Automatic driving adaptive system and method based on driver comfort monitoring

By establishing a scene mapping and comfort evaluation model, combining vehicle and passenger data, the driving planning of the autonomous driving system is adjusted in real time, the problem of insufficient monitoring of passenger comfort in the existing technology is solved, and personalized driving experience and improvement are achieved High adaptability.

CN118928465APending Publication Date: 2024-11-12CHINA AUTOMOTIVE ENG RES INST

Patent Information

Application Number
CN202411007564.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing autonomous driving system mainly focuses on the driver's behavior and health status monitoring. It lacks the combination of monitoring of physiological comfort parameters of passengers in the car and its adaptive adjustments, making it difficult to meet the personalized driving comfort needs of diversified driving groups. .

Method used

By collecting physiological parameters and vehicle driving parameters of drivers and passengers, establishing a scene mapping model and comfort evaluation model, monitoring and adjusting the driving plan of the autonomous driving system in real time, introducing non-comfort punishments to optimize driving strategies, and meeting the driving and riding of different users. Comfort requirements.

Benefits of technology

Real-time monitoring and adaptive adjustment of physiological parameters related to the comfort of the driver and passengers is realized, personalized driving style adjustments are provided, and adaptability and comfort of the autonomous driving experience are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928465A_ABST
    Figure CN118928465A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automatic driving, and discloses an automatic driving adaptive system and method based on driver comfort monitoring, and the method comprises the following steps: 1, collecting target data; step 2, establishing a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for a target scene; step 3, collecting a plurality of driving plans currently made by the vehicle automatic driving system; classifying driving plans made by a vehicle automatic driving system through the scene mapping model; determining a vehicle control parameter threshold based on the target data to limit the driving plans, calculating the discomfort of each driving plan by a comfort evaluation model, and introducing a non-comfort punishment to a vehicle automatic driving system; the automated driving system selects a driving plan to be performed based on the non-comfort penalty. According to the method, the vehicle driving strategy can be adjusted in a self-adaptive mode so as to meet the individual requirements of different users for driving comfort, and adaptability is high.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving adaptive system and method based on driver comfort monitoring. Background Art

[0002] In recent years, autonomous driving and intelligent network technology have developed rapidly, and the scope of use of vehicles equipped with related technologies has gradually expanded. Intelligent driving technology can effectively reduce traffic congestion and reduce the incidence of traffic accidents through precise path planning, efficient traffic flow management and accurate obstacle detection. At the same time, automated operation greatly reduces labor costs and operating expenses, especially in large-scale transportation and distribution services. Therefore, it has broad application prospects in the fields of public transportation and logistics distribution. With the popularization of autonomous driving vehicles, the public's expectations for intelligent driving experience continue to rise. Given the high complexity of the autonomous driving system, which involves the collaborative work of many algorithm domain controls, driving style - that is, vehicle acceleration and deceleration strategies, steering softness and other factors - has a direct impact on driving comfort. However, due to significant individual differences, a single standardized driving style is difficult to meet the comfort needs of all drivers and passengers. In particular, in the face of a diverse group of drivers and passengers, how to achieve personalized driving style adjustment and meet the needs of different users for driving comfort has become the key to technological breakthroughs.

[0003] At present, although some research attempts to solve this problem, such as patent CN 117774996A discloses an adaptive assisted driving system that takes into account the different faces of different people. By learning the driver's driving style and adjusting the vehicle driving parameters, the assisted driving system can be adaptively adjusted to reduce the takeover rate; patent CN 115092153A discloses an intelligent driving decision-making method based on different groups of people. The driver can adjust the intelligent driving to meet his personalized needs by manually modifying the parameters; patent CN 115054267A discloses a driver status monitoring system based on electrocardiogram signals. By real-time collection and processing of the driver's electrocardiogram signals, the driver's health status can be monitored to avoid accidents that cause the vehicle to lose control; patent CN 114889634A discloses a method for automatic switching of human-vehicle driving rights based on electromyography signals. By changing the electromyography state at the moment of driver takeover, the automatic driving mode and the manual driving mode can be smoothly switched.

