325

Claims (10)

1. A vehicle control method, characterized in that the method comprises: Acquiring multi-mode data of a seat of an automobile and a driver and a passenger positioned on the seat; Obtaining first evaluation information of the seat and second evaluation information of the driver and the passenger based on the multi-mode data, wherein the first evaluation information at least comprises pressure distribution evaluation information and comfort evaluation information, and the second evaluation information at least comprises muscle fatigue evaluation information and driving posture evaluation information; obtaining a current seat comfort value of the seat according to the first evaluation information and the second evaluation information; According to the current seat comfort value and the target seat comfort value of the seat, adjusting current parameters of the seat component related to the first evaluation information and the second evaluation information to obtain parameters to be adjusted of the seat component; and generating an adjusting instruction of the seat according to the parameter to be adjusted, wherein the adjusting instruction is used for indicating to adjust the seat part based on the parameter to be adjusted.
2. The method of claim 1, further comprising, after acquiring the multimodal data of the seat of the vehicle and the occupant located in the seat: inputting the multi-modal data, the seat and the historical multi-modal data of the driver and the passenger into a pre-trained human body state prediction model to obtain predicted second evaluation information of the driver and the passenger in a first time period in the future; Based on the predicted second evaluation information, performing fatigue recognition processing on the driver and the passenger to obtain a predicted fatigue state of the driver and the passenger in the future first time period; If the predicted fatigue state is detected to meet the preset fatigue driving condition, obtaining a first safety parameter of the seat according to the predicted second evaluation information; And generating a first safety adjustment instruction of the seat according to the first safety parameter, wherein the first safety adjustment instruction is used for indicating that the adjustment of the vibration element of the seat is completed before the first future time period comes based on the first safety parameter.
3. The method of claim 1, further comprising, after acquiring the multimodal data of the seat of the vehicle and the occupant located in the seat: Inputting the multi-modal data, the seat and the historical multi-modal data of the driver and the passenger into a pre-trained seat state prediction model to obtain predicted first evaluation information of the seat in a second time period in the future; based on the predicted first evaluation information, carrying out driving state recognition processing on the driver and the passenger to obtain a predicted driving state of the driver and the passenger in the future second time period; If the predicted driving state is detected to meet the preset violent driving condition, obtaining second safety parameters of the seat according to the predicted first evaluation information; and generating a second safety adjustment instruction of the seat according to the second safety parameter, wherein the second safety adjustment instruction is used for indicating that the adjustment of the vibration element of the seat is completed before the second future time period is reached based on the second safety parameter.
4. The method of claim 1, wherein the obtaining the current seat comfort value of the seat based on the first and second evaluation information comprises: Determining a first weight corresponding to the pressure distribution evaluation information, a second weight corresponding to the comfort evaluation information, a third weight corresponding to the muscle fatigue evaluation information and a fourth weight corresponding to the driving posture evaluation information according to the current driving condition data of the automobile and the historical adjustment data of the seat; And according to the first weight, the second weight, the third weight and the fourth weight, carrying out fusion processing on the pressure distribution evaluation information, the comfort evaluation information, the muscle fatigue evaluation information and the driving posture evaluation information to obtain a current seat comfort value of the seat.
5. The method according to claim 4, wherein the adjusting the current parameters of the seat component associated with the first evaluation information and the second evaluation information according to the current seat comfort value and the target seat comfort value of the seat to obtain the parameters to be adjusted of the seat component includes: Determining target pressure distribution evaluation information corresponding to the pressure distribution evaluation information, target comfort evaluation information corresponding to the comfort evaluation information, target muscle fatigue evaluation information corresponding to the muscle fatigue evaluation information and target driving posture evaluation information corresponding to the driving posture evaluation information according to the first weight, the second weight, the third weight, the fourth weight and the target seat comfort value; Based on the target pressure distribution evaluation information, carrying out parameter optimization processing on the current parameters of the first seat component related to the pressure distribution evaluation information to obtain parameters to be adjusted of the first seat component; Based on the target comfort evaluation information, carrying out parameter optimization processing on the current parameters of the second seat component related to the comfort evaluation information to obtain parameters to be adjusted of the second seat component; Performing parameter optimization processing on the current parameters of the third seat part related to the muscle fatigue evaluation information based on the target muscle fatigue evaluation information to obtain parameters to be adjusted of the third seat part; And carrying out parameter optimizing processing on the current parameters of the fourth seat component related to the driving posture evaluation information based on the target driving posture evaluation information to obtain parameters to be adjusted of the fourth seat component.
6. The method of claim 1, wherein the obtaining the first evaluation information of the seat and the second evaluation information of the occupant based on the multimodal data comprises: inputting the multi-mode data into a pre-trained comfort evaluation model to obtain comfort evaluation information of the seat, wherein the comfort evaluation model is obtained through training in a mode of supervised learning and reinforcement learning; Obtaining pressure distribution evaluation information of the seat based on target pressure data in the multi-mode data; Inputting the multi-mode data into a pre-trained muscle fatigue evaluation model to obtain muscle fatigue evaluation information of the driver and the passenger; and inputting the multi-mode data into a pre-trained driving posture evaluation model to obtain driving posture evaluation information of the driver and the passengers.
7. The method of claim 1, wherein the acquiring multi-modal data of a seat of an automobile and a driver located on the seat comprises: Acquiring raw data of the seat and a driver on the seat in visual aspect, touch aspect, auditory aspect and physiological aspect; Preprocessing a plurality of original data to obtain a plurality of preprocessed data of the seat and the driver; Performing space-time synchronization processing on the various preprocessed data to obtain various synchronized data of the seat and the driver; and inputting the multiple synchronized data into a multi-modal fusion model to obtain multi-modal data of the seat and the driver and the passengers.
8. The method of claim 7, wherein the raw data includes at least video data, gesture data, pressure data, audio data, and physiological data; The acquiring raw data of the seat and a driver on the seat in visual aspect, touch aspect, auditory aspect and physiological aspect comprises: acquiring video data of the driver and the passenger sitting on the seat, and performing human body posture detection processing on the video data to obtain the posture data of the driver and the passenger in the visual aspect; obtaining the pressure data of the touch aspect according to the captured resistance value change information of the conductive material associated with the seat caused by the physical deformation of the seat; Obtaining the audio data of the hearing aspect according to the captured voice signal and the captured ambient sound signal of the internal environment of the automobile; And obtaining the physiological data of the physiological aspect according to the captured physiological signal of the driver.
9. A vehicle control apparatus, characterized in that the apparatus comprises: the data acquisition module is used for acquiring multi-mode data of a seat of an automobile and a driver and a passenger positioned on the seat; The information evaluation module is used for obtaining first evaluation information of the seat and second evaluation information of the driver and the passenger based on the multi-mode data, wherein the first evaluation information at least comprises pressure distribution evaluation information and comfort evaluation information, and the second evaluation information at least comprises muscle fatigue evaluation information and driving posture evaluation information; The comfort evaluation module is used for obtaining the current seat comfort value of the seat according to the first evaluation information and the second evaluation information; The parameter optimization module is used for adjusting the current parameters of the seat component related to the first evaluation information and the second evaluation information according to the current seat comfort value and the target seat comfort value of the seat to obtain parameters to be adjusted of the seat component; The seat adjusting module is used for generating an adjusting instruction of the seat according to the parameter to be adjusted, and the adjusting instruction is used for indicating to adjust the seat part based on the parameter to be adjusted.
10. An automobile comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the method according to any one of claims 1 to 8.

Description

Vehicle control method and device and automobile Technical Field The present application relates to the field of vehicle control technologies, and in particular, to a vehicle control method and apparatus, and an automobile. Background The performance of the vehicle control technology, which is the core interaction technology between a driver and a vehicle, directly relates to the comfort and the safety of the driver in driving the vehicle. For example, a control technique for a vehicle seat is one of vehicle control techniques frequently used by a driver and a passenger to drive a vehicle. The current vehicle seat control technology mainly adopts a manual adjustment or simple electric adjustment scheme, and part of high-end vehicle models are provided with memory functions, so that a limited number of fixed seat position parameters can be stored. However, these adjustment methods are mainly dependent on a passive adjustment mechanism manually triggered by a driver, and lack of perception of the state of the driver and active adjustment of the seat result in poor control of the vehicle seat. Disclosure of Invention Based on this, the present application addresses the above-mentioned technical problems by providing a vehicle control method, apparatus, automobile, computer-readable storage medium and computer program product that are capable of improving at least the control effect of a vehicle seat. In a first aspect, the present application provides a vehicle control method including: Acquiring multi-mode data of a seat of an automobile and a driver and a passenger positioned on the seat; Obtaining first evaluation information of the seat and second evaluation information of the driver and the passenger based on the multi-mode data, wherein the first evaluation information at least comprises pressure distribution evaluation information and comfort evaluation information, and the second evaluation information at least comprises muscle fatigue evaluation information and driving posture evaluation information; obtaining a current seat comfort value of the seat according to the first evaluation information and the second evaluation information; According to the current seat comfort value and the target seat comfort value of the seat, adjusting current parameters of the seat component related to the first evaluation information and the second evaluation information to obtain parameters to be adjusted of the seat component; and generating an adjusting instruction of the seat according to the parameter to be adjusted, wherein the adjusting instruction is used for indicating to adjust the seat part based on the parameter to be adjusted. According to the vehicle control method, the first evaluation information covering the pressure distribution and the comfortableness of the seat and the second evaluation information containing the muscle fatigue and the driving posture of the driver are obtained based on the multi-mode data, the fusion perception and evaluation of four dimensions of pressure-comfort-physiology-posture are achieved, the first evaluation information and the second evaluation information are combined to calculate the current seat comfort value of the seat, the current seat comfort value is compared with the preset target seat comfort value, the parameters to be adjusted of the seat component are intelligently decided based on the difference of the comfort values, the adjustment instruction of the seat is generated according to the parameters, the seat component is finally driven to execute the adjustment action, the dynamic self-adaptive adjustment of the parameters such as the support and the posture of the seat is achieved, the comfortableness of the seat is effectively improved, the driving posture of the driver is optimized, the muscle fatigue of the driver is relieved, and the driving safety is improved. In an alternative embodiment of the first aspect, after acquiring the multimodal data of the seat of the vehicle and the occupant located in the seat, the method further comprises: inputting the multi-modal data, the seat and the historical multi-modal data of the driver and the passenger into a pre-trained human body state prediction model to obtain predicted second evaluation information of the driver and the passenger in a first time period in the future; Based on the predicted second evaluation information, performing fatigue recognition processing on the driver and the passenger to obtain a predicted fatigue state of the driver and the passenger in the future first time period; If the predicted fatigue state is detected to meet the preset fatigue driving condition, obtaining a first safety parameter of the seat according to the predicted second evaluation information; And generating a first safety adjustment instruction of the seat according to the first safety parameter, wherein the first safety adjustment instruction is used for indicating that the adjustment of the vibration element of the