Vehicle control method, device and equipment and computer readable storage medium

By integrating driver attitude, physiological and environmental data, and updating the control strategy of autonomous driving vehicles, the impact of driver emotional and environmental factors on driving safety and comfort is solved, and a safer and more comfortable autonomous driving experience is achieved.

CN118907143APending Publication Date: 2024-11-08VOYAH AUTOMOBILE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411138150.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In autonomous driving technology, the emotional state and environmental factors of the driver have a great impact on driving safety and passenger comfort, and it is difficult for the prior art to effectively consider these factors for vehicle control.

Method used

By obtaining the driver's real-time attitude data, physiological data and environmental data, performing fusion processing, using the confidence level evaluation model to output the target confidence level level, and updating the vehicle control strategy based on this level to adapt to the driver's trust level and comfort needs.

Benefits of technology

The driving safety and passenger comfort of autonomous driving vehicles are improved. Through precise vehicle control strategy adjustments, the risk of accidents and driver tension are reduced, and the intelligence level of the autonomous driving system is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118907143A_ABST
    Figure CN118907143A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle control method, device and equipment and a computer readable storage medium, and relates to the technical field of automatic driving control, and the method comprises the steps: obtaining real-time posture data, real-time physiological data and real-time environment data of a driver under a current vehicle control strategy; fusing the real-time posture data, the real-time physiological data and the real-time environment data to obtain fused data; the fusion data is input to a preset confidence level evaluation model, so that the confidence level evaluation model outputs a target confidence level grade based on the fusion data, and the target confidence level grade is used for representing the trust degree of a driver to a current vehicle control strategy; and updating the current vehicle control strategy based on the target confidence level grade so as to perform vehicle control based on a new vehicle control strategy. According to the invention, the automatic driving vehicle can be effectively controlled, so that the driving safety and the comfort level of passengers are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving control technology, and specifically to a vehicle control method, device, equipment and computer-readable storage medium. Background Art

[0002] With the development of L2 to L3 autonomous driving technology, the role and experience of the driver in the driving process are changing; however, the driver's emotional state and environmental factors are still important factors affecting the driving experience and driving safety. For example, emotional fluctuations of the driver may lead to distraction, slow reaction or operational errors, thereby increasing the risk of traffic accidents. Therefore, in order to improve the driving safety of autonomous vehicles, passenger comfort and the intelligence level of autonomous driving systems, how to comprehensively consider various factors to achieve effective control of autonomous vehicles is an issue that needs to be solved urgently. Summary of the invention

[0003] The present application provides a vehicle control method, device, equipment and computer-readable storage medium, which can achieve effective control of an autonomous driving vehicle to improve driving safety and passenger comfort.

[0004] In a first aspect, an embodiment of the present application provides a vehicle control method, the vehicle control method comprising:

[0005] Under the current vehicle control strategy, obtain the driver's real-time posture data, real-time physiological data and real-time environmental data;

[0006] fusing the real-time posture data, the real-time physiological data and the real-time environmental data to obtain fused data;

[0007] Inputting the fused data into a preset confidence level assessment model, so that the confidence level assessment model outputs a target confidence level grade based on the fused data, wherein the target confidence level grade is used to characterize the driver's trust in the current vehicle control strategy;

[0008] The current vehicle control strategy is updated based on the target confidence level to control the vehicle based on a new vehicle control strategy.

[0009] In combination with the first aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a speed adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0010] Based on the target confidence level, a preset vehicle speed calculation model and / or a preset acceleration calculation model is updated to obtain an updated vehicle speed calculation model and / or an updated acceleration calculation model;

[0011] The current vehicle control strategy is updated according to the updated vehicle speed calculation model and / or the updated acceleration calculation model to output a new vehicle control strategy.

[0012] In combination with the first aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a lane change adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0013] updating a preset lane change probability calculation model based on the target confidence level to obtain an updated lane change probability calculation model;

[0014] The current vehicle control strategy is updated according to the updated lane change probability calculation model to output a new vehicle control strategy.

[0015] In combination with the first aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a safety distance adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0016] Based on the target confidence level, a preset basic safety distance calculation model or a preset severe weather safety distance calculation model is updated to obtain an updated basic safety distance calculation model or an updated severe weather safety distance calculation model;

[0017] The current vehicle control strategy is updated according to the updated basic safety distance calculation model or the updated severe weather safety distance calculation model to output a new vehicle control strategy.

[0018] In combination with the first aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is an obstacle avoidance adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0019] Updating a preset obstacle avoidance degree calculation model based on the target confidence level to obtain an updated obstacle avoidance degree calculation model;

[0020] The current vehicle control strategy is updated according to the updated obstacle avoidance degree calculation model to output a new vehicle control strategy.

[0021] In combination with the first aspect, in one implementation, if the target scene corresponding to the current vehicle control strategy is a field of view adjustment scene, updating the current vehicle control strategy based on the target confidence level includes:

[0022] Based on the target confidence level, a preset brightness calculation model is updated to obtain an updated brightness calculation model;

[0023] The current vehicle control strategy is updated according to the updated brightness calculation model to output a new vehicle control strategy.

