Vehicle control method, vehicle, storage medium, and product

Abstract

The application discloses a vehicle control method, a vehicle, a storage medium and a product, relates to the technical field of vehicles, and the method comprises the following steps: acquiring feedback information made by a passenger in a vehicle based on a driving environment of the vehicle; and in the case that it is determined that the vehicle is in a risk state according to the feedback information, determining to perform risk avoidance control on the vehicle based on the feedback information. That is, the vehicle will determine whether the vehicle is in a risk state according to the feedback information made by the passenger in the vehicle based on the driving environment, and in the case that it is determined that the vehicle is in a risk state, corresponding risk avoidance control is performed according to the feedback information. It can be understood that, compared with the related scheme of referring to traditional collection equipment such as a vehicle-mounted radar and an ultrasonic sensor to make a decision, the feedback information made by the passenger based on the driving environment is also used as a decision basis for automatic driving in the embodiment of the application, the dimension of the automatic driving decision reference is increased, the stability of the automatic driving is improved, and the vehicle safety is ensured.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a vehicle control method, a vehicle, a storage medium, and a product. Background Technology

[0002] As autonomous driving levels advance from L2 to L4 and even L5, vehicles no longer rely solely on driver intervention but need to possess a high degree of autonomous decision-making and the ability to respond to emergencies. Currently, autonomous driving is primarily achieved through hardware data collection devices and software control algorithms deployed on the vehicle. Therefore, in practical applications, if an autonomous vehicle encounters hardware failure, such as a malfunctioning onboard radar or ultrasonic sensor, the resulting data collection issues will severely impact the autonomous driving's decision-making, potentially placing passengers in a high-risk situation.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a vehicle control method, vehicle, storage medium, and product, which aims to solve the technical problem that passengers are in a high safety risk situation when autonomous vehicles encounter hardware damage.

[0005] To achieve the above objectives, this application proposes a vehicle control method, which includes the following steps:

[0006] Acquire feedback information from occupants in the vehicle based on the vehicle's driving environment, wherein the feedback information includes the occupants' voice feature data and / or the occupants' facial feature data;

[0007] If the vehicle is determined to be in a risky state based on the feedback information, risk avoidance control is implemented on the vehicle based on the feedback information.

[0008] Optionally, the step of obtaining feedback information from occupants in the vehicle based on the vehicle's driving environment includes:

[0009] Collect facial image data of the occupants, and detect the occupants' facial orientation based on the facial image data;

[0010] When the face is facing the car window, the occupant's voice feature data is extracted from the vehicle's in-vehicle audio data, and / or, the occupant's mouth feature data and eye feature data are extracted from the facial image data to obtain the facial feature data.

[0011] Optionally, after the step of acquiring feedback information from occupants in the vehicle based on the vehicle's driving environment, the method includes:

[0012] Based on the voice feature data, and / or the mouth feature data and eye feature data in the facial feature data, determine whether the occupant has an emergency response;

[0013] If it is determined that the occupants have an emergency response capability, the vehicle is determined to be in a state of risk.

[0014] Optionally, the step of determining whether the occupant has an emergency response based on the voice feature data, and / or the mouth feature data and eye feature data in the facial feature data includes:

[0015] The speech feature data, and / or mouth feature data and eye feature data are compared with preset emergency response index conditions, wherein the preset emergency response index conditions include decibel index conditions, audio index conditions and timbre index conditions corresponding to the speech feature data, mouth opening and closing index conditions corresponding to the mouth feature data, and eye movement index conditions corresponding to the eye feature data.

[0016] If the preset emergency response index conditions are met, it is determined that the occupant has an emergency response capability.

[0017] Optionally, the step of performing risk avoidance control on the vehicle based on the feedback information includes:

[0018] The predicted risk source direction of the vehicle is determined based on the feedback information;

[0019] When the predicted risk source direction is different from the detected risk source direction of the vehicle, risk avoidance control is performed on the vehicle based on the predicted risk source direction, wherein the risk avoidance control includes changing lanes to a lane away from the predicted risk source direction, and / or reducing the vehicle speed.

[0020] Optionally, the feedback information also includes the occupant's facial orientation, and the step of determining the predicted risk source direction of the vehicle based on the feedback information includes:

[0021] In the case of multiple occupants in the vehicle, determine the intersection of the faces of each occupant;

[0022] The direction of the predicted risk source is determined based on the direction of the intersection point.

