Method and apparatus for adaptively optimizing an automated driving system

Abstract

A method and apparatus for adaptively optimizing an automated driving system are disclosed. The method and apparatus relate to the field of automated driving technology and solve the problem of the driving behavior of a vehicle controlled by the automated driving system being inconsistent with the driver's driving intention. The method and apparatus may be applied to intelligent vehicles and connected vehicles. A specific solution includes the steps of: an automated driving device acquiring the driving intention of a driver of a target vehicle (step 501); an automated driving device detecting, based on the driver's driving intention, a contradiction between the driving behavior of the target vehicle controlled by the automated driving system and the driver's driving intention (step 502); and an automated driving device updating the automated driving system so that the updated driving behavior of the target vehicle controlled by the automated driving system is consistent with the driver's driving intention (step 503). The method and apparatus are used in the automated driving process of a vehicle.

Description

[Technical field]

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method and apparatus for adaptively optimizing an autonomous driving system. [Background technology]

[0002] As autonomous driving technology develops, it brings many conveniences for people to drive vehicles. Autonomous driving means that one or more autonomous driving modes can be configured on a vehicle. The driver selects an autonomous driving mode suitable for the current driving scenario from one or more autonomous driving modes based on the driver's requirements, and triggers the driving of the vehicle based on the autonomous driving mode.

[0003] However, the number of existing configurations of the autonomous driving mode is limited. The driving requirements of all drivers in all different driving scenarios are not always taken into account when the autonomous driving mode is configured. In some driving scenarios, the autonomous driving mode configured on the vehicle cannot meet the driving requirements of the driver. In this case, the driver needs to switch the autonomous driving mode to a manual driving mode.

[0004] For example, in a driving scenario, when the driving behavior of the vehicle controlled by the automated driving system conflicts with the driver's driving intention (e.g., the driver's expected driving plan), the driver usually takes over the vehicle directly and drives the vehicle manually. However, the automated driving plan included in the vehicle's automated driving system is not adjusted based on the current conflict. As a result, in a later same driving scenario, the driving behavior of the vehicle controlled by the automated driving system is still inconsistent with the driver's driving intention and cannot meet the driver's personal requirements. Summary of the Invention [Means for solving the problem]

[0005] The present application provides a method and apparatus for adaptively optimizing an autonomous driving system to solve a problem in the current technology where the driving behavior of a vehicle under the control of the autonomous driving system conflicts with the driver's driving intention.

[0006] In order to achieve the above objectives, the following technical solutions are used in this application:

[0007] According to a first aspect, a method for adaptively optimizing an autonomous driving system is provided. The method may be applied to an autonomous driving device of a vehicle. For example, the autonomous driving device may be an in-vehicle device, or the autonomous driving device may be applied to a chip or a system-on-chip of the in-vehicle device. The method may include: the autonomous driving device acquires a driving intention of a driver of an autonomous vehicle controlled by the autonomous driving system; the autonomous driving device detects, based on the driving intention of the driver, that a contradiction exists between a driving behavior of a target vehicle controlled by the autonomous driving system and the driving intention of the driver; and the autonomous driving device updates the autonomous driving system, so that the driving behavior of the target vehicle controlled by the autonomous driving system after the update matches the driving intention of the driver.

[0008] According to the method for adaptively optimizing an automatic driving system provided in the first aspect, when it is detected that the driving intention of the driver of an automatic driving vehicle controlled by the automatic driving system is inconsistent with the driving behavior of the vehicle controlled by the automatic driving system, the automatic driving system is updated, so that the driving behavior of the vehicle controlled by the automatic driving system after the update matches the driving intention of the driver. On this basis, the subsequent driving behavior controlled by the automatic driving system after the update can satisfy the driving requirements of the driver. In this way, the problem that the driving behavior of the vehicle controlled by the automatic driving system is inconsistent with the driving intention of the driver is solved.

[0009] In a possible implementation, the driving intent is represented by feature parameters corresponding to the driver's behavior, where the driver's behavior includes one or more of the driver's operating behavior, visual behavior, emotional behavior, and physical posture behavior.

[0010] Based on this possible implementation, the driver's driving intention may be determined comprehensively and accurately from multiple angles based on the driver's multiple characteristic behaviors.

[0011] In a possible implementation form, the existence of a conflict between the driving behavior of the target vehicle controlled by the autonomous driving system and the driver's driving intention includes a feature parameter corresponding to the driver's behavior exceeding a preset range, and / or a period during which the feature parameter corresponding to the driver's behavior exceeds the preset range being equal to or greater than a first preset value, and / or a number of times the feature parameter corresponding to the driver's behavior exceeds the preset range being equal to or greater than a second preset value.

[0012] In this possible implementation, the driver's behavior can accurately reflect the driver's driving intention. Based on this, when the characteristic parameter corresponding to the driver's behavior exceeds a preset range and / or the duration and / or number of times that the characteristic parameter corresponding to the driver's behavior exceeds the preset range is equal to or greater than a preset value, it can be accurately determined that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system.

[0013] In a possible implementation form, the autonomous driving device acquires, based on the driver's driving intention and the driving behavior of a target vehicle controlled by the autonomous driving system, a first feature parameter used to represent the driver's driving intention and driving data corresponding to the driving behavior of the target vehicle controlled by the autonomous driving system, the autonomous driving device inputs the first feature parameter into a pre-configured neural network model used to determine driving behavior that matches the driver's driving intention to acquire the first driving behavior, and the autonomous driving device updates the autonomous driving system based on the first driving behavior.

[0014] Based on this possible implementation form, the preset neural network model may be pre-configured in the automatic driving device of the vehicle. Thus, the automatic driving device may input the feature parameters representing the driver's driving intention and driving data corresponding to the driving behavior of the vehicle controlled by the automatic driving system into the preset neural network model to obtain a first behavior feature. Then, the automatic driving device updates the automatic driving system based on the first behavior feature. This is simple and convenient.

[0015] In a possible implementation, the automated driving device presents one or more questions to the driver, the automated driving device receives answers to the one or more questions from the driver, the answers to the one or more questions are used to instruct the driver whether to update the automated driving system, and if the answers to the one or more questions are used to instruct the driver to update the automated driving system, the automated driving device updates the automated driving system based on the first driving behavior.

[0016] Based on a possible implementation, after the driver's driving intention is determined, the driver's driving intention may be further confirmed based on one or more questions. The driver's answers to the one or more questions may reflect the driver's actual driving intention. In this way, the driver's driving intention can be more accurately determined. Furthermore, whether to update the automated driving system may be determined based on the driver's answers. When the automated driving system is instructed to update using the answers to the one or more questions, the automated driving system is updated based on the driving behavior that matches the driving intention, so that the driving behavior of the vehicle controlled by the automated driving system after the update matches the driver's driving intention.

[0017] In a possible implementation form, when the first driving behavior matches the safe driving behavior of the target vehicle, the autonomous driving device uses the first driving behavior as the driving behavior of the target vehicle controlled by the updated autonomous driving system, or when the first driving behavior does not match the safe driving behavior of the target vehicle, the autonomous driving device uses the safe driving behavior as the driving behavior of the target vehicle controlled by the updated autonomous driving system.

[0018] Based on this possible implementation form, when the driving behavior of the vehicle controlled by the updated automated driving system matches the driving intention of the driver and the driving behavior matches the safe driving behavior of the vehicle, the driving behavior may be used as the behavior controlled by the updated automated driving system. Alternatively, when the driving behavior does not match the safe driving behavior of the vehicle, the safe driving behavior may be used as the behavior controlled by the updated automated driving system, so as to ensure that the vehicle runs safely under the control of the automated driving system. In this way, the vehicle can run safely under the control of the automated driving system.

[0019] According to a second aspect, an apparatus for adaptively optimizing an autonomous driving system is provided. The apparatus may be applied to an autonomous driving device or a chip or system-on-chip in the autonomous driving device, or may be a functional module located within the autonomous driving device and configured to implement the method according to the first aspect or any possible design of the first aspect. The apparatus may implement the functions performed by the autonomous driving device in the above aspects or possible designs. The functions may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. For example, an apparatus for adaptively optimizing an autonomous driving system includes a communication unit and a processing unit.

[0020] The communication unit is configured to acquire a driving intention of a driver of a target vehicle, the target vehicle being an autonomous vehicle controlled by an autonomous driving system.

[0021] The processing unit is configured to detect, based on the driver's driving intention, that a contradiction exists between the driving behavior of the target vehicle under the automatic driving control and the driver's driving intention.

[0022] The processing unit is further configured to update the autonomous driving system, so that a driving behavior of the target vehicle controlled by the updated autonomous driving system matches the driver's driving intention.

[0023] For a specific implementation form of the device for adaptively optimizing an autonomous driving system, please refer to the behavior function of the autonomous driving device in the method for adaptively optimizing an autonomous driving system according to the first aspect or any possible design of the first aspect. Details will not be described repeatedly in this specification. Therefore, the provided device for adaptively optimizing an autonomous driving system can achieve the same beneficial effect as the effect of the first aspect or any possible design of the first aspect.

[0024] According to a third aspect, an autonomous driving device is provided. The autonomous driving device may be an in-vehicle device or a chip or system-on-chip in the in-vehicle device. The autonomous driving device may implement the functions performed by the autonomous driving device in the above aspects or possible designs. The functions may be implemented by hardware. For example, in a possible design, the autonomous driving device may include a processor and a communication interface. The processor is configured to execute a computer program or instructions and implement a method for adaptively optimizing an autonomous driving system according to the first aspect or any possible implementation of the first aspect.

[0025] In another possible design, the autonomous driving device may further include a memory, the memory configured to store computer-executable instructions and data required for the autonomous driving device. When the autonomous driving device is operated, the processor executes the computer-executable instructions stored in the memory, thereby enabling the autonomous driving device to perform the method for adaptively optimizing the autonomous driving system according to the first aspect or any possible design of the first aspect.

[0026] According to a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium may be a readable non-volatile storage medium. The computer readable storage medium stores computer instructions or programs. When the computer instructions or programs are executed on a computer, the computer is enabled to perform a method for adaptively optimizing an autonomous driving system according to the first aspect or any possible design of the above aspects.

[0027] According to a fifth aspect, there is provided a computer program product comprising instructions which, when executed on a computer, enable the computer to perform a method for adaptively optimizing an autonomous driving system according to the first aspect or any possible design of the above aspects.

[0028] According to a sixth aspect, an autonomous driving device is provided. The autonomous driving device may be an autonomous driving device or an autonomous driving device chip or a system-on-chip. The autonomous driving device includes one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, and the one or more memories are configured to store computer program code, the computer program code including computer instructions. When the one or more processors execute the computer instructions, the autonomous driving device is enabled to perform a method for adaptively optimizing an autonomous driving system according to the first aspect or any possible design of the first aspect.

[0029] According to a seventh aspect, a chip system is provided. The chip system includes a processor and a communication interface. The chip system may be configured to perform a function performed by the autonomous driving device in the first aspect or any possible design of the first aspect. For example, the processor is configured to obtain the driver's operation characteristics by using the communication interface.

[0030] For the technical effects brought about by any design of the second to seventh aspects, please refer to the technical effects brought about by the first aspect or any possible design of the first aspect. Details will not be described repeatedly.

[0031] According to an eighth aspect, a communication system is provided. The communication system includes an autonomous driving device and a vehicle to everything (V2X) server. The autonomous driving device is communicatively connected to the V2X server. The autonomous driving device may be configured to implement a function performed by the autonomous driving device in the first aspect or any possible design of the first aspect. The V2X server may be configured to provide a plurality of pieces of information about the autonomous driving device. For example, the plurality of pieces of information may include characteristic information such as driver characteristic information, driving behavior of a vehicle controlled by the autonomous driving system, etc. [Brief description of the drawings]

[0032] [Figure 1] FIG. 1 is a schematic diagram of the structure of a communication system according to an embodiment of the present application; [Diagram 2] 1 is a schematic diagram of a vehicle structure according to an embodiment of the present application; [Diagram 3] FIG. 1 is a schematic diagram of the structure of an automatic driving device according to an embodiment of the present application. [Figure 4] FIG. 2 is a schematic diagram of the structure of a V2X server according to an embodiment of the present application; [Diagram 5] 1 is an exemplary flowchart of a method for adaptively optimizing an autonomous driving system according to an embodiment of the present application. [Figure 6a] 2 is an exemplary diagram of a driver performing an operation on an accelerator pedal of a vehicle according to an embodiment of the present application; [Figure 6b] 2 is an exemplary diagram of a driver performing an operation on a decelerator pedal of a vehicle according to an embodiment of the present application; [Figure 6c] FIG. 2 is an exemplary diagram of a driver performing an operation on a steering wheel of a vehicle according to an embodiment of the present application. [Figure 7] 1 is a schematic diagram of a vehicle structure according to an embodiment of the present application; [Figure 8] FIG. 1 is a schematic diagram of a vehicle display interface according to an embodiment of the present application. [Figure 9] 1 is an exemplary flowchart of another method for adaptively optimizing an autonomous driving system according to an embodiment of the present application. [Figure 10] FIG. 1 is a schematic diagram of the structure of an automatic driving device 1000 according to an embodiment of the present application. [Figure 11] FIG. 1 is a schematic diagram of the structure of a communication system according to an embodiment of the present application; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0033] Before describing the embodiments of the present application, the terms used in the embodiments of the present application will be described.

[0034] The traffic information may also be referred to as a key element, a traffic feature, a traffic feature, etc. This is not limited. The traffic information may be used to indicate the traffic environment of the roadway in the driving process of the vehicle. Specifically, the traffic information may include one or more of vehicle information, which is information about the roadway of the vehicle, obstacle information, pedestrian information, and traffic environment information.