[0024] In combination with the first aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a mode switching adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0025] updating a preset mode switching time calculation model based on the target confidence level to obtain an updated mode switching time calculation model;

[0026] The current vehicle control strategy is updated according to the updated mode switching time calculation model to output a new vehicle control strategy.

[0027] In a second aspect, an embodiment of the present application provides a vehicle control device, the vehicle control device comprising:

[0028] A data acquisition module, which is used to acquire the driver's real-time posture data, real-time physiological data and real-time environmental data under the current vehicle control strategy;

[0029] A data fusion module, which is used to fuse the real-time posture data, the real-time physiological data and the real-time environmental data to obtain fused data;

[0030] A confidence assessment module, which is used to input the fused data into a preset confidence level assessment model, so that the confidence level assessment model outputs a target confidence level of the driver for the current vehicle control strategy based on the fused data;

[0031] A vehicle control module is used to update the current vehicle control strategy based on the target confidence level to control the vehicle based on a new vehicle control strategy.

[0032] In conjunction with the second aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a speed adjustment scenario, the vehicle control module is specifically configured to:

[0033] Based on the target confidence level, a preset vehicle speed calculation model and / or a preset acceleration calculation model is updated to obtain an updated vehicle speed calculation model and / or an updated acceleration calculation model;

[0034] The current vehicle control strategy is updated according to the updated vehicle speed calculation model and / or the updated acceleration calculation model to output a new vehicle control strategy.

[0035] In conjunction with the second aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a lane change adjustment scenario, the vehicle control module is further configured to:

[0036] updating a preset lane change probability calculation model based on the target confidence level to obtain an updated lane change probability calculation model;

[0037] The current vehicle control strategy is updated according to the updated lane change probability calculation model to output a new vehicle control strategy.

[0038] In conjunction with the second aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a safety distance adjustment scenario, the vehicle control module is further configured to:

[0039] Based on the target confidence level, a preset basic safety distance calculation model or a preset severe weather safety distance calculation model is updated to obtain an updated basic safety distance calculation model or an updated severe weather safety distance calculation model;

[0040] The current vehicle control strategy is updated according to the updated basic safety distance calculation model or the updated severe weather safety distance calculation model to output a new vehicle control strategy.

[0041] In conjunction with the second aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is an obstacle avoidance adjustment scenario, the vehicle control module is further configured to:

[0042] Updating a preset obstacle avoidance degree calculation model based on the target confidence level to obtain an updated obstacle avoidance degree calculation model;

[0043] The current vehicle control strategy is updated according to the updated obstacle avoidance degree calculation model to output a new vehicle control strategy.

[0044] In conjunction with the second aspect, in one implementation, if the target scene corresponding to the current vehicle control strategy is a field of view adjustment scene, the vehicle control module is further configured to:

[0045] Based on the target confidence level, a preset brightness calculation model is updated to obtain an updated brightness calculation model;

[0046] The current vehicle control strategy is updated according to the updated brightness calculation model to output a new vehicle control strategy.

[0047] In conjunction with the second aspect, in one implementation, if the target scenario corresponding to the current vehicle control strategy is a mode switching adjustment scenario, the vehicle control module is further configured to:

[0048] updating a preset mode switching time calculation model based on the target confidence level to obtain an updated mode switching time calculation model;

[0049] The current vehicle control strategy is updated according to the updated mode switching time calculation model to output a new vehicle control strategy.

[0050] In the third aspect, an embodiment of the present application provides a vehicle control device, which includes a processor, a memory, and a vehicle control program stored in the memory and executable by the processor, wherein when the vehicle control program is executed by the processor, the steps of the vehicle control method as described above are implemented.

[0051] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a vehicle control program is stored, wherein when the vehicle control program is executed by a processor, the steps of the vehicle control method as described above are implemented.

[0052] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0053] By fusing the driver's real-time posture data, real-time physiological data and real-time environmental data under the current vehicle control strategy, the uncertainty, noise and redundant information between different data sources are removed, so as to effectively combine the complementary information of different data sources and improve the accuracy and robustness of the perception of the driver's state; and based on the confidence level assessment model, the fused data is evaluated and predicted to output the driver's target confidence level for the current vehicle control strategy. The target confidence level represents the driver's trust in the control strategy adopted by the autonomous driving system; and the current vehicle control strategy is updated and adjusted according to the target confidence level, so that the new vehicle control strategy can better meet the driver's actual driving needs and comfort needs. Therefore, the new vehicle control strategy can not only achieve effective control of the autonomous driving vehicle, but also improve the driving safety and passenger comfort of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of a flow chart of an embodiment of a vehicle control method of the present application;

[0055] Figure 2 A schematic diagram of functional modules of an embodiment of a vehicle control device of the present application;

[0056] Figure 3 This is a schematic diagram of the hardware structure of the vehicle control device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0059] In a first aspect, an embodiment of the present application provides a vehicle control method.

[0060] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of the vehicle control method of the present application. Figure 1 As shown, the vehicle control method includes:

[0061] Step S10: Under the current vehicle control strategy, the real-time posture data, real-time physiological data and real-time environmental data of the driver are obtained.