[0023] Optionally, after the step of determining the intersection of the facial orientations of each occupant, the method includes:

[0024] In the case of multiple intersection points, determine the angular difference between the directions of each intersection point;

[0025] If the angle difference is greater than a preset angle threshold, the direction of the predicted risk source is determined based on the facial orientation of the target occupant located at a preset position among the occupants.

[0026] Furthermore, to achieve the above objectives, this application also proposes a vehicle control device, the vehicle control device comprising:

[0027] The acquisition module is used to acquire feedback information made by occupants in the vehicle based on the driving environment of the vehicle, wherein the feedback information includes the occupants' voice feature data and / or the occupants' facial feature data.

[0028] The avoidance module is used to perform risk avoidance control on the vehicle based on the feedback information when it is determined that the vehicle is in a risky state.

[0029] In addition, to achieve the above objectives, this application also proposes a vehicle, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle control method as described above.

[0030] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the vehicle control method described above.

[0031] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the vehicle control method described above.

[0032] One or more technical solutions proposed in this application have at least the following technical effects:

[0033] In this embodiment, feedback information from vehicle occupants based on the vehicle's driving environment is acquired. This feedback information includes the occupants' voice feature data and / or facial feature data. If the vehicle is determined to be in a risky state based on the feedback information, risk avoidance control is implemented. That is, the vehicle determines whether it is in a risky state based on the feedback information from vehicle occupants based on the driving environment, including the occupants' voice feature data and facial feature data. If a risky state is determined, corresponding risk avoidance control is implemented based on the feedback information. It is understood that compared to related solutions that rely on traditional data acquisition devices such as vehicle-mounted radar and ultrasonic sensors for decision-making, this embodiment also uses the occupants' feedback information based on the driving environment as a decision-making basis, increasing the dimension of vehicle control decision reference and thus improving the stability of autonomous driving. Therefore, even if autonomous driving-related data acquisition devices malfunction or fail, this application can still implement risk avoidance control based on the occupants' feedback information, thereby maximizing vehicle safety and protecting the personal and property safety of vehicle owners. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating the first embodiment of the vehicle control method of this application;

[0037] Figure 2 This is a flowchart illustrating the second embodiment of the vehicle control method in this application;

[0038] Figure 3 This is a flowchart illustrating the third embodiment of the vehicle control method in this application;

[0039] Figure 4 This is a schematic diagram of the overall process framework of the vehicle control method in this application;

[0040] Figure 5 This is a structural schematic diagram of the vehicle control device corresponding to this application;

[0041] Figure 6This is a schematic diagram of the equipment structure of the hardware operating environment involved in the vehicle control method in the embodiments of this application.

[0042] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0044] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0045] As autonomous driving levels advance from L2 to L4 and even L5, vehicles no longer rely solely on driver intervention but need to possess a high degree of autonomous decision-making and the ability to respond to emergencies. Currently, autonomous driving is primarily achieved through hardware data collection devices and software control algorithms deployed on the vehicle. Therefore, in practical applications, if an autonomous vehicle encounters hardware failure, such as sensor malfunction, the resulting data collection issues will severely impact the autonomous driving's decision-making, potentially placing passengers in a high-risk situation.

[0046] The main solution of this application embodiment is: to obtain feedback information made by occupants in the vehicle based on the driving environment of the vehicle, wherein the feedback information includes the occupants' voice feature data and / or the occupants' facial feature data; and to perform risk avoidance control on the vehicle based on the feedback information when it is determined that the vehicle is in a risky state.

[0047] In other words, the vehicle will determine whether it is in a risky state based on feedback information from vehicle occupants regarding the driving environment, including occupant voice and facial feature data. If a risky state is determined, the vehicle will take corresponding risk avoidance control measures based on the feedback information. It is understandable that, compared to related solutions that rely on traditional data collection devices such as onboard radar and ultrasonic sensors for decision-making, this application embodiment also uses occupant feedback information based on the driving environment as a decision-making basis, increasing the dimension of vehicle control decision-making reference and thus improving the stability of autonomous driving. Therefore, even if autonomous driving-related data collection devices malfunction or fail, this application can still take risk avoidance control measures based on occupant feedback information, thereby maximizing vehicle safety and protecting the personal and property safety of vehicle owners.

[0048] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication and program execution functions, such as a cloud platform, vehicle, computer, mobile phone, etc., or a vehicle capable of performing the above functions.

