Adaptive driving assist control method and device

Abstract

The application relates to the technical field of vehicle control, in particular to a self-adaptive driving boost control method and device, which comprises the following steps: obtaining driver identity information, collecting driving environment information and driving parameter information in vehicle driving, identifying each driving scene in the driving environment information, obtaining driving parameters corresponding to each driving scene according to the driving parameter information, inputting each driving scene and the corresponding driving parameter into a pre-trained deep learning model to obtain a boost curve, and performing boost control on the vehicle according to the boost curve when a confirmation instruction for the boost curve is received. According to the application, the driving environment information and the driving parameter information in vehicle driving are collected, the boost curve is updated by using the pre-trained deep learning model, that is, the boost curve is updated according to the driving data of the driver, different drivers can obtain different boost curves, and the targeted boost control improves the convenience of the driver in driving the vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, specifically to an adaptive driving assistance control method and device. Background Technology

[0002] As new energy vehicles continue to upgrade and iterate in terms of electrification, intelligence, and connectivity, users' demands for intelligent features are also constantly increasing. For new energy vehicles, the driver's actions can be broken down into pressing the accelerator, pressing the brake, and turning the steering wheel to complete normal driving. Generally, car manufacturers only provide drivers with uniform fixed modes such as normal mode, sport mode, and eco mode. Each mode has a fixed assist curve for the power steering of pressing the accelerator, pressing the brake, and turning the steering wheel. For anyone, the same assist curve is used when controlling the vehicle. However, each driver's driving habits and operating preferences are different. Uniform power steering makes it difficult for drivers to drive the vehicle conveniently.

[0003] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention

[0004] This application provides an adaptive driving assistance control method and device to solve the technical problem in related technologies where the same assistance curve is used when assisting the vehicle, and the uniform assistance control makes it difficult for the driver to drive the vehicle conveniently.

[0005] To achieve the above objectives, this application adopts the following technical solution: The first aspect of this application provides an adaptive driving assistance control method, comprising the following steps: Obtain driver identification information and collect driving environment and driving parameter information while the vehicle is in motion; Identify each driving scenario in the driving environment information, and obtain the driving parameters corresponding to each driving scenario based on the driving parameter information; Each driving scenario and its corresponding driving parameters are input into a pre-trained deep learning model to obtain the assist curve; When a confirmation command for the assist curve is received, the vehicle is assisted in accordance with the assist curve.

[0006] Based on the above technical means, the embodiments of this application collect driving environment information and driving parameter information during vehicle operation, and update the assistance curve using a pre-trained deep learning model. That is, the assistance curve is updated according to the driver's driving data, and different drivers can obtain different assistance curves. Targeted assistance control improves the convenience of driving the vehicle for the driver.

[0007] Optionally, in one embodiment of this application, the driver identity information includes driver facial information and / or driver fingerprint information, the driving environment information includes vehicle road condition information, traffic flow information and obstacle information, the driving scenario includes one or more of starting scenario, acceleration scenario, cruising scenario, braking scenario and steering scenario, and the driving parameter information includes accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle.

[0008] Based on the above technical means, in this embodiment of the application, the driver's identity is identified, and the driver's facial information and / or fingerprint information are saved and bound to the driver's driving habits and operating preferences, thereby completing the driver's personalized switching of driving habits and operating preferences.

[0009] Optionally, in one embodiment of this application, before obtaining the driver's identity information and collecting driving environment information and driving parameter information during vehicle operation, the method further includes: Receive the login command for the adaptive driving assistance system; If this is the first login, the driver's identity information will be collected and stored; When a vehicle component position adjustment instruction is received, the vehicle component position information is obtained based on the current vehicle component position, and a first correspondence is established between the driver identity information and the vehicle component position information.

[0010] Based on the above technical means, the embodiments of this application can directly call the corresponding vehicle component position information and automatically adjust the position of vehicle components such as rearview mirrors and seats, realizing the automatic adjustment of vehicle component positions according to personal preferences and habits, and achieving personalized customization.