[0004] However, these existing solutions mainly focus on monitoring the driver's behavior and health status, while there is a relative lack of research on monitoring the physiological comfort parameters of passengers in the vehicle and their combination with the adaptive adjustment of the autonomous driving system. Summary of the invention

[0005] The present invention aims to provide an autonomous driving adaptive system and method based on driver comfort monitoring, which can realize real-time monitoring of physiological parameters related to driver comfort, and adaptively adjust the vehicle driving strategy based on the monitoring data to meet the personalized needs of different users for driving comfort, and has strong adaptability.

[0006] To achieve the above objectives, the present invention provides the following basic solutions.

[0007] Solution 1

[0008] An automatic driving adaptive method based on driver comfort monitoring comprises the following steps:

[0009] Step 1, collecting target data; the target data includes physiological parameters of the driver and passengers when the vehicle is in a normal scene of autonomous driving, physiological parameters when the driver performs unconventional driving actions, and vehicle driving parameters;

[0010] Step 2: Based on the target data, a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for the target scene are established; the target scene is a non-comfortable driving scene that has a negative stimulus on the driver's comfort;

[0011] Step 3, collect multiple driving plans currently made by the vehicle's automatic driving system; classify the driving plans made by the vehicle's automatic driving system by the scene mapping model; confirm the vehicle control parameter threshold based on the target data to restrict the driving plan, and then calculate the discomfort of each driving plan by the comfort evaluation model, and introduce non-comfort penalty to the vehicle's automatic driving system; the automatic driving system selects the driving plan to be executed based on the non-comfort penalty.

[0012] Solution 2

[0013] An autonomous driving adaptive system based on driver comfort monitoring, used to execute an autonomous driving adaptive method based on driver comfort monitoring as described in Scheme 1; comprising a collection module and an analysis module; the analysis module establishes a communication connection with the vehicle's autonomous driving system;

[0014] The acquisition module includes a vehicle data acquisition unit and a driver and passenger data acquisition unit; the vehicle data acquisition unit is used to acquire vehicle driving parameters; the driver and passenger data acquisition unit is used to acquire the physiological parameters of the driver and passenger when the vehicle is in a normal scene of automatic driving and the physiological parameters of the driver when an unconventional driving action occurs;

[0015] The analysis module establishes a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for a target scene; the target scene is a non-comfortable driving scene that has a negative stimulus on the driver's comfort;

[0016] The analysis module is used to collect multiple driving plans currently made by the vehicle's automatic driving system; and the scene mapping model is used to classify the driving plans made by the vehicle's automatic driving system; and based on the target data, the vehicle control parameter threshold is confirmed to restrict the driving plan, and then the comfort evaluation model is used to calculate the discomfort of each driving plan, and non-comfort penalty is introduced into the vehicle's automatic driving system; the automatic driving system selects the driving plan to be executed based on the non-comfort penalty.

[0017] The working principle and advantages of the present invention are:

[0018] The present invention provides an autonomous driving adaptive system and method based on driver comfort monitoring, which establishes a scene mapping model and a comfort evaluation model in combination with vehicle driving data and the physiological data of the driver and passengers. The model is used in conjunction with the vehicle's real-time driving data and physiological monitoring data to adjust the driving plan of the vehicle's autonomous driving system to a certain extent, thereby achieving adaptive adjustment of the autonomous driving, meeting the personalized needs of different users for driving comfort, and having strong adaptability.

[0019] Among them, the scene mapping model can determine whether the driving scenarios corresponding to various driving plans belong to the target scenarios (i.e., uncomfortable scenarios that will have a negative impact on the driver's comfort) based on the driving plans currently made by the vehicle's automatic driving system, and then the comfort evaluation model calculates the discomfort accordingly, thereby introducing non-comfort penalties for the driving planning decisions of the automatic driving system, so that the driving planning decisions finally made by the automatic driving system can be more adapted to the driver's current physiological state, thereby realizing personalized driving style adjustments and meeting the needs of different users for driving comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a method flow of an embodiment of an automatic driving adaptive system and method based on driver comfort monitoring of the present invention;

[0021] Figure 2 A schematic diagram of scene mapping model generation for an embodiment of an autonomous driving adaptive system and method based on driver comfort monitoring of the present invention. DETAILED DESCRIPTION

[0022] The following is a further detailed description through specific implementation methods:

[0023] The embodiment is basically as shown in the attached Figure 1 As shown: An automatic driving adaptive method based on driver comfort monitoring includes the following steps:

[0024] Step 1: Collect target data. The target data includes physiological parameters of the driver and passengers when the vehicle is in a normal driving scenario of autonomous driving, physiological parameters of the driver when an unconventional driving action is performed, and vehicle driving parameters.

[0025] Specifically, the physiological parameters include electrocardiogram parameters, electrodermal parameters, electroencephalogram parameters, pupil diameter, and blinking frequency; they also include statistical parameters of the above parameters, such as average heart rate, maximum heart rate, heart rate variability extremely low frequency power, skin conductivity level, pupil diameter, blinking frequency, etc.

[0026] The non-routine driving actions include those that are opposite to normal driving actions, such as active acceleration, braking, and direction adjustment, which are actions performed by the driver to significantly intervene in the vehicle control process in the automatic driving mode.

[0027] Step 2: Based on the target data, a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for the target scene are established. The target scene is a non-comfortable driving scene that has a negative impact on the driver's comfort.

[0028] Specifically, the non-comfortable driving scenarios include negative balance scenarios and negative vision scenarios; the negative balance scenarios include lane changing, entering and exiting a highway, and stopping at traffic lights; the negative vision scenarios include emergency avoidance, detouring around obstacles, and pedestrian games.

[0029] In this step, based on the vehicle driving parameters, the balance sense negative scenes and the visual negative scenes are identified and annotated to form a reference data set; the vehicle driving parameters include the accelerator pedal opening, the decelerator pedal opening, the lateral speed, the longitudinal speed, the lateral acceleration, and the longitudinal acceleration; the reference data set is input into the BP neural network and constructed as a scene mapping model between the vehicle driving parameters and the scene classification, such as Figure 2 shown.

[0030] The steps of establishing the comfort evaluation model include: collecting the driving history data of the vehicle and normalizing the vehicle control parameters therein; the normalization formula is as follows:

[0031]

[0032] Where p is the number of parameters, n is the number of samples; x kl is the l parameter in k samples, is x in n samples l The average value, S l is the sample variance.

[0033] By combining the above formulas, the vehicle control parameters are normalized.

[0034] And calculate the deviation value J of each vehicle control parameter in different scenarios; the deviation value J of each vehicle control parameter when the vehicle is in the takeover scenario m as a deviation from the limit.

[0035] in, a p is the variance contribution rate of vehicle control parameters, expressed as a p As the deviation calculation coefficient of the vehicle control parameter deviation value. p is the vehicle control parameter, x0 is the vehicle control parameter under normal driving conditions and serves as the reference value, and p is the number of parameters.

[0036] Confirm the vehicle control parameters when the vehicle is in the normal driving scene of automatic driving in the driving history data as the benchmark vehicle control parameters, and confirm their benchmark values; collect the vehicle control parameters when the vehicle is in the takeover scene as the reference vehicle control parameter thresholds; take the parameter deviation value of the vehicle control parameters compared to the benchmark value as the discomfort value; the J m It is the parameter deviation value of the reference vehicle control parameter threshold compared to the benchmark value.

[0037] The takeover scenario refers to a scenario in which the driver intervenes in the automatic driving control process and takes over the control of the vehicle during the driving process of the vehicle in the automatic driving mode. And the non-comfortable driving scenario includes the takeover scenario.

[0038] Furthermore, the physiological parameters of the driver and passengers when the vehicle is in a normal driving scenario of autonomous driving are confirmed and used as a baseline physiological indicator set A, and the physiological parameters of the driver and passengers when the vehicle is in a takeover scenario are used as a reference physiological indicator set B; and by comparing indicator set A and indicator set B, the specific change trends and takeover thresholds (the takeover threshold refers to the values ​​of each control parameter of the vehicle at the takeover moment) of the physiological parameters of different drivers and passengers are analyzed. Then, through correlation analysis, the correlation coefficient calculated after normalizing different physiological parameters is directly used as a weight factor for comfort evaluation, that is, as a weight factor of the BP neural network, to confirm the parameter input weight when training the model.

[0039] The relative deviation value y is used as the model training dependent variable, and the vehicle's driving history data is used to perform regression training on the BP neural network to obtain a comfort evaluation model for the target scenario; where y = J / J m .

[0040] The vehicle control parameters include lateral acceleration a y , acceleration a z , risk factor TCC, longitudinal acceleration a x , lateral jerk a yy , longitudinal jerk a xx .

[0041] Moreover, as the vehicle's driving history data and corresponding physiological parameter data increase, the model formed by this solution will be optimized and calibrated accordingly, and the model performance will be better.

[0042] Step 3, collect multiple driving plans currently made by the vehicle's automatic driving system; classify the driving plans made by the vehicle's automatic driving system by the scene mapping model; confirm the vehicle control parameter threshold based on the target data to restrict the driving plan (in this embodiment, the automatic driving system includes a planning module for generating a driving plan and a decision module for deciding the driving plan to be executed, and the vehicle control parameter threshold is transmitted to the planning module to restrict the driving plan), and then the comfort evaluation model calculates the discomfort of each driving plan, and introduces the non-comfort penalty to the vehicle's automatic driving system (specifically introduces the decision module of the automatic driving system); the automatic driving system selects the driving plan to be executed based on the non-comfort penalty.

[0043] Among them, when confirming the vehicle control parameter threshold, the takeover data is mainly used to confirm the vehicle control parameters when taking over (that is, confirming the takeover threshold), so as to confirm the deviation threshold of the control parameters for the driver and the vehicle control parameters during normal driving (such as when it is confirmed that the control parameter deviation value becomes larger, the driver takes over), and thus confirm that the vehicle control parameter deviation value cannot exceed the deviation threshold to restrict the driving plan.

[0044] In this step, control influencing factors a, b, and c for different control parameters are also introduced into the autonomous driving system according to the scene mapping model to adjust the longitudinal control parameters, lateral control parameters, and collision control parameters in the driving planning.

[0045] Specifically, according to the scene mapping model, in the classification of balance negative scenes and visual negative scenes, the main influencing parameters of each vehicle control parameter are obtained through principal component analysis and other means (for example, in the balance negative stimulus recognition model, the steering angle change rate, braking deceleration, etc. are obtained as the main influencing parameters; in the visual negative stimulus recognition model, TCC, etc. are obtained as the main influencing parameters). According to the results of the principal component analysis (the degree of influence of each parameter), control influencing factors a, b, c, etc. for different control parameters are introduced into the automatic driving system to adjust the longitudinal control parameters, lateral control parameters, collision control parameters, etc. in the driving planning.

[0046] In the current PNC module of the autonomous driving system, multiple limiting factors are introduced to control the path planning (for example, the basic path planning is a 5th-order polynomial, and it needs to meet the requirements of vehicle dynamics and obstacle avoidance, so the 5th-order polynomial will be restricted and optimized to meet the above requirements). In this process, the various influencing factors of the comfort control parameters can guide the path planning. Through the above settings, this solution can guide the planning of the autonomous driving system (specifically its PNC module) by analyzing the influence of various control parameters on different negative stimulation scenarios (balance, vision), which helps to achieve a better driving experience.

[0047] Preferably, when selecting the driving plan to be executed, the autonomous driving system also makes a comprehensive decision based on the efficiency penalty factor, the lateral impact penalty factor, the longitudinal impact penalty factor and the risk penalty factor.

[0048] Specifically, since the timing planning of the autonomous driving system is mostly discrete, that is, multiple plans will be made simultaneously in each frame, different penalty factors (efficiency penalty factor, lateral impact penalty factor, longitudinal impact penalty factor and risk penalty factor, etc.) are introduced here, combined with non-comfort penalty (based on the comfort evaluation model to judge the discomfort level of each plan, such as the more uncomfortable, the higher the non-comfort penalty, and the less likely the decision to choose the plan is), this scheme can select the most comprehensive driving plan, and the decision is more reliable.

[0049] This embodiment also provides an autonomous driving adaptive system based on driver comfort monitoring, which is used to execute an autonomous driving adaptive method based on driver comfort monitoring as described above; it includes an acquisition module and an analysis module; the analysis module establishes a communication connection with the vehicle's autonomous driving system.

[0050] The acquisition module includes a vehicle data acquisition unit and a driver and passenger data acquisition unit. The vehicle data acquisition unit is used to acquire vehicle driving parameters; the driver and passenger data acquisition unit is used to acquire the physiological parameters of the driver and passenger when the vehicle is in a normal driving scenario of automatic driving and the physiological parameters of the driver when an unconventional driving action is performed.

[0051] Specifically, the driver and passenger data collection unit includes physiological information monitoring sensors integrated in components such as the steering wheel, instrument panel, seat belts and passenger handles in the vehicle cabin. In this embodiment, conventional electrocardiogram, electrodermal and electroencephalogram collectors, high-definition cameras or eye trackers (for collecting eye movement indicators and pupil diameter) can be used to fully monitor the physiological state of the driver and passengers.

[0052] The analysis module establishes a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for a target scene; the target scene is a non-comfortable driving scene that has a negative stimulus on the driver's comfort;

[0053] The analysis module is used to collect multiple driving plans currently made by the vehicle's automatic driving system; and the scene mapping model is used to classify the driving plans made by the vehicle's automatic driving system; and based on the target data, the vehicle control parameter threshold is confirmed to restrict the driving plan, and then the comfort evaluation model is used to calculate the discomfort of each driving plan, and non-comfort penalty is introduced into the vehicle's automatic driving system; the automatic driving system selects the driving plan to be executed based on the non-comfort penalty.

[0054] The present embodiment provides an autonomous driving adaptive system and method based on driver comfort monitoring, which can realize real-time monitoring of physiological parameters related to driver comfort, and adaptively adjust the vehicle driving strategy based on the monitoring data to meet the personalized needs of different users for driving comfort, and has strong adaptability.

[0055] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field are aware of all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement the scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for the ordinary technicians in the relevant field to implement this application. It should be pointed out that for the technicians in this field, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent.

Claims

1. An adaptive method for automatic driving based on driver comfort monitoring, characterized in that: The following steps are involved: Step 1, collecting target data; the target data includes physiological parameters of the driver and passengers when the vehicle is in a normal scene of autonomous driving, physiological parameters when the driver performs unconventional driving actions, and vehicle driving parameters; Step 2: Based on the target data, a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for the target scene are established; the target scene is a non-comfortable driving scene that has a negative stimulus on the driver's comfort; Step 3, collecting multiple driving plans currently made by the vehicle's automatic driving system; The scene mapping model is used to classify the driving plans made by the vehicle's autonomous driving system; Based on the target data, the threshold of the vehicle control parameters is confirmed to restrict the driving plan. The comfort evaluation model then calculates the discomfort of each driving plan and introduces non-comfort penalty into the vehicle's automatic driving system. The automatic driving system selects the driving plan to be executed based on the non-comfort penalty.

2. The method for autonomous driving adaptation based on driver comfort monitoring according to claim 1, characterized in that: The non-comfortable driving scenarios include negative balance scenarios and negative visual scenarios; The negative balance sense scenarios include lane changing, entering or exiting a highway, and stopping at a traffic light; the negative vision scenarios include emergency avoidance, circumventing obstacles, and pedestrian games.

3. The method for adaptive automatic driving based on driver comfort monitoring according to claim 2, characterized in that: In step 2, based on the vehicle driving parameters, balance-negative scenes and visual-negative scenes are identified and labeled to form a reference data set; the vehicle driving parameters include accelerator pedal opening, decelerator pedal opening, lateral speed, longitudinal speed, lateral acceleration, and longitudinal acceleration; the reference data set is input into the BP neural network and constructed as a scene mapping model between vehicle driving parameters and scene classification.

4. The method for autonomous driving adaptation based on driver comfort monitoring according to claim 1, characterized in that: In step 3, according to the scene mapping model, control influencing factors a, b, and c of different control parameters are used in the autonomous driving system to adjust the longitudinal control parameters, lateral control parameters, and collision control parameters in the driving plan.

5. The method for adaptive automatic driving based on driver comfort monitoring according to claim 1, characterized in that: When selecting the driving plan to be executed, the autonomous driving system also makes a comprehensive decision based on the efficiency penalty factor, lateral impact penalty factor, longitudinal impact penalty factor and risk penalty factor.

6. The method for adaptive automatic driving based on driver comfort monitoring according to claim 1, characterized in that: The steps of establishing the comfort evaluation model include: collecting the driving history data of the vehicle, normalizing the vehicle control parameters therein, and calculating the deviation value J of each vehicle control parameter in different scenarios; taking the deviation value J of each vehicle control parameter when the vehicle is in the takeover scenario as the deviation value J m as a deviation from the limit; The relative deviation value y is used as the model training dependent variable, and the vehicle's driving history data is used to perform regression training on the BP neural network to obtain a comfort evaluation model for the target scenario; where y = J / J m .

7. The method for adaptive automatic driving based on driver comfort monitoring according to claim 6, characterized in that: The vehicle control parameters include lateral acceleration a y , acceleration a z , risk factor TCC, longitudinal acceleration a x , lateral jerk a yy , longitudinal jerk a xx .

8. The method for autonomous driving adaptation based on driver comfort monitoring according to claim 6, characterized in that: The step of establishing the comfort evaluation model further includes: confirming the vehicle control parameters when the vehicle is in the normal driving scene of the automatic driving as the reference vehicle control parameters, and confirming the reference values; collecting the vehicle control parameters when the vehicle is in the takeover scene as the reference vehicle control parameter thresholds; taking the parameter deviation value of the vehicle control parameters compared to the reference value as the discomfort value; and m It is the parameter deviation value of the reference vehicle control parameter threshold compared to the benchmark value.

9. The method for autonomous driving adaptation based on driver comfort monitoring according to claim 1, characterized in that: The physiological parameters include electrocardiogram parameters, electrodermal parameters, electroencephalogram parameters, pupil diameter, and blinking frequency.

10. An autonomous driving adaptive system based on driver comfort monitoring, characterized in that: Used to execute an autonomous driving adaptive method based on driver comfort monitoring as described in any one of claims 1 to 9; comprising a collection module and an analysis module; the analysis module establishes a communication connection with the vehicle's autonomous driving system; The acquisition module includes a vehicle data acquisition unit and a driver and passenger data acquisition unit; the vehicle data acquisition unit is used to acquire vehicle driving parameters; the driver and passenger data acquisition unit is used to acquire the physiological parameters of the driver and passenger when the vehicle is in a normal scene of automatic driving and the physiological parameters of the driver when an unconventional driving action occurs; The analysis module establishes a scene mapping model between vehicle driving parameters and scene classification, and a comfort evaluation model for a target scene; the target scene is a non-comfortable driving scene that has a negative stimulus on the driver's comfort; The analysis module is used to collect multiple driving plans currently made by the vehicle's automatic driving system; The scene mapping model is used to classify the driving plans made by the vehicle's autonomous driving system; Based on the target data, the vehicle control parameter thresholds are confirmed to restrict the driving plan. The comfort evaluation model then calculates the discomfort of each driving plan and introduces non-comfort penalties into the vehicle's automatic driving system. The automatic driving system selects the driving plan to be executed based on the non-comfort penalties.

Citation Information

Patent Citations

  • Man-vehicle driving right automatic switching method based on electromyographic signals

    CN114889634A

  • Driver state monitoring system based on electrocardiosignal

    CN115054267A

  • Intelligent driving decision-making method based on different crowds

    CN115092153A

  • Self-adaptive auxiliary driving system considering thousands of people and thousands of faces

    CN117774996A

Cited By

  • Automatic driving takeover control method and device, intelligent driving system and vehicle

    CN120963771A

  • Control method and device for automatic driving takeover, intelligent driving system, vehicle

    CN120963771B

  • Method for automatically setting local path planning parameters of mobile robot and related equipment

    CN121069998A