[0049] Based on this, embodiments of this application provide a vehicle control method, referring to... Figure 1 This is a flowchart illustrating the first embodiment of the vehicle control method of this application.

[0050] In this embodiment, the vehicle control method includes steps S10 to S20:

[0051] Step S10: Obtain feedback information from occupants in the vehicle based on the vehicle's driving environment, wherein the feedback information includes the occupants' voice feature data and / or the occupants' facial feature data.

[0052] In this embodiment, the vehicle control method can be executed by a vehicle. Furthermore, the vehicle control method can be a part of an autonomous driving control method. It is understood that current autonomous driving is primarily achieved through hardware acquisition devices and software control algorithms deployed on the vehicle. If the hardware malfunctions, the data input to the autonomous driving control algorithm may be problematic, leading to errors or failures in autonomous driving decisions. This would place the vehicle and passengers in a high-risk situation. Therefore, this embodiment addresses this by using feedback information from the occupants' driving environment to implement risk avoidance control. This aims to improve vehicle safety and protect the safety of the vehicle owner's life and property, even in the event of hardware failure or malfunction related to autonomous driving (in which case the vehicle, the execution entity of autonomous driving, may not be aware of the problem and will continue operating in autonomous driving mode).

[0053] For example, the vehicle will collect feedback information from occupants based on the vehicle's driving environment. For instance, the feedback information may include voice feature data from inside the vehicle, or it may include facial feature data of the occupants. Accordingly, the vehicle may be equipped with a microphone to collect the occupants' voice feature data, and a camera may also be installed to capture facial images of the occupants, obtaining facial feature data. The facial images of the occupants may include at least the driver's facial image. Furthermore, to determine whether the voice and facial feature data are based on the occupants' actions in relation to the driving environment, this can be determined based on the occupants' facial features (i.e., facial images). For example, when the occupant's face is facing the window (i.e., outside the vehicle), it can be determined that the voice and facial feature data collected at this time (and for a preset period thereafter) are both feedback information based on the driving environment. It should be understood that the feedback information may include only the occupants' voice feature data, only the occupants' facial feature data, or both. The specific settings can be configured by technicians according to actual needs, with the preferred option being to include both voice feature data and facial feature data.

[0054] Step S20: If it is determined that the vehicle is in a risky state based on the feedback information, risk avoidance control is performed on the vehicle based on the feedback information.

[0055] It should be noted that in this embodiment, feedback information will also be used to determine whether the vehicle is in a risky state. For example, in-vehicle audio data in the feedback information can be used to determine whether the occupants are shouting, screaming, or exclaiming, or facial images in the feedback information can be used to determine whether the occupants are showing signs of tension or fear. If the occupants exhibit any of the above behaviors or expressions, the vehicle can be determined to be in a risky state. Accordingly, risk avoidance control will be implemented on the vehicle based on the feedback information. It is understood that the main purpose of risk avoidance control is to keep the vehicle away from the risk source. If the feedback information includes in-vehicle audio data, and the in-vehicle audio data determines that the occupants are screaming, the corresponding risk avoidance control could be to control the vehicle to slow down or brake. If the feedback information includes facial feature data of the occupants, the direction of the risk source can be predicted by the occupants' facial orientation during the determination of the vehicle being in a risky state. Accordingly, the risk avoidance control could be to change lanes based on the direction of the risk source, thereby moving away from the risk source as much as possible and ensuring vehicle safety. It is understandable that if the feedback information includes in-vehicle audio data and facial feature data, technicians can refer to the above examples and combine them with actual needs to set the parameters, so it will not be elaborated here.

[0056] In this embodiment, feedback information from vehicle occupants based on the vehicle's driving environment is acquired. This feedback information includes the occupants' voice feature data and / or facial feature data. If the vehicle is determined to be in a risky state based on the feedback information, risk avoidance control is implemented. That is, the vehicle determines whether it is in a risky state based on the feedback information from vehicle occupants based on the driving environment, including the occupants' voice feature data and / or facial feature data. If a risky state is determined, corresponding risk avoidance control is implemented based on the feedback information. It is understood that compared to related solutions that rely on traditional data acquisition devices such as vehicle-mounted radar and ultrasonic sensors for decision-making, this embodiment also uses the occupants' feedback information based on the driving environment as a decision-making basis, increasing the dimension of vehicle control decision reference and thus improving the stability of autonomous driving. Therefore, even if autonomous driving-related data acquisition devices malfunction or fail, this application can still implement risk avoidance control based on occupant feedback information, thereby maximizing vehicle safety and protecting the personal and property safety of vehicle owners.

[0057] In one feasible implementation, the facial feature data includes mouth feature data and eye feature data, and the step of obtaining feedback information from occupants in the vehicle based on the vehicle's driving environment includes steps S11 to S13:

[0058] Step S11: Collect facial image data of the occupant and detect the occupant's facial orientation based on the facial image data;

[0059] Step S12: When the face is facing the car window, the occupant's voice feature data is extracted from the vehicle's in-vehicle audio data, and / or the occupant's mouth feature data and eye feature data are extracted from the facial image data to obtain the facial feature data.

[0060] For example, a vehicle can be equipped with a microphone and a camera. The microphone is used to collect in-vehicle audio data, and the camera is used to collect facial image data of the occupants. In practical applications, cameras can be installed in both the front and rear rows of the vehicle to collect facial image data of the occupants in both rows. However, to save costs and considering that the driver is more attentive to the driving environment, a camera for collecting the driver's facial image data can be prioritized.

[0061] Firstly, the occupant's facial orientation can be detected based on facial image data. It's worth noting that facial orientation detection can be achieved using a pre-trained AI model. This AI model can be an LVQ (Learning Vector Quantization) neural network model. Features from the facial image data are input into the neural network model, which then identifies the occupant's facial orientation in the image. During model training, facial images with different orientations are first acquired, and facial feature vectors, especially those for the eye positions, are extracted. The images are then preprocessed, including cropping, converting to grayscale, and using the Sobel edge detection operator to extract eye position information. The extracted feature vectors are used as input to the LVQ neural network, with different orientations (e.g., left, left-front, front, right-front, and right) represented by different numbers as the network output. The model parameters are then updated based on the difference between the network output and the image labels. Following this method, after training the model using images from the training set, a predictive model can be obtained, capable of determining and recognizing the orientation of any given facial image.

[0062] In an optional implementation, since the installation position and shooting angle of the camera that captures occupant facial images are usually fixed in practical applications, the camera's installation position and shooting angle can be used as prior information. This prior information, combined with facial features in the facial image, is then used to calculate the occupant's facial orientation. Taking the driver as an example, the camera is usually installed above and in front of the driver. Therefore, the more facial features detected, the higher the driver's face is facing, and vice versa. For the left-right direction, the orientation can be determined based on the distribution of facial features in the facial image. Since the camera is installed above and in front of the driver, if the driver is facing directly forward, their facial features are approximately symmetrically distributed in the facial image. Therefore, in actual detection, the driver's facial orientation angle in the left-right direction is calculated based on the deviation angle between the actual distribution of facial features in the facial image and the symmetrical distribution. In addition, considering that AI model recognition requires high computing power and the real-time performance will be lower when the computing power of the vehicle is limited, the above method of combining prior information and facial features in the facial image to calculate the occupant's facial orientation can be selected when the vehicle's computing power is limited. When the computing power is sufficient, the above method of recognizing facial orientation through AI model can be selected.

[0063] Determining whether a passenger's face is facing the window primarily involves judging the vertical orientation of their face. If the face is within a preset angle range in the vertical direction, the passenger's face can be determined to be facing the window. Correspondingly, the passenger's reaction can be considered to be based on the driving environment. Therefore, when the face is determined to be facing the window, voice feature data can be extracted from the in-vehicle audio data, and mouth and eye feature data can be extracted from the facial image data. These voice feature data, and / or mouth and eye feature data, can then be used as feedback information. The extraction of voice feature data mainly involves removing environmental noise from the in-vehicle audio data. It is understood that environmental noise, normal passenger conversation, and emergency calls are fundamentally different and can be distinguished by decibel level and timbre. The decibel levels, timbre, and audio patterns (peak values ​​and variation curves) of various emergency calls, normal conversations, and environmental noise can be stored in memory. The noise and voice parameter value ranges can then be fitted as extraction standards. Additionally, mouth and eye feature data can be extracted using facial recognition technology. Since facial recognition technology is currently quite mature, it will not be elaborated upon here. It is understood that the feedback information can include only voice feature data, only mouth and eye feature data, or all of these simultaneously.

[0064] Reference Figure 2 This is a flowchart illustrating the second embodiment of the vehicle control method based on the first embodiment of this application. Contents identical or similar to those in the above embodiments can be found in the above description and will not be repeated hereafter. After the step of obtaining feedback information from occupants in the vehicle based on the vehicle's driving environment, the method includes steps A10 to A20:

[0065] Step A10: Based on the voice feature data, and / or the mouth feature data and eye feature data in the facial feature data, determine whether the occupant has an emergency response;

[0066] Step A20: If it is determined that the occupants have an emergency response capability, the vehicle is determined to be in a risky state.

[0067] For example, in this embodiment, the vehicle will use voice feature data, mouth feature data, and eye feature data in the feedback information to determine whether the occupant has an emergency response. An emergency response refers to the subconscious reaction made by the occupant in an emergency, such as screaming, shouting, widening eyes, opening mouth, and frowning. If it is determined from the voice feature data, mouth feature data, and eye feature data that the occupant has exhibited the above-mentioned reactions, it can be considered that the occupant has an emergency response, and accordingly, the vehicle is determined to be in a risky state.

[0068] In one feasible implementation, the step of determining whether the occupant has an emergency response based on the voice feature data and / or the mouth feature data and eye feature data in the facial feature data includes steps A11 to A12:

[0069] Step A11: Compare the voice feature data, and / or mouth feature data and eye feature data with preset emergency response index conditions, wherein the preset emergency response index conditions include decibel index conditions, audio index conditions and timbre index conditions corresponding to the voice feature data, mouth opening and closing index conditions corresponding to the mouth feature data, and eye movement index conditions corresponding to the eye feature data.

[0070] Step A12: If the preset emergency response index conditions are met, it is determined that the occupant has an emergency response capability.

[0071] For example, by comparing voice feature data, and / or mouth feature data and eye feature data, with preset emergency response index conditions, it can be determined whether the occupant has an emergency response. The preset emergency response index conditions may include decibel index conditions, audio index conditions, and timbre index conditions corresponding to voice feature data; mouth opening and closing index conditions corresponding to mouth feature data; and eye movement index conditions corresponding to eye feature data. The decibel index conditions, audio index conditions, timbre index conditions, and eye opening and closing index conditions can be preset thresholds or ranges. Similarly, there is a fundamental difference between the normal conversational voice of an occupant and the emergency call sound. This can be determined by the decibel level and timbre. First, the decibel, timbre, and audio patterns (peak values ​​and variation curves) of various emergency call sounds, normal conversational voices, and environmental noise are stored in the memory. The stored data comes from 10 sets of data recorded by an audio acquisition device under different groups of people and different in-vehicle conditions. The parameter value ranges of emergency call sounds and normal conversational voices (i.e., the aforementioned decibel index conditions, audio index conditions, and timbre index conditions) are fitted and used as the judgment criteria. To avoid overlapping sampling frequencies, a sound sampling frequency of 2000 Hz is recommended. On the other hand, drivers often open their mouths when making emergency calls; therefore, the degree of mouth opening and closing during calls from different groups can be statistically analyzed to obtain an opening and closing index. Additionally, eye movement index conditions can include frowning and widening the eyes. It should be noted that in one feasible approach, if any one of the occupant's relevant characteristic data (voice characteristic data, mouth characteristic data, or eye characteristic data) meets the preset emergency response index conditions, it can be determined that the occupant has an emergency response. Furthermore, in practical applications, to ensure detection accuracy, the relevant characteristic data can be comprehensively analyzed. For example, voice characteristic data can be compared with decibel index conditions, audio index conditions, and timbre index conditions to obtain a score under each index condition (e.g., the closer the data is to the decibel index conditions, audio index conditions, and timbre index conditions, the higher the score). Similarly, following the above process, the mouth feature data is compared with the opening and closing degree index condition, and the eye feature data is compared with the eye movement index condition. A score is obtained for each index condition, and the scores are then accumulated to obtain a total score. If the total score is greater than the preset score, the preset emergency response index condition is considered met, and it can be determined that the occupant has an emergency response. Conversely, if the total score is less than the preset emergency response index condition, it is considered that the preset emergency response index condition is not met, and it can be determined that the occupant does not have an emergency response, and no risk avoidance control is implemented.

[0072] Reference Figure 3This is a flowchart illustrating a third embodiment based on the first and second embodiments of the vehicle control method of this application. Contents identical or similar to those in the above embodiments can be found in the preceding description and will not be repeated hereafter. The steps for performing risk avoidance control on the vehicle based on the feedback information include steps S21 to S22:

[0073] Step S21: Determine the predicted risk source direction of the vehicle based on the feedback information;

[0074] Step S22: If the predicted risk source direction is different from the detected risk source direction of the vehicle, risk avoidance control is performed on the vehicle based on the predicted risk source direction. The risk avoidance control includes changing lanes to a lane away from the predicted risk source direction and / or reducing the vehicle speed.

[0075] For example, in this embodiment, the predicted risk source direction of the vehicle can be determined based on feedback information. For instance, when the feedback information determines that the vehicle is in a risky state, the predicted risk source direction is then determined based on the occupant's facial orientation in or corresponding to the feedback information; for example, the occupant's facial orientation can be directly used as the predicted risk source direction. After obtaining the predicted risk source direction, it can be compared with the vehicle's detected risk source direction, where the detected risk source direction is the direction in which obstacles (such as other vehicles) are detected by the vehicle's sensors and radar. It is understood that in this embodiment, the risk avoidance control based on feedback information is mainly to ensure that even if the autonomous driving-related hardware in the vehicle malfunctions or fails, obstacles can still be avoided to reduce vehicle safety risks. Therefore, to avoid redundant control, risk avoidance control can be performed only when the predicted risk source direction differs from the vehicle's detected risk source direction. Accordingly, risk avoidance control includes changing lanes to a lane away from the predicted risk source direction and / or reducing the vehicle's speed. For example, suppose a vehicle is traveling on a three-lane one-way road, divided into left, middle, and right lanes. If the vehicle is in the right lane and the predicted risk source is forward, the vehicle can reduce its speed and attempt to change lanes sequentially from the right lane to the middle lane and then the left lane. If the vehicle is in the middle lane and the predicted risk source is forward, the vehicle can attempt to change lanes from the middle lane to the left or right lane. If the vehicle is in the left lane and the predicted risk source is to the right front, the vehicle can decelerate and remain in its current lane, or apply emergency braking in its current lane. Furthermore, technicians can refer to the above examples to set other risk avoidance strategies. Additionally, it is understandable that risk avoidance control based on feedback information indicates a potential anomaly in the vehicle's autonomous driving system. Therefore, after implementing risk avoidance control, the driver can be prompted to take over vehicle control, thereby reducing the safety risks associated with autonomous driving.

[0076] In one feasible implementation, the feedback information further includes the occupant's facial orientation, and the step of determining the predicted risk source direction of the vehicle based on the feedback information includes steps S211 to S212:

[0077] Step S211: If there are multiple occupants in the vehicle, determine the intersection of the faces of each occupant.

[0078] Step S212: Determine the direction of the predicted risk source based on the direction of the intersection point.

[0079] For example, in some cases, there may be multiple occupants in a vehicle. To ensure the accuracy of the determined predicted risk source direction, this embodiment will combine the occupants' facial orientation to determine the predicted risk source direction. For instance, the focal point of the occupants' facial orientation can be determined first. Taking two occupants as an example, the facial orientations of these two occupants can be determined separately, and then the intersection of these two facial orientations can be determined. If an intersection exists, the direction of the intersection can be directly determined as the predicted risk source direction. If no intersection exists, the driver's facial orientation is used as the predicted risk source direction.

[0080] In one feasible implementation, after the step of determining the intersection of the facial orientations of each occupant, the method includes steps S213 to S214:

[0081] Step S213: In the case of multiple intersection points, determine the angle difference between the directions of each intersection point;

[0082] Step S214: When the angle difference is greater than a preset angle threshold, the direction of the predicted risk source is determined based on the facial orientation of the target occupant located at a preset position among the occupants.

[0083] For example, if there are multiple intersection points, the angular differences between the directions of each intersection point can be determined. If the angular differences are large, it indicates that the facial orientations of the occupants are not uniform, meaning that determining the predicted risk source direction by referring to the facial orientations of the occupants may have a large error. Therefore, to ensure the accuracy of the predicted risk source direction, the facial orientation of the target occupant located in the preset position (i.e., the driver's position) is directly used as the predicted risk source direction.