[0011] Optionally, in one embodiment of this application, the various driving scenarios and corresponding driving parameters are input into a pre-trained deep learning model to obtain assist curves, including: Obtain all driving scenarios and corresponding driving parameters within a preset time period; All the driving scenarios and corresponding driving parameters are input into a pre-trained deep learning model to obtain the assistance curve, and a second correspondence is established between the assistance curve and the driver's identity information.

[0012] Based on the above technical means, this application embodiment obtains historical data according to the driver's identity information, and updates the power assist curve using all driving scenarios and corresponding driving parameters within a preset time period, thereby improving the accuracy of updating the power assist curve.

[0013] Optionally, in one embodiment of this application, after receiving the adaptive driving assistance system login command, the method further includes: If this is not the first login, then the driver's identity information is collected, and the first and second correspondences are found based on the driver's identity information; Based on the first correspondence, vehicle component location information corresponding to the driver's identity information is obtained; based on the second correspondence, assist curve corresponding to the driver's identity information is obtained. The positions of the vehicle components are adjusted according to the aforementioned vehicle component position information.

[0014] Based on the above technical means, in this embodiment of the application, when the driver uses the vehicle again, the driver's identity information will be automatically identified and the relevant settings will be adjusted to the memory position to achieve adaptive interaction with the user and bring the user a convenient and fast operating experience.

[0015] Optionally, in one embodiment of this application, before performing power assist control on the vehicle according to the power assist curve upon receiving a confirmation command for the power assist curve, the method further includes: If a power assist curve adjustment instruction is received, the power assist curve is adjusted according to the instruction.

[0016] Based on the above-mentioned technical means, the embodiments of this application can manually confirm and adjust details on the new assist curve, further improving the personalization and convenience of assist control.

[0017] Optionally, in one embodiment of this application, the deep learning model is a convolutional neural network or a recurrent neural network.

[0018] Based on the above technical means, the deep learning model used in the embodiments of this application can continuously optimize and adjust the fitting parameters of the accelerator pedal, brake pedal, and steering wheel rotation assist curves under different scenarios, thereby generating an assist curve that can adapt to driving.

[0019] A second aspect of this application provides an adaptive driving assistance control device, comprising: The data acquisition module is used to obtain driver identity information and collect driving environment information and driving parameter information during vehicle operation; The identification module is used to identify each driving scenario in the driving environment information and obtain the driving parameters corresponding to each driving scenario based on the driving parameter information. The input module is used to input each driving scenario and the corresponding driving parameters into a pre-trained deep learning model to obtain the assist curve; The control module is used to perform power assist control on the vehicle according to the power assist curve when a confirmation command for the power assist curve is received.

[0020] A third aspect of this application provides a vehicle, the vehicle including a memory, a processor, and an adaptive driving assistance control program stored in the memory and executable on the processor, wherein when the processor executes the adaptive driving assistance control program, it implements the steps of the adaptive driving assistance control method as described above.

[0021] A fourth aspect of this application provides a computer-readable storage medium storing an adaptive driving assistance control program, which, when executed by a processor, implements the steps of the adaptive driving assistance control method as described above.

[0022] The beneficial effects of this application are: (1) This application collects driving environment information and driving parameter information during vehicle driving, and uses a pre-trained deep learning model to update the assist curve. That is, the assist curve is updated according to the driver's driving data. Different drivers can obtain different assist curves. Targeted assist control improves the convenience of driving the vehicle for the driver.

[0023] (2) When the driver uses the vehicle again, this application will automatically identify the driver's identity information, adjust the relevant settings to the memory position, realize adaptive interaction with the user, and bring the user a convenient and fast operating experience.

[0024] (3) This application obtains historical data based on the driver's identity information and updates the power assist curve using all driving scenarios and corresponding driving parameters within a preset time period, thereby improving the accuracy of updating the power assist curve.

[0025] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0026] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating an adaptive driving assistance control method provided in this application embodiment; Figure 2 This is a schematic diagram of the processing logic of the adaptive driving assistance control method according to an embodiment of this application. Figure 3 This is a flowchart of a specific embodiment of the adaptive driving assistance control method according to this application.

[0027] Figure 4 This is a schematic diagram of the adaptive driving assistance control device according to an embodiment of this application; Figure 5 This is a block diagram illustrating the internal structure of a vehicle as provided in an embodiment of this application. Detailed Implementation

[0028] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0029] The adaptive driving assistance control method and apparatus of this application are described below with reference to the accompanying drawings. Addressing the problem mentioned in the background art where the same assistance curve is used for all vehicle assistance control, leading to inconvenience for drivers, this application provides an adaptive driving assistance control method. In this method, driver identity information is obtained, and driving environment information and driving parameter information during vehicle operation are collected; various driving scenarios in the driving environment information are identified, and driving parameters corresponding to each driving scenario are obtained based on the driving parameter information; each driving scenario and its corresponding driving parameters are input into a pre-trained deep learning model to obtain an assistance curve; when a confirmation command for the assistance curve is received, assistance control is applied to the vehicle according to the assistance curve. This application embodiment, by collecting driving environment information and driving parameter information during vehicle operation and updating the assistance curve using a pre-trained deep learning model, updates the assistance curve based on the driver's driving data. Different drivers can obtain different assistance curves, and targeted assistance control improves the convenience of driving and solves the problem of using the same assistance curve for all vehicle assistance control, which makes driving inconvenient for drivers.

[0030] Specifically, Figure 1 This is a schematic flowchart of an adaptive driving assistance control method provided in an embodiment of this application.

[0031] like Figure 1 As shown, the adaptive driving assistance control method includes the following steps: In step S101, driver identity information is obtained, and driving environment information and driving parameter information during vehicle operation are collected.

[0032] In this embodiment, the vehicle is equipped with onboard sensors and a data acquisition module. The onboard sensors are used to obtain the driver's identity information, and the data acquisition module is used to collect driving environment information and driving parameter information in real time while the vehicle is in motion, thereby enabling personalized training of the assist curve.

[0033] In step S102, each driving scenario in the driving environment information is identified, and the driving parameters corresponding to each driving scenario are obtained based on the driving parameter information.

[0034] In this embodiment, the real-time collected driving environment information is cleaned and processed to obtain the corresponding driving scenario. Both the driving environment information and the driving parameter information are time-series data, and there will be corresponding current driving parameters in a certain driving scenario.

[0035] In one embodiment of this application, the driver identity information includes driver facial information and / or driver fingerprint information, the driving environment information includes vehicle road condition information, traffic flow information and obstacle information, the driving scenario includes one or more of the following: starting scenario, acceleration scenario, cruising scenario, braking scenario and steering scenario, and the driving parameter information includes accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle.

[0036] This embodiment can collect driver facial information or driver fingerprint information through cameras and fingerprint sensors, or both, to increase recognition accuracy. Furthermore, it uses vehicle-mounted sensors such as LiDAR, millimeter-wave radar, cameras, and GPS to collect and process real-time information about the vehicle's surrounding environment, including road conditions, traffic flow, and obstacles. Simultaneously, it collects real-time data on accelerator pedal operation, brake pedal operation, and steering wheel rotation. The processed driving environment information is categorized into driving scenarios, including common scenarios such as starting, acceleration, cruising, braking, and steering. Driving parameters include accelerator pedal acceleration, brake pedal acceleration, and steering wheel rotation angle, which are then input into the deep learning model. During daily driving, the data acquisition module collects and processes real-time information on accelerator pedal operation, brake pedal operation, steering wheel rotation, and surrounding environment information, providing data for updating the power assist curve.

[0037] This application embodiment identifies the driver's identity, saves the driver's facial information and / or fingerprint information, and binds it to the driver's driving habits and operating preferences, thereby completing the personalized switching of the driver's driving habits and operating preferences.

[0038] In one embodiment of this application, before step S101, the method further includes: receiving an adaptive driving assistance system login instruction; if it is the first login, collecting and storing driver identity information; when a vehicle component position adjustment instruction is received, obtaining vehicle component position information based on the current vehicle component position, and establishing a first correspondence between driver identity information and vehicle component position information.

[0039] In this embodiment, when a driver uