Driving behavior model generation method and device, vehicle control method and device and automobile

Abstract

The invention provides a driving behavior model generation method, a vehicle control method and device and an automobile, and aims to solve the problem that automatic driving planning and decision making cannot be performed according to different user requirements in the prior art. The method for generating the driving behavior model matched with the passenger demand comprises the steps that a passenger sits on a test vehicle, a plurality of drivers drive the test vehicle to run on a driving route containing a plurality of driving scenes, and a plurality of groups of test data are obtained; one group of test data comprises related passenger data, vehicle data and external vehicle data when a driver drives a vehicle in a driving scene; according to the multiple groups of test data, determining driving behavior data meeting different passenger requirements in different driving scenes; and generating a driving behavior model according to the driving behavior data meeting the requirements of different passengers in different driving scenes.

Description

Technical Field

[0001] The present invention relates to the field of automatic driving control, and specifically to a driving behavior model generation method, a vehicle control method, a device and a car. Background Art

[0002] From the perspective of business processes, autonomous driving technology is divided into three core processes, namely environmental perception and positioning, decision-making and planning, and execution and control. Environmental perception and positioning mainly uses sensor technology, cameras, GPS and other technologies to obtain environmental indicators during the driving process of the car, and collect data. Decision-making and planning are to judge and guide the next behavior of the vehicle through the collected data. The execution decision is how to pass the decision to the functional components of the vehicle after environmental perception and decision-making planning, and implement the throttle, brake, steering, and shifting instructions. The more feasible solution for autonomous driving cars is to control the behavior of each component through the CAN power bus, and transmit the instructions to each component through electronic signals. This is also the main sensing method of electric vehicles at present.

[0003] Decision planning is the decisive content that determines the system's user experience. In order to make smart driving products have a good experience, it is necessary to continuously optimize decision planning and obtain smart driving control logic that is more like natural driving behavior.

[0004] Not all natural driving behaviors are of reference value. Only driving behaviors that ensure the sense of safety and comfort of the passengers (the front driver and rear passengers in manual driving, and the driver and other passengers in autonomous driving) and do not disturb surrounding traffic participants are worthy of autonomous driving planning and control learning.

[0005] Existing evaluation methods for driving behavior are mainly used for long-term driving behavior evaluation, and do not consider the subjective feelings of passengers; or consider the evaluation method of autonomous driving comfort, but do not consider how to import the results into the autonomous driving system; that is, the existing solutions can never be installed on the vehicle to truly meet the user's usage needs. Summary of the invention

[0006] The present invention provides a driving behavior model generation method, a vehicle control method, a device and a car, which are used to solve the problem that the existing technology cannot make automatic driving planning decisions according to different user needs.

[0007] The technical solution of the present invention is:

[0008] The present invention provides a method for generating a driving behavior model that matches passenger needs, comprising:

[0009] Passengers are seated in the test vehicle, and multiple drivers drive the test vehicle on a driving route including multiple driving scenarios, thereby obtaining multiple sets of test data; one set of test data includes: passenger data, vehicle data, and external vehicle data related to a driver driving in a driving scenario;

[0010] Based on multiple sets of test data, determine the driving behavior data that meets the needs of different passengers in different driving scenarios;

[0011] A driving behavior model is generated based on driving behavior data that meets different passenger needs in different driving scenarios.

[0012] Preferably, the step of determining driving behavior data that meets different passenger needs in different driving scenarios based on multiple sets of test data includes:

[0013] Determine passenger demand;

[0014] For each driving scenario, find a target group of test data from multiple groups of test data so that the passenger data and the external vehicle data meet the passenger's needs;

[0015] Perform minimum and maximum value screening on the vehicle data in the target group test data to obtain driving behavior data that meets the passenger's needs in a corresponding driving scenario;

[0016] The driving behavior data includes: a vehicle speed interval, a lateral offset interval, a lateral acceleration interval and a steering wheel angular velocity interval of the vehicle.

[0017] Preferably, the passenger data includes: passenger subjective evaluation data and passenger physiological characteristic data;

[0018] In different driving scenarios, the target group test data that makes the passenger data and external vehicle data meet the passenger needs must meet the following requirements: the passenger subjective evaluation data meets the evaluation criteria corresponding to the passenger needs, the passenger physiological characteristic data meets the physiological criteria corresponding to the passenger needs, and the external vehicle data indicates that the external vehicle has not engaged in dangerous driving behavior.

[0019] Preferably, the plurality of driving scenarios include: on-ramp scenario, merging scenario, congested driving scenario, left-turning scenario at an intersection, straight-going scenario at an intersection, right-turning scenario at an intersection, static obstacle avoidance scenario, avoiding large vehicles scenario, simple lane change scenario, simple overtaking scenario, simple following scenario, being jammed, scenario with obstructions on both sides of a single lane, mixed traffic of non-motor vehicles and motor vehicles, U-turn scenario, roundabout scenario, fork scenario, turning a wide bend scenario, going up a hump bridge scenario, going down a long slope scenario and / or crossing and merging scenario;

[0020] Different passenger demands include: comfort first demand, efficiency first demand and / or comfort and efficiency demand;

[0021] The driving scene that the test vehicle is currently in is identified by the main examiner riding in the test vehicle. After the main examiner identifies the driving scene that the test vehicle is currently in, he prompts the passengers to make subjective evaluations on the evaluation questions corresponding to the driving scene that the test vehicle is currently in.

[0022] The present invention also provides a vehicle control method for matching passenger needs, comprising:

[0023] During autonomous driving, identify the vehicle’s current driving scenario and current passenger needs;

[0024] Inputting the current driving scene and the current passenger demand into a driving behavior model to generate target driving behavior data that meets the current passenger demand;

[0025] Performing automatic vehicle control according to the target driving behavior data;

[0026] The driving behavior model is a driving behavior model obtained by using the method for generating a driving behavior model that matches passenger needs.

[0027] Preferably, the method further comprises:

[0028] During manual driving, real-time driving parameters are collected under the same driving scenarios as during automatic driving;

[0029] According to the real-time driving parameters, the driving behavior data in the relevant driving scenarios in the driving behavior model are updated through self-learning.

[0030] Preferably, the step of identifying the current driving scene of the vehicle and the current passenger demand includes:

[0031] Identify the current driving scene of the vehicle based on the external environment data sensed by the sensing device on the vehicle;

[0032] Based on passenger selection, identify current passenger needs.

[0033] The present invention also provides a driving behavior model generation device that matches passenger needs, comprising:

[0034] The data collection module is used for obtaining multiple groups of test data when a passenger is riding in a test vehicle and multiple drivers drive the test vehicles on a driving route including multiple driving scenarios; one group of test data includes: passenger data, vehicle data and external vehicle data related to a driver driving in a driving scenario;

[0035] A driving behavior data determination module, used to determine driving behavior data that meets different passenger needs in different driving scenarios based on multiple sets of test data;

[0036] A driving behavior model is generated based on driving behavior data that meets different passenger needs in different driving scenarios.

[0037] The present invention also provides a vehicle control device that matches passenger needs, comprising:

[0038] An identification module, used to identify the current driving scene of the vehicle and the current passenger needs;

[0039] a target driving behavior data generating module, configured to input the current driving scenario and the current passenger demand into a driving behavior model, and generate target driving behavior data that meets the current passenger demand;

[0040] A vehicle control module, used for automatically controlling the vehicle according to the target driving behavior data;

[0041] The driving behavior model is a driving behavior model obtained by using the above-mentioned driving behavior model generation device that matches passenger needs.

[0042] The present invention also provides a vehicle, comprising the above-mentioned vehicle control device for matching passenger needs.

[0043] The beneficial effects of the present invention are:

[0044] By processing the test data of the test vehicle in the actual driving scenario, we find the driving behavior data that matches the needs of different passengers, and then generate a driving behavior model that can meet the needs of various passengers in various driving scenarios; by installing the driving behavior model on the actual vehicle, we can find the most suitable target driving behavior data in the current driving scenario according to the current passenger needs, and then perform autonomous vehicle control. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of a method for generating a driving behavior model that matches passenger needs in an embodiment of the present application;

[0046] Figure 2 A specific schematic diagram of a method for generating a driving behavior model that matches passenger needs in an embodiment of the present application;

[0047] Figure 3 A schematic diagram of generating a driving behavior sub-model in an embodiment of the present application;

[0048] Figure 4 This is a schematic diagram of a passenger's subjective evaluation of driving behavior in different driving scenarios in an embodiment of the present application;

[0049] Figure 5 This is a schematic diagram of data collection during actual vehicle testing in an embodiment of the present application;

[0050] Figure 6 A schematic diagram of determining driving behavior data that meets passenger comfort needs in an embodiment of the present application;

[0051] Figure 7 A schematic diagram of determining whether the test data meets the passenger's needs in an embodiment of the present application;

[0052] Figure 8 A flow chart of a vehicle control method for matching passenger needs in an embodiment of the present application;

[0053] Fig. 9 A detailed flow chart of a vehicle control method for matching passenger needs in an embodiment of the present application;

[0054] Fig.10 A structural block diagram of a driving behavior model generating device that matches passenger needs in an embodiment of the present application;

[0055] Fig.11 This is a structural block diagram of a vehicle control device that matches passenger needs in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the appended claims. The flowcharts shown in the accompanying drawings are merely exemplary and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the order described. For example, some operations / steps may be further decomposed, while some operations / steps may be combined or partially combined, so the actual order of execution may change according to actual conditions.

[0057] Combination Figures 1 to 7 , the embodiment of the present application provides a method for generating a driving behavior model that matches passenger needs, including:

[0058] S101, a passenger is seated in a test vehicle, and multiple drivers respectively drive the test vehicles on a driving route including multiple driving scenarios, to obtain multiple sets of test data; a set of test data includes: passenger data, vehicle data, and external vehicle data related to a driver driving in a driving scenario;

[0059] S102, determining driving behavior data that meets different passenger needs in different driving scenarios based on the multiple test data sets;

[0060] S103: Generate a driving behavior model based on driving behavior data that meets different passenger needs in different driving scenarios.

[0061] In the embodiment of the present application, the passenger's evaluation of the driver's driving behavior mainly needs to consider two parts: the passenger's feedback and the surrounding environment's feedback. Passengers need to establish a subjective evaluation standard for judging and evaluating excellent drivers from the passenger dimension, and summarize their physiological and psychological characteristics regularly to obtain the perception-physiological mapping relationship of the passenger's evaluation of the driver, and passengers are required to evaluate the driving behavior in real time on the actual vehicle, which has ecological benefits.

[0062] Before conducting a real vehicle test, it is necessary to customize the detailed description of passenger needs in the early stage to clarify the specific content of different passenger needs. In the embodiment of this application, three types of passenger needs are provided as shown in the following Table 1:

[0063] Passenger demand Specific content Detailed description Requirement 1 Comfort first The user has a comfortable ride and cannot feel the movement of the vehicle or the bumps on the road. Requirement 2 Efficiency first Able to reach the destination faster than the time planned on the map Requirement 3 Comfortable and efficient The ride is comfortable and can reach the destination quickly

[0064] Table 1

[0065] Before conducting the actual vehicle test, it is also necessary to define different driving scenarios according to the current actual vehicle driving environment, and to answer specific questions that require passengers to conduct subjective evaluations in different driving scenarios according to the aforementioned passenger needs. As shown in Table 2 below, 21 driving scenarios are provided in the embodiment of this application:

[0066] Serial number content Serial number Detailed description Scenario 1 On the ramp Scene 12 Being cut in line Scenario 2 Confluence Scene 13 The bicycle lane is blocked on both sides Scene 3 Traffic congestion Scene 14 Mixed traffic of people and vehicles (non-motor vehicles) Scene 4 Turn left at the intersection Scene 15 U-turn Scene 5 Go straight at the intersection Scene 16 a roundabout Scene 6 Turn right at the intersection Scene 17 Fork Scene 7 Obstacle Avoidance (Static) Scene 18 Turning a corner Scene 8 Avoid large vehicles Scene 19 Upper Hump Bridge Scene 9 Simple lane change Scene 20 Down a long slope Scene 10 Simple overtaking Scene 21 Cross Import Scene 11 Simple car following

[0067] Table 2

[0068] For each driving scenario in Table 2, specific questions that require users to make subjective evaluations of the driver's driving behavior in different driving scenarios are further defined according to different passenger needs, as shown in Table 3:

[0069]

[0070]

[0071]

[0072]

[0073]

[0074]

[0075] Table 3

[0076] During the actual test, passengers are required to give real-time scores or evaluations on all questions that require subjective evaluation in the current driving scenario of the test vehicle.

[0077] After completing the above design, you can start the actual vehicle test. During the actual vehicle test, the collected passenger data includes passenger subjective evaluation data and passenger physiological characteristic data. Passenger subjective evaluation data is data that scores the driver's driving behavior in the current driving scenario based on the specific driving scenario in Table 3 above; passenger physiological characteristic data is the passenger's objective response data to the driver's driving behavior in the current driving scenario. Passenger physiological characteristic data includes but is not limited to the passenger's heart rate, which can be collected using equipment that can measure the passenger's heart rate.

[0078] During the actual vehicle test, the collected vehicle data mainly refers to the vehicle motion data, which in the embodiment of the present application includes: vehicle speed, acceleration, yaw angular velocity, jerk, steering wheel angular velocity, steering wheel angle offset, power consumption, driving time, lighting time and other data.

[0079] During the actual vehicle test, the external vehicle data collected mainly includes the acceleration data of the vehicle in front, the left vehicle and the right vehicle of the vehicle. These external vehicle data can be collected through physiological equipment (such as cameras, radars, etc.) carried on the vehicle.

[0080] Combination Figure 5 During the actual vehicle test, the test subject is required to sit in the test vehicle and wear a physiological device that measures their physiological characteristics (such as heart rate) to evaluate the driver's driving behavior in real time. In order to enable the passengers to recognize the current driving scene of the test vehicle, experienced personnel can be used as the main test personnel to judge the current real-time driving environment of the test vehicle. The main test personnel will inform the passengers of the current real-time driving environment of the vehicle, so as to enable the passengers to make subjective evaluations of the driving behavior in the real-time driving scene.

[0081] Combination Figure 3 During the actual vehicle test, all drivers are required to drive the test vehicle from starting point A to end point B according to the set route to ensure the accuracy of the main test personnel in identifying the driving scene.

[0082] Each driver will get multiple passengers (such as Figure 4 Each vehicle has three passengers, namely passenger a, passenger b and passenger c) subjective evaluation data and physiological characteristic data of the driver's driving behavior in multiple driving scenarios, external vehicle data corresponding to other vehicles when the driver's driving behavior occurs in multiple driving scenarios, and vehicle data of the vehicle when the driver's driving behavior occurs in multiple driving scenarios. Figure 6 For example, a set of test data obtained when driver A is driving on the on-ramp includes the data in Table 4 below:

[0083]

[0084] Table 4

[0085] After collecting the above data, you can conduct post-analysis. Post-analysis of surrounding environment feedback mainly relies on the environmental perception system to collect and process data about the surrounding environment. Different driving behaviors will cause different manifestations of surrounding vehicles. Summarizing them can obtain the relationship between driving behavior and surrounding environment feedback.

[0086] In the post-analysis, the data needs to be time-matched first, that is, the passenger data (including subjective evaluation data and physiological characteristic data), vehicle data, and external vehicle data need to be matched according to the natural time recorded by the experimenter.

[0087] Combination Figure 7 , taking the "comfort priority" passenger demand among the above three passenger demands as an example, for different driving scenarios, it is necessary to filter out data that meets the following conditions: ① Subjective evaluation users feel comfortable (for example, the passenger score is above 4.5 points); ② The passenger's physiological characteristic data (such as heart rate) is in the stable range prescribed by medicine; ③ The external vehicle does not have dangerous driving behaviors such as sudden acceleration (in this embodiment, sudden acceleration is defined as acceleration exceeding the set acceleration) and sudden deceleration (in this embodiment, sudden deceleration is defined as deceleration exceeding the set deceleration). After filtering out the data that meets these conditions, this set of test data can be selected as the target group test data. That is to say, in the embodiment of the present application, in different driving scenarios, the target group test data that makes the passenger data and the external vehicle data meet the passenger needs all need to meet the following requirements: the passenger's subjective evaluation data meets the evaluation criteria corresponding to the passenger needs, the passenger's physiological characteristic data meets the physiological standards corresponding to the passenger needs, and the external vehicle data indicates that the external vehicle has not engaged in dangerous driving behaviors.

[0088] Taking the on-ramp driving scenario as an example, after screening in steps S1021 and S1022, assuming that the two sets of test data corresponding to drivers A and B driving in the on-ramp driving scenario meet the above requirements, these two sets of test data can be determined as the target set test data.

[0089] Reference Figure 2 In the embodiment of the present application, step S102 further includes:

[0090] Step S1021, determining passenger demand;

[0091] Step S1022, for each driving scenario, find a target group of test data from multiple groups of test data that makes the passenger data and the external vehicle data meet the passenger's needs;

[0092] Step S1023, performing minimum and maximum value screening processing on the vehicle data in the target group test data to obtain driving behavior data that meets the passenger's needs in the corresponding driving scenario.

[0093] In the embodiment of the present application, the driving behavior data includes: a vehicle speed interval, a lateral offset interval, a lateral acceleration interval, and a steering wheel angular velocity interval.

[0094] For example: the passenger demand in step S1021 is set to a passenger comfort score between 4.0 and 4.5 points; through analysis, it is determined that in the driving scenario of overtaking on the highway, the comfort level of passenger a on the test vehicle is 4.4 points, passenger b is 4.0 points, and passenger c is 4.2 points. That is, this group of test data can be used as the target group test data, and then the vehicle data in the target group test data is filtered for maximum and minimum values ​​to obtain the required driving behavior data.

[0095] Combination Figure 3 In the embodiment of the present application, a driving behavior sub-model is generated for each user demand and multiple driving behavior data obtained in the driving scenario; then, based on a passenger demand, a driving behavior sub-model that meets a passenger demand is generated; finally, multiple driving behavior sub-models that meet different passenger demands together constitute the driving behavior model in step S103.

[0096] The above-mentioned method for generating a driving behavior model that matches passenger needs in an embodiment of the present application processes the test data of the test vehicle in an actual driving scenario, finds driving behavior data that matches different passenger needs, and then generates a driving behavior model that can meet various passenger needs in various driving scenarios.

[0097] Based on the above-mentioned method for generating a driving behavior model that matches passenger needs, the embodiment of the present application also provides a vehicle control method that matches passenger needs, referring to Figure 8 , the method comprising:

[0098] S201, during automatic driving, identifying the current driving scene of the vehicle and the current passenger needs;

[0099] S202, inputting the current driving scene and the current passenger demand into a driving behavior model to generate target driving behavior data that meets the current passenger demand;

[0100] S203, performing automatic vehicle control according to the target driving behavior data;

[0101] The driving behavior model is a driving behavior model obtained by using the above-mentioned driving behavior model generation method that matches passenger needs.

[0102] This method can identify different passenger needs, allowing the vehicle to provide more personalized services that are closer to the passengers' real needs, such as adjusting the driving style according to the passengers' comfort preferences, or optimizing the driving route according to the passengers' time requirements; the autonomous driving system reduces passenger discomfort and improves the riding experience by adjusting parameters such as acceleration and deceleration.

[0103] Among them, step S201 of identifying the current driving scene of the vehicle and the current passenger needs includes: identifying the current driving scene of the vehicle based on the external environment data perceived by the sensing device on the vehicle; and identifying the current passenger needs based on the passenger selection.

[0104] The sensing devices on the vehicle include surrounding view systems, radars and other vehicle environment sensing devices. The current driving scenario of the vehicle is one of the driving scenarios mentioned in the above embodiments, and the current passenger demand is one of the passenger demands mentioned in the above embodiments.

[0105] Reference Fig. 9 , the vehicle control method matching passenger needs also includes:

[0106] S204, during manual driving, collecting real-time driving parameters in the same driving scenario as during automatic driving;

[0107] S205: According to the real-time driving parameters, self-learning and updating the driving behavior data in the relevant driving scenarios in the driving behavior model.

[0108] By self-learning and updating the driving behavior data, the output of the driving behavior model can be more accurately aligned with the actual needs of passengers.

[0109] Reference Fig.10 The embodiment of the present invention further provides a driving behavior model generation device that matches passenger needs, including:

[0110] The data collection module 101 is used for obtaining multiple groups of test data when a passenger is riding in a test vehicle and multiple drivers drive the test vehicles on a driving route including multiple driving scenarios; one group of test data includes: passenger data, vehicle data and external vehicle data related to a driver driving in a driving scenario;

[0111] A driving behavior data determination module 102, for determining driving behavior data that respectively meets different passenger needs in different driving scenarios based on multiple sets of test data;

[0112] The driving behavior model generation module 103 is used to generate a driving behavior model according to driving behavior data that meets different passenger needs in different driving scenarios.

[0113] Reference Fig.11 , an embodiment of the present invention further provides a vehicle control device that matches passenger needs, including:

[0114] Identification module 201, used to identify the current driving scene of the vehicle and the current passenger needs;

[0115] A target driving behavior data generating module 202 is used to input the current driving scene and the current passenger demand into a driving behavior model to generate target driving behavior data that meets the current passenger demand;

[0116] A vehicle control module 203, configured to automatically control the vehicle according to the target driving behavior data;

[0117] The driving behavior model is a driving behavior model obtained by using the above-mentioned driving behavior model generation device that matches passenger needs.

[0118] An embodiment of the present invention further provides a vehicle, comprising the above-mentioned vehicle control device for matching passenger needs.

[0119] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0120] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended 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.

[0121] It should also be noted that, in this article, the orientation or position relationship indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, relational terms such as "first" and "second" are 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, nor can they be understood as indicating or implying relative importance. 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 does not include those elements, but also includes other elements 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.

[0122] The technical solution provided by the present invention is described in detail above. The principle and implementation mode of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the present invention, and the content of this specification should not be understood as limiting the present invention. At the same time, for those skilled in the art, according to the present invention, there will be different forms of changes in the specific implementation mode and application scope. It is not necessary and impossible to list all the implementation modes here, and the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for generating a driving behavior model that matches passenger needs, characterized in that: include: Passengers are seated in the test vehicle, and multiple drivers drive the test vehicle on a driving route containing multiple driving scenarios to obtain multiple sets of test data; A set of test data includes: passenger data, vehicle data and external vehicle data related to a driver driving in a driving scenario; Based on multiple sets of test data, determine the driving behavior data that meets the needs of different passengers in different driving scenarios; A driving behavior model is generated based on driving behavior data that meets different passenger needs in different driving scenarios.

2. The method for generating a driving behavior model matching passenger needs according to claim 1, characterized in that: The steps of determining driving behavior data that meets different passenger needs in different driving scenarios based on multiple sets of test data include: Determine passenger demand; For each driving scenario, find a target group of test data from multiple groups of test data so that the passenger data and the external vehicle data meet the passenger's needs; Perform minimum and maximum value screening on the vehicle data in the target group test data to obtain driving behavior data that meets the passenger's needs in a corresponding driving scenario; The driving behavior data includes: a vehicle speed interval, a lateral offset interval, a lateral acceleration interval and a steering wheel angular velocity interval of the vehicle.

3. The method for generating a driving behavior model matching passenger needs according to claim 2, characterized in that: The passenger data includes: passenger subjective evaluation data and passenger physiological characteristic data; In different driving scenarios, the target group test data that makes the passenger data and external vehicle data meet the passenger needs must meet the following requirements: the passenger subjective evaluation data meets the evaluation criteria corresponding to the passenger needs, the passenger physiological characteristic data meets the physiological criteria corresponding to the passenger needs, and the external vehicle data indicates that the external vehicle has not engaged in dangerous driving behavior.

4. The method for generating a driving behavior model matching passenger needs according to claim 1, characterized in that: The multiple driving scenarios include: on-ramp scenario, merging scenario, congested driving scenario, left-turn scenario at an intersection, straight-ahead scenario at an intersection, right-turn scenario at an intersection, static obstacle avoidance scenario, large vehicle avoidance scenario, simple lane change scenario, simple overtaking scenario, simple following scenario, being squeezed in, scene with obstructions on both sides of a single lane, mixed traffic of non-motor vehicles and motor vehicles, U-turn scenario, roundabout scenario, fork scenario, wide turn scenario, hump bridge scenario, long slope down scenario and / or cross-merge scenario; Different passenger demands include: comfort first demand, efficiency first demand and / or comfort and efficiency demand; The driving scene that the test vehicle is currently in is identified by the main examiner riding in the test vehicle. After the main examiner identifies the driving scene that the test vehicle is currently in, he prompts the passengers to make subjective evaluations on the evaluation questions corresponding to the driving scene that the test vehicle is currently in.

5. A vehicle control method for matching passenger needs, characterized in that: include: During autonomous driving, identify the vehicle’s current driving scenario and current passenger needs; Inputting the current driving scene and the current passenger demand into a driving behavior model to generate target driving behavior data that meets the current passenger demand; Performing automatic vehicle control according to the target driving behavior data; The driving behavior model is a driving behavior model obtained by using the method for generating a driving behavior model matching passenger needs as described in any one of claims 1 to 4.

6. The vehicle control method for matching passenger needs according to claim 5, characterized in that: The method further comprises: During manual driving, real-time driving parameters are collected under the same driving scenarios as during automatic driving; According to the real-time driving parameters, the driving behavior data in the relevant driving scenarios in the driving behavior model are updated through self-learning.

7. The vehicle control method for matching passenger needs according to claim 5, characterized in that: The steps of identifying the current driving scenario of the vehicle and the current passenger needs include: Identify the current driving scene of the vehicle based on the external environment data sensed by the sensing device on the vehicle; Based on passenger selection, identify current passenger needs.

8. A driving behavior model generation device that matches passenger needs, characterized in that: include: The data collection module is used for obtaining multiple groups of test data when a passenger is riding in a test vehicle and multiple drivers drive the test vehicles on a driving route including multiple driving scenarios; one group of test data includes: passenger data, vehicle data and external vehicle data related to a driver driving in a driving scenario; A driving behavior data determination module, used to determine driving behavior data that meets different passenger needs in different driving scenarios based on multiple sets of test data; The driving behavior model generation module is used to generate a driving behavior model based on driving behavior data that meets different passenger needs in different driving scenarios.

9. A vehicle control device that matches passenger needs, characterized in that: include: An identification module, used to identify the current driving scene of the vehicle and the current passenger needs; a target driving behavior data generating module, configured to input the current driving scenario and the current passenger demand into a driving behavior model, and generate target driving behavior data that meets the current passenger demand; A vehicle control module, used for automatically controlling the vehicle according to the target driving behavior data; The driving behavior model is a driving behavior model obtained by using the driving behavior model generation device matching passenger needs as described in claim 8.

10. A vehicle, characterized in that: The vehicle control device comprising the vehicle control device matching passenger needs as claimed in claim 9.

Images