[0084] Reference Figure 4 This is a schematic diagram of the overall process framework of the vehicle control method in this application. Figure 4 The lieutenant general used the example of a driver as a crew member to illustrate his point. For example... Figure 4 As shown, the vehicle can monitor driver behavior in real time to determine if the driver is making an emergency call, for example, by analyzing voice data from occupants inside the vehicle. The vehicle will also recognize the driver's facial features in real time to determine if there are any abnormalities in the driver's mouth, eyes, or other features. If an emergency call is made, or if facial features are abnormal, it can be assumed that the driver has responded to an emergency. Correspondingly, the vehicle's autonomous driving system may be malfunctioning, and the vehicle's ECU (Electronic Control Unit) can then implement appropriate risk avoidance control measures, such as activating automatic emergency braking, lane keeping assist, and collision warning.

[0085] This application also provides a vehicle control device, as shown in the reference. Figure 5 The vehicle control device includes:

[0086] The acquisition module 10 is used to acquire feedback information made by the occupants in the vehicle based on the driving environment of the vehicle, wherein the feedback information includes the occupants' voice feature data and / or the occupants' facial feature data.

[0087] The avoidance module 20 is used to perform risk avoidance control on the vehicle based on the feedback information when it is determined that the vehicle is in a risky state.

[0088] Optionally, the facial feature data includes mouth feature data and eye feature data, and the acquisition module 10 is further configured to:

[0089] Collect facial image data of the occupants, and detect the occupants' facial orientation based on the facial image data;

[0090] When the face is facing the car window, the occupant's voice feature data is extracted from the vehicle's in-vehicle audio data, and / or, the occupant's mouth feature data and eye feature data are extracted from the facial image data to obtain the facial feature data.

[0091] Optionally, the vehicle control device further includes a determining module 30, the determining module being used for:

[0092] Based on the voice feature data, and / or the mouth feature data and eye feature data in the facial feature data, determine whether the occupant has an emergency response;

[0093] If it is determined that the occupants have an emergency response capability, the vehicle is determined to be in a state of risk.

[0094] Optionally, the determining module 30 is further configured to:

[0095] The speech feature data, and / or mouth feature data and eye feature data are compared with preset emergency response index conditions, wherein the preset emergency response index conditions include decibel index conditions, audio index conditions and timbre index conditions corresponding to the speech feature data, mouth opening and closing index conditions corresponding to the mouth feature data, and eye movement index conditions corresponding to the eye feature data.

[0096] If the preset emergency response index conditions are met, it is determined that the occupant has an emergency response capability.

[0097] Optionally, the evasion module 20 is used for:

[0098] The predicted risk source direction of the vehicle is determined based on the feedback information;

[0099] When the predicted risk source direction is different from the detected risk source direction of the vehicle, risk avoidance control is performed on the vehicle based on the predicted risk source direction, wherein the risk avoidance control includes changing lanes to a lane away from the predicted risk source direction, and / or reducing the vehicle speed.

[0100] Optionally, the feedback information also includes the occupant's facial orientation, and the avoidance module 20 is used to:

[0101] In the case of multiple occupants in the vehicle, determine the intersection of the faces of each occupant;

[0102] The direction of the predicted risk source is determined based on the direction of the intersection point.

[0103] Optionally, the evasion module 20 is used for:

[0104] In the case of multiple intersection points, determine the angular difference between the directions of each intersection point;

[0105] If the angle difference is greater than a preset angle threshold, the direction of the predicted risk source is determined based on the facial orientation of the target occupant located at a preset position among the occupants.

[0106] The vehicle control device provided in this application, employing the vehicle control method described in the above embodiments, can solve the technical problem of placing passengers in a high-safety-risk situation when an autonomous vehicle encounters hardware damage. Compared with the prior art, the beneficial effects of the vehicle control device provided in this application are the same as those of the vehicle control method provided in the above embodiments, and other technical features in the vehicle control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0107] This application provides a vehicle, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the vehicle control method in Embodiment 1 above.

[0108] The following is for reference. Figure 6The diagram illustrates a structural schematic suitable for implementing the vehicle embodiments of this application. The vehicle in these embodiments may include, but is not limited to, mobile terminals such as computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as computers. Figure 6 The vehicle shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0109] like Figure 6 As shown, the vehicle may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for vehicle operation. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the vehicle to communicate wirelessly or wiredly with other devices to exchange data. Although vehicles with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0110] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0111] The vehicle provided in this application, employing the vehicle control method described in the above embodiments, can solve the technical problem that passengers are placed in a high-safety-risk situation when an autonomous vehicle encounters hardware damage. Compared with the prior art, the beneficial effects of the vehicle provided in this application are the same as those of the vehicle control method provided in the above embodiments, and other technical features of the vehicle are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0112] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0114] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle control method in the above embodiments.

[0115] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0116] The aforementioned computer-readable storage medium may be included in the vehicle or may exist independently and not installed in the vehicle.

[0117] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a vehicle, cause the vehicle to:

[0118] Acquire feedback information from occupants in the vehicle based on the vehicle's driving environment, wherein the feedback information includes the occupants' voice feature data and / or the occupants' facial feature data;

[0119] If the vehicle is determined to be in a risky state based on the feedback information, risk avoidance control is implemented on the vehicle based on the feedback information.

[0120] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0122] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0123] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle control method. This addresses the technical problem that passengers are placed in a high-risk situation when an autonomous vehicle encounters hardware damage. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle control method provided in the above embodiments, and will not be elaborated upon here.

[0124] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle control method described above.

[0125] The computer program product provided in this application can solve the technical problem of vehicle control. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the vehicle control method provided in the above embodiments, and will not be repeated here.

[0126] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A vehicle control method characterized by, The vehicle control method comprises the following steps: acquiring feedback information made by an occupant in the vehicle based on a driving environment of the vehicle, wherein the feedback information comprises voice feature data of the occupant and / or facial feature data of the occupant; in a case where it is determined according to the feedback information that the vehicle is in a risk state, performing risk avoidance control on the vehicle based on the feedback information; wherein the step of performing risk avoidance control on the vehicle based on the feedback information comprises: determining a predicted risk source direction of the vehicle based on the feedback information; in a case where the predicted risk source direction is different from a detected risk source direction of the vehicle, performing risk avoidance control on the vehicle based on the predicted risk source direction, wherein the risk avoidance control comprises changing lanes to a lane away from the predicted risk source direction and / or reducing a vehicle speed of the vehicle; the feedback information further comprises a face orientation of the occupant, and the step of determining the predicted risk source direction of the vehicle based on the feedback information comprises: in a case where there are multiple occupants in the vehicle, determining an intersection of face orientations of the occupants; determining the predicted risk source direction according to a direction in which the intersection is located.

2. The vehicle control method according to claim 1, characterized by, The step of acquiring the feedback information made by the occupant in the vehicle based on the driving environment of the vehicle comprises: collecting facial image data of the occupant, and detecting a face orientation of the occupant based on the facial image data; in a case where the face orientation is a direction of a vehicle window, extracting voice feature data of the occupant from in-vehicle audio data of the vehicle, and / or extracting mouth feature data and eye feature data of the occupant from the facial image data to obtain the facial feature data.

3. The vehicle control method according to claim 1, characterized by, After the step of acquiring the feedback information made by the occupant in the vehicle based on the driving environment of the vehicle, the method comprises: determining whether the occupant has an emergency reaction based on the voice feature data, and / or mouth feature data and eye feature data in the facial feature data; in a case where it is determined that the occupant has an emergency reaction, determining that the vehicle is in a risk state.

4. The vehicle control method according to claim 3, characterized by, The step of determining whether the occupant has an emergency reaction based on the voice feature data, and / or mouth feature data and eye feature data in the facial feature data comprises: comparing the voice feature data, and / or the mouth feature data and the eye feature data, with preset emergency reaction index conditions, wherein the preset emergency reaction index conditions comprise a decibel index condition, an audio index condition and a timbre index condition corresponding to the voice feature data, an opening and closing degree index condition corresponding to the mouth feature data, and an eye movement index condition corresponding to the eye feature data; in a case where the preset emergency reaction index conditions are met, determining that the occupant has an emergency reaction.

5. The vehicle control method according to claim 1, characterized by, After the step of determining the intersection of the face orientations of the occupants, the method comprises: in a case where there are multiple intersections, determining an angle difference between directions in which the intersections are located. In a case where the angle difference is greater than a preset angle threshold, a direction of the predicted risk source is determined according to a face orientation of a target occupant located at a preset position among the occupants.

6. A vehicle characterized by comprising: The vehicle comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the vehicle control method according to any one of claims 1 to 5.

7. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the vehicle control method according to any one of claims 1 to 5.

8. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by a processor to implement the steps of the vehicle control method according to any one of claims 1 to 5.

Images