[0062] Exemplarily, in this embodiment, the current vehicle control strategy refers to the driving control strategy adopted by the autonomous driving vehicle in the current scenario to achieve the corresponding driving task. It should be noted that the real-time posture data includes but is not limited to the driver's facial data and hand data; among them, it is preferred to use a high-resolution and wide-angle camera in the cab to take real-time photos of the driver and the shooting screen must cover the driver's face and hands to obtain real-time posture image data, thereby providing an important basis for confidence level assessment.

[0063] Real-time physiological data include but are not limited to the driver's heart rate, electrodermal activity (EDA) and blood pressure; among them, wearable devices and fixed devices in the car, such as smart watches, heart rate belts, electrodermal activity sensors, etc., can be preferably used to monitor the driver's heart rate, electrodermal activity, blood pressure and other physiological indicators in real time to obtain real-time physiological data for evaluating the driver's emotional state and health status.

[0064] Real-time environmental data includes but is not limited to light intensity, temperature and humidity; among them, light sensors, temperature sensors, humidity sensors, etc. can be preferably used to detect environmental changes inside and outside the vehicle in real time to obtain real-time environmental data for predicting the impact of environmental changes on driver comfort and driving safety; it should be noted that it can also be combined with the driver's personalized needs and environmental preferences to provide environmental information support for the adjustment of autonomous driving strategies.

[0065] Step S20: fusing the real-time posture data, the real-time physiological data and the real-time environmental data to obtain fused data.

[0066] Exemplarily, in this embodiment, multi-source perception data such as posture data, physiological data and environmental data are fused to form fused data that can be used to comprehensively characterize the driver's state perception, achieve complementarity and optimization between different data sources, and thereby improve the accuracy and reliability of the evaluation results.

[0067] Specifically, the original real-time posture data, real-time physiological data, and real-time environmental data received from each sensor are first pre-processed by data cleaning, standardization, synchronization, etc. to ensure the accuracy and consistency of the data. It should be noted that the implementation method and principle of data pre-processing are common knowledge in the art and will not be repeated here for the sake of brevity.

[0068] Then, the data pre-processed by fusion algorithms such as Kalman filtering and weighted averaging are fused to remove uncertainty, noise and redundant information between different data sources, and effectively combine complementary information from different data sources, thereby improving the accuracy and robustness of the perception of the driver's state. It should be understood that the fusion data output after fusion processing can effectively characterize the driver's emotional state, health status, degree of trust in the control strategy adopted by the automatic driving system, and attention level to the driving task. It should be noted that the method and principle of realizing data fusion processing using fusion algorithms such as Kalman filtering and weighted averaging are common knowledge in the art, and for the sake of brevity of description, they will not be repeated here.

[0069] Step S30: inputting the fused data into a preset confidence level assessment model, so that the confidence level assessment model outputs a target confidence level grade based on the fused data, wherein the target confidence level grade is used to characterize the driver's trust in the current vehicle control strategy.

[0070] Exemplarily, in this embodiment, deep learning models such as Transformer (a deep learning model architecture for natural language processing and other sequence-to-sequence tasks) and BERT (Bidirectional Encoder Representations from Transformers) can be preferably used to build a confidence level assessment model.

[0071] Specifically, taking the Transformer deep learning model to build a confidence level assessment model as an example, a data set including multiple groups of historical data is obtained, and each group of data includes historical posture data, historical physiological data and historical environmental data; wherein, each group of historical data in the data set can be labeled with a confidence level according to a preset level standard. The confidence level is used to characterize the driver's trust in the driving task performed by the autonomous driving system, that is, the driver's trust in the vehicle control strategy adopted by the autonomous driving system.

[0072] It should be noted that the specific content of the grade standard and the specific division of the confidence level can be determined according to actual needs and are not limited here. For example, the confidence level can be divided into five levels: low, lower, medium, higher and high. When a group of historical data shows that the driver's face is relatively relaxed, the driver drives hands-free or holds the steering wheel lightly with hands and does not make large movements (for example, there is no phone call, drinking water, etc.), the heart rate is stable, the skin resistance is increased, the external light is sufficient, and the temperature and humidity are suitable, and the driver also tends to choose to use automatic driving in a wider environment and a more aggressive driving style in the personalized settings, then the confidence level grade label of this group of historical data can be set to high; and when a certain historical data shows that the driver's face was relatively nervous, his hands were tightly holding the steering wheel, or, the heart rate was unstable, the skin resistance was reduced, the external light was insufficient, and the temperature and humidity were not suitable, and the driver also tended to choose to use automatic driving in a safer environment and a more conservative driving style in the personalized settings, then the confidence level grade label of this group of historical data can be set to low.

[0073] Then, each set of historical data is preprocessed and fused in turn to obtain the historical fusion data corresponding to each set of historical data. It can be understood that the historical fusion data carries the confidence level label corresponding to each set of historical data, and all historical fusion data and their corresponding confidence level labels constitute a training data set; the Transformer deep learning model is trained through the training data set so that the model can learn the driver's confidence changes in different scenarios until the number of training times reaches the preset number of iterations or the training loss value reaches the preset threshold, and the model training is stopped to achieve the construction of the confidence level assessment model. It can be understood that the confidence level assessment model generated by training can accurately predict the driver's confidence level; at the same time, the model parameters and structure of the confidence level assessment model can be continuously updated through online learning and optimization mechanisms to further improve the model's adaptability and accuracy to the driver's state perception. In addition, the autonomous driving system can also optimize its own driving strategy and parameter settings by continuously learning the driver's driving behavior and confidence level; for example, according to the driver's driving habits and confidence level changes, the parameters such as vehicle speed, acceleration and steering angle are automatically adjusted to improve driving safety and comfort.

[0074] Therefore, after the fused data is output in step S20, the fused data can be input into the confidence level assessment model so that the confidence level assessment model can perform accurate assessment and prediction based on the fused data to output the corresponding quantitative assessment result of the driver's confidence level, that is, output the target confidence level grade of the driver in the current vehicle control strategy, and the target confidence level grade represents the driver's degree of trust in the current driving task.

[0075] Step S40: updating the current vehicle control strategy based on the target confidence level to control the vehicle based on a new vehicle control strategy.

[0076] Exemplarily, in this embodiment, the current vehicle control strategy will be updated and adjusted through the target confidence level so that the newly generated vehicle control strategy can better meet the driver's actual driving needs and comfort needs, and then the new vehicle control strategy will be used to achieve effective control of the autonomous driving vehicle, thereby improving the driving safety and passenger comfort of the autonomous driving vehicle.

[0077] Specifically, for example, when the target confidence level is low (that is, the driver is at a low confidence level), the new vehicle control strategy will significantly reduce the vehicle speed and increase the distance to the vehicle in front when following a vehicle, that is, prioritizing safety distance rather than efficiency; when driving on a curve, the new vehicle control strategy will automatically reduce the vehicle speed to ensure safe passing, while increasing the intensity of lane keeping assist to reduce the operating requirements for the driver; in addition, in lane changing and overtaking decisions, the new vehicle control strategy will be more conservative, avoiding active lane changes unless necessary to reduce the risk of accidents, while giving the driver more time to adapt.

[0078] When the target confidence level is low, the speed corresponding to the new vehicle control strategy will be slightly lower than the normal level, but it will be improved compared to the low confidence level, and the acceleration will be smoother to reduce sudden acceleration or deceleration; at the same time, the new vehicle control strategy will also provide more assistance when the driver intends to change lanes, such as visual and sound prompts of the surrounding environment, planning the lane change path in advance, and improving the driver's trust and participation in autonomous driving. In addition, for intersection navigation scenarios, the navigation strategy can also be adjusted according to the target confidence level; for example, for drivers with a lower target confidence level, a simpler route with less traffic will be selected, and during the waiting period at the intersection, the target confidence level will be used to decide whether to accelerate in advance or maintain the current speed to reduce the driver's tension. In addition, for highway cruising scenarios, the target confidence level can be used to adjust parameters such as cruising speed and following distance; for example, for drivers with a lower target confidence level, a more conservative cruising strategy will be selected, and when changing lanes to overtake, the target confidence level will be used to decide whether to automatically perform lane changes or only provide auxiliary prompts.

[0079] When the target confidence level is medium, the vehicle speed and acceleration corresponding to the new vehicle control strategy will be close to normal driving habits, and the system will provide moderate assistance when changing lanes and overtaking to allow the driver to participate more in the decision-making process, but be ready to intervene at any time to ensure safety; at the same time, the new vehicle control strategy will also adjust lighting, air conditioning, etc. according to the environment to improve driving comfort.

[0080] When the target confidence level is high, the speed and acceleration corresponding to the new vehicle control strategy will be optimized according to driving needs and road conditions, and efficient driving will be encouraged, such as automatic lane changing and overtaking at the right time while maintaining a safe distance; in complex environments such as intersections or bad weather, the new vehicle control strategy will provide streamlined prompts to ensure that the driver can respond quickly according to the prompts.

[0081] When the target confidence level is high, the new vehicle control strategy will allow higher speeds and more flexible driving operations, which may include automatically selecting the optimal route, dynamically adjusting the following distance, and autonomously responding to complex traffic scenarios. At night or in severe weather conditions, the new vehicle control strategy will adjust according to the environment but will not intervene excessively, allowing the driver to enjoy driving pleasure.

[0082] It should be noted that this embodiment can also automatically adjust personalized parameters and settings in the autonomous driving system according to the driver's target confidence level to provide a driving experience that better meets the driver's needs; for example, when the driver's confidence level is low, the system's auxiliary functions and safety prompts are added. At the same time, the driver's confidence level can be regularly and proactively evaluated, and personalized driving suggestions and feedback can be provided based on the evaluation results, which helps the driver understand his or her driving ability and confidence level, so as to better utilize the autonomous driving system.

[0083] It can be seen that this embodiment realizes the intelligent adjustment of the autonomous driving strategy by integrating the results of image recognition, physiological data and environmental data, which has significant beneficial effects on improving driving safety, enhancing driver experience, and promoting the development of intelligent transportation systems.

[0084] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a speed adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0085] Based on the target confidence level, a preset vehicle speed calculation model and / or a preset acceleration calculation model is updated to obtain an updated vehicle speed calculation model and / or an updated acceleration calculation model;

[0086] The current vehicle control strategy is updated according to the updated vehicle speed calculation model and / or the updated acceleration calculation model to output a new vehicle control strategy.

[0087] For example, in this embodiment, a vehicle speed calculation model and an acceleration calculation model are constructed. Specifically, the vehicle speed calculation model is constructed using the following formula: v = v base +f(c,e), where v represents the actual vehicle speed, v baserepresents the basic vehicle speed (which can be set according to the road speed limit and driving conditions), c represents the driver's confidence level (which can be quantified as a value of 0-4), e represents environmental factors (such as weather, road conditions, etc.), and f(c, e) represents the influence function related to the confidence level and environmental factors, through which the vehicle speed adjustment for different confidence levels and environmental conditions can be achieved. It should be noted that the specific form of the f(c, e) function can be determined according to actual needs and is not limited here. For example, f(c, e) = αc + βe + γ, α, β, γ are all weight parameters and the specific values ​​can be determined according to actual needs.

[0088] It should be understood that for the curve scene, the curve speed can also be automatically adjusted according to the curve curvature and the driver's confidence level. That is, the vehicle speed calculation model can be updated by the curve curvature b, then v = v base +f(c,b), so the adaptive adjustment of the curve speed can be achieved through the f(c,b) function; for example, when the driver's target confidence level is low, f(c,b) will appropriately reduce the vehicle speed to ensure safe passing through the curve; it should be noted that the specific form of the f(c,b) function can be determined according to actual needs and is not limited here. In addition, when driving on a curve, for drivers with a low confidence level, this embodiment can also provide more active lane keeping assistance.

[0089] Use the following formula to implement the acceleration calculation model: a = a base +g(c), where a represents the actual acceleration, a base represents the basic acceleration (which can be set based on the driving task and road conditions), g(c) represents the confidence level influence function, which can adjust the smoothness or aggressiveness of the acceleration according to the driver's confidence level c; it should be noted that the specific form of the g(c) function can be determined according to actual needs and is not limited here.

[0090] Therefore, for the target scenario of the current vehicle control strategy, which is the speed adjustment scenario, after determining the target confidence level, the target confidence level can be substituted into the vehicle speed calculation model and / or the acceleration calculation model to obtain an updated vehicle speed calculation model and / or an updated acceleration calculation model; then the current vehicle control strategy is updated according to the actual vehicle speed and / or actual acceleration calculated by the updated vehicle speed calculation model and / or the updated acceleration calculation model to output a new vehicle control strategy. For example, when the target confidence level is low, f(c,e) will reduce the vehicle speed in the new vehicle control strategy to improve driving safety, and g(c) will make the acceleration in the new vehicle control strategy more smoothly adjusted to reduce abruptness and increase safety; and when the target confidence level is high, f(c,e) will increase the vehicle speed in the new vehicle control strategy and g(c) will allow the new vehicle control strategy to have a faster acceleration change to improve driving efficiency.

[0091] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a lane change adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0092] updating a preset lane change probability calculation model based on the target confidence level to obtain an updated lane change probability calculation model;

[0093] The current vehicle control strategy is updated according to the updated lane change probability calculation model to output a new vehicle control strategy.

[0094] Exemplarily, in this embodiment, a lane change probability calculation model will be constructed for lane change adjustment scenarios related to lane selection and lane change timing. Specifically, the lane change probability calculation model is modeled using the following formula: P(lane change) = h(c, t, n), where P(lane change) represents the lane change probability, and h(c, t, n) represents a function related to the driver's confidence level c, traffic flow t, and the number of surrounding vehicles n, which is used to select the best time to change lanes. It should be noted that the specific form of the h(c, t, n) function can be determined according to actual needs and is not limited here.

[0095] Therefore, for the target scenario corresponding to the current vehicle control strategy, which is the lane change adjustment scenario, after determining the target confidence level, the target confidence level can be substituted into the lane change probability calculation model to obtain an updated lane change probability calculation model; then the current vehicle control strategy is updated according to the lane change probability calculated by the updated lane change probability calculation model to output a new vehicle control strategy. For example, when the target confidence level is low, h(c, t, n) will tend to choose to change lanes when the traffic flow is small and there are few surrounding vehicles; otherwise, lane changes will be considered in more scenarios to improve driving efficiency. In addition, during the lane change process, for drivers with low confidence levels, this embodiment can also remind the driver to pay attention to surrounding vehicles through sound, images or other means, and provide clearer lane change instructions and longer preparation time.

[0096] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a safety distance adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0097] Based on the target confidence level, a preset basic safety distance calculation model or a preset severe weather safety distance calculation model is updated to obtain an updated basic safety distance calculation model or an updated severe weather safety distance calculation model;

[0098] The current vehicle control strategy is updated according to the updated basic safety distance calculation model or the updated severe weather safety distance calculation model to output a new vehicle control strategy.

[0099] Exemplarily, in this embodiment, a basic safety distance calculation model and a bad weather safety distance calculation model are constructed; specifically, the following formula is used to implement the modeling of the basic safety distance calculation model: D = D min +k(c,v), D represents the safety distance, which is composed of the minimum safety distance D min It is composed of an adjustment term k(c,v) based on the confidence level c and the vehicle speed v. When the confidence level is low, k(c,v) will increase the extra safety distance to reduce the risk of collision. When the confidence level is high, k(c,v) will allow a shorter safety distance to meet the needs of the driver. It should be noted that the specific form of the k(c,v) function can be determined according to actual needs and is not limited here.

[0100] Use the following formula to implement the modeling of the bad weather safety distance calculation model: D weather =D clear +n(c,w),D weather Indicates the safe distance in bad weather conditions, D clearrepresents the safe distance in clear weather, and n(c,w) represents the adjustment item based on the confidence level c and the weather condition w; when the confidence level is low, n(c,w) will increase the additional safe distance to cope with more complex driving conditions. It should be noted that the specific form of the n(c,w) function can be determined according to actual needs and is not limited here.

[0101] Therefore, for the current vehicle control strategy, the target scenario is the safety distance adjustment scenario. After determining the target confidence level, the target confidence level can be substituted into the basic safety distance calculation model or the bad weather safety distance calculation model to obtain an updated basic safety distance calculation model or an updated bad weather safety distance calculation model; then the safety distance calculated by the updated basic safety distance calculation model or the updated bad weather safety distance calculation model is used to update the current vehicle control strategy to output a new vehicle control strategy. For example, when dynamically following a vehicle in normal weather, if the driver's target confidence level is low, k(c,v) will increase the following distance in the new vehicle control strategy to reduce the risk of rear-end collisions; in bad weather, n(c,w) will dynamically adjust the safety distance from the vehicle in front according to the target confidence level to ensure safe driving even in bad weather.

[0102] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is an obstacle avoidance adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0103] Updating a preset obstacle avoidance degree calculation model based on the target confidence level to obtain an updated obstacle avoidance degree calculation model;

[0104] The current vehicle control strategy is updated according to the updated obstacle avoidance degree calculation model to output a new vehicle control strategy.

[0105] For example, in this embodiment, an obstacle avoidance degree calculation model is constructed; specifically, the following formula is used to implement the modeling of the obstacle avoidance degree calculation model: obstacle =l(c,d,S),A obsracle represents the urgency or mode of obstacle avoidance action, and l(c, d, s) represents a function based on the confidence level c, obstacle distance d, and obstacle speed s; when the driver's confidence level is low, even if the obstacle is far away or slow, l(c, d, s) will enable the system to take earlier warnings and clearer avoidance actions to enhance the driver's sense of security. It should be noted that the specific form of the l(c, d, s) function can be determined according to actual needs and is not limited here.

[0106] Therefore, the target scenario corresponding to the current vehicle control strategy is the obstacle avoidance adjustment scenario. After determining the target confidence level, the target confidence level can be substituted into the obstacle avoidance degree calculation model to obtain an updated obstacle avoidance degree calculation model. Then, the obstacle avoidance action urgency A calculated according to the updated obstacle avoidance degree calculation model is obstacle The current vehicle control strategy is updated to output a new vehicle control strategy. For example, in a pedestrian avoidance scenario, when the system detects a pedestrian, in addition to basic avoidance actions, for drivers with lower confidence levels, l(c, d, s) will provide longer reaction times and clearer avoidance prompts (such as increasing alarm frequency or sound, etc.) in the new vehicle control strategy; in an emergency avoidance scenario, for drivers with lower confidence levels, l(c, d, s) will provide stronger avoidance actions (such as outputting a larger steering wheel angle) and clearer avoidance prompts in the new vehicle control strategy, and during the avoidance process, the system will continuously evaluate the driver's confidence level and adjust the avoidance strategy accordingly.

[0107] Further, in one embodiment, if the target scene corresponding to the current vehicle control strategy is a field of view adjustment scene, updating the current vehicle control strategy based on the target confidence level includes:

[0108] Based on the target confidence level, a preset brightness calculation model is updated to obtain an updated brightness calculation model;

[0109] The current vehicle control strategy is updated according to the updated brightness calculation model to output a new vehicle control strategy.

[0110] For example, in this embodiment, a brightness calculation model is constructed for the nighttime driving field of vision adjustment scene; specifically, the following formula is used to implement the brightness calculation model: L = L base +m(c), L represents the brightness of vehicle lights, L base represents the basic brightness, and m(c) represents the gain or loss adjusted according to the confidence level; for drivers with a low confidence level, m(c) will increase the light brightness or turn on more auxiliary lighting to improve visibility and confidence during nighttime driving. It should be noted that the specific form of the m(c) function can be determined according to actual needs and is not limited here.

[0111] Therefore, for the target scenario corresponding to the current vehicle control strategy, which is the field of view adjustment scenario, the brightness and range of the vehicle lights will be automatically adjusted according to the driver's confidence level to provide the best nighttime driving field of view; specifically, after determining the target confidence level, the target confidence level can be substituted into the brightness calculation model to obtain an updated brightness calculation model; then the current vehicle control strategy is updated according to the vehicle light brightness calculated by the updated brightness calculation model to output a new vehicle control strategy. For example, when driving at night, for drivers with a low confidence level, m(c) will increase the light brightness in the new vehicle control strategy, and the system will also turn on more safety assistance systems to enhance the driver's confidence.

[0112] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a mode switching adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes:

[0113] updating a preset mode switching time calculation model based on the target confidence level to obtain an updated mode switching time calculation model;

[0114] The current vehicle control strategy is updated according to the updated mode switching time calculation model to output a new vehicle control strategy.

[0115] Exemplarily, in this embodiment, a mode switching time calculation model is constructed; specifically, the following formula is used to implement the modeling of the mode switching time calculation model: T switch =p(c,e),T switch represents the threshold time for switching between the automatic driving mode and the manual driving mode, and p(c, e) is a function related to the driver's confidence level c and the environmental factor e. When the driver's confidence decreases, p(c, e) will extend the switching time or provide more obvious prompts to ensure a safe transition.

[0116] Therefore, the target scenario corresponding to the current vehicle control strategy is the driving mode switching adjustment scenario. After determining the target confidence level, the target confidence level can be substituted into the mode switching time calculation model to obtain an updated mode switching time calculation model; then the current vehicle control strategy is updated according to the mode switching time threshold calculated by the updated mode switching time calculation model to output a new vehicle control strategy. For example, when switching between automatic driving and manual driving, if the driver's confidence level is low, p(c,e) will extend the time required for switching in the new vehicle control strategy, so that the system provides longer preparation time and clearer switching prompts; and during the switching process, the system will continue to monitor the changes in the driver's confidence level, and adjust the switching buffer time and safety accordingly; if the driver's confidence continues to decline, the system may automatically take over the driving task to ensure driving safety.

[0117] In summary, this embodiment uses a variety of sensors to sense and monitor the driver's posture changes, physiological changes, and changes in the external environment, and determines the driver's confidence level based on this; at the same time, the confidence level is used to adjust the automatic driving strategy including vehicle speed, acceleration, lane selection, lane change timing, safe distance, and obstacle avoidance strategy, and timely warnings can be issued to reduce accident risks and avoid dangerous situations, thereby improving the driving safety of automatic driving vehicles, passenger comfort, and the intelligence level of automatic driving systems. In addition, the driver's confidence status and vehicle environment information can be fed back in real time to help the driver better understand the current driving conditions, and personalized driving settings can be provided to improve driver comfort and product satisfaction, thereby enhancing the driver experience. It can be understood that as an important part of the intelligent transportation system, this embodiment can provide the system with accurate driver status information, which is helpful to achieve coordinated driving and traffic flow optimization between vehicles in the future, and through the analysis of a large amount of driver status data, it can provide strong support for traffic planning and management.

[0118] In a second aspect, an embodiment of the present application also provides a vehicle control device.

[0119] In one embodiment, referring to Figure 2 , Figure 2 This is a functional module diagram of an embodiment of the vehicle control device of the present application. Figure 2 As shown, the vehicle control device includes:

[0120] A data acquisition module, which is used to acquire the driver's real-time posture data, real-time physiological data and real-time environmental data under the current vehicle control strategy;

[0121] A data fusion module, which is used to fuse the real-time posture data, the real-time physiological data and the real-time environmental data to obtain fused data;

[0122] A confidence assessment module, which is used to input the fused data into a preset confidence level assessment model, so that the confidence level assessment model outputs a target confidence level of the driver for the current vehicle control strategy based on the fused data;

[0123] A vehicle control module is used to update the current vehicle control strategy based on the target confidence level to control the vehicle based on a new vehicle control strategy.

[0124] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a speed adjustment scenario, the vehicle control module is specifically configured to:

[0125] Based on the target confidence level, a preset vehicle speed calculation model and / or a preset acceleration calculation model is updated to obtain an updated vehicle speed calculation model and / or an updated acceleration calculation model;

[0126] The current vehicle control strategy is updated according to the updated vehicle speed calculation model and / or the updated acceleration calculation model to output a new vehicle control strategy.

[0127] Furthermore, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a lane change adjustment scenario, the vehicle control module is further configured to:

[0128] updating a preset lane change probability calculation model based on the target confidence level to obtain an updated lane change probability calculation model;

[0129] The current vehicle control strategy is updated according to the updated lane change probability calculation model to output a new vehicle control strategy.

[0130] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a safety distance adjustment scenario, the vehicle control module is further configured to:

[0131] Based on the target confidence level, a preset basic safety distance calculation model or a preset severe weather safety distance calculation model is updated to obtain an updated basic safety distance calculation model or an updated severe weather safety distance calculation model;

[0132] The current vehicle control strategy is updated according to the updated basic safety distance calculation model or the updated severe weather safety distance calculation model to output a new vehicle control strategy.

[0133] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is an obstacle avoidance adjustment scenario, the vehicle control module is further configured to:

[0134] Updating a preset obstacle avoidance degree calculation model based on the target confidence level to obtain an updated obstacle avoidance degree calculation model;

[0135] The current vehicle control strategy is updated according to the updated obstacle avoidance degree calculation model to output a new vehicle control strategy.

[0136] Furthermore, in one embodiment, if the target scene corresponding to the current vehicle control strategy is a field of view adjustment scene, the vehicle control module is further configured to:

[0137] Based on the target confidence level, a preset brightness calculation model is updated to obtain an updated brightness calculation model;

[0138] The current vehicle control strategy is updated according to the updated brightness calculation model to output a new vehicle control strategy.

[0139] Further, in one embodiment, if the target scenario corresponding to the current vehicle control strategy is a mode switching adjustment scenario, the vehicle control module is further configured to:

[0140] updating a preset mode switching time calculation model based on the target confidence level to obtain an updated mode switching time calculation model;

[0141] The current vehicle control strategy is updated according to the updated mode switching time calculation model to output a new vehicle control strategy.

[0142] Among them, the functional implementation of each module in the above-mentioned vehicle control device corresponds to the various steps in the above-mentioned vehicle control method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0143] In a third aspect, an embodiment of the present application provides a vehicle control device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0144] Reference Figure 3 , Figure 3 Schematic diagram of the hardware structure of the vehicle control device involved in the embodiment of the present application. In the embodiment of the present application, the vehicle control device may include a processor, a memory, a communication interface and a communication bus.

[0145] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0146] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces, which are used to interconnect the devices inside the vehicle control device, and interfaces used to interconnect the vehicle control device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0147] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0148] The processor may be a general-purpose processor, which may call the vehicle control program stored in the memory and execute the vehicle control method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle control program is called may refer to the various embodiments of the vehicle control method of the present application, which will not be described in detail here.

[0149] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0150] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0151] A vehicle control program is stored on the readable storage medium of the present application, wherein when the vehicle control program is executed by the processor, the steps of the vehicle control method as described above are implemented.

[0152] Among them, the method implemented when the vehicle control program is executed can refer to the various embodiments of the vehicle control method of the present application, and will not be repeated here.

[0153] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0154] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0155] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0156] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0157] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0158] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0159] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle control method, characterized in that: The vehicle control method comprises: Under the current vehicle control strategy, obtain the driver's real-time posture data, real-time physiological data and real-time environmental data; fusing the real-time posture data, the real-time physiological data and the real-time environmental data to obtain fused data; Inputting the fused data into a preset confidence level assessment model, so that the confidence level assessment model outputs a target confidence level grade based on the fused data, wherein the target confidence level grade is used to characterize the driver's trust in the current vehicle control strategy; The current vehicle control strategy is updated based on the target confidence level to control the vehicle based on a new vehicle control strategy.

2. The vehicle control method according to claim 1, characterized in that: If the target scenario corresponding to the current vehicle control strategy is a speed adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes: Based on the target confidence level, a preset vehicle speed calculation model and / or a preset acceleration calculation model is updated to obtain an updated vehicle speed calculation model and / or an updated acceleration calculation model; The current vehicle control strategy is updated according to the updated vehicle speed calculation model and / or the updated acceleration calculation model to output a new vehicle control strategy.

3. The vehicle control method according to claim 1, characterized in that: If the target scenario corresponding to the current vehicle control strategy is a lane change adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes: updating a preset lane change probability calculation model based on the target confidence level to obtain an updated lane change probability calculation model; The current vehicle control strategy is updated according to the updated lane change probability calculation model to output a new vehicle control strategy.

4. The vehicle control method according to claim 1, characterized in that: If the target scenario corresponding to the current vehicle control strategy is a safety distance adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes: Based on the target confidence level, a preset basic safety distance calculation model or a preset severe weather safety distance calculation model is updated to obtain an updated basic safety distance calculation model or an updated severe weather safety distance calculation model; The current vehicle control strategy is updated according to the updated basic safety distance calculation model or the updated severe weather safety distance calculation model to output a new vehicle control strategy.

5. The vehicle control method according to claim 1, characterized in that: If the target scenario corresponding to the current vehicle control strategy is an obstacle avoidance adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes: Updating a preset obstacle avoidance degree calculation model based on the target confidence level to obtain an updated obstacle avoidance degree calculation model; The current vehicle control strategy is updated according to the updated obstacle avoidance degree calculation model to output a new vehicle control strategy.

6. The vehicle control method according to claim 1, characterized in that: If the target scene corresponding to the current vehicle control strategy is a field of view adjustment scene, updating the current vehicle control strategy based on the target confidence level includes: Based on the target confidence level, a preset brightness calculation model is updated to obtain an updated brightness calculation model; The current vehicle control strategy is updated according to the updated brightness calculation model to output a new vehicle control strategy.

7. The vehicle control method according to claim 1, characterized in that: If the target scenario corresponding to the current vehicle control strategy is a mode switching adjustment scenario, updating the current vehicle control strategy based on the target confidence level includes: updating a preset mode switching time calculation model based on the target confidence level to obtain an updated mode switching time calculation model; The current vehicle control strategy is updated according to the updated mode switching time calculation model to output a new vehicle control strategy.

8. A vehicle control device, characterized in that: The vehicle control device comprises: A data acquisition module, which is used to acquire the driver's real-time posture data, real-time physiological data and real-time environmental data under the current vehicle control strategy; A data fusion module, which is used to fuse the real-time posture data, the real-time physiological data and the real-time environmental data to obtain fused data; A confidence assessment module, which is used to input the fused data into a preset confidence level assessment model, so that the confidence level assessment model outputs a target confidence level of the driver for the current vehicle control strategy based on the fused data; A vehicle control module is used to update the current vehicle control strategy based on the target confidence level to control the vehicle based on a new vehicle control strategy.

9. A vehicle control device, characterized in that: The vehicle control device includes a processor, a memory, and a vehicle control program stored in the memory and executable by the processor, wherein when the vehicle control program is executed by the processor, the steps of the vehicle control method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle control program, wherein when the vehicle control program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 7 are implemented.