Driver behavior evaluation and prediction method and system based on driving scene

Abstract

The invention relates to the technical field of intelligent driving, and particularly discloses a driver behavior evaluation and prediction method and system based on a driving scene, and the method comprises the steps: monitoring and extracting the driving scene, the information of people in a vehicle, and the state information of a driver; a driving scene and environment model is established according to the driving scene, a vehicle using scene model is established according to information of people in the vehicle, and a driver model, intelligent driving performance parameters and driver behavior evaluation parameters are generated according to driver state information of a driver in different driving modes; comprehensively evaluating the driving behavior and the driving style of the driver in the manual driving process based on the driving scene and environment model, the vehicle using scene model and the driver model so as to adjust and predict intelligent driving performance parameters and driver behavior evaluation parameters; and a driving strategy in the intelligent driving process is optimized and adjusted based on the driving performance parameters and the driver behavior evaluation parameters, so that the interactive experience of the driver is improved, and the safety of intelligent driving is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a driver behavior evaluation and prediction method and system based on driving scenarios. Background Art

[0002] With the continuous development of intelligent driving assistance technology, more and more functions are applied to intelligent driving cars, which brings great convenience to users. However, due to insufficient understanding of the functions, there is over-reliance and abuse of assisted driving functions, which brings safety risks to users. In order to further improve the intelligence of assisted driving, so that the vehicle can better understand the driver and the driver can better understand the vehicle, it is necessary to evaluate and predict the driver's driving style, so that the driver can better understand the boundaries of the assistance function, and the assistance function can better understand the driver's reaction and driving ability boundaries, so as to provide a safer and smarter interactive experience.

[0003] The current driver behavior assessment method is mainly carried out in two ways. One is to rate the driver's style through driving control actuators, such as the driver's throttle opening, steering angle and other information; the other is to perceive and recognize the driver's face and movements through DMS to judge the driver's concentration, and then issue warnings for unsafe driving conditions such as distraction or drowsiness. However, the information input by these two methods is relatively simple, and the relevant assessment information given based on the level division is also relatively broad. It is difficult to adapt to complex and changing scenarios based solely on the driver's behavior in the car.

[0004] The driving behavior evaluation and prediction method based on driving scenarios provided by the present invention solves the above-mentioned problems of excessive dependence caused by insufficient understanding of the ability boundary of the intelligent assisted driving function by the driver, and insufficient evaluation of different driver styles by assisted intelligent driving, resulting in untimely warning or poor interactive experience. At the same time, it overcomes the problem of limited evaluation information based only on the driver's driving actions and monitoring. Summary of the invention

[0005] To achieve the purpose of the present invention, the present application provides a driver behavior assessment and prediction method based on driving scenarios, comprising:

[0006] Step S1: monitoring and extracting driving scenes, information of occupants, and driver status information;

[0007] Step S2: establishing a driving scenario and environment model according to the driving scenario, establishing a vehicle use scenario model according to the information of the occupants, and generating a driver model as well as intelligent driving performance parameters and driver behavior evaluation parameters according to the driver state information of the driver in different driving modes;

[0008] Step S3: comprehensively evaluating the driver's driving behavior and driving style during manual driving based on the driving scenario and environment model, the vehicle scenario model and the driver model, so as to adjust and predict the intelligent driving performance parameters and the driver behavior evaluation parameters;

[0009] Step S4: Optimizing and adjusting the driving strategy during the intelligent driving process based on the driving performance parameters and the driver behavior evaluation parameters.

[0010] In some specific embodiments, step S1 includes:

[0011] Use external sensors to collect driving scenarios, including lane lines, surrounding vehicle trajectories, traffic light status, weather conditions, and road surface characteristics;

[0012] Use DMS to monitor driver status information, including driver pupil movement, eye closure time, head posture, and operation information;

[0013] Use the in-vehicle monitoring system to monitor the number of passengers and seat distribution in the vehicle, or use the out-of-vehicle monitoring system to monitor the type of load, weight and volume distribution of the load.

[0014] In some of the specific embodiments, in step S2, a convolutional neural network is used to extract features from the collected data of different driving scenarios, classify and identify changes in driving scenarios, and a dynamic time series model is combined to capture the changing patterns of driving scenarios over time, so as to achieve accurate modeling of the dynamic driving scenario characteristics of the vehicle.

[0015] In some specific embodiments, in step S2, the K-means clustering algorithm is used to classify the information of the occupants and the driver's status information, extract typical driving habits, and analyze the consistency of the driver's operating behavior in different driving scenarios through a dynamic time warping algorithm, and a driver model is constructed in combination with the driver's long-term behavior data.

[0016] In some of the specific embodiments, in step S3, the driver's operating behavior in different driving scenarios is statistically analyzed, the lane change time, speed difference with the vehicle in front, relative distance and curvature control speed in the curve scene under different driving scenarios are extracted, and the intelligent driving performance parameters and driver behavior evaluation parameters are generated using a multi-objective optimization algorithm.

[0017] To achieve the same invention purpose, the present application also provides a driver behavior assessment and prediction system based on driving scenarios, including:

[0018] Information extraction module: used to monitor and extract driving scenes, information about people in the car, and driver status information;

[0019] Model building module: used to establish a driving scenario and environment model according to the driving scenario, establish a vehicle use scenario model according to the information of the occupants, and generate a driver model as well as intelligent driving performance parameters and driver behavior evaluation parameters according to the driver state information of the driver in different driving modes;

[0020] Parameter prediction module: used to comprehensively evaluate the driver's driving behavior and driving style during manual driving based on the driving scenario and environment model, the vehicle scenario model and the driver model, so as to adjust and predict intelligent driving performance parameters and driver behavior evaluation parameters;

[0021] Strategy optimization module: used to optimize and adjust the driving strategy in the intelligent driving process based on the driving performance parameters and driver behavior evaluation parameters.

[0022] In some specific embodiments, the information extraction module is used to:

[0023] Use external sensors to collect driving scenarios, including lane lines, surrounding vehicle trajectories, traffic light status, weather conditions, and road surface characteristics;

[0024] Use DMS to monitor driver status information, including driver pupil movement, eye closure time, head posture, and operation information;

[0025] Use the in-vehicle monitoring system to monitor the number of passengers and seat distribution in the vehicle, or use the out-of-vehicle monitoring system to monitor the type of load, weight and volume distribution of the load.

[0026] In some specific embodiments, the model building module is used to:

[0027] The convolutional neural network is used to extract features from the collected image data of different driving scenes, classify them, and identify changes in driving scenes. The dynamic time series model is combined to capture the changing patterns of driving scenes over time, so as to achieve accurate modeling of the dynamic driving scene characteristics of the vehicle.

[0028] In some specific embodiments, the model building module is used to:

[0029] The K-means clustering algorithm is used to classify the information of the occupants and the driver's status information, extract typical driving habits, and analyze the consistency of the driver's operating behavior in different driving scenarios through the dynamic time warping algorithm. The driver model is constructed in combination with the driver's long-term behavior data.

[0030] In some specific embodiments, the parameter prediction module is used to:

[0031] Statistical analysis is performed on the driver's operating behavior in different driving scenarios to extract the lane change time, speed difference with the vehicle in front, relative distance and curvature control speed in curve scenarios. The multi-objective optimization algorithm is used to generate intelligent driving performance parameters and driver behavior evaluation parameters.

[0032] Beneficial effects of the above technical solution:

[0033] The present application provides a driver behavior evaluation and prediction method and system based on driving scenarios. Through the driver's control behavior in different driving scenarios, the driver's behavior is comprehensively evaluated and predicted, and different models are established. Therefore, when using the intelligent driving function, based on the vehicle's passenger and cargo information and the driver's behavior analysis during safe driving, intelligent driving performance parameters suitable for different drivers and vehicle usage scenarios are given, thereby improving the intelligent driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 A flowchart of a method for evaluating and predicting driver behavior based on driving scenarios provided by an embodiment of the present invention;

[0036] Figure 2 A diagram of a driver behavior assessment and prediction architecture based on a driving scenario of a driver behavior assessment and prediction method based on a driving scenario provided by an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the structure of a driver behavior assessment and prediction system based on driving scenarios provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0039] Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar symbols throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0040] Embodiment 1

[0041] An embodiment of the present invention provides a driver behavior evaluation and prediction method based on a driving scenario, referring to Figure 1 , Figure 2 As shown, including:

[0042] Step S1: Monitor and extract driving scenes, information about people in the car, and driver status information.

[0043] In a specific embodiment of the present invention, step S1 includes:

[0044] Use external sensors to collect driving scenarios, including lane lines, surrounding vehicle trajectories, traffic light status, weather conditions, and road surface characteristics;

[0045] Use DMS to monitor driver status information, including driver pupil movement, eye closure time, head posture, and operation information;

[0046] Specifically, the driver's physiological and behavioral data, including pupil movement, eye closure time, head posture, and operation data, including: throttle force, brake force, and steering wheel angle rate, are obtained through the driver monitoring system (DMS).

[0047] Use the in-vehicle monitoring system to monitor the number of passengers and seat distribution in the vehicle, or use the out-of-vehicle monitoring system to monitor the type of load, weight and volume distribution of the load.

[0048] Specifically, external vehicle sensors include: cameras, millimeter-wave radars, and lidars; driving scenarios include lane lines, surrounding vehicle trajectories, traffic light status, weather conditions (such as rain, snow, and fog) and road surface features (such as curves and ramps).

[0049] Step S2: Establish a driving scenario and environment model according to the driving scenario, establish a vehicle use scenario model according to the information of the occupants in the vehicle, and generate a driver model as well as intelligent driving performance parameters and driver behavior evaluation parameters according to the driver status information of the driver in different driving modes.

[0050] In a specific embodiment of the present invention, in step S2, a convolutional neural network is used to extract features from the collected image data of different driving scenes, classify and identify changes in driving scenes, identify driving scenes such as lane changing, overtaking, and following a vehicle, and combine with a dynamic time series model to capture the changing patterns of driving scenes over time, so as to achieve accurate modeling of the dynamic driving scene characteristics of the vehicle.

[0051] In a specific embodiment of the present invention, in step S2, the K-means clustering algorithm is used to classify the information of the occupants and the driver's status information, extract typical driving habits (such as aggressive driving and conservative driving), and use the dynamic time warping algorithm to analyze the consistency of the driver's operating behavior in different driving scenarios, and build a driver model in combination with the driver's long-term behavior data.

[0052] Step S3: Comprehensively evaluate the driver's driving behavior and driving style during manual driving based on the driving scenario and environment model, the vehicle scenario model and the driver model to adjust and predict intelligent driving performance parameters and driver behavior evaluation parameters.

[0053] In a specific embodiment of the present invention, in step S3, the driver's operating behavior in different driving scenarios is statistically analyzed, the lane change time, speed difference with the front vehicle, relative distance and curvature control speed in the curve scene under different driving scenarios are extracted, and the intelligent driving performance parameters and driver behavior evaluation parameters are generated using a multi-objective optimization algorithm.

[0054] Specifically, the driver's behavior is comprehensively evaluated in the manual driving mode. By extracting different scenarios and driver manipulation, the driver's behavior is comprehensively evaluated, such as lane change time, habits during overtaking, speeds at different curves, following distance, and reaction time to dangerous scenes. First, by statistically analyzing the driver's operating behavior in different scenarios, quantitative parameters such as lane change time, speed difference with the front vehicle, relative distance, and curvature control speed in the curve scene are extracted; combined with the driver's reaction time to dangerous scenes (such as sudden jamming), throttle and brake operation characteristics, the driver's style is comprehensively determined, and a quantitative model of driving behavior is established. Subsequently, a time series prediction model (such as LSTM or GRU) is used to model and predict the driver's operating behavior during driving. Combined with the output of the scenario model, driver behavior model, and in-vehicle scenario model, personalized driving performance parameters such as acceleration change rate, braking force, and steering response speed are generated through a multi-objective optimization algorithm.

[0055] In the intelligent driving mode, the intelligent driving system strategy is dynamically adjusted based on personalized driving performance parameters. For example, in highway scenarios, the following distance is dynamically optimized based on the passenger information in the car; during braking, the comfort of the braking process is improved by adjusting the deceleration change rate; in bad weather or dangerous scenarios, the vehicle control response time and alarm threshold are adjusted according to the driver's style to ensure safety and reliability.

[0056] Step S4: Optimizing and adjusting the driving strategy during the intelligent driving process based on the driving performance parameters and the driver behavior evaluation parameters.

[0057] This application continuously optimizes and enriches driving scenarios and refines evaluation indicators to continuously improve the safety and interactive experience of intelligent driving. The present invention realizes a closed loop of the entire process from data collection to behavior modeling, evaluation prediction and strategy optimization, ensuring more accurate driving behavior evaluation and significantly improving the safety and interactive experience of intelligent driving.

[0058] Embodiment 2

[0059] An embodiment of the present invention provides a driver behavior evaluation and prediction system based on driving scenarios, referring to Figure 3 As shown, including:

[0060] Information extraction module 10: used to monitor and extract driving scenes, information about people in the car, and driver status information;

[0061] Model building module 20: used to establish a driving scenario and environment model according to the driving scenario, establish a vehicle use scenario model according to the information of the occupants, and generate a driver model as well as intelligent driving performance parameters and driver behavior evaluation parameters according to the driver state information of the driver in different driving modes;

[0062] Parameter prediction module 30: used to comprehensively evaluate the driver's driving behavior and driving style during manual driving based on the driving scenario and environment model, the vehicle scenario model and the driver model, so as to adjust and predict the intelligent driving performance parameters and the driver behavior evaluation parameters;

[0063] Strategy optimization module 40: used for optimizing and adjusting the driving strategy in the intelligent driving process based on the driving performance parameters and the driver behavior evaluation parameters.

[0064] In a specific embodiment of the present invention, the information extraction module 10 is used to:

[0065] Use external sensors to collect driving scenarios, including lane lines, surrounding vehicle trajectories, traffic light status, weather conditions, and road surface characteristics;

[0066] Use DMS to monitor driver status information, including driver pupil movement, eye closure time, head posture, and operation information;

[0067] Use the in-vehicle monitoring system to monitor the number of passengers and seat distribution in the vehicle, or use the out-of-vehicle monitoring system to monitor the type of load, weight and volume distribution of the load.

[0068] Specifically, external vehicle sensors include: cameras, millimeter-wave radars, and lidars; driving scenarios include lane lines, surrounding vehicle trajectories, traffic light status, weather conditions (such as rain, snow, and fog) and road surface features (such as curves and ramps).

[0069] In a specific embodiment of the present invention, the model building module 20 is used to:

[0070] The convolutional neural network is used to extract features from the collected image data of different driving scenes, classify them, and identify changes in driving scenes. The dynamic time series model is combined to capture the changing patterns of driving scenes over time, so as to achieve accurate modeling of the dynamic driving scene characteristics of the vehicle.

[0071] In a specific embodiment of the present invention, the model building module 20 is used to:

[0072] The K-means clustering algorithm is used to classify the information of the occupants and the driver's status information, extract typical driving habits, and analyze the consistency of the driver's operating behavior in different driving scenarios through the dynamic time warping algorithm. The driver model is constructed in combination with the driver's long-term behavior data.

[0073] In a specific embodiment of the present invention, the parameter prediction module 30 is used to:

[0074] Statistical analysis is performed on the driver's operating behavior in different driving scenarios to extract the lane change time, speed difference with the vehicle in front, relative distance and curvature control speed in curve scenarios. The multi-objective optimization algorithm is used to generate intelligent driving performance parameters and driver behavior evaluation parameters.

[0075] Specifically, the driver's behavior is comprehensively evaluated in the manual driving mode. By extracting different scenarios and driver manipulation, the driver's behavior is comprehensively evaluated, such as lane change time, habits during overtaking, speeds at different curves, following distance, and reaction time to dangerous scenes. First, by statistically analyzing the driver's operating behavior in different scenarios, quantitative parameters such as lane change time, speed difference with the front vehicle, relative distance, and curvature control speed in the curve scene are extracted; combined with the driver's reaction time to dangerous scenes (such as sudden jamming), throttle and brake operation characteristics, the driver's style is comprehensively determined, and a quantitative model of driving behavior is established. Subsequently, a time series prediction model (such as LSTM or GRU) is used to model and predict the driver's operating behavior during driving. Combined with the output of the scenario model, driver behavior model, and in-vehicle scenario model, personalized driving performance parameters such as acceleration change rate, braking force, and steering response speed are generated through a multi-objective optimization algorithm.

[0076] In the intelligent driving mode, the intelligent driving system strategy is dynamically adjusted based on personalized driving performance parameters. For example, in highway scenarios, the following distance is dynamically optimized based on the passenger information in the car; during braking, the comfort of the braking process is improved by adjusting the deceleration change rate; in bad weather or dangerous scenarios, the vehicle control response time and alarm threshold are adjusted according to the driver's style to ensure safety and reliability.

[0077] The present application provides a driver behavior evaluation and prediction method and system based on driving scenarios. Through the driver's control behavior in different driving scenarios, the driver's behavior is comprehensively evaluated and predicted, and different models are established. Therefore, when using the intelligent driving function, based on the vehicle's passenger and cargo information and the driver's behavior analysis during safe driving, intelligent driving performance parameters suitable for different drivers and vehicle usage scenarios are given, thereby improving the intelligent driving experience.

[0078] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0079] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referenced to each other. The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention. Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0080] The method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", "one specific embodiment" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A driver behavior assessment and prediction method based on driving scenarios, characterized in that: include: Step S1: monitoring and extracting driving scenes, information of occupants, and driver status information; Step S2: establishing a driving scenario and environment model according to the driving scenario, establishing a vehicle use scenario model according to the information of the occupants, and generating a driver model as well as intelligent driving performance parameters and driver behavior evaluation parameters according to the driver state information of the driver in different driving modes; Step S3: comprehensively evaluating the driver's driving behavior and driving style during manual driving based on the driving scenario and environment model, the vehicle scenario model and the driver model, so as to adjust and predict the intelligent driving performance parameters and the driver behavior evaluation parameters; Step S4: Optimizing and adjusting the driving strategy during the intelligent driving process based on the driving performance parameters and the driver behavior evaluation parameters.

2. The driver behavior evaluation and prediction method based on driving scenarios according to claim 1 is characterized in that: Step S1 includes: Use external sensors to collect driving scenarios, including lane lines, surrounding vehicle trajectories, traffic light status, weather conditions, and road surface characteristics; Use DMS to monitor driver status information, including driver pupil movement, eye closure time, head posture, and operation information; Use the in-vehicle monitoring system to monitor the number of passengers and seat distribution in the vehicle, or use the out-vehicle monitoring system to monitor the type of load, weight and volume distribution of the load.

3. The driver behavior evaluation and prediction method based on driving scenarios according to claim 1, characterized in that: In step S2, the convolutional neural network is used to extract features from the collected image data of different driving scenes, classify and identify changes in driving scenes, and combined with a dynamic time series model to capture the changing patterns of driving scenes over time, so as to achieve accurate modeling of the dynamic driving scene characteristics of the vehicle.

4. The driver behavior evaluation and prediction method based on driving scenarios according to claim 1, characterized in that: In step S2, the K-means clustering algorithm is used to classify the information of the occupants and the driver's status information, extract typical driving habits, and analyze the consistency of the driver's operating behavior in different driving scenarios through the dynamic time warping algorithm, and the driver model is constructed in combination with the driver's long-term behavior data.

5. The driver behavior evaluation and prediction method based on driving scenarios according to claim 1, characterized in that: Step S3 includes: statistically analyzing the driver's operating behavior in different driving scenarios, extracting the lane change time, speed difference with the front vehicle, relative distance and curvature control speed in the curve scene under different driving scenarios, and using a multi-objective optimization algorithm to generate intelligent driving performance parameters and driver behavior evaluation parameters.

6. A driver behavior assessment and prediction system based on driving scenarios, characterized in that: include: Information extraction module: used to monitor and extract driving scenes, information about people in the car, and driver status information; Model building module: used to establish a driving scenario and environment model according to the driving scenario, establish a vehicle use scenario model according to the information of the occupants, and generate a driver model as well as intelligent driving performance parameters and driver behavior evaluation parameters according to the driver state information of the driver in different driving modes; Parameter prediction module: used to comprehensively evaluate the driver's driving behavior and driving style during manual driving based on the driving scenario and environment model, the vehicle scenario model and the driver model, so as to adjust and predict intelligent driving performance parameters and driver behavior evaluation parameters; Strategy optimization module: used to optimize and adjust the driving strategy in the intelligent driving process based on the driving performance parameters and driver behavior evaluation parameters.

7. The driver behavior evaluation and prediction system based on driving scenarios according to claim 6, characterized in that: The information extraction module is used for: Use external sensors to collect driving scenarios, including lane lines, surrounding vehicle trajectories, traffic light status, weather conditions, and road surface characteristics; Use DMS to monitor driver status information, including driver pupil movement, eye closure time, head posture, and operation information; Use the in-vehicle monitoring system to monitor the number of passengers and seat distribution in the vehicle, or use the out-vehicle monitoring system to monitor the type of load, weight and volume distribution of the load.

8. The driver behavior evaluation and prediction system based on driving scenarios according to claim 6, characterized in that: The model building module is used to: The convolutional neural network is used to extract features from the collected image data of different driving scenes, classify them, and identify changes in driving scenes. The dynamic time series model is combined to capture the changing patterns of driving scenes over time, so as to achieve accurate modeling of the dynamic driving scene characteristics of the vehicle.

9. The driver behavior evaluation and prediction system based on driving scenarios according to claim 6, characterized in that: The model building module is used to: The K-means clustering algorithm is used to classify the information of the occupants and the driver's status information, extract typical driving habits, and analyze the consistency of the driver's operating behavior in different driving scenarios through the dynamic time warping algorithm. The driver model is constructed in combination with the driver's long-term behavior data.

10. The driver behavior evaluation and prediction system based on driving scenarios according to claim 6, characterized in that: The parameter prediction module is used for: Statistical analysis is performed on the driver's operating behavior in different driving scenarios to extract the lane change time, speed difference with the vehicle in front, relative distance and curvature control speed in curve scenarios. The multi-objective optimization algorithm is used to generate intelligent driving performance parameters and driver behavior evaluation parameters.

Images