Vehicle control method and device, vehicle, medium, program product and chip system

Abstract

The invention provides a vehicle control method and device, a vehicle, a medium, a program product and a chip system, and relates to the technical field of vehicle intelligent driving, and the method comprises the steps: determining a target driving style, the target driving style can be determined based on environment information around the vehicle, and then determining driving parameters of the vehicle according to an automatic driving style, the driving parameters comprise at least one of the following parameters: path selection parameters, target vehicle speed and acceleration, overtaking decision, control of automatic driving of the vehicle according to the driving parameters, and planning of different driving parameters according to different driving styles, so that the flexibility of automatic driving is improved, automatic driving is closer to real driving of a driver, and the vehicle using experience is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of vehicle intelligent driving, in particular to a vehicle control method and device, vehicle, medium, program product and chip system. BACKGROUND

[0002] In related technologies, the driving style is fixed, which is different from manual driving by users, thereby leading to poor user experience of intelligent driving. SUMMARY

[0003] To overcome the problems in related technologies, the present disclosure provides a vehicle control method, device, vehicle, medium, program product and chip system.

[0004] According to a first aspect of an embodiment of the present disclosure, a vehicle control method is provided, the method comprising: determining a target driving style; wherein the target driving style is determined based on environmental information of a vehicle periphery; determining a driving parameter of the vehicle according to the target driving style; and controlling the vehicle to perform automatic driving according to the driving parameter; wherein the driving parameter comprises at least one of the following: a path selection parameter, a target vehicle speed and acceleration, and a passing decision. Thus, different driving styles are determined for the periphery environment of the vehicle to plan driving parameters corresponding to the driving styles, improve the flexibility of automatic driving, make the automatic driving closer to real driving by drivers, and improve the user experience of using the vehicle.

[0005] In some possible implementation manners, the target driving style is determined based on the environmental information of the vehicle periphery, comprising: determining target scene description information for the environmental information according to the environmental information of the vehicle periphery; and determining the target driving style matched with the target scene description information based on a preset target scene description information-driving style association model. Thus, the target driving style can be accurately obtained through the association model.

[0006] In some possible implementation manners, the preset target scene description information-driving style association model supports user self-defined operations, and the self-defined operations comprise adding a new association between target scene description information and a driving style, deleting an existing association between target scene description information and a driving style, or modifying a corresponding relationship between target scene description information and a driving style. Thus, flexible adjustment of the association model is realized.

[0007] In a possible implementation, the preset target scene description information-driving style association model can be updated based on a driving operation record actually performed by the vehicle; the updating based on the user actual operation record comprises: collecting the driving operation record actually performed by the vehicle; determining environment information according to the driving operation record, and determining a driving style actually adopted under target scene description information corresponding to the environment information; and updating a corresponding relationship between the target scene description information and the driving style in the preset target scene description information-driving style association model based on the target scene description information and the driving style actually adopted. In this way, the updating of the association model is realized, so that the association model can more accurately match the actual driving style of the user.

[0008] In some possible implementations, when the driving parameter comprises a path selection parameter, the determining of the driving parameter of the vehicle according to the target driving style comprises: determining the path selection parameter of the vehicle according to the environment information and the target driving style, wherein the path selection parameter is used to determine a driving path. In this way, the driving path can be determined based on the current environment information and in combination with the user preference, so that the automatic driving is closer to the actual demand of the driver, and the vehicle experience is improved.

[0009] In some possible implementations, the determining of the path selection parameter of the vehicle according to the environment information and the target driving style comprises: acquiring target object information in the environment according to the environment information; determining a plurality of candidate paths according to the target object information, wherein each candidate path in the plurality of candidate paths corresponds to a driving style; determining the driving path corresponding to the target driving style from the plurality of candidate paths, and determining the path selection parameter according to the driving path. In this way, the optimal route is selected based on the surrounding environment information, and the corresponding driving style is matched based on the selected optimal route, so that the user experience is ensured and the safety is improved.

[0010] In some possible implementations, the determining of the driving parameter of the vehicle according to the target driving style comprises: determining the driving parameter of the vehicle according to the target driving style by a parameter output model, wherein the parameter output model is obtained according to a sample driving style corresponding to sample environment information and a sample driving path parameter. In this way, different driving paths are planned for different driving styles based on the parameter output model, the flexibility of the automatic driving is improved, the automatic driving is closer to the real driving of the driver, and the vehicle experience is improved.

[0011] In some possible implementation manners, the determining the target driving style comprises: determining a selected target driving style from a plurality of driving styles in response to a style selection operation; or determining a driving style memorized by the vehicle as the target driving style; or determining a driving style with the highest score from the plurality of driving styles as the target driving style according to scores of the user on each driving style in the plurality of driving styles; or determining the target driving style according to historical driving behavior data of the user in a region where a current surrounding environment of the vehicle is located when the user has previously visited the region. In this way, the target driving style is determined so that the vehicle performs automatic driving more in line with the driving habits of the driver, and meanwhile, the user is given the flexibility to change the driving style, thereby improving the driving experience and increasing the flexibility of automatic driving.

[0012] In some possible implementation manners, the method further includes: determining corresponding in-vehicle atmosphere adjustment parameters based on the target driving style; and adjusting one or more atmosphere components in the vehicle interior according to the in-vehicle atmosphere adjustment parameters, wherein the atmosphere components at least include a light system and a sound system. In this way, the interest of using the vehicle is improved.

[0013] According to a second aspect of the embodiments of the present disclosure, a vehicle control apparatus is provided, which includes: a style determination module configured to determine a target driving style, wherein the target driving style is determined based on environment information of a surrounding of the vehicle; a parameter determination module configured to determine a driving path of the vehicle according to the target driving style; and a driving control module configured to control the vehicle to perform automatic driving according to the driving path, wherein the driving parameter includes at least one of the following: a path selection parameter, a target vehicle speed and acceleration, and a passing decision.

[0014] In some possible implementation manners, the style determination module includes: a target scene description information determination module configured to determine target scene description information corresponding to the environment information of the surrounding of the vehicle according to the environment information; and a style generation module configured to determine the target driving style matched with the target scene description information based on a preset target scene description information-driving style association model.

[0015] In some possible implementation manners, the parameter determination module includes: a model processing module configured to determine the driving parameter of the vehicle according to the target driving style by a parameter output model, wherein the parameter output model is obtained by training according to sample driving styles corresponding to sample environment information and sample driving parameters.

[0016] In some possible embodiments, the device further includes: an adjustment parameter acquisition module, configured to determine corresponding in-vehicle atmosphere adjustment parameters based on the target driving style; an atmosphere adjustment module, configured to adjust one or more atmosphere components inside the vehicle according to the in-vehicle atmosphere adjustment parameters; wherein the atmosphere components include at least a lighting system and an audio system.

[0017] According to a third aspect of an embodiment of the present disclosure, a vehicle is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the steps of the method described in the first aspect when executing the instructions.

[0018] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method provided in the first aspect of the present disclosure are implemented.

[0019] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0020] According to the sixth aspect of an embodiment of the present disclosure, a chip system is provided, which includes a processor and an interface circuit, the processor obtains program instructions through the interface circuit, the program instructions are executed by the processor, and the processor is used to execute the steps of the method described in the first aspect.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0023] Figure 1 The figure is a flow chart of a vehicle control method according to an exemplary embodiment of the present disclosure.

[0024] Figure 2 is a schematic diagram of a driving model according to an exemplary embodiment of the present disclosure.

[0025] Figure 3 1 is a schematic diagram of vehicle automatic driving according to an exemplary embodiment of the present disclosure.

[0026] Figure 4 It is a block diagram of a vehicle control device according to an exemplary embodiment of the present disclosure.

[0027] Figure 5is a block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0029] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the corresponding data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0030] In order to solve the problem of rigid driving style and poor user experience in related technologies, this disclosure provides a vehicle control method. Figure 1 , the vehicle control method can be applied to Figure 4 The vehicle control device 400 shown, Figure 5 The vehicle 600, computer program product, computer readable storage medium and chip system shown in FIG. In this embodiment, the vehicle is used as an example. Figure 1 The process shown in FIG. 1 is described in detail. The vehicle control method may include the following steps: Step S110: Determine a target driving style; wherein the target driving style is determined based on environmental information surrounding the vehicle.

[0031] The target driving style refers to the driving characteristics exhibited during the autonomous driving process. For example, the driving characteristics may include target vehicle speed, acceleration, deceleration, steering, overtaking, lane preference (such as preference for the left lane (fast lane)), and other characteristics.

[0032] Optionally, the target driving style is determined based on environmental information surrounding the vehicle. Exemplarily, environmental information surrounding the vehicle is collected, and the target driving style is determined based on the environmental information.

[0033] Optionally, the target driving style may also be automatically acquired. For example, the target driving style may be automatically acquired based on the vehicle's environment, or the target driving style may be automatically acquired by analyzing the driver's driving habits based on the driver's historical driving data.

[0034] Optionally, the target driving style can also be set manually by the driver.

[0035] Step S120: Determine driving parameters of the vehicle according to the target driving style; wherein the driving parameters include at least one of the following: path selection parameters, target vehicle speed and acceleration, and overtaking decision.

[0036] For example, driving parameters include route selection parameters. Based on a target driving style, route selection parameters matching the target driving style are generated. The route selection parameters are used to instruct the vehicle to automatically drive along the driving route. For example, each driving style corresponds to at least one route. A driving route can be determined based on the target driving style, and the vehicle's driving parameters can be generated based on the driving route. For example, the vehicle's driving target is to travel from location A to location B. There are multiple routes between locations A and B, including a country road w1, a highway w2, an urban road w3, or a winding mountain road w4. Each driving style corresponds to at least one route. The corresponding relationship can be: the first driving style corresponds to country road w1, the second driving style corresponds to highway w2, the third driving style corresponds to urban road w3, and the fourth driving style corresponds to winding mountain road w4. For example, if the target driving style is the fourth driving style, the aforementioned corresponding relationship can be used to determine that the driving route corresponding to the fourth driving style is winding mountain road w4, and the corresponding driving parameters can be generated based on winding mountain road w4.

[0037] The target speed can be set appropriately based on the user's driving habits, preferred lane, and the speed limit on the current road section. For example, on a highway with a speed limit of 120km / h, if the user prefers to drive in the left lane and usually drives at a speed of no less than 115km / h, the target speed can be set to 115km / h, or 116km / h, etc. The above acceleration includes positive and negative accelerations. When it is positive, it means the vehicle is accelerating; when it is negative, it means the vehicle is decelerating.

[0038] Overtaking Decision is used to determine whether to overtake. It's easy to understand that when Overtaking Decision is used to determine whether to overtake, the vehicle is accelerated to overtake. Alternatively, when Overtaking Decision is used to determine whether to overtake, the vehicle's speed is maintained to continue following the vehicle, or the vehicle's speed is reduced to increase the distance between the vehicle and the vehicle ahead.

[0039] Step S130: Control the vehicle to perform automatic driving according to the driving parameters.

[0040] According to the planned path parameters, the vehicle is controlled by the vehicle control system to achieve autonomous driving.

[0041] The vehicle control method provided in the embodiment determines a target driving style, which can be determined based on environmental information of a vehicle surrounding, and determines driving parameters of the vehicle according to the automatic driving style, wherein the driving parameters include at least one of path selection parameters, target vehicle speed and acceleration, and overtaking decision, and the vehicle is controlled to perform automatic driving according to the driving parameters. Different driving parameters are planned for different environmental information and driving styles, which improves the flexibility of automatic driving and makes the automatic driving closer to real driving of a driver, thereby improving the vehicle experience.

[0042] Optionally, the vehicle control method further includes displaying the target driving style.

[0043] For example, the driving target driving style is displayed on a central control screen of the vehicle, or on a user terminal bound to the vehicle. The driving style can be displayed in the form of text, icon, or combination of icon and text, as long as it can inform the user. The specific display manner is not limited herein.

[0044] The embodiment displays the target driving style to show the target driving style to the driver, so that the driver can understand the driving style and the automatic driving behavior of the vehicle is provided with explainability.

[0045] Optionally, the vehicle control method can further include determining corresponding in-vehicle atmosphere adjustment parameters based on the target driving style, and adjusting one or more atmosphere components in the vehicle interior according to the in-vehicle atmosphere adjustment parameters, wherein the atmosphere components at least include a light system and a sound system.

[0046] Based on the target driving style, in-vehicle atmosphere adjustment parameters adapted to the driving style are determined. The in-vehicle atmosphere adjustment parameters are used to adjust the working state of the atmosphere components in the vehicle. According to the in-vehicle atmosphere adjustment parameters, the atmosphere components in the vehicle are adjusted, so that the in-vehicle atmosphere created by the atmosphere components is adapted to the target driving style, thereby improving the vehicle experience.

[0047] The atmosphere assembly includes one or more. Exemplarily, the atmosphere assembly at least includes a light system and a sound system. For example, the atmosphere assembly includes the light system, and controls the working state of the light system according to the in-vehicle atmosphere adjustment parameter. For example, a correspondence between the in-vehicle atmosphere adjustment parameter and the working state of the light system is established in advance, and the light system is controlled to work in the working state corresponding to the in-vehicle atmosphere adjustment parameter according to the correspondence. The working state can be manifested as the brightness, color, etc. displayed by the light system, or the working state can be manifested as the frequency of the light system. Exemplarily, for the in-vehicle atmosphere adjustment parameter corresponding to the aggressive target driving style, the corresponding light system has a high flashing frequency, a bright color, and a large brightness. For the in-vehicle atmosphere adjustment parameter corresponding to the moderate target driving style, the corresponding light system has a low flashing frequency, a soft color temperature of the light, and a small brightness. The aggressive target driving style can be manifested as the number of overtaking times exceeding a preset number and / or the vehicle speed exceeding a preset vehicle speed, for example, the aggressive target driving style is an overtaking style. The moderate target driving style can be manifested as the number of overtaking times being lower than the preset number and / or the vehicle speed being lower than the preset vehicle speed, for example, the moderate target driving style is a following style.

[0048] For another example, the atmosphere assembly includes the sound system, and controls the sound box system to play music adapted to the target driving style according to the in-vehicle atmosphere adjustment parameter. For example, a correspondence between the in-vehicle atmosphere adjustment parameter and the music played by the sound box system is established in advance, and the sound box system is controlled to play the music corresponding to the in-vehicle atmosphere adjustment parameter according to the correspondence. For example, for the in-vehicle atmosphere adjustment parameter corresponding to the aggressive target driving style, the rhythm of the music played by the sound box system is relatively fast. For the in-vehicle atmosphere adjustment parameter corresponding to the moderate target driving style, the rhythm of the music played by the sound box system is relatively slow.

[0049] In an embodiment, the step S110 can be a manner of determining the selected target driving style from the plurality of driving styles in response to the style selection operation.

[0050] The plurality of driving styles are displayed, for example, on the central control screen of the vehicle or the user terminal bound to the vehicle, the driver performs a style selection operation such as touch, click, input (including text input or voice input) on the displayed driving styles, and the vehicle determines the driving style selected by the driver as the target driving style from the plurality of driving styles in response to the style selection operation.

[0051] The embodiment determines the selected target driving style from the plurality of driving styles in response to the style selection operation according to the style selection operation of the driver, sets the target driving style according to the driving habit of the driver, so that the vehicle automatically drives according to the driving habit of the driver, improves the driving experience, and increases the flexibility of automatic driving.

[0052] In another implementation, step S110 can be implemented as follows: obtaining the target driving style according to the environment information of the environment in which the vehicle is located.

[0053] The vehicle is provided with sensors, and the environment information of the environment in which the vehicle is located is collected through the sensors. For example, the sensors can include cameras, laser radars, etc. The environment information can include image information of the environment in which the vehicle is located collected by the cameras, and the environment information can also include target object information in the environment in which the vehicle is located collected by the laser radars, etc.

[0054] As one way, the target scene description information corresponding to the environment information is determined according to the environment information of the surroundings of the vehicle; and the target driving style matched with the target scene description information is determined based on a preset target scene description information-driving style association model.

[0055] The target scene description information-driving style association model can be a VLM model.

[0056] For example, the association model is obtained according to the preset configuration information. It is not difficult to understand that the association model can be configured by the user and customized according to the user's demand.

[0057] For example, the association model is obtained according to historical driving data. The historical driving data includes historical driving speed, acceleration, historical driving style, historical driving path, etc. of the vehicle. The association model can be generated by analyzing the historical driving data, and can be a data model.

[0058] The preset target scene description information-driving style association model can be updated based on the driving operation records actually performed by the vehicle; wherein the updating based on the user's actual operation records includes: collecting the driving operation records actually performed by the vehicle, for example, the driving operation records are stored in the vehicle or the server connected with the vehicle, and the driving operation records are obtained therefrom. The driving operation records can include all data in the driving process of the vehicle, for example, including images around the vehicle, driving operation information of the user, driving state generated by the vehicle in response to the driving operation of the user, etc. The environment information is determined according to the driving operation records, and the driving style actually adopted under the target scene description information corresponding to the environment information is determined. Based on the target scene description information and the driving style actually adopted, the corresponding relationship between the target scene description information and the driving style in the preset target scene description information-driving style association model is updated.

[0059] By updating the target scene description information-driving style association model in the above manner, the association model is more adapted to the user's habits and can output a driving style that is more in line with the user's driving habits, thereby enabling autonomous driving according to the user's personal habits and improving the user's car experience.

[0060] Alternatively, a preset correspondence relationship can be established, including a correspondence between environmental information and a target driving style. Based on this preset correspondence, the target driving style corresponding to the environmental information is obtained. Alternatively, this correspondence relationship can be pre-stored in the vehicle by the manufacturer before the vehicle leaves the factory. Alternatively, the preset correspondence relationship can be obtained by continuously analyzing and summarizing the driver's driving data during vehicle use.

[0061] As another way, target scene description information for the environmental information is obtained based on the environmental information of the environment in which the vehicle is located; and the target driving style is determined based on the target scene description information.

[0062] Obtain target scene description information for environmental information. The target scene description information can be used to describe the vehicle's environment. For example, the target scene information can be used to describe a vehicle in a forest, highway, or desert. The target scene description information can also be used to describe obstacles in the environment. Obstacles can be moving objects, such as moving vehicles, falling rocks, or moving sheep. Obstacles can also be stationary, such as parked vehicles or fallen rocks in the middle of the road.

[0063] For example, the environmental information can be image or video information captured by a camera on a vehicle. A visual language model (VLM) can be used to process the environmental information to obtain a target scene description for the environmental information. The VLM model can be deployed on the vehicle or on a server that communicates with the vehicle.

[0064] Exemplarily, the target driving style is determined in the following manner: according to a preset mapping relationship, the target driving style corresponding to the target scene is obtained, wherein the preset mapping relationship is pre-set, and the preset mapping relationship includes a correspondence between each scene description information in a plurality of scene description information and its corresponding driving style.

[0065] For example, the preset mapping relationship includes a corresponding relationship between first scene information and a first driving style, and a corresponding relationship between second scene information and a second driving style. The first scene information is used to represent that the driving speed of the vehicle exceeds a preset speed threshold, and the number of obstacles around the vehicle does not exceed a preset number. The scene represented by the first scene information can be understood as a high-speed and sparse obstacle scene, and the first driving style is used to represent a speed-oriented driving style. The second scene information is used to represent that the driving speed of the vehicle exceeds a preset speed threshold, and the number of obstacles around the vehicle exceeds a preset number. The scene represented by the second scene information can be understood as a high-speed and dense obstacle scene, and the second driving style is used to represent a safety-oriented style. The scenes represented by the first scene information and the second scene information can be highway scenes.

[0066] The preset mapping relationship further includes a corresponding relationship between third scene information and a third driving style, and a corresponding relationship between fourth scene information and a fourth driving style. The third scene information is used to represent that the vehicle is in an urban scene, and the number of obstacles around the vehicle does not exceed a preset number. The scene represented by the third scene information can be understood as an urban and sparse obstacle scene, and the third driving style is used to represent a dexterous style. The fourth scene information is used to represent that the vehicle is in an urban scene, and the number of obstacles around the vehicle exceeds a preset number. The scene represented by the fourth scene information can be understood as an urban and dense obstacle scene, and the fourth driving style is used to represent a safety-oriented style.

[0067] The preset mapping relationship further includes a corresponding relationship between fifth scene information and a fifth driving style. The fifth scene information is used to represent a race track scene, and the fifth driving style is used to represent an aggressive style.

[0068] It should be noted that the scene description information and the driving style are not limited to this, and there can be more or fewer scenes.

[0069] In another embodiment, the step S110 can include determining a target driving style according to driving behavior data of the driver. The driving behavior data is data collected according to the body movements of the driver. As one way, a corresponding relationship between behavior data and driving style is preset, and based on the corresponding relationship, the target driving style corresponding to the driving behavior data can be obtained. For example, the corresponding relationship includes that a nodding behavior data corresponds to an aggressive driving style, and a blinking behavior data corresponds to a gentle driving style. When the driving behavior data of the user is the nodding behavior data, the target driving style determined based on the corresponding relationship is the aggressive driving style. In this way, the target driving style is personalized according to the individualization setting of the driver.

[0070] As another way, the plurality of driving styles are arranged in an order, for example, the plurality of driving styles can be stored in a list locally in the vehicle. A movement is preset as a switching movement, when a situation of the switching movement is detected, the current driving style is determined as the target driving style in the order. It is not difficult to understand that the driving behavior data collected each time represents the switching movement, and the target driving style is switched according to the order.

[0071] Optionally, the target driving style can also be determined by determining the driving style memorized by the vehicle as the target driving style. For example, the memorized driving style can be the driving style set by the driver last time, or the driving style used by the vehicle last time.

[0072] Optionally, the target driving style can also be determined by determining the driving style with the highest score from the plurality of driving styles as the target driving style according to the score of each driving style in the plurality of driving styles by the user. The score can be obtained by the user manually scoring the driving style used after driving. The user can be the driver, and can also be the passenger in the vehicle.

[0073] In an embodiment, when the driving parameter includes a path selection parameter, step S120 can include determining the path selection parameter of the vehicle according to the environment information and the target driving style.

[0074] For example, according to the environment information, target object information is obtained, for example, the target object information includes the position, moving speed, acceleration, moving direction, etc. of the target object, and the target object can be a person, a vehicle, a movable baby stroller, a luggage box or a static object (such as an ice cream cone, a crash barrier, etc.). According to the target object information, a plurality of candidate paths are determined, wherein each candidate path in the plurality of candidate paths corresponds to a driving style. The driving path corresponding to the target driving style is determined from the plurality of candidate paths, and the path selection parameter is generated according to the determined driving path, wherein the path selection parameter is used to control the vehicle to drive according to the driving path.

[0075] For example, according to the target object information, a candidate path corresponding to the first driving style, a candidate path corresponding to the second driving style, a candidate path corresponding to the third driving style, a candidate path corresponding to the fourth driving style, and a candidate path corresponding to the fifth driving style are planned. When the target driving style is the first driving style, the candidate path corresponding to the first driving style is determined as the driving path.

[0076] The candidate path corresponding to the first driving style can be a path avoiding the target object, the candidate path corresponding to the second driving style can be a path with less lane changing and turning, the candidate path corresponding to the third driving style can be a path shuttling between different target objects, the candidate path corresponding to the fourth driving style can be a path with more lane changing and turning, and the candidate path corresponding to the fifth driving style can be a path following the movement of the target object.

[0077] In an implementation, the step S120 can include determining the driving parameter of the vehicle according to the target driving style by a parameter output model, wherein the parameter output model is trained according to sample environment information, sample driving style corresponding to the sample environment information, and sample driving parameter.

[0078] Optionally, the parameter output model can be a LLM (Large Language Model).

[0079] The parameter output model and the target scene description information-driving style association model can be sub-models in the same model, or can be two separate models, which are not limited in the present disclosure.

[0080] For example, the association model and the parameter output model belong to the same driving model, and the driving parameter is taken as the path selection parameter. Figure 2 The present disclosure can obtain a driving path by using the driving model 200. The driving model 200 is used to generate a driving path selection parameter according to environment information. For example, after the sensor on the vehicle collects the environment information, the environment information is input into the driving model 200 to obtain the driving path selection parameter output by the driving model 200. As an implementation, the target driving style is obtained by the driving model according to the environment information of the environment in which the vehicle is located. The driving path selection parameter of the vehicle is determined by the driving model according to the target driving style, wherein the driving model is trained according to sample environment information, sample driving style corresponding to the sample environment information, and sample driving path selection parameter.

[0081] Compared with the driving model in the related art, the driving model 200 of the present disclosure combines the driving style and plans different driving paths for different driving styles, improves the flexibility of automatic driving, makes the automatic driving closer to the real driving of the driver, and improves the riding experience.

[0082] Please continue to refer to Figure 2As a manner, the driving model 200 comprises an association model 230 and a parameter output model 240. The target driving style is obtained by the following manners: obtaining target scene description information for the environment information according to the environment information of the vehicle environment by the association model 230; determining the target driving style according to the target scene description information by the parameter output model 240.

[0083] As another manner, the target object information for the environment information is obtained by processing of the perception module 210 of the driving model 200. The target scene description information is obtained by the association model 230 according to the target object information. The target driving style is determined by the parameter output model 240 according to the target scene description information.

[0084] For the driving model 200 in Figure 2 , the training sample further comprises sample scene description information corresponding to the sample environment information, and the driving model is trained by the sample environment information, the sample scene description information, the sample driving style corresponding to the sample environment information, and the sample driving path.

[0085] Please continue to refer to Figure 2 , the driving model 200 further comprises a planning module 220. The environment information is input into the driving model 200, and the perception module 210 processes to obtain target object information. The planning module 220 obtains path selection parameters according to the target object information obtained by the perception module 210 and the target driving style obtained by the parameter output model 240. For example, the planning module 220 obtains the path selection parameters by the following manner: determining a plurality of candidate paths according to the target object information, wherein each candidate path in the plurality of candidate paths corresponds to a driving style; determining the driving path corresponding to the target driving style from the plurality of candidate paths, and generating the path selection parameters according to the path.

[0086] Optionally, the driving model 200 can be deployed on the vehicle, and can also be deployed on a server in communication with the vehicle.

[0087] Optionally, the association model 230 can be a VLM model, and the parameter output model 240 can be a LLM model.

[0088] Compared with the driving model in the related art, the driving model 200 of the present disclosure adds the association model 230 and the parameter output model 240, obtains the target driving style through the association model 230 and the parameter output model 240, and plans different driving paths for different driving styles in combination with the driving style, thereby improving the flexibility of automatic driving, making the automatic driving closer to the real driving of the driver, and improving the riding experience.

[0089] Optionally, the user can feed back the automatic driving of the vehicle, and the driving model is iteratively trained according to the user feedback, the driving path planned by the iteratively trained driving model is more in line with the user's expectation, a driving style that is more in line with the driver's demand is provided, and the user experience of automatic driving is improved.

[0090] For example, the feedback interface on the central control screen can evaluate the automatic driving to realize the feedback on the automatic driving.

[0091] Optionally, the vehicle control method further includes: determining a target vehicle speed according to the target driving style; and controlling the vehicle to automatically drive at the target vehicle speed according to the driving path.

[0092] Taking the automatic driving on a highway environment as an example, please refer to Figure 3 , which includes the vehicle 310 and other vehicles 320, 330 and 340. In the planned path, S1 is a candidate path corresponding to the first driving style that focuses on speed, S2 is a candidate path corresponding to the third driving style that focuses on agility, and S3 is a candidate path corresponding to the second driving style that focuses on safety. In order to show the difference between different candidate paths, Figure 3 The three candidate paths are displayed, and the driving path is determined from the candidate paths according to the target driving style, and the automatic driving is performed according to the driving path. For example, the target driving style can be the third driving style, and the automatic driving is performed according to the path S2.

[0093] If the path of the vehicle automatic driving does not meet the user's expectation, the user can manually switch the target driving style to switch the driving path. For example, the user can set the target driving style to the first driving style, and the vehicle automatically drives according to the path S1 corresponding to the first driving style.

[0094] The vehicle control method provided in this embodiment can improve the flexibility of automatic driving by manually switching the driving style by the user to switch the driving path.

[0095] Optionally, the vehicle control method provided by the present disclosure can determine the driving path of the vehicle according to the target driving style, and the method can also be applied to other scenarios that require path planning, such as unmanned aerial vehicles, robots, etc.

[0096] Based on the same inventive concept, the present disclosure also provides a vehicle control device, Figure 4 is a block diagram of a vehicle control device according to an example embodiment. Please refer to Figure 4 , the vehicle control device 400 includes a style determination module 410, a parameter determination module 420 and a driving control module 430.

[0097] The style determination module 410 is configured to determine a target driving style, wherein the target driving style is determined based on environment information of a vehicle surrounding; The parameter determination module 420 is configured to determine a driving path of the vehicle according to the target driving style; The driving control module 430 is configured to control the vehicle to perform automatic driving according to the driving path, wherein the driving parameter comprises at least one of the following: a path selection parameter, a target vehicle speed and acceleration, and a passing decision.

[0098] In some possible implementation manners, the style determination module 410, the parameter determination module 420 and the driving control module 430 can belong to one driving model.

[0099] In some possible implementation manners, the style determination module 410 comprises: A target scene description information determination module configured to determine target scene description information corresponding to the environment information of the vehicle surrounding according to the environment information of the vehicle surrounding; A style generation module configured to determine the target driving style matching the target scene description information based on a preset target scene description information-driving style association model.

[0100] In some possible implementation manners, the preset target scene description information-driving style association model supports user self-defined operations, and the self-defined operations comprise adding a new association between target scene description information and driving style, deleting an existing association between target scene description information and driving style, or modifying a corresponding relationship between target scene description information and driving style.

[0101] In some possible implementation manners, the preset target scene description information-driving style association model can be updated based on a driving operation record actually performed by the vehicle; The vehicle control apparatus 400 further comprises: A driving operation record collection module configured to collect the driving operation record actually performed by the vehicle; A driving operation record analysis module configured to determine environment information according to the driving operation record, and determine a driving style actually adopted under target scene description information corresponding to the environment information; An updating module configured to update a corresponding relationship between the target scene description information and the driving style in the preset target scene description information-driving style association model based on the target scene description information and the driving style actually adopted.

[0102] In some possible implementation manners, when the driving parameter comprises a path selection parameter, the parameter determination module 420 comprises: The path selection parameter module is configured to determine the path selection parameter of the vehicle according to the environment information and the target driving style, wherein the path selection parameter is used to determine the driving path.

[0103] In some possible implementation manners, the path selection parameter module is specifically configured to acquire target object information in the environment according to the environment information; determine a plurality of candidate paths according to the target object information, wherein each candidate path in the plurality of candidate paths corresponds to a driving style; determine the driving path corresponding to the target driving style from the plurality of candidate paths, and determine the path selection parameter according to the driving path.

[0104] In some possible implementation manners, the parameter determination module comprises: The model processing module is configured to determine the driving parameter of the vehicle according to the target driving style by using a parameter output model, wherein the parameter output model is trained according to sample driving styles corresponding to sample environment information and sample driving parameters.

[0105] In some possible implementation manners, the style determination module comprises: The target driving style determination module is configured to determine a selected target driving style from a plurality of driving styles in response to a style selection operation; or determine a driving style memorized by the vehicle as the target driving style; or determine a driving style with the highest score from the plurality of driving styles as the target driving style according to scores of each driving style in the plurality of driving styles input by the user; or determine the target driving style according to historical driving behavior data of the user in a region where the current surrounding environment of the vehicle is located when the user has visited the region before.

[0106] In one possible implementation manner, the vehicle control apparatus 400 further comprises: The adjustment parameter acquisition module is configured to determine corresponding in-vehicle atmosphere adjustment parameters based on the target driving style. The atmosphere adjustment module is configured to adjust one or more atmosphere components in the vehicle interior according to the in-vehicle atmosphere adjustment parameters, wherein the atmosphere components at least include a lighting system and a sound system.

[0107] As to the vehicle control apparatus 400 in the above embodiments, the specific manners in which the modules perform operations have been described in detail in the embodiments of the method, and will not be described in detail here.

[0108] The present disclosure also provides a computer readable storage medium having computer program instructions stored thereon, the program instructions being executed by a processor to implement the steps of the vehicle control method provided by the present disclosure.

[0109] The present disclosure also provides a chip system, which comprises a processor and an interface circuit, the processor acquires program instructions through the interface circuit, the program instructions are executed by the processor, and the processor is used for executing the steps of the aforementioned vehicle control method.

[0110] Figure 5 is a block diagram of a vehicle 600 according to an exemplary embodiment. For example, the vehicle 600 can be a hybrid vehicle, or a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 600 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0111] Referring to Figure 5 , the vehicle 600 can include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. The vehicle 600 can include more or fewer subsystems, and each subsystem can include multiple components. In addition, each subsystem of the vehicle 600 and each component can be interconnected by wired or wireless means.

[0112] In some embodiments, the infotainment system 610 can include a communication system, an entertainment system, a navigation system, and the like.

[0113] The perception system 620 can include several sensors for sensing information about the environment surrounding the vehicle 600. For example, the perception system 620 can include a global positioning system (which can be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera.

[0114] The decision control system 630 can include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0115] The drive system 640 can include components that provide power motion for the vehicle 600. In one embodiment, the drive system 640 can include an engine, an energy source, a transmission system, and wheels. The engine can be one or a combination of an internal combustion engine, an electric motor, an air compression engine. The engine can convert energy provided by the energy source into mechanical energy.

[0116] Part or all of the functions of the vehicle 600 are controlled by the computing platform 650. The computing platform 650 can include at least one processor 651 and a memory 652, and the processor 651 can execute instructions 653 stored in the memory 652.

[0117] The processor 651 can be any conventional processor, such as a commercial available CPU. The processor can also include a Graphic Process Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0118] The memory 652 can be implemented by any type of volatile or nonvolatile memory devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0119] In addition to the instructions 653, the memory 652 can also store data, such as road map, route information, the position, direction, speed of the vehicle, and the like. The data stored in the memory 652 can be used by the computing platform 650.

[0120] In the embodiments of the present disclosure, the processor 651 can execute the instructions 653 to complete all or part of the steps of the vehicle control method described above.

[0121] In another exemplary embodiment, a computer program product is also provided, which contains a computer program executable by a programmable device, and the computer program has code portions for executing the vehicle control method described above when executed by the programmable device.

[0122] Those skilled in the art can also understand that the various illustrative logical blocks and steps listed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of both. Whether the function is implemented by hardware or software depends on the specific application and design requirements of the whole system. Those skilled in the art can implement the described functions for each specific application by various methods, but such implementation should not be understood as beyond the scope of protection of the embodiments of the present application.

[0123] Furthermore, the word "exemplary" is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects or designs. Rather, use of the word exemplary is intended to present concepts in a concrete manner. As used in this application, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise, or clear from context, "X employs A or B" is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then "X employs A or B" is satisfied under any of the foregoing instances. In addition, the articles "a" and "an" as used in this application and the appended claims should generally be construed to mean "one or more" unless specified otherwise or clear from context to be directed to a singular form. Thus, use of the articles in this application and the following claims is not limiting.

[0124] Also, although the disclosure has been described with respect to only one or more implementations thereof, those skilled in the art will readily appreciate that other alternatives can be used. It is contemplated that the disclosure can be carried out in other specific ways than those expressly disclosed herein. Any and all such changes and modifications other than those already described and claimed are intended to be included within the scope of the disclosure. Specifically with respect to the various functions performed by the components (e.g., elements, resources, etc.) described above, unless otherwise specified, the terms used are intended to encompass any component which performs the specified function for an equivalent result. In addition, it is contemplated that various combinations or sub-combinations of the specific features and / or aspects of the disclosure can be made, and are intended to be within the scope of the disclosure. Further, unless otherwise specified, use of the terms in the description above are intended to be inclusive of the singular and the plural. Additionally, although the disclosure has been described with respect to only a few implementations, it will be appreciated that those skilled in the art will readily apply the principles of the disclosure to other implementations and applications without departing from the spirit and scope of the disclosure. It is intended, therefore, that the disclosure be limited only by the scope of the appended claims.

[0125] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features of the disclosure disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0126] It is understood that the present disclosure is not limited to the precise construction disclosed and as illustrated in the accompanying drawings, and that various modifications can be made by those skilled in the art without departing from the scope of the disclosure. The scope of the disclosure is limited only by the claims appended hereto.

Claims

1. A vehicle control method, characterized in that: The method comprises: Determining a target driving style; wherein the target driving style is determined based on environmental information surrounding the vehicle; determining driving parameters of the vehicle according to the target driving style; Controlling the vehicle to perform automatic driving according to the driving parameters; wherein the driving parameters include at least one of the following: a path selection parameter; Target vehicle speed and acceleration; Overtaking decision.

2. The method according to claim 1, characterized in that The target driving style is determined based on environmental information surrounding the vehicle, including: Determining target scene description information for the environmental information based on the environmental information around the vehicle; Based on a preset target scene description information-driving style association model, the target driving style matching the target scene description information is determined.

3. The method according to claim 2, characterized in that The preset target scene description information-driving style association model supports user customization operations, which include adding new associations between target scene description information and driving styles, deleting existing associations between target scene description information and driving styles, or modifying existing correspondences between target scene description information and driving styles.

4. The method according to claim 2, characterized in that The preset target scenario description information-driving style association model can be updated based on the driving operation record actually performed by the vehicle; wherein, the updating based on the user's actual operation record includes: Collecting a record of the driving operation actually performed by the vehicle; determining environmental information based on the driving operation record, and determining a driving style actually adopted under target scenario description information corresponding to the environmental information; Based on the target scene description information and the actually adopted driving style, the correspondence between the target scene description information and the driving style in the preset target scene description information-driving style association model is updated.

5. The method according to claim 1, wherein In a case where the driving parameters include path selection parameters, determining the driving parameters of the vehicle according to the target driving style includes: The path selection parameter of the vehicle is determined according to the environmental information and the target driving style, wherein the path selection parameter is used to determine a driving path.

6. The method according to claim 5, characterized in that The determining the path selection parameter of the vehicle according to the environmental information and the target driving style includes: Acquiring target object information in the environment according to the environmental information; determining a plurality of candidate paths according to the target object information, wherein each candidate path in the plurality of candidate paths corresponds to a driving style; The driving path corresponding to the target driving style is determined from the plurality of candidate paths, and the path selection parameter is determined according to the driving path.

7. The method according to claim 1, characterized in that Determining the driving parameters of the vehicle according to the target driving style includes: The driving parameters of the vehicle are determined according to the target driving style through a parameter output model, wherein the parameter output model is obtained by training based on a sample driving style corresponding to sample environmental information and sample driving parameters.

8. The method according to claim 1, characterized in that Determining the target driving style includes: In response to a style selection operation, determining a selected target driving style from a plurality of driving styles; or, determining the driving style memorized by the vehicle as the target driving style; or, based on the user's rating of each driving style among the multiple driving styles, determining the driving style with the highest rating from the multiple driving styles as the target driving style; Alternatively, when the user has previously visited the area where the vehicle's current surrounding environment is located, the target driving style is determined based on the user's historical driving behavior data in the area.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: determining corresponding in-vehicle atmosphere adjustment parameters based on the target driving style; adjusting one or more atmosphere components inside the vehicle according to the in-vehicle atmosphere adjustment parameters; Wherein, the atmosphere components at least include a lighting system and a sound system.

10. A vehicle control device, characterized in that: The device comprises: a style determination module configured to determine a target driving style; wherein the target driving style is determined based on environmental information surrounding the vehicle; a parameter determination module, configured to determine a driving parameter of the vehicle according to the target driving style; A driving control module is configured to control the vehicle to perform automatic driving according to the driving path; wherein the driving parameters include at least one of the following: path selection parameters, target vehicle speed and acceleration, and overtaking decision.

11. The device according to claim 10, characterized in that The style determination module includes: a target scene description information determination module, configured to determine target scene description information for the environmental information based on the environmental information around the vehicle; The style generation module is configured to determine the target driving style that matches the target scene description information based on a preset target scene description information-driving style association model.

12. The device according to claim 10, characterized in that The parameter determination module includes: The model processing module is configured to determine the driving parameters of the vehicle according to the target driving style through a parameter output model, wherein the parameter output model is obtained by training based on a sample driving style corresponding to sample environmental information and sample driving parameters.

13. The device according to claim 10, characterized in that The device further comprises: an adjustment parameter acquisition module configured to determine corresponding in-vehicle atmosphere adjustment parameters based on the target driving style; The atmosphere adjustment module is configured to adjust one or more atmosphere components inside the vehicle according to the in-vehicle atmosphere adjustment parameters; wherein the atmosphere components include at least a lighting system and an audio system.

14. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the steps of the method described in any one of claims 1 to 9 when executing the instruction.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

16. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

17. A chip system, characterized in that: The chip system includes a processor and an interface circuit, the processor obtains program instructions through the interface circuit, the program instructions are executed by the processor, and the processor is used to execute the steps of the method according to any one of claims 1 to 9.

Images