[0035] The vehicle information, obstacle information, and pedestrian information may indicate the position, speed, etc. of other vehicles relative to the host vehicle, pedestrians, or obstacles. Specifically, the vehicle information may include the amount of vehicles, the vehicle speed, the distance from a vehicle to the host vehicle, and the vehicle type. The obstacle information may include height limiting poles, guardrails, etc. on the road. The pedestrian information may include the amount of pedestrians, the pedestrian speed, and the distance from a pedestrian to the host vehicle. The traffic environment information may include road information, light conditions, and weather conditions. For example, the road information may be information about trunk roads, national roads, prefectural roads, city roads, rural roads, etc. The road information may further include information about road closure signs, traffic lights, lanes, closed roads, unclosed roads, etc. This is not limited.

[0036] Traffic signs may indicate the maximum speed limit on a road, the minimum speed limit on a road, stop signs, etc. Traffic lights can indicate whether to stop, turn left, or turn right. Lanes may indicate the direction of vehicle driving, turning radius, lane direction on both sides, whether lane changes are possible, etc.

[0037] In this way, when the driver faces various traffic information in the process of driving the vehicle traveling on the road, the driver may control the vehicle to perform driving behavior corresponding to the traffic information.

[0038] Driving behavior is also called driving-subject task. Driving behavior means that in the process of driving on the road, a vehicle needs to complete different driving actions in different traffic environments before reaching a destination. The different actions may be following a vehicle, keeping a lane, changing lanes to cut in, being cut in by other vehicles while driving, etc. For example, when a vehicle is cut in by other vehicles while driving, the driving behavior of the host vehicle is to reduce the vehicle speed when the host vehicle is cut in.

[0039] The vehicle may perform one or more driving behaviors corresponding to one traffic information. The one or more driving behaviors may be used to reflect the driver's driving intention.

[0040] For example, when the traffic information includes information that the roadway is curved, the driving behavior of the vehicle may include driving while decelerating, adjusting the driving direction based on the curvature, etc. The traffic information and one or more vehicle driving behaviors corresponding to the traffic information may constitute a driving scenario.

[0041] The driving scenario may also be referred to as a driving function domain. The driving scenario refers to clustering a plurality of traffic information having the same or similar characteristics and vehicle driving behaviors corresponding to the traffic information based on a preset clustering algorithm to obtain a plurality of categories, and each of the plurality of categories may include one kind of traffic information and at least one driving behavior corresponding to the traffic information. One category corresponds to one driving scenario. In each different driving scenario, the in-vehicle device has a different driving behavior under the control of the automated driving system.

[0042] The preset clustering algorithm may be a k-means clustering algorithm (k-means). For the k-means clustering algorithm, please refer to the current art, and the details will not be repeated in this specification.

[0043] For example, as shown in Table 1, the driving scenarios may include driving in the traffic direction along urban rush hour road segments, driving in the traffic direction along closed roads, driving at low speed on unclosed roads, traversing urban road intersections, traversing non-urban road intersections, etc. The traffic information and driving behaviors included in the above driving scenarios may be the traffic information and driving behaviors shown in Table 1.

[0044] [Table 1]

[0045] In Table 1, the traffic information in each driving scenario may further include other information, such as road vehicle information and pedestrian information. For specific explanation, please refer to the above description of traffic information. Details will not be repeated. Table 1 may further include other driving scenarios. This is not limited.

[0046] The driver's driving intention refers to the operation performed by the driver on the vehicle, or the driving behavior that the driver wants the vehicle to perform when the vehicle is moving. The driving behavior may include the vehicle, changing to the left lane, changing to the right lane, overtaking the vehicle, etc. For example, in a driving scenario, the driving behavior that the driver wants the vehicle to perform is to overtake another vehicle. When the vehicle performs the driving behavior of overtaking another vehicle, the driving operation of the driver is to control the accelerator pedal, so that the vehicle performs the accelerating driving behavior. The driving operation of the driver controlling the accelerator pedal and the driving behavior of the vehicle performing the accelerating may be referred to as natural driving data.

[0047] Naturalistic driving data is a general term that refers to the driving behavior of a vehicle and the operating characteristics performed by a driver on a vehicle as the driver operates the vehicle.

[0048] The operation features may include, but are not limited to, controlling a steering wheel, controlling an accelerator pedal, controlling a decelerator pedal, etc.

[0049] The autonomous driving mode means that the driver inputs a destination into the autonomous driving system, and the autonomous driving system may determine an appropriate driving route based on preset parameters. The driving route may include multiple traffic information. For example, the multiple traffic information may include multiple curves, multiple intersections, etc.

[0050] The autonomous driving system may control the vehicle configured with the autonomous driving system to perform corresponding driving behaviors based on different driving scenarios on the driving route. For example, when the driving route curves, the autonomous driving system may adjust the driving behavior of the vehicle based on the curvature of the road. For example, the autonomous driving system may adjust the turning direction, turning angle, and vehicle speed of the vehicle, so that the vehicle runs smoothly and safely.

[0051] In the current technology, the amount of the automated driving mode configured for the vehicle is limited, and the driving requirements of all the drivers in all scenarios are not considered when the automated driving mode is configured for the vehicle. Therefore, the automated driving mode configured for the vehicle in some driving scenarios cannot meet the driving requirements of the driver. Alternatively, in the automated driving technology, in the case of a scenario that cannot be handled by the automated driving system, the automated driving system reminds the driver to take over the driving right of the vehicle and drive manually. In this case, the driver needs to switch the automated driving mode to the manual driving mode. For example, in a driving scenario, when the driving behavior performed by the vehicle controlled by the automated driving system is inconsistent with the driver's driving intention (e.g., the driving plan expected by the driver), the driver usually takes over the vehicle and drives the vehicle manually. However, the driving behavior of the vehicle under the control of the automated driving mode is not adjusted based on the current inconsistency. As a result, in the same driving scenario, the driving behavior of the vehicle controlled by the automated driving system thereafter still conflicts with the driver's driving intention and cannot meet the driver's personal requirements.

[0052] In order to solve the above technical problems, an embodiment of the present application provides a method for adaptively optimizing an automatic driving system, the method being applied to an automatic driving device of a vehicle. The method includes: the automatic driving device obtaining a driver's driving intention; the automatic driving device detecting, based on the driver's driving intention, that there is a contradiction between the driving behavior of the vehicle controlled by the automatic driving system and the driver's driving intention; and the automatic driving device updating the automatic driving system, so that the driving behavior of the vehicle controlled by the updated automatic driving system is consistent with the driver's driving intention.

[0053] Based on this technical solution, when it is detected that the driving intention of the driver of the automated vehicle controlled by the automated driving system is inconsistent with the driving behavior of the vehicle controlled by the automated driving system, the automated driving system is updated, so that the driving behavior of the vehicle controlled by the automated driving system after the update is consistent with the driving intention of the driver. Based on this, the subsequent driving behavior controlled by the automated driving system after the update can meet the driving requirements of the driver. In this way, the problem that the driving behavior of the vehicle controlled by the automated driving system is inconsistent with the driving intention of the driver is solved.

[0054] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, implementation forms of the embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0055] FIG. 1 illustrates an exemplary diagram of a communication system according to an embodiment of the present application. As shown in FIG. 1, the communication system may include a vehicle 10 and a V2X server 20. The vehicle 10 may communicate with the V2X server 20 by using a V2X communication technology. The vehicle 20 may further communicate with the V2X server 20 via a wireless link. For example, the vehicle 20 and the V2X server 20 may communicate with each other via a fifth generation (5G) network, or in other manners. This is not limited.

[0056] The vehicle 10 may be an intelligent network driving vehicle and is a typical vehicle-to-everything terminal. Those skilled in the art should understand that the internal functional units or devices of the vehicle 10 may be used to specifically execute the method for adaptively optimizing an autonomous driving system in this embodiment of the present application. For example, the vehicle 10 may include an autonomous driving device configured to perform the method for adaptively optimizing an autonomous driving system provided in this embodiment of the present application. The autonomous driving device may be communicatively connected to other components of the vehicle 10 via a controller area network (CAN) bus. The specific structure of the vehicle 10 will be described in detail in the embodiment shown in FIG. 2.

[0057] The V2X server 20 may provide the vehicle 10 with natural driving data of multiple driving behaviors of the vehicle controlled by the autonomous driving system and / or natural driving data of multiple drivers. The V2X server 20 may be further configured to receive image information of the driver from the vehicle 10 and recognize the image information of the driver to obtain the physical posture behavior of the driver. For example, the physical posture behavior may include whether the driver is using a mobile phone, whether the driver is driving in a fatigued state, etc. The V2X server 20 may further send information regarding the physical posture behavior of the driver to the vehicle 10. The V2X server 20 may be a physical server or a virtual server, for example, a cloud server. This is not limited. A specific structure of the V2X server 20 will be described in detail in the embodiment shown in FIG. 4.

[0058] It should be noted that the communication system described in the present embodiment of the present application is intended to more clearly describe the technical solutions in the embodiments of the present application, and does not constitute any limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will recognize that with the evolution of communication systems and the emergence of other communication systems, the technical solutions provided in the embodiments of the present application can also be applied to similar technical problems.

[0059] 2 is a schematic diagram of a structure of a vehicle 10 according to an embodiment of the present application. As shown in FIG. 2, the vehicle 10 may include an automatic driving device 101, a vehicle body gateway 102, a vehicle body antenna 103, etc. The automatic driving device 101 may be communicatively connected to the vehicle body antenna 103 through a radio frequency (RF) cable.

[0060] It will be understood that the structure shown in FIG. 2 does not constitute a specific limitation for the vehicle 10. In some embodiments, the vehicle 10 may include more or less components than those shown in FIG. 2, or may include components in which some components shown in FIG. 2 are combined, or may include components in which the components shown in FIG. 2 are divided, etc. For example, the vehicle 10 may further include a domain controller (DC), a multi-domain controller (MDC), etc. The components shown in FIG. 2 may be implemented by hardware, software, or a combination of software and hardware. For example, the autonomous driving device 101 in the vehicle 10 may be a vehicle-to-everything chip, etc. A specific structure of the autonomous driving device 101 will be described in detail in the embodiment shown in FIG. 3.

[0061] The autonomous driving device 101 may also be called an on-board unit (OBU), an in-vehicle terminal, etc. For example, the autonomous driving device 101 may be a telematics box (T-Box). The autonomous driving device 101 is mainly configured to perform a method for adaptively optimizing an autonomous driving system provided in this embodiment of the present application.

[0062] The vehicle body gateway 102 is mainly configured to receive and transmit vehicle information. The vehicle body gateway 102 may be connected to the autonomous driving device 101 through a CAN bus. For example, the vehicle body gateway 102 may obtain from the autonomous driving device 101 an updated autonomous driving system and a driving behavior of a vehicle controlled by the autonomous driving system, which is obtained after the autonomous driving device 101 performs a method for adaptively optimizing an autonomous driving system according to this embodiment of the present application. The vehicle body gateway 102 then sends the obtained updated autonomous driving system and a driving behavior of a vehicle controlled by the autonomous driving system to other components of the vehicle 10.

[0063] The vehicle body antenna 103 may have a built-in communication antenna, which is responsible for receiving and transmitting signals. For example, the communication antenna may send vehicle information of the vehicle to an automatic driving device of another vehicle, or may receive vehicle information sent by the automatic driving device of another vehicle.

[0064] 3 is a schematic diagram of the structure of an autonomous driving device 101 according to an embodiment of the present application. As shown in FIG. 3, the autonomous driving device 101 may include an autonomous driving sensing module 1011, an intelligent cockpit interaction module 1012, a driving intention conflict detection module 1013, and an autonomous driving control module 1014.

[0065] The autonomous driving sensing module 1011 may be configured to recognize and classify traffic information and driving behavior of the vehicle 10. The intelligent cockpit interaction module 1012 is mainly configured to obtain image information and voice information of the driver, and may further perform voice recognition on the driver's voice information. The driving intention conflict detection module 1013 may be configured to determine the driver's driving intention and detect whether the driver's driving intention is conflicting with the driving behavior of the vehicle controlled by the autonomous driving system. The autonomous driving control module 1014 may be configured to control the driving behavior of the vehicle during autonomous driving.

[0066] For example, the intelligent cockpit interaction module 1012 may recognize the voice information of the driver by using a long short-term memory-deep neural network (LSTM-DNN) model. For example, the LSTM-DNN is configured for the intelligent cockpit interaction module 1012. The automatic driving device may obtain the voice information of the person inside the vehicle by using a voice collection device, and input the voice information of the person inside the vehicle into the LSTM-DNN model of the intelligent cockpit interaction module 1012, so that the intelligent cockpit interaction module 1012 can recognize the voice information of the person inside the vehicle. Please refer to this embodiment for the following description of voice information recognition. Details will not be described hereafter.

[0067] In a possible design, as shown in Fig. 3, the autonomous driving device 101 may further include a driver online adaptation module 1015. The driver online adaptation module 1015 may be configured to adjust the driving behavior of the vehicle controlled by the autonomous driving system in the driving scenario based on the driving intention of the driver of the vehicle in the driving scenario, and transmit information regarding the adjusted driving behavior of the vehicle controlled by the autonomous driving system and the driving scenario to the autonomous driving control module 1014.

[0068] After receiving the information regarding the adjusted driving behavior and driving scenario of the vehicle controlled by the autonomous driving system from the driver online adaptation module 1015, the autonomous driving control module 1014 may update the autonomous driving system. For example, the autonomous driving control module 1014 replaces the driving behavior of the vehicle controlled by the autonomous driving system with the adjusted driving behavior of the vehicle controlled by the autonomous driving system.

[0069] It will be understood that the structure shown in Figure 3 does not constitute a particular limitation on the automated driving device 101. In some other embodiments, the automated driving device 101 may include more or fewer components than those shown in Figure 3, or the automated driving device 101 may include components that combine some of the components shown in Figure 3, or the automated driving device 101 may include components that separate the components shown in Figure 3, etc. The components shown in Figure 3 may be implemented by hardware, software, or a combination of software and hardware.

[0070] In this embodiment of the present application, the device shown in Figure 3 may alternatively be a chip or chip system in an autonomous driving device. The chip system may include a chip, or may include a chip and other discrete components.

[0071] 4 is a schematic diagram of the structure of the V2X server 20 according to an embodiment of the present application. As shown in FIG. 4, the V2X server 20 may include a driver preference and history operation database 2011 and a highest driver acceptable parameter module 2012.

[0072] The driver preference and history operation database 2011 is configured to store natural driving data of a plurality of drivers within a preset period and at least one driving behavior of a vehicle controlled by the automated driving system. The highest driver acceptable parameter module 2012 is configured to store a most frequently used automated driving mode in at least one automated driving mode.

[0073] Furthermore, the V2X server 20 may further update the data in the driver preference and history operation database 2011 and the highest driver acceptable parameter module 2012 based on a preset repetition period. The preset repetition period may be preset by the V2X server 20. Alternatively, the V2X server 20 may update the data in the driver preference and history operation database 2011 and the highest driver acceptable parameter module 2012 by interacting with the automatic driving device 101. For example, after updating the driving behavior of the vehicle controlled by the automatic driving system, the automatic driving device sends the updated driving behavior of the vehicle controlled by the automatic driving system to the V2X server. After receiving the updated driving behavior of the vehicle controlled by the automatic driving system from the automatic driving device, the V2X server may replace the driving behavior of the vehicle controlled by the automatic driving system that exists in the V2X server with the updated driving behavior of the vehicle controlled by the automatic driving system.

[0074] In a possible design, the V2X server 20 may further include a driver online adaptation module 1015 of Fig. 2. For the function of the driver online adaptation module 1015, please refer to the above description. Details will not be repeated in this specification.

[0075] It will be understood that the structure shown in Figure 4 does not constitute any particular limitation on the V2X server 20. In some other embodiments, the V2X server 20 may include more or fewer components than those shown in Figure 4, or may include a combination of some of the components shown in Figure 4, or may include separate components of the components shown in Figure 4, etc. The components shown in Figure 4 may be implemented by hardware, software, or a combination of software and hardware.

[0076] In this embodiment of the present application, the device shown in Figure 4 may be a chip or a chip system in a V2X server. The chip system may include a chip, or may include a chip and other discrete components.

[0077] In the embodiments of the present application, words such as "example" or "for example" are used to indicate an example, an illustration, or an explanation. Any embodiment or design manner described in the embodiments of the present application as "example" or "for example" should not be described as being preferred or having more advantages over other embodiments or design manners. Rather, the use of words such as "example" or "for example" is intended to present the relevant concept in a particular manner.

[0078] The terms "first" and "second" below are merely for explanatory purposes and should not be understood as an indication or implicit indication of the relative importance or quantity of the technical features shown. Thus, a feature qualified by "first" or "second" may explicitly or implicitly include one or more features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0079] All the methods in the following embodiments may be implemented in an automatic driving device having the above hardware structure. With reference to the communication system shown in FIG. 1, the following describes in detail the method for adaptively optimizing the automatic driving system provided in this embodiment of the present application.

[0080] It should be noted that in this embodiment of the present application, the method for adaptively optimizing an autonomous driving system may be executed by an autonomous driving device. For example, the autonomous driving device may be the autonomous driving device of FIG. 2 or FIG. 3. Alternatively, the method may be implemented by a chip or a system-on-chip in the autonomous driving device. This is not limited. In the following, an example in which the method for adaptively optimizing an autonomous driving system is executed by an autonomous driving device is used for the purpose of explanation.

[0081] 5 is a schematic flowchart of a method for adaptively optimizing an autonomous driving system according to an embodiment of the present application. As shown in FIG. 5, the method may include the following steps:

[0082] Step 501: The automatic driving device acquires the driving intention of the driver of the target vehicle.

[0083] The target vehicle is an autonomous vehicle controlled by an autonomous control system. The target vehicle may be the vehicle of FIG. 1, and the target vehicle may have the components described in FIG. 2. The autonomous vehicle may include one or more of the modules in FIG. 3.

[0084] The driver may be a driver who has driven the target vehicle before, or a driver who has not driven the target vehicle before, or may be described as a new driver. The automatic driving device may detect whether the driver is a driver who has driven the target vehicle before or a new driver based on the driver's characteristic information. One piece of characteristic information is used to identify one driver.

[0085] In a possible implementation, the driver's driving intention may be represented by a feature parameter corresponding to the driver's behavior. In other words, the automated driving device may detect the driver's driving intention based on the driver's behavior.

[0086] The driver behavior may include one or more of the driver's handling behavior, visual behavior, emotional behavior, and physical postural behavior.

[0087] The driver's operation behavior may refer to the driver's manual operation behavior with respect to the vehicle in the automatic driving process of the vehicle. For example, the driver's operation behavior may include the driver's operation behavior with respect to the steering wheel of the vehicle, the driver's operation behavior with respect to the accelerator pedal of the vehicle, and the driver's operation behavior with respect to the decelerator pedal of the vehicle.

[0088] The automated driving device may acquire the driver's driving intention in a plurality of ways. For example, the plurality of ways may include the following. That is, the automated driving device may acquire the driver's driving intention by inputting feature parameters corresponding to the driver's behavior into a driving intention model, the automated driving device may determine the driver's driving intention based on the driver's operation behavior, and the automated driving device may determine the driver's driving intention based on the driver's emotional behavior. The automated driving device may further determine the driver's driving intention in other ways. This is not limited. Such ways will be described below.

[0089] Method 1: The autonomous driving device acquires the driver's intention by inputting feature parameters corresponding to the driver's behavior into a driving intention model.

[0090] The input parameters of the driving intention model are characteristic parameters of the driver's behavior, and the output parameters of the driving intention are the driver's intention. The driving intention model may be preset by the automated driving system.

[0091] For example, the method for determining the driving intention model may be the following: using a hidden Markov model to train the behavior features of multiple drivers in a preset period and corresponding natural driving data to obtain a driving intention model. For the method for training the hidden Markov model, please refer to the current technology. Details will not be repeated in this specification.

[0092] Specifically, the autonomous driving device may input the characteristic parameters of the driver's behavior into a driving intention model to obtain the driver's driving intention. The autonomous driving device may compare the driver's driving intention with the driving behavior of the vehicle controlled by the autonomous driving system. When the driver's driving intention is not consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the autonomous driving device may determine that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system.

[0093] Method 2: The autonomous driving device may determine the driver's driving intentions based on the driver's operating behavior.

[0094] The driver's operation characteristics may include an operation performed by the driver on the accelerator pedal, an operation performed by the driver on the decelerator pedal, and an operation performed by the driver on the steering wheel. A method for the automated driving device to determine the driver's driving intention based on the driver's operation characteristics will be specifically described below.

[0095] For example, the autonomous driving device may obtain parameter characteristics corresponding to the driver's behavior by using one or more sensors. For example, the sensors may include one or more of an accelerator pedal position sensor, a decelerator pedal position sensor, and a steering wheel torque sensor.

[0096] The accelerator pedal position sensor is configured to detect position change information of the accelerator pedal of the target vehicle, the decelerator pedal position sensor is configured to detect position change information of the decelerator pedal of the target vehicle, and the steering wheel torque sensor is configured to detect rotation angle information of the steering wheel of the target vehicle. The automated driving device may determine the driver's operation behavior with respect to the accelerator pedal by using the accelerator pedal change information. The automated driving device may determine the driver's operation behavior with respect to the decelerator pedal by using the decelerator pedal change information. The automated driving device may determine the driver's operation behavior with respect to the steering wheel by using the steering wheel torque change information. The detection of the driver's driving intention by the automated driving device based on the driver's operation behavior will be described below.

[0097] 1. The autonomous driving device acquires the driver's driving intentions based on the driver's operating behavior regarding the vehicle steering wheel.

[0098] As shown in FIG. 6a, assume that the automated driving device detects that the position of the accelerator pedal of the target vehicle has moved from a first position to a second position. When the accelerator pedal of the target vehicle is located at the first position, the vehicle speed of the target vehicle is a first vehicle speed, or when the accelerator pedal of the target vehicle is located at the second position, the vehicle speed of the target vehicle is a second vehicle speed. The second vehicle speed is greater than the first vehicle speed. In this case, the automated driving device may determine that the driver's driving intention is to increase the driving speed of the target vehicle in the driving scenario.

[0099] 2. The automatic driving device acquires the driver's driving intention based on the driver's operation behavior on the deceleration pedal.

[0100] Suppose the automated driving device detects that the position of the decelerator pedal of the target vehicle has moved from a third position to a fourth position, as shown in FIG. 6b. When the decelerator pedal of the target vehicle is located at the third position, the vehicle speed of the target vehicle is a third vehicle speed, or when the decelerator pedal of the target vehicle is located at the fourth position, the vehicle speed of the target vehicle is a fourth vehicle speed. The fourth vehicle speed is smaller than the third vehicle speed. In this case, the automated driving device may determine that the driver's driving intention is to reduce the driving speed of the target vehicle in the driving scenario.

[0101] 3. The automatic driving device acquires the driver's driving intentions based on the driver's operating behavior toward the steering wheel.

[0102] The steering torque change information may include steering torque change information of a first direction and a second direction, the first direction and the second direction being opposite to each other, for example, as shown in FIG. 6c, when the steering wheel is rotated in a first direction, the target vehicle turns toward the left side of the driving direction, or when the steering wheel is rotated in a second direction, the target vehicle turns toward the right side of the driving direction.

[0103] For example, by using a steering torque sensor, the autonomous driving device may determine that the driver's driving intention is to expect the target vehicle to turn toward the first direction when it detects that the steering wheel has been rotated an angle α in the first direction.

[0104] Method 3: The autonomous driving device may determine the driver's driving intentions based on the driver's emotional behavior.

[0105] When the driver's emotional behavior is negative emotional behavior, the automated driving device may determine that the driver's driving intention is to be dissatisfied with the driving behavior of the target vehicle controlled by the automated driving system in the driving scenario.

[0106] Furthermore, the autonomous driving system may further determine whether the driver is concentrating on the driving behavior of the target vehicle and whether the driver is performing a second task by using the driver's physical posture behavior.

[0107] When the driver is not performing the second task, the automated driving device determines that the driver's driving intention is to be dissatisfied with the driving behavior of the vehicle controlled by the automated driving system. In other words, in the driving scenario, the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system.

[0108] The driver's visual and physical postural behavior may be used to reflect the driver's concentration level in the driving behavior of the target vehicle.

[0109] The driver's visual behavior may include the driver's head behavior and gaze behavior. For example, the driver's head behavior may include the driver's head rotation direction, rotation angular velocity, rotation angle, etc. The driver's gaze behavior includes the driver's blink frequency, eyelid closure duration, etc. Of course, the driver's visual behavior may further include the driver's other eye behaviors. This is not limited.

[0110] The driver's physical posture behavior may be further used to determine the driver's second behavior. For example, the second behavior may be other behaviors than focusing on the driving behavior of the target vehicle. For example, the second behavior may include the driver using a mobile phone, the driver talking to a person in another seat, etc.

[0111] The driver's emotional behavior is used to reflect whether the driver is satisfied with the driving behavior of the target vehicle controlled by the autonomous driving system. The driver's emotional behavior may include the driver's facial expressions and language features.

[0112] In one example, the autonomous driving device may acquire multiple types of images of the driver in a preset period by using a photographing device. The autonomous driving device may recognize the multiple images to acquire the visual behavior, physical posture behavior, and facial expression of the driver. The preset period may be preset based on requirements.

[0113] In yet another example, the autonomous driving device may obtain the driver's voice information by using a voice collecting device. For example, the voice collecting device may be a microphone, etc. The autonomous driving device may recognize the driver's voice information to obtain the driver's language characteristics.

[0114] The facial expression of the driver may include a first facial expression and a second facial expression. The linguistic features of the driver may include a first linguistic feature and a second linguistic feature.

[0115] For example, the first and second expression libraries may be preset in the automatic driving device, and after acquiring the driver's expression, the automatic driving device compares the driver's expression with each expression in the first and second expression libraries to determine whether the driver's expression belongs to the first expression or the second expression.

[0116] For example, when the similarity between the driver's facial expression and the facial expression in the first facial expression library is equal to or greater than a first preset threshold, the automatic driving device may determine that the driver's facial expression is the first facial expression. Alternatively, when the similarity between the driver's facial expression and the facial expression in the second facial expression library is equal to or greater than a second preset threshold, the automatic driving device may determine that the driver's facial expression is the second facial expression. The first preset threshold and the second preset threshold may be preset based on requirements. This is not limited.

[0117] A plurality of voice collecting devices may be disposed in the target vehicle. The plurality of voice collecting devices may be communicatively connected to the automatic driving device. The automatic driving device may acquire a voice of a person inside the target vehicle by using the plurality of voice collecting devices, and may recognize the voice of the person inside the target vehicle to determine a source of the voice. For example, the automatic driving device may identify a source of the voice based on an audio signal of the voice and determine the source of the voice. When the automatic driving device determines that the source of the voice includes a plurality of seats, and the plurality of seats includes the driver's seat, the automatic driving device determines that the driver is talking to a person in another seat.

[0118] For example, as shown in FIG. 7, an example is used in which the target vehicle includes a front row seat of the vehicle and a rear row seat of the vehicle. The voice collecting device 1 and the voice collecting device 2 may be disposed in the target vehicle. The voice collecting device 1 is configured to collect the voice of the driver and the person in the front passenger seat, and the voice collecting device 2 is configured to collect the voice of the person in the rear seat of the target vehicle. The voice collecting device 1 and the voice collecting device 2 may send the collected voice to the automatic driving device to enable the automatic driving device to recognize the voice, so that the automatic driving device may determine whether the driver is talking to the person in the other seat. For example, the voice collecting device 1 may collect the voice of the driver, and the voice collecting device 2 may collect the voice of the person in the rear seat of the target vehicle. In this case, the automatic driving device may determine that the driver is talking to the person in the rear seat. In the target vehicle, a voice collecting device may further be disposed in each seat of the vehicle, so that the automatic driving device can more accurately determine the source of the voice.

[0119] For the method of determining the first and second language features of the driver, please refer to the above method of determining the first and second facial expressions, and the details will not be described repeatedly in this specification.

[0120] It should be noted that the first facial feature and the first language feature may be used to express that the driver's emotional behavior is a positive emotional behavior. When the driver's emotional behavior is a positive emotional behavior, the driver's driving intention is to be satisfied with the driving behavior of the target vehicle controlled by the automatic control system.

[0121] For example, the first facial features may include happy, satisfied, and the like, and the first linguistic features may include not bad, good, and the like.

[0122] It should be noted that the second facial feature and the second language feature may be used to express that the driver's emotional behavior is a negative emotional behavior. When the driver's emotional behavior is a negative emotional behavior, the driver's driving intention is to be dissatisfied with the driving behavior of the target vehicle controlled by the automatic control system.

[0123] For example, the second facial expressions may include anxious, angry, etc. The second linguistic features may include really awful, better not use, etc.

[0124] In another possible implementation form, the autonomous driving system may input feature parameters corresponding to the driver's behavior into a driving intention model to obtain the driver's driving intention.

[0125] Step 502: The automatic driving device detects, based on the driver's driving intention, that there is a contradiction between the driving behavior of the target vehicle controlled by the automatic control system and the driver's driving intention.

[0126] In a possible implementation form, the automatic driving device may detect whether there is a contradiction between the driver's driving intention and the driving behavior of the vehicle controlled by the automatic control system based on the feature parameter corresponding to the driver's behavior. For example, when the feature parameter corresponding to the driver's behavior exceeds a preset range, and / or the period during which the feature parameter corresponding to the driver's behavior exceeds the preset range is equal to or greater than a first preset value, and / or the number of times the feature parameter corresponding to the driver's behavior exceeds the preset range is equal to or greater than a second preset value, the automatic driving device may detect that there is a contradiction between the driver's driving intention and the driving behavior of the vehicle controlled by the automatic control system.

[0127] Alternatively, the number of times that the characteristic parameter corresponding to the driver's behavior exceeds the preset range is equal to or greater than the second preset value. The number of times that the characteristic parameter corresponding to the driver's behavior exceeds the preset range within a preset period is equal to or greater than the second preset value. The preset period may be preset based on requirements.

[0128] For example, as shown in Fig. 6a, the change range of the accelerator pedal corresponding to the target vehicle in the autonomous driving system is a first range. The first range may be preset based on requirements.

[0129] When the change range of the accelerator pedal moving from the first position to the second position exceeds a first range, and / or the period during which the change range of the accelerator pedal moving from the first position to the second position exceeds the first range exceeds a first threshold, and / or the number of times the change range of the accelerator pedal moving from the first position to the second position exceeds the first range exceeds a second threshold, the autonomous driving device may detect that there is a conflict between the driving behavior of the target vehicle controlled by the autonomous driving system and the driver's driving intentions.

[0130] In another example, as shown in Fig. 6b, the change range of the deceleration pedal corresponding to the target vehicle in the autonomous driving system is a second range. The second range may be preset based on requirements.

[0131] When the change range of the decelerator pedal moving from the third position to the fourth position exceeds the second range, and / or the period during which the change range of the decelerator pedal moving from the third position to the fourth position exceeds the second range exceeds a third threshold, and / or the number of times the change range of the decelerator pedal moving from the third position to the fourth position exceeds the second range exceeds a fourth threshold, the autonomous driving device may detect that there is a conflict between the driving behavior of the target vehicle controlled by the autonomous driving system and the driver's driving intentions.

[0132] In another example, as shown in Fig. 6c, the driving behavior of the target vehicle controlled by the autonomous driving system is the following driving behavior: the angle threshold for the target vehicle to turn in a first direction is a first angle. The first angle may be preset based on requirements.

[0133] When the angle α by which the steering wheel is rotated in the first direction is greater than the first angle, and / or the period during which the angle α by which the steering wheel is rotated in the first direction is greater than the first angle exceeds a fifth threshold, and / or the number of times that the angle α by which the steering wheel is rotated in the first direction is greater than the first angle exceeds a sixth threshold, the autonomous driving device may detect that there is a contradiction between the driving behavior of the target vehicle controlled by the autonomous driving system and the driver's driving intentions.

[0134] It should be noted that in the above three examples, the first threshold value to the sixth threshold value may be preset based on requirements.

[0135] Furthermore, in order to more accurately determine that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system, the automated driving device may determine a period during which the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system / a number of times of inconsistency. When the period of inconsistency is equal to or greater than a preset period / the number of times of inconsistency is equal to or greater than a preset number of times, the automated driving device may determine that the driver's driving intention is inconsistent with the driving behavior of the target vehicle controlled by the automated driving system. The preset period and the preset number of times may be preset. This is not limited. In the following, a method for the automated driving device to determine a period during which the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system and a number of times of inconsistency will be separately described in detail using an example in which the automated driving device determines the driver's driving intention based on the driver's visual behavior.

[0136] 1. The automated driving device determines the period of time when the driver's driving intentions and the driving behavior of the vehicle controlled by the automated driving system are in conflict.

[0137] The autonomous driving device may perform statistics on a period of time during which the driver's driving intention and the driving behavior of the vehicle controlled by the autonomous driving system are inconsistent. When the period of time of inconsistency is equal to or greater than a preset period of time, the autonomous driving device may determine that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system. When the period of inconsistency is less than a preset period of time, the autonomous driving device may determine that the driver's driving intention is consistent with the driving behavior of the vehicle controlled by the autonomous driving system.

[0138] In one example, a timer is provided in the autonomous driving device. When the autonomous driving device detects that the driver's driving intention is not consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the autonomous driving device triggers the timer to start timing. The steps performed by the autonomous driving device are as follows.

[0139] The autonomous driving device acquires the visual behavior of the driver and inputs the visual behavior into the above-mentioned driving intention model of the driver to acquire the driving intention of the driver.

[0140] When the automated driving device determines that the driver's driving intention is still not consistent with the driving behavior of the vehicle controlled by the automated driving system, the automated driving device may repeatedly execute the above steps until the driver's driving intention determined by the automated driving device based on the driver's visual behavior is consistent with the driving behavior of the vehicle controlled by the automated driving system. When the automated driving device determines that the driver's driving intention is consistent with the driving behavior of the vehicle controlled by the automated driving system, it triggers the timer to stop timing. The automated driving device determines a period during which the driver's driving intention and the driving behavior of the vehicle controlled by the automated driving system are inconsistent based on the timer's timing start and stop times.

[0141] For example, when the timer starts timing, the automatic driving device periodically or randomly acquires the visual behavior of the driver and determines the driving intention of the driver. This is not limited to the above.

[0142] Based on the above embodiment, when the period during which the driver's driving intention, determined by the autonomous driving device based on the driver's visual behavior, is inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system, is longer than a predetermined period, the autonomous driving device determines that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system.

[0143] In other possible implementation forms, when a feature parameter corresponding to the driver's visual behavior exceeds a preset range and / or a feature parameter corresponding to the physical posture behavior exceeds a preset range, the autonomous driving device may detect that the driving behavior of the target vehicle controlled by the autonomous driving system is inconsistent with the driver's driving intentions.

[0144] For example, a counter is provided in the automatic driving device. When the automatic driving device detects that the driver's driving intention is not consistent with the driving behavior of the vehicle controlled by the automatic driving system, the automatic driving device acquires a plurality of visual behaviors of the driver within a preset period of time, inputs the plurality of visual behaviors into the driving intention model, and acquires the driver's driving intention corresponding to each of the plurality of visual behaviors. The automatic driving device may separately compare whether the driver's driving intention corresponding to each of the plurality of visual behaviors is consistent with the driving behavior of the vehicle controlled by the automatic driving system.

[0145] When the driver's driving intention corresponding to a certain visual behavior is not consistent with the driving behavior of the vehicle controlled by the automated driving system, the counter records a first value, or when the driver's driving intention corresponding to a certain visual behavior is consistent with the driving behavior of the vehicle controlled by the automated driving system, the counter records a second value. When the quantity of the first value obtained by the statistics performed by the counter is equal to or greater than a preset value, the automated driving device may determine that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system. The preset period and the preset value are preset. This is not limited.

[0146] For example, at a first time point, the autonomous driving device determines that the driver's driving intention at the first time point is not consistent with the driving behavior of the vehicle controlled by the autonomous driving system. In this case, the autonomous driving device may obtain visual behaviors of the driver corresponding to N time points within a preset period after the first time point. For example, the visual behaviors are visual behavior 1, visual behavior 2, . . . visual behavior N, respectively, where N is a positive integer equal to or greater than 1, and the time intervals between the N time points may be the same or different. This is not limited.

[0147] The automated driving device may determine the driver's driving intention corresponding to each of the N visual behaviors based on the driver's driving intention model. For example, the driver's driving intentions determined by the automated driving device include driving intention 1, driving intention 2, . . . driving intention N, in which case the visual behaviors correspond one-to-one to the driving intentions. For example, visual behavior 1 corresponds to driving intention 1, visual behavior 2 corresponds to driving intention 2, and visual behavior N corresponds to driving intention 3. Driving Intention Corresponds to N.

[0148] The autonomous driving device separately compares whether the N driving intentions are consistent with the driving behavior of the vehicle controlled by the autonomous driving system. When the N driving intentions are not consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the counter may record a first value. For example, the first value is 1. When the N driving intentions are consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the counter may record a second value. For example, the second value may be 0. For example, the autonomous driving device compares whether driving intention 1 is consistent with the driving behavior of the vehicle controlled by the autonomous driving system. When driving intention 1 is not consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the counter may record 1. When driving intention 1 is consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the counter may record 0. The autonomous driving device compares whether driving intention 2 is consistent with the driving behavior of the vehicle controlled by the autonomous driving system. When driving intention 2 is not consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the counter may add 1 based on 1. In other words, the counter may record 2. This process continues until the automated driving device completes the comparison of the N driving intentions with the driving behavior of the vehicle controlled by the automated driving system.

[0149] In yet another possible implementation form, when the autonomous driving device detects that the driver's driving intention is not consistent with the driving behavior of the vehicle controlled by the autonomous driving system, the autonomous driving device obtains the driver's visual behavior, inputs the visual behavior into the above driving intention model to obtain the driver's driving intention corresponding to the visual behavior, and compares whether the driver's driving intention corresponding to the visual behavior is consistent with the driving behavior of the vehicle controlled by the autonomous driving system.

[0150] The counter may record a first value when the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system, or the counter may record a second value when the driver's driving intention is consistent with the driving behavior of the vehicle controlled by the autonomous driving system.

[0151] It should be noted that the autonomous driving device may cyclically perform steps 3 to 4 above during a preset period of time, and then determine the number of times during the preset period that the driver's driving intentions are inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system.

[0152] For example, at a first time point, the automated driving device determines that the driver's driving intention at the first time point is not consistent with the driving behavior of the vehicle controlled by the automated driving system. In this case, the automated driving device may determine whether the driver's driving intention corresponding to the driver's visual behavior 2 at a second time point after the first time point is consistent with the driving behavior of the vehicle controlled by the automated driving system based on step 3 and step 4. When the driver's driving intention is not consistent with the driving behavior of the vehicle controlled by the automated driving system, the counter records 1. Or, when the driver's driving intention is consistent with the driving behavior of the vehicle controlled by the automated driving system, the counter does not count and records 0. In this way, the automated driving device performs the above steps. 3and repeatedly performing step 4 to determine the number of times during a preset period that the driver's driving intention is inconsistent with the driving behavior of the vehicle controlled by the automated driving system.

[0153] In yet another possible implementation form, when the driver's emotional behavior is a negative emotional behavior, the automated driving device may determine that the driver's driving intention is not satisfied with the driving behavior of the target vehicle controlled by the automated driving system. In other words, the automated driving device may detect that there is a contradiction between the driving behavior of the target vehicle controlled by the automated driving system and the driver's driving intention.

[0154] Step 503: The autonomous driving device updates the autonomous driving system.

[0155] The driving behavior of the target vehicle controlled by the updated autonomous driving system matches the driver's driving intention.

[0156] In a possible implementation form, the autonomous driving device may acquire a first feature parameter based on driving data corresponding to the driver's driving intention and the driving behavior of a target vehicle controlled by the autonomous driving system, the autonomous driving device inputs the first feature parameter into a pre-configured neural network model to acquire the first driving behavior, and the autonomous driving device updates the autonomous driving system based on the first driving behavior.

[0157] The first feature parameter represents driving data corresponding to the driver's driving intention and the driving behavior of the target vehicle controlled by the automated driving system.

[0158] For example, the first feature parameter may be a feature vector. The feature vector may include a plurality of parameters, and each of the plurality of parameters may be used to represent one driving data. For example, the first feature parameter may include a distance between the target vehicle and another vehicle, a vehicle speed of the target vehicle, a driving direction, a steering angle, etc.

[0159] The pre-defined neural network model is used to determine a driving behavior that is consistent with the driver's driving intention. The pre-defined neural network model may be pre-defined. For example, the pre-defined neural network model may be a deep feedforward neural network regression model.

[0160] For example, the preset neural network model is obtained by training based on a plurality of historical driving data of the driver. The input of the preset neural network model is a feature parameter, and the output is a first driving behavior that matches the driving intention of the driver. In other words, the first driving behavior is a driving behavior that matches the driving intention of the driver. The first driving behavior may include one or more driving data. For example, the one or more driving data may include the vehicle speed of the vehicle, the distance from the preceding vehicle, etc. For the training method of the preset neural network model, please refer to the current technology. Details will not be repeated in this specification.

[0161] In this embodiment of the present application, the autonomous driving device may input the above feature parameters in the form of a feature vector into a pre-configured neural network model to obtain an output vector corresponding to the feature vector. The output vector may include one or more parameters, and each of the one or more parameters corresponds to one driving behavior.

[0162] The autonomous driving device updating the autonomous driving system based on the first driving behavior means that the autonomous driving device compares the first driving behavior with the driving behavior of the vehicle controlled by the autonomous driving system and updates the autonomous driving system based on the comparison result. For example, the autonomous driving device may replace the driving behavior of the vehicle controlled by the autonomous driving system with the first driving behavior.

[0163] For example, a first driving behavior determined by the automated driving device is to increase the vehicle speed of the target vehicle to a first vehicle speed. A driving behavior of the target vehicle controlled by the automated driving system is to maintain the vehicle speed of the target vehicle as a second vehicle speed. The first vehicle speed is greater than the second vehicle speed. The automated driving device may replace the vehicle speed of the target vehicle controlled by the automated driving system with the first vehicle speed, so that the vehicle speed of the target vehicle controlled by the automated driving system becomes the first vehicle speed.

[0164] In this embodiment of the present application, in the automatic driving process of the target vehicle, the automatic driving device may cyclically execute the above steps 501 to 503 until the target vehicle stops driving. The target vehicle stops driving in the following cases, that is, when the driver controls the target vehicle to stop driving, or when the automatic driving system of the target vehicle is disabled by the driver and, for example, replaced by manual driving by the driver.

[0165] Based on the technical solution of Figure 5, when the automatic driving device detects that the driving intention of the driver of the automatic driving vehicle controlled by the automatic driving system is inconsistent with the driving behavior of the vehicle controlled by the automatic driving system, the automatic driving device updates the automatic driving system, so that the driving behavior of the vehicle controlled by the automatic driving system after the update is consistent with the driving intention of the driver. On this basis, the subsequent driving behavior controlled by the automatic driving system after the update can meet the driving requirements of the driver. In this way, the problem that the driving behavior of the vehicle controlled by the automatic driving system is inconsistent with the driving intention of the driver is solved.

[0166] In a possible implementation form of the method shown in FIG. 5, the method provided in this embodiment of the present application may further include the following: the autonomous driving device detects whether the driver of the target vehicle is a new driver.

[0167] A new driver means someone who has never driven the target vehicle.

[0168] In one example, when the automated driving device detects that the target vehicle has started, the automated driving device obtains driver characteristic information and compares the driver characteristic information with the characteristic information of a plurality of drivers stored in the automated driving device. When the driver characteristic information does not match the characteristic information of each of the plurality of drivers, the automated driving device determines that the driver of the target vehicle is a new driver, or when the driver characteristic information matches the characteristic information of each of the plurality of drivers, the automated driving device determines that the driver of the target vehicle is a driver who has driven the target vehicle before.

[0169] In another possible implementation form of the method shown in FIG. 5 according to the method provided in this embodiment of the present application, the autonomous driving device may further determine a driving mode of the target vehicle to be controlled by the autonomous driving system based on characteristic information of the driver of the target vehicle.

[0170] When the driver of the target vehicle is not a new driver, the automatic driving device determines the automatic driving mode of the target vehicle based on the driver's characteristic information. In other words, when the driver of the target vehicle is a driver who has driven the target vehicle before, the automatic driving device may determine the automatic driving mode of the target vehicle based on the driver's characteristic information.

[0171] For example, the autonomous driving device may obtain an autonomous driving mode that has been used by a driver from the V2X server shown in FIG. 4, and use the autonomous driving mode that has been used as the autonomous driving mode of the target vehicle.

[0172] Alternatively, the automatic driving device may store an automatic driving mode that has been used by the driver in the past. The automatic driving device may use the stored automatic driving mode that has been used by the driver as the automatic driving mode of the target vehicle. This is not limited to the above.

[0173] When the driver of the target vehicle is a new driver, the automatic driving device may use a preset automatic driving mode as the automatic driving mode of the target vehicle. The preset automatic driving mode may be preset in the automatic driving device. Alternatively, the automatic driving device may obtain the preset automatic driving mode from automatic driving modes used by multiple drivers in the past and stored in the V2X server. This is not limited. For example, the automatic driving device may select the most frequently used automatic driving mode as the preset automatic driving mode from the automatic driving modes used by multiple drivers in the past.

[0174] In yet another possible implementation form of the method shown in FIG. 5, the method provided in this embodiment of the present application may further include the following: the autonomous driving device acquiring the driving behavior of a target vehicle controlled by the autonomous driving system.

[0175] In different driving scenarios, the target vehicle has different driving behaviors under the control of the automated driving system. Specifically, the driving scenarios and the corresponding driving behaviors of the target vehicle controlled by the automated driving system can be shown in Table 1. Details will not be repeated.

[0176] A first driving scenario as an example. The autonomous driving device may obtain a driving intention of a driver in the first driving scenario and a driving behavior of a target vehicle controlled by an autonomous control system corresponding to the first driving scenario. When the autonomous driving device detects that a contradiction exists between the driving intention of the driver in the first scenario and the driving behavior of the target vehicle controlled by the autonomous control system, the autonomous driving device may update the autonomous driving system.

[0177] It should be noted that in this embodiment of the present application, after the autonomous driving device determines that the driving behavior of the target vehicle in the first scenario is inconsistent with the driver's driving intention, in the driving process of the target vehicle, the autonomous driving device may exist in the autonomous driving system and update the driving behavior corresponding to the first driving scenario. Alternatively, after the target vehicle stops driving, the autonomous driving device may exist in the autonomous driving system and update the autonomous driving behavior corresponding to the first driving scenario. For example, after the target vehicle arrives at the destination, the autonomous driving device may exist in the autonomous driving system and update the autonomous driving behavior corresponding to the first driving scenario. This is not limited.

[0178] For example, in the process of the target vehicle autonomously driving, the automatic driving device may record the driver's driving intention and multiple driving scenarios that are inconsistent with the driver's driving intention. For example, the driving scenarios recorded by the automatic driving device include driving scenario 1 and driving scenario 2. Driving scenario 1 and driving scenario 2 are driving scenarios in which the driving behavior of the vehicle controlled by the automatic driving system is inconsistent with the driver's driving intention. After the vehicle ends the automatic driving, the automatic driving device may update the driving behavior of the vehicle controlled by the automatic driving system corresponding to driving scenario 1, and update the driving behavior of the vehicle controlled by the automatic driving system corresponding to driving scenario 2.

[0179] For example, the autonomous driving device may acquire the first driving scenario of the target vehicle in a plurality of ways. For example, the plurality of ways may include the following, that is, the autonomous driving device acquires the first driving scenario of the target vehicle by using a device of the target vehicle. For example, the autonomous driving device may acquire the first driving scenario of the target vehicle by using a plurality of types of sensors. The autonomous driving device acquires the first driving scenario of the target vehicle through interaction with other devices. For example, the autonomous driving device may acquire the first driving scenario of the target vehicle through interaction with a V2X server, or the autonomous driving device may acquire the first driving scenario of the target vehicle through interaction with an autonomous driving device of another vehicle. Alternatively, the autonomous driving device may acquire the first driving scenario of the target vehicle in one or more of the above plurality of ways. This is not limited. The above plurality of ways will be described below.

[0180] 1. The autonomous driving device may obtain a first driving scenario of a target vehicle by using multiple types of sensors.

[0181] The autonomous driving device may collect traffic information of the roads on which the target vehicle travels by using multiple sensors, and integrate the collected traffic information of the roads on which the target vehicle travels to obtain a first driving scenario for the target vehicle.

[0182] In this embodiment of the present application, the multiple sensors may include, but are not limited to, a laser radar, a millimeter wave radar, an ultrasonic radar, a monocular or binocular camera, etc.

[0183] For example, the autonomous driving device may obtain the vehicle speeds of vehicles around the target vehicle, the speeds of pedestrians, etc., by using a laser radar. The autonomous driving device may obtain road condition information of the road on which the target vehicle is traveling, the number of vehicles, the number of pedestrians, etc., by using a monocular or binocular camera. This is not limited to the above.

[0184] 2. The autonomous driving device may obtain a first driving scenario of the target vehicle through interaction with the V2X server.

[0185] The autonomous driving device may transmit request information to the V2X server for use in requesting the first driving scenario. In response, the V2X server receives request information from the autonomous driving device for use in requesting the first driving scenario. The V2X server determines the first driving scenario based on the request information and transmits the first driving scenario to the autonomous driving device.

[0186] For example, the autonomous driving device may send coordinate information (e.g., global positioning system (GPS) coordinates) of the target vehicle to the V2X server by using the vehicle body antenna in FIG. 2. After receiving the coordinate information of the target vehicle, the V2X server determines a driving scenario corresponding to the coordinate information based on the coordinate information. The V2X server sends a first driving scenario corresponding to the coordinate information to the autonomous driving device. In response, the autonomous driving device may receive the first driving scenario corresponding to the coordinate information by using the vehicle body antenna.

[0187] 3. The autonomous driving device may obtain a first driving scenario for the target vehicle through interactions with other vehicles.

[0188] For example, for this method, please refer to the method in which the autonomous driving device interacts with the V2X server to obtain the first driving scenario of the target vehicle, and the details will not be described repeatedly in this specification.

[0189] For example, after acquiring a first driving scenario, the autonomous driving device may acquire behavior characteristics of the driver in the first driving scenario and determine the driver's driving intention based on the behavior characteristics of the driver.

[0190] The driver's behavior characteristics may be used to indicate whether the driver is satisfied with the driving behavior of the target vehicle controlled by the automated driving system. For example, the driver's behavior characteristics may include the driver's operation characteristics, visual behavior, emotional behavior, physical posture behavior, etc. In this case, the automated driving device may determine the driver's driving intention based on one or more of these behavior characteristics. Specifically, for related descriptions of the driver's behavior characteristics and the implementation form in which the in-vehicle device determines the driver's driving intention based on the driver's behavior characteristics, please refer to the technical solution shown in FIG. 5.

[0191] In this possible implementation, when the autonomous driving device detects that the driving intention of the driver of the vehicle in the first driving scenario is inconsistent with the driving behavior of the vehicle controlled by the autonomous driving system, the autonomous driving device may adjust the driving behavior corresponding to the autonomous driving system to a driving behavior that matches the driving intention of the driver in the first driving scenario, so that when the autonomous driving device subsequently faces the same type of driving scenario, the driving behavior of the vehicle controlled by the autonomous driving system can meet the driver's requirements. In this way, the problem of the driving behavior of the vehicle controlled by the autonomous driving system being inconsistent with the driving intention of the driver is solved.

[0192] In yet another possible implementation form of the method shown in FIG. 5, the method provided in this embodiment of the present application may further include the following: the autonomous driving device determining an autonomous driving mode of the target vehicle in the first driving scenario.

[0193] For the relevant description of the automatic driving mode, please refer to the above description, and the details will not be repeated.

[0194] The automatic driving device determining the automatic driving mode of the target vehicle in the first driving scenario may include the following, that is, the automatic driving device performs automatic selection or the driver performs manual selection. When the automatic driving device performs automatic selection, for example, the automatic driving device automatically selects the automatic driving mode of the target vehicle from a plurality of pre-set automatic driving modes based on certain relevant information of the first driving scenario. When the driver performs manual selection, for example, when the driver expects automatic driving, the driver manually selects an appropriate automatic driving mode and triggers the automatic driving device to perform automatic driving based on the automatic driving mode selected by the driver. Specifically, for this method, please refer to Method 1 or Method 2 below.

[0195] Method 1: The automatic driving device performs automatic selection.

[0196] The autonomous driving device may select an autonomous driving mode from one or more autonomous driving modes based on the characteristic information of the driver. The characteristic information of one driver is used to uniquely identify the driver. The one or more autonomous driving modes may be autonomous driving modes stored in the autonomous driving device or may be autonomous driving modes obtained by the autonomous driving device from the V2X server in FIG. 2.

[0197] For example, the automatic driving device may acquire image information of the driver by using a photographing device, and the image information may be video information or picture information. The image information may include the driver's facial features or eye features. The automatic driving device may determine the driver's feature information by recognizing the driver's image information. Alternatively, the automatic driving device may send the driver's image information to the V2X server, so that the V2X server recognizes the driver's image information and acquires the driver's feature information.

[0198] For example, the automatic driving device may compare the driver's characteristic information with characteristic information of a plurality of drivers stored in the automatic driving device, and determine an automatic driving mode that matches the driver's characteristic information. Each of the characteristic information of the plurality of drivers has a corresponding automatic driving mode. For example, the automatic driving device may use an automatic driving mode that is included in the characteristic information of the plurality of drivers and corresponds to the characteristic information of a driver whose similarity to the characteristic information of the driver of the target vehicle is greater than a preset value, as the automatic driving mode of the driver of the target vehicle. The preset value may be preset by the automatic driving device. This is not limited.

[0199] In another example, the automatic driving device may alternatively send the acquired characteristic information of the driver to the V2X server. After receiving the driver's characteristic information, the V2X server may match the driver's characteristic information with the driver's characteristic information corresponding to one or more automatic driving modes, and select and determine an automatic driving mode that matches the driver's characteristic information from the one or more automatic driving modes. After determining the automatic driving mode that matches the driver's characteristic information, the V2X server may send the automatic driving mode that matches the driver's characteristic information to the automatic driving device. Accordingly, after receiving the automatic driving mode that matches the driver's characteristic information from the V2X server, the automatic driving device controls the target vehicle to perform automatic driving based on the automatic driving mode that matches the driver's characteristic information. For specific details, please refer to the above description of the manner in which the automatic driving device determines the automatic driving mode of the driver of the target vehicle. Details will not be repeated.

[0200] Method 2: The driver performs a manual selection.

[0201] In method 2, in a possible design, the autonomous driving mode may be an autonomous driving mode that is manually selected by the driver after the vehicle is started. For example, a display device may be arranged in the target vehicle. When the autonomous driving device detects that the target vehicle is started, the display device may trigger the display device to display the display interface shown in FIG. 8. The driver may select the autonomous driving mode on the display interface based on the requirements. After detecting an operation instruction from the driver, the autonomous driving device may determine an autonomous driving mode corresponding to the operation instruction based on the operation instruction from the driver.

[0202] For example, the display interface in FIG. 8 may include multiple touch buttons "Mode 1" to "Mode 6". Each touch button corresponds to one type of autonomous driving mode. When the driver taps a touch button, the autonomous driving device may be triggered to obtain the autonomous driving mode corresponding to the touch button. For example, when the driver taps the touch button "Mode 5", the autonomous driving device may be triggered to obtain the autonomous driving mode corresponding to the touch button "Mode 5".

[0203] In another possible design of the method 2, the driver may manually select the autonomous driving mode by using the terminal corresponding to the target vehicle, and trigger the terminal corresponding to the target vehicle to notify the autonomous driving device of the selected autonomous driving mode. The autonomous driving device determines the autonomous driving mode of the target vehicle in the first driving scenario based on the notification from the terminal.

[0204] The terminal corresponding to the automatic driving device may include any device for controlling the target vehicle, such as, but not limited to, a smartphone, a removable hard disk, a personal notebook computer, or a tablet computer.

[0205] For example, the terminal is a smartphone. The driver sends the autonomous driving mode stored in the terminal such as a mobile phone to the autonomous driving device in a wired manner, or in a wireless manner by using the mobile phone. For example, in the wired manner, the autonomous driving device may be connected via a universal serial bus (USB), Type-C, or the like. In the wireless manner, the autonomous driving device may be connected via Bluetooth, wireless fidelity (Wi-Fi), or the like. This is not limited. In response, the autonomous driving device may receive the autonomous driving mode from the smartphone.

[0206] In yet another possible implementation form shown in FIG. 5, before step 503, the method provided in this embodiment of the present application may further include the following steps:

[0207] S1: The autonomous driving device determines a first feature parameter based on the driver's driving intention and the driving behavior of the vehicle controlled by the autonomous driving system.

[0208] The first feature parameter may be a feature vector. In the following, using an example in which the first feature parameter is a feature vector, the feature vector determined by the automatic driving device based on the driver's driving intention and the driving behavior of the vehicle controlled by the automatic driving system is separately described when the driving scenario is a scenario of following a vehicle in the direction of traffic in urban rush hour, a scenario of following a vehicle in the direction of traffic in urban rush hour, and a scenario of a vehicle actively cutting in during urban rush hour.

[0209] It should be noted that after determining the driver's driving intention, the automatic driving device may determine feature parameters corresponding to the driving scenario by using numbers or letters to represent the driver's driving intention and vehicle information.

[0210] For example, v+ indicates that the driver's intention is to increase the vehicle speed, v- indicates that the driver's intention is to decrease the vehicle speed, s indicates that the driver's intention is to stop, s indicates that the driver's intention is to approach the left lane, r indicates that the driver's intention is to approach the right lane, l+v indicates that the driver's intention is to increase the vehicle speed when approaching the left lane, lv indicates that the driver's intention is to decrease the vehicle speed when approaching the left lane, etc. The driver's intention may also be expressed in other ways. This is not limited.

[0211] In other examples, the vehicle type may be represented by a number or a letter. For example, a number may be used to indicate the vehicle type. A "1" may indicate that the vehicle type is a car, a "2" may indicate that the vehicle type is a truck, and a "3" may indicate that the vehicle type is a bus. This is not limiting.

[0212] Driving Scenario 1: The driving scenario is following a vehicle in the direction of traffic during rush hour in a city.

[0213] When a vehicle follows a vehicle in the direction of traffic, the driving parameters of the target vehicle are related to the vehicle information of the preceding vehicle. Therefore, the automatic driving device may create a feature vector based on the vehicle information of the target vehicle and the vehicle information of the preceding vehicle. For example, the feature vector determined by the automatic driving device may be the following vector: f={v+,d f ,v f ,v e ,s f ,l}

[0214] In this vector, d f represents the distance between the target vehicle and the preceding vehicle, and v f represents the speed of the leading vehicle, and v e represents the speed of the target vehicle, and sf represents the size of the leading vehicle, and i f represents the type of vehicle of the preceding vehicle. Each vehicle in the feature vector may include multiple dimensions. For example, the size of the vehicle may include three dimensions: vehicle length, vehicle width, and vehicle height. The vehicle type may include car, truck, bus, etc.

[0215] Driving Scenario 2: The driving scenario is to maintain driving in a lane in the direction of traffic during rush hour in a city.

[0216] When the target vehicle performs lane keeping, the driving parameters of the target vehicle are related to the vehicle information of the preceding vehicle, the vehicle information of the left vehicle, and the vehicle information of the right vehicle. Therefore, the automatic driving device may create a feature vector based on the vehicle information of the target vehicle, the vehicle information of the preceding vehicle, the vehicle information of the left vehicle, and the vehicle information of the right vehicle. For example, the feature vector determined by the vehicle device is a vector as follows: f={v-,d f ,v f ,v e ,s f ,i f ,i l ,s l ,v lv ,v ll ,d l ,i r ,s r ,v rv ,v rl ,d r}

[0217] d f , v f , v e , s f , i f For details, please refer to the description of Driving Scenario 1. Details will not be repeated in this specification.

[0218] In this vector, i l indicates the type of the left vehicle, and s l indicates the size of the left vehicle, and vlv indicates the lateral speed of the left vehicle, and v ll indicates the longitudinal speed of the left vehicle, and d l indicates the lateral relative distance between the left vehicle and the target vehicle. The lateral relative distance refers to the horizontal distance between the two vehicles.

[0219] In this vector, i r indicates the type of the right vehicle, and s r indicates the size of the right vehicle, and v rv indicates the lateral speed of the right vehicle, and v rl indicates the longitudinal speed of the right vehicle, and d r indicates the relative lateral distance between the right vehicle and the target vehicle.

[0220] Furthermore, when there is no vehicle in front of the target vehicle and no vehicles on the left or right side, the autonomous driving device may perform auxiliary processing on the feature vector according to the following criteria so that the dimensions of the feature vectors in all driving scenarios of each main task are equal. A preset value is assigned to the parameter in the feature vector so that the feature vector acquired after the assignment does not affect the driving of the target vehicle. For example, when there is no vehicle ahead of the target vehicle, the following settings may be used.

[0221] The type of the leading vehicle is a bicycle, the size of the leading vehicle is small enough, e.g., {0,0,0}, the distance between the leading vehicle and the target vehicle is a large value, e.g., 3000 m, and the speed of the leading vehicle is a large value, e.g., 800 km / h.

[0222] For a method in which the automatic driving device performs auxiliary processing on a parameter in a feature vector when there is no vehicle on the left side of the target vehicle and no vehicle on the right side of the target vehicle, please refer to the above method in which the automatic driving device performs auxiliary processing on that parameter in a feature vector when there is no vehicle in front of the target vehicle, and the details will not be described repeatedly in this specification.

[0223] Driving Scenario 3: The driving scenario is a vehicle actively cutting in during urban rush hour.

[0224] When a vehicle actively cuts in, the driving parameters of the target vehicle are related to the vehicle information of the cut-in vehicle. Therefore, the automatic driving device may create a feature vector based on the vehicle information of the target vehicle and the vehicle information of the cut-in vehicle. For example, the feature vector determined by the automatic driving device is a vector as follows: f={lv,d l ,d v ,v ev ,v el ,v l ,i,s}

[0225] In this vector, d l denotes the longitudinal distance between the target vehicle and the vehicle being cut in, and d v denotes the lateral distance between the target vehicle and the vehicle being cut in, and v ev indicates the cut-in speed of the target vehicle, and v el denotes the longitudinal speed of the target vehicle when it cuts in, and v i denotes the longitudinal speed of the cut-in vehicle, i denotes the type of the cut-in vehicle, and s denotes the size of the cut-in vehicle.

[0226] S2: The autonomous driving device inputs the characteristic parameters into a pre-configured neural network model to obtain a first driving behavior.

[0227] The preset neural network model is obtained through training based on the driver's historical driving data in a plurality of driving scenarios. The input of the preset neural network model is the feature parameters, and the output is a first driving behavior that matches the driver's driving intention. In other words, the first driving behavior is a driving behavior that matches the driver's driving intention. The first driving behavior may include one or more driving data. For example, the one or more driving data may include the vehicle's speed, the distance from a leading vehicle, etc.

[0228] The pre-configured neural network model may be pre-configured, for example, the pre-configured neural network model may be a deep feed-forward neural network regression model.

[0229] The pre-defined neural network model may be obtained through training based on a plurality of sample feature parameters, and one sample feature parameter corresponds to the driving behavior of the driver. For the method of training the pre-defined neural network model, please refer to the current technology. Details will not be described repeatedly in this specification.

[0230] It should be understood that in this embodiment of the present application, the autonomous driving device inputs the above feature parameters into a pre-configured neural network model in the form of a feature vector, and obtains an output vector corresponding to the feature vector. The output vector may include one or more parameters, and each of the one or more parameters corresponds to one driving behavior.

[0231] For example, when the driving scenario is to follow a vehicle in the direction of traffic during rush hour in a city, the feature vector corresponding to the feature parameters is f={w, d f ,v f ,v e ,s f ,i f}={v-,5,40,50,(4.6,1.7,1.4),1}. In other words, the driver's driving intention is to reduce the speed of the vehicle, the distance between the target vehicle and the preceding vehicle is 5m, the vehicle speed of the vehicle preceding the target vehicle is 40km / h, the vehicle speed of the target vehicle is 50km / h, the length, width, and height of the preceding vehicle are 4.6m, 1.7m, and 1.4m, respectively, and the type of the preceding vehicle is an automobile. The automatic driving device inputs the feature vector into a pre-set neural network model to obtain an output vector {40,0,0,0}. In this vector, 40 indicates that the vehicle speed of the target vehicle is 40km / h, and the last three 0s indicate that the target vehicle will not slow down, will not stop, and will not exit the following mode, respectively. In other words, the first driving behavior is to control the vehicle speed of the target vehicle to be 40km / h.

[0232] S3: The automated driving device presents one or more questions to the driver and receives the driver's answers to the one or more questions. The answers to the one or more questions may be used to indicate whether to update the automated driving system.

[0233] For example, the autonomous driving device may select one or more questions from a pre-defined question library based on the first driving behavior and the first driving scenario, and may play the one or more questions via an audio player or display the one or more questions on a display device.

[0234] The preset question library is determined based on the driving behaviors of multiple drivers within a preset period. The implementation process of this embodiment may be as follows.

[0235] 1. The autonomous driving device compares the driving behavior of the vehicle controlled by the autonomous driving system with a first driving behavior to determine whether the driving behavior of the vehicle controlled by the autonomous driving system is consistent / the same as the first driving behavior. For example, when the difference between the driving behavior of the vehicle controlled by the autonomous driving system and the first driving behavior meets a preset condition / does not exceed a preset range, the autonomous driving device determines that the driving behavior of the vehicle controlled by the autonomous driving system is consistent / the same as the first driving behavior, or when the difference between the driving behavior of the vehicle controlled by the autonomous driving system and the first driving behavior does not meet a preset condition / exceeds a preset range, the autonomous driving device determines that the driving behavior of the vehicle controlled by the autonomous driving system is inconsistent / different from the first driving behavior.

[0236] For example, in a first driving scenario, when a target vehicle overtakes this vehicle, the driving behavior of the vehicle controlled by the automated driving system is to increase the vehicle speed of the target vehicle to 80 km / h. The first driving behavior is to increase the vehicle speed of the target vehicle to 81 km / h, and the preset range is {-2 km / h, 2 km / h}. Since 80 km / h-81 km / h=-1 km / h, that is, the difference between the vehicle speed of the vehicle controlled by the automated driving system and the vehicle speed corresponding to the first driving behavior is within the preset range, the automated driving device determines that the driving behavior of the vehicle controlled by the automated driving system is consistent / the same as the first driving behavior.

[0237] In another example, in a first driving scenario, when a target vehicle follows a vehicle, the driving behavior of the vehicle controlled by the automated driving system is to control the distance between the target vehicle and the leading vehicle to be 10 m. The first driving behavior is to control the distance between the target vehicle and the leading vehicle to be 15 m. The preset condition is to control the distance between the target vehicle and the leading vehicle not to exceed 12 m. Since 15 m is greater than 12 m, i.e., the first driving behavior does not satisfy the preset condition, the automated driving device determines that the driving behavior of the vehicle controlled by the automated driving system is inconsistent / different from the first driving behavior.

[0238] When the driving behavior of the vehicle controlled by the automated driving system is consistent / the same as the first driving behavior, the automated driving device may determine that the driving behavior of the vehicle controlled by the automated driving system is consistent with the driver's driving intention. Alternatively, when the driving behavior of the vehicle controlled by the automated driving system is inconsistent / different from the first driving behavior, the automated driving device may compare the driving behavior of the vehicle controlled by the automated driving system with the first driving behavior to determine driving data included in the plurality of driving data of the driving behavior of the vehicle controlled by the automated driving system and inconsistent with the driving data of the first driving behavior, and determine change information for the inconsistent driving data.

[0239] 2. The automatic driving device compares the inconsistent / different driving data and the change information of the inconsistent / different driving data with a pre-set question library, and determines questions corresponding to the inconsistent / different driving data.

[0240] 3. The automatic driving device plays the question corresponding to the inconsistent driving data in a voice format or displays the question corresponding to the inconsistent driving data on a display device. The automatic driving device receives the driver's voice by using a microphone, recognizes the driver's voice, and determines the driver's answer to the one or more questions. The driver's voice is the driver's answer to the question corresponding to the inconsistent driving data.

[0241] It should be noted that when the automated driving device does not receive the driver's voice within a preset period of time, the automated driving device may replay the question corresponding to the inconsistent driving data, or the automated driving device may use a preset answer as the driver's answer. The preset period may be preset by the automated driving device. This is not limited. For example, the preset period is 10s. When the automated driving device does not receive the driver's voice within 10s, the preset answer present in the automated driving device is an affirmative answer. For example, the affirmative answer may be "yes".

[0242] 4. When instructed to update the automated driving system with answers to one or more questions, the automated driving device may update the automated driving system.

[0243] For example, when the answer to one or more questions is “yes,” the answer to the one or more questions may be used to instruct the automated driving system to be updated.

[0244] In this embodiment of the present application, in order to reduce the complexity of determining the driver's driving intention, the questions in the question library may be set to simple and direct questions. For example, the questions may be set to definitive questions. Accordingly, the answers given by the driver may be "yes" or "no".

[0245] In one example, when the driving scenario is to follow a vehicle in the direction of traffic in rush hour in a city, the corresponding question library may be the library shown in Table 2.

[0246] [Table 2]

[0247] It should be noted that when the question played by the automated driving device based on the questions in Table 2 is question 1, when the driver's answer received by the automated driving device is "yes", the automated driving device determines that the driver's driving intention is to increase the vehicle's speed.

[0248] In the following, the process of the above implementation is described with reference to the problem in Table 2 and the feature and output vectors in the above example.

[0249] 1. The autonomous driving device compares the driving behavior of a vehicle controlled by the autonomous driving system (the target vehicle's speed is 50 km / h) with a first driving behavior (the target vehicle's speed is 40 km / h), and determines that the driving data in which the driving behavior of the vehicle controlled by the autonomous driving system is inconsistent with the first driving behavior is the target vehicle's speed, and that the change information for the target vehicle's speed is to reduce the vehicle speed from 50 km / h to 40 km / h.

[0250] 2. The automated driving device compares the target vehicle's speed and speed change information with the questions in Table 2, and determines that the question corresponding to the target vehicle's speed is question 2 in Table 2.

[0251] 3. The automatic driving device plays back question 2 in Table 2 in audio form. The automatic driving device receives the driver's voice by using a microphone, recognizes the driver's voice, and determines the driver's answer.

[0252] If the automated driving device determines, based on the recognized voice, that the driver's response is "yes," the automated driving device may determine that the driver's driving intent is to reduce the vehicle speed of the target vehicle.

[0253] 4. If the autonomous driving device determines that the driver's answer is "yes," it reduces the target vehicle's speed to 40 km / h and updates the vehicle speed in the driving behavior of the vehicle controlled by the autonomous driving system to 40 km / h.

[0254] If the automated driving device determines, based on the recognized voice, that the driver's answer is "no," the automated driving device may determine that the driver's driving intention is not to reduce the vehicle speed of the target vehicle.

[0255] When the driver's answer is "No", the automated driving device may further continue to play question 1 in Table 2. When the automated driving device determines that the driver's answer corresponding to question 1 in Table 2 is "No", the automated driving device does not update the driving behavior of the vehicle controlled by the automated driving system.

[0256] In another example, when the driving scenario is to maintain driving in a certain lane in the direction of traffic during urban rush hour, the corresponding question library may be the library shown in Table 3.

[0257] [Table 3]

[0258] In yet another example, when the driving scenario is that a vehicle traveling in the direction of traffic actively cuts in during urban rush hour, the corresponding question library may be the library shown in Table 4.

[0259] [Table 4]

[0260] Please refer to Table 2 above for the process by which the autonomous driving device updates the driving behavior of the vehicle controlled by the autonomous driving system based on the questions in Table 3 and Table 4. Details will not be repeated in this specification. The questions in Table 2, Table 3, and Table 4 are only examples, and each table may further include other questions. This is not limited.

[0261] In addition, after the automatic driving device determines the first driving behavior, the automatic driving device may further detect whether the first driving behavior is included in a preset driving behavior. The preset driving behavior may be a behavior that matches the safe driving behavior of the target vehicle.

[0262] When the first driving behavior matches the safe driving behavior of the target vehicle, the autonomous driving device may use the first driving behavior as the driving behavior of the target vehicle controlled by the updated autonomous driving system, or when the first driving behavior does not match the safe driving behavior of the target vehicle, the autonomous driving device may use the safe driving behavior as the driving behavior of the target vehicle controlled by the updated autonomous driving system.

[0263] For example, the autonomous driving device determines that the first driving behavior is to increase the vehicle speed of the target vehicle to 80 km / h. However, when the maximum vehicle speed of the vehicle is limited to 60 km / h on the road on which the target vehicle travels, the autonomous driving device detects that the first driving behavior does not match the safe driving behavior of the target vehicle. In this case, the autonomous driving device may use the vehicle speed of 60 km / h as the vehicle speed of the vehicle controlled by the autonomous driving system after the update. In other words, in the subsequent autonomous driving process of the target vehicle, the vehicle speed of the target vehicle controlled by the autonomous driving system is 60 km / h.

[0264] Additionally, the automated driving system may send prompt information, where the prompt information is used to inform the driver that the target vehicle is about to accelerate.

[0265] Furthermore, the method provided in this embodiment of the present application may further include: the autonomous driving device determines characteristic information of a driver of the target vehicle in a second driving scenario. When the first driving scenario matches the second driving scenario and the characteristic information of the driver in the first driving scenario is consistent with the characteristic information of the driver in the second driving scenario, the autonomous driving device determines that the driving behavior of the target vehicle in the second driving scenario is the driving behavior in the updated autonomous driving system.

[0266] The autonomous driving mode used by the target vehicle in the second driving scenario is the updated autonomous driving mode.

[0267] The first driving scenario matching the second driving scenario means that the similarity between the first driving scenario and the second driving scenario is equal to or greater than a preset value. The driver characteristic information in the first driving scenario is consistent with the driver characteristic information in the second driving scenario means that the driver of the target vehicle in the first driving scenario and the driver of the target vehicle in the second driving scenario are the same driver.

[0268] Based on this possible implementation, the autonomous driving device may control the driving of the target vehicle based on the updated driving behavior in the autonomous driving system when subsequently facing the same or similar driving scenario, thereby solving the problem that the driving behavior of the vehicle controlled by the autonomous driving system still contradicts the driving intention of the driver in the same or similar driving scenario as the first driving scenario.

[0269] In the following, the method shown in FIG. 5 will be described in detail with reference to the communication system shown in FIG.

[0270] 9 illustrates another method for adaptively optimizing an autonomous driving system according to an embodiment of the present application. The method may include:

[0271] In the following, the method shown in FIG. 5 will be described in detail with reference to the communication system shown in FIG.

[0272] 9 illustrates a method for adaptively optimizing an autonomous driving system according to an embodiment of the present application. The method may include the following steps:

[0273] Step 901: The automated driving system detects whether the driver of the target vehicle is a new driver.

[0274] Step 902: The automatic driving device determines an automatic driving mode of the target vehicle based on the driver's characteristic information.

[0275] In other words, when the driver of the target vehicle is a driver who has driven the target vehicle before, the automatic driving device may determine the automatic driving mode of the target vehicle based on the driver's characteristic information.

[0276] The autonomous driving device may acquire an autonomous driving mode that has been used by the driver from the V2X server shown in FIG. 4, and use the autonomous driving mode that has been used as the autonomous driving mode of the target vehicle. Alternatively, the autonomous driving device may store an autonomous driving mode that has been used by the driver in the past. The autonomous driving device may use the stored autonomous driving mode that has been used by the driver as the autonomous driving mode of the target vehicle. This is not limited.

[0277] Step 903: The autonomous driving device acquires feature parameters corresponding to the driver's behavior in the first driving scenario.

[0278] Step 904: The automatic driving device determines the driver's driving intention based on the feature parameters corresponding to the driver's behavior.

[0279] Step 905: The automatic driving device determines a first characteristic parameter based on the driver's driving intention and the driving behavior of the vehicle controlled by the automatic driving system.

[0280] Step 906: The automatic driving device inputs the first feature parameters into a pre-configured neural network model to obtain a first driving behavior.

[0281] Step 907: The autonomous driving device updates the autonomous driving system based on the first driving behavior.

[0282] For the description of the above steps 901 to 907, please refer to the technical method in Figure 5. The details will not be described repeatedly.

[0283] The solutions in the above embodiments of the present application may be combined on the premise that the solutions are not contradictory to each other.

[0284] In the above embodiments provided in the present application, the method provided in the embodiment of the present application is described from the perspective of an automatic driving device. To implement the functions of the method provided in the above embodiments of the present application, it will be understood that the automatic driving device includes a corresponding hardware structure and / or software module for performing such functions. Those skilled in the art will easily recognize that the present application can be implemented by hardware or a combination of hardware and computer software by referring to the algorithm steps in the examples described in the embodiments disclosed herein. Whether a function is performed by hardware or by hardware driven by computer software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use various methods to implement the above-mentioned functions for each specific application, but the implementation should not be considered as going beyond the scope of the present application.

[0285] In the embodiment of the present application, the autonomous driving device may be divided into functional modules based on the above method example. For example, each functional module may be obtained by dividing each corresponding function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in the form of hardware or in the form of a software functional module. It should be noted that in the embodiment of the present application, the module division is an example and is merely a logical function division. In the actual implementation, other division methods may be used.

[0286] When an integrated unit is used, Fig. 10 shows a possible schematic diagram of the structure of the device (shown as autonomous driving device 100) in the above embodiment. The autonomous driving device 100 includes a communication unit 1002 and a processing unit 1001, and may further include a storage unit 1003. The schematic diagram of the structure shown in Fig. 10 may be used to show the structure of the autonomous driving device in the above embodiment. The schematic diagram of the structure shown in Fig. 10 may be used to show the structure of the V2X server in the above embodiment.

[0287] Using the schematic diagram of the structure shown in FIG. 10 to illustrate the structure of the autonomous driving device in the above embodiment, the processing unit 1001 is configured to control and manage the actions of the autonomous driving device. For example, the processing unit 1001 is configured to use the communication unit 1002 to perform steps 501, 502, and 503 of FIG. 5, perform steps 901, 902, 904, 905, 906, 907, and 907 of FIG. 9, perform step 903 of FIG. 9, and / or perform actions performed by the autonomous driving device in other processes described in the embodiments of the present application. The processing unit 1001 may communicate with other network entities by using the communication unit 1002. For example, the processing unit 1001 communicates with the V2X server 20 shown in FIG. 1. The storage unit 1003 is configured to store program codes and data of the autonomous driving device.

[0288] Using the structural schematic diagram shown in FIG. 10 to illustrate the structure of the autonomous driving device in the above embodiment, the autonomous driving device 100 may be an autonomous driving device or a chip in the autonomous driving device.

[0289] When the autonomous driving device 100 is an autonomous driving device, the processing unit 1001 may be a processor or a controller, and the communication unit 1002 may be a communication interface, a transceiver, a transceiver device, a transceiver circuit, a transceiver device, etc. The communication interface is a general term and may include one or more interfaces. The storage unit 1003 may be a memory. When the autonomous driving device 100 is a chip in the autonomous driving device, the processing unit 1001 may be a processor or a controller, and the communication unit 1002 may be an input interface and / or an output interface, a pin, a circuit, etc. The storage unit 1003 may be a storage unit (e.g., a register or a cache) in the chip, or a storage unit (e.g., a read-only memory (ROM) or a random access memory (RAM) that exists in the autonomous driving device and is located outside the chip).

[0290] Using the schematic diagram of the structure shown in FIG. 10 to illustrate the structure of the V2X server in the above embodiment, the processing unit 1001 is configured to control and manage the actions of the V2X server. For example, the processing unit 1001 is configured to execute the actions performed by the V2X server in other processes described in the embodiments of the present application. The processing unit 1001 may communicate with other network entities by using the communication unit 1002. For example, the processing unit 1001 communicates with the vehicle 10 shown in FIG. 1. The storage unit 1003 is configured to store program codes and data of the V2X server.

[0291] Using the structural schematic diagram shown in FIG. 10 to illustrate the structure of the V2X server in the above embodiment, the autonomous driving device 100 may be the V2X server, or may be a chip in the V2X server.

[0292] When the autonomous driving device 100 is a V2X server, the processing unit 1001 may be a processor or a controller, and the communication unit 1002 may be a communication interface, a transceiver, a transceiver device, a transceiver circuit, a transceiver device, etc. The communication interface is a general term and may include one or more interfaces. The storage unit 1003 may be a memory. When the autonomous driving device 100 is a chip in the autonomous driving device, the processing unit 1001 may be a processor or a controller, and the communication unit 1002 may be an input interface and / or an output interface, a pin, a circuit, etc. The storage unit 1003 may be a storage unit (e.g., a register or a cache) in the chip, or a storage unit (e.g., a read-only memory (ROM) or a random access memory (RAM) that exists in the autonomous driving device and is located outside the chip).

[0293] When the integrated unit in FIG. 10 is implemented in the form of a software function module and sold or used as an independent product, the integrated unit may be stored in a computer-readable storage medium. Based on such understanding, essentially the technical solutions in the embodiments of the present application, or the part contributing to the current technology, or all or part of the technical solutions may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes some instructions for instructing a computer device (which may be a personal computer, a server, a first access network device, etc.) or a processor to perform all or some of the steps of the method described in the embodiments of the present application. The storage medium for storing the computer software product includes any medium that can store program code, such as a USB flash drive, a removable hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0294] The units in Figure 10 may alternatively be referred to as modules, for example a processing unit may be referred to as a processing module.

[0295] 11 shows an exemplary diagram of a communication system according to an embodiment of the present application. The communication system includes a V2X server 1101 and an autonomous driving device 1102.

[0296] The V2X server 1101 is configured to execute the actions performed by the V2X server in the above embodiment. For example, the V2X server 1101 sends a preset autonomous driving mode to the autonomous driving device.

[0297] The autonomous driving device 1102 is configured to execute the actions performed by the autonomous driving device in the above embodiments. For example, the autonomous driving device 1102 is configured to execute the steps in FIGS.

[0298] In the implementation process, the steps in the method provided in this embodiment may be completed by using a hardware integrated logic circuit in a processor, or by using instructions in the form of software. The steps of the method disclosed with reference to the embodiments of this application may be directly executed and completed by a hardware processor, or may be executed and completed by using a combination of hardware and software modules in a processor.

[0299] A processor in this application may include at least one of computing devices that execute software, such as, but not limited to, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor. Each computing device may include one or more cores configured to execute software instructions to perform operations or processes. The processor may be an independent semiconductor chip, or may be integrated with other circuits to form a semiconductor chip. For example, the processor may form a SoC (system on chip) that includes other circuits (codec circuits, hardware acceleration circuits, or various bus and interface circuits). Alternatively, the processor may be incorporated in an ASIC as an embedded processor of the ASIC, or the ASIC integrated with the processor may be packaged separately or with other circuits. In addition to the cores configured to execute software instructions to perform operations or processes, the processor may further include necessary hardware accelerators, such as a field programmable gate array (FPGA), a programmable logic device (PLD), or logic circuits that perform dedicated logic operations.

[0300] The memory in the embodiments of the present application may include at least one of the following types: read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or may be electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory may further be, but is not limited to, compact disc read-only memory (CD-ROM) or other compact disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), disc storage media, or other magnetic storage devices, or any other medium that can be used to hold or store the anticipated program code in the form of instructions or data structures and that can be accessed by a computer.

[0301] All or some of the above embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implementing the embodiments using a software program, all or some of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or some of the processes or functions according to the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired (e.g., coaxial cable, optical fiber, or digital subscriber line (DSL)) or wireless (e.g., infrared, radio, or microwave) manner. The computer-readable storage medium may be any available medium accessible by a computer, or a data storage device, such as a server or data center, that integrates one or more available media. The available media may be magnetic media (e.g., floppy disk, hard disk, or magnetic tape), optical media (e.g., DVD), semiconductor media (e.g., solid state disk (SSD)), and the like.

[0302] Although the present application has been described with reference to embodiments herein, in the process of implementing the application for which protection is claimed, those skilled in the art may understand and implement other variations of the disclosed embodiments by studying the accompanying drawings, the disclosure, and the appended claims. In the claims, "comprises" does not exclude other elements or other steps, and "a" or "one" does not exclude "plurality". A single processor or other unit may perform several functions recited in the claims. Although some means are recited in mutually different dependent claims, this does not mean that these means cannot be combined to good effect.

[0303] Although the present application has been described with reference to certain features and embodiments thereof, it is apparent that various modifications and combinations of the specific features and embodiments may be made without departing from the spirit and scope of the present application. Accordingly, the specification and accompanying drawings are merely exemplary descriptions of the present application as defined by the appended claims, and any or all modifications, variations, combinations, or equivalents that are within the scope of the present application are to be considered. It is apparent that those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if the modifications and variations of the present application are within the scope of the claims of the present application and their equivalent techniques, the present application is intended to cover those modifications and variations. [Explanation of symbols]

[0304] 1. Audio collection device 2. Audio collection device 10 Vehicles 20 V2X Server 100 Automatic Driving Device 101 Automatic Driving Device 102 Vehicle Gateway 103 Car body antenna 1001 Processing Unit 1002 Communication unit 1003 Storage Unit 1011 Autonomous Driving Sensing Module 1012 Intelligent Cockpit Interaction Module 1013 Driver Intention Conflict Detection Module 1014 Autonomous Driving Control Module 1015 Driver Online Adaptation Module 1101 V2X Server 1102 Automatic driving device 2011 Driver Preferences and Historical Operation Database 2012 Highest Driver Tolerance Parameter Module

Claims

1. 1. A method for adaptively optimizing an automated driving system, comprising: acquiring a driving intention of a driver of a target vehicle, the target vehicle being an autonomous vehicle controlled by the autonomous driving system, and the driving intention being to increase a vehicle speed of the target vehicle, to decrease a vehicle speed of the target vehicle, to stop the target vehicle, to approach a left lane, to approach a right lane, to increase a vehicle speed of the target vehicle when approaching a left lane, to decrease a vehicle speed of the target vehicle when approaching a left lane, to increase a vehicle speed of the target vehicle when approaching a right lane, or to decrease a vehicle speed of the target vehicle when approaching a right lane; Detecting, based on the driver's driving intention, a contradiction exists between a driving behavior of the target vehicle controlled by the automated driving system and the driver's driving intention; A step of updating the automated driving system so that a driving behavior of the target vehicle controlled by the updated automated driving system matches a driving intention of the driver, acquiring a first feature parameter based on the driving intention of the driver and the driving behavior of the target vehicle controlled by the automated driving system, the first feature parameter representing driving data corresponding to the driving intention of the driver and the driving behavior of the target vehicle controlled by the automated driving system; inputting the first feature parameters into a preset neural network model to obtain a first driving behavior, the preset neural network model being used to determine a driving behavior consistent with a driving intention of the driver; and updating the automated driving system based on the first driving behavior.

2. 2. The method for adaptively optimizing an automated driving system of claim 1, wherein the driving intention is represented by feature parameters corresponding to the driver's behavior, and the driver's behavior includes one or more of the driver's operation behavior, visual behavior, emotional behavior, and physical posture behavior.

3. 3. The method for adaptively optimizing an autonomous driving system of claim 2, wherein the emotional behavior is emotional behavior acquired when the driver is concentrating on the driving behavior of the target vehicle or when the driver is not performing a second task other than driving operations, and the visual behavior and the physical postural behavior of the driver are used to reflect that the driver is concentrating on the driving behavior of the target vehicle, and the physical postural behavior of the driver is used to reflect that the driver is not performing the second task.

4. The existence of the inconsistency between the driving behavior of the target vehicle controlled by the automated driving system and the driving intention of the driver is determined by The characteristic parameter corresponding to the driver's behavior exceeds a preset range, and / or the duration during which the characteristic parameter corresponding to the driver's behavior is outside the preset range is equal to or greater than a first preset value; and / or 3. The method for adaptively optimizing an autonomous driving system as described in claim 2, further comprising: a number of times that the feature parameter corresponding to the driver's behavior exceeds the preset range being equal to or greater than a second preset value.

5. Prior to the step of updating the automated driving system based on the first driving behavior, the method further comprises: presenting one or more questions to the driver; receiving a response to the one or more questions from the driver, the response to the one or more questions being used to indicate whether to update the automated driving system; 5. The method for adaptively optimizing an automated driving system of claim 1, wherein the step of updating the automated driving system based on the first driving behavior includes the step of updating the automated driving system based on the first driving behavior when the answer to the one or more questions is used to indicate updating the automated driving system.

6. The step of updating the automated driving system based on the first driving behavior includes: using the first driving behavior as a driving behavior of the target vehicle controlled by the updated automated driving system when the first driving behavior matches a safe driving behavior of the target vehicle; or 6. The method for adaptively optimizing an autonomous driving system according to claim 1, further comprising: when the first driving behavior does not match the safe driving behavior of the target vehicle, using the safe driving behavior as the driving behavior of the target vehicle controlled by the updated autonomous driving system.

7. An apparatus for adaptively optimizing an automated driving system, comprising: a communication unit configured to acquire a driving intention of a driver of a target vehicle, the target vehicle being an autonomous vehicle controlled by the autonomous driving system, and the driving intention being to increase a vehicle speed of the target vehicle, to decrease a vehicle speed of the target vehicle, to stop the target vehicle, to approach a left lane, to approach a right lane, to increase a vehicle speed of the target vehicle when approaching a left lane, to decrease a vehicle speed of the target vehicle when approaching a left lane, to increase a vehicle speed of the target vehicle when approaching a right lane, or to decrease a vehicle speed of the target vehicle when approaching a right lane; and a processing unit configured to detect, based on the driver's driving intention, a contradiction exists between a driving behavior of the target vehicle controlled by the automated driving system and the driver's driving intention; The processing unit is further configured to update the autonomous driving system so that a driving behavior of the target vehicle controlled by the updated autonomous driving system matches a driving intention of the driver, specifically, obtaining a first characteristic parameter based on the driving intention of the driver and the driving behavior of the target vehicle controlled by the automated driving system, the first characteristic parameter representing driving data corresponding to the driving intention of the driver and the driving behavior of the target vehicle controlled by the automated driving system; inputting the first feature parameters into a pre-defined neural network model, the pre-defined neural network model being used to determine a driving behavior consistent with the driver's driving intention, to obtain a first driving behavior; and updating the automated driving system based on the first driving behavior. A device for adaptively optimizing an autonomous driving system.

8. 8. The apparatus for adaptively optimizing an automated driving system of claim 7, wherein the driving intention is represented by feature parameters corresponding to the driver's behavior, and the driver's behavior includes one or more of the driver's operation behavior, visual behavior, emotional behavior, and physical posture behavior.

9. 9. The apparatus for adaptively optimizing an autonomous driving system as described in claim 8, wherein the emotional behavior is emotional behavior acquired when the driver is concentrating on the driving behavior of the target vehicle or when the driver is not performing a second task other than driving operations, and the visual behavior and the physical postural behavior of the driver are used to reflect that the driver is concentrating on the driving behavior of the target vehicle, and the physical postural behavior of the driver is used to reflect that the driver is not performing the second task.

10. The existence of the inconsistency between the driving behavior of the target vehicle controlled by the automated driving system and the driving intention of the driver is determined by The characteristic parameter corresponding to the driver's behavior exceeds a preset range, and / or the duration during which the characteristic parameter corresponding to the driver's behavior is outside the preset range is equal to or greater than a first preset value; and / or 9. The apparatus for adaptively optimizing an autonomous driving system as described in claim 8, further comprising: a number of times that the characteristic parameter corresponding to the driver's behavior exceeds the preset range being equal to or greater than a second preset value.

11. The communication unit further comprises: Presenting the driver with one or more questions; and and receiving from the driver a response to the one or more questions, the response being used to indicate whether to update the automated driving system; Specifically, the processing unit includes:

11. The apparatus for adaptively optimizing an automated driving system of claim 7, wherein the apparatus is configured to update the automated driving system based on the first driving behavior when the answer to the one or more questions is used to instruct the automated driving system to update.

12. The processing unit further comprises: using the first driving behavior as a driving behavior of the target vehicle controlled by the updated automated driving system when the first driving behavior matches a safe driving behavior of the target vehicle; or 12. The apparatus for adaptively optimizing an autonomous driving system according to claim 7, wherein when the first driving behavior does not match a safe driving behavior of the target vehicle, the safe driving behavior is used as the driving behavior of the target vehicle controlled by the updated autonomous driving system.

13. An automated driving device comprising: one or more processors; and one or more memories, the one or more memories coupled to the one or more processors, the one or more memories configured to store computer program code or computer instructions; When the one or more processors execute the computer instructions, the autonomous driving device is enabled to perform the method for adaptively optimizing an autonomous driving system according to any one of claims 1 to 6.

14. 7. A computer readable storage medium storing computer instructions or programs, the computer instructions or programs being enabled, when executed on a computer, to perform the method for adaptively optimizing an automated driving system according to any one of claims 1 to 6.

15. A chip comprising a processor and a communication interface, the processor being coupled to a memory through the communication interface, and the method for adaptively optimizing an autonomous driving system according to any one of claims 1 to 6 being performed when the processor executes computer programs or instructions in the memory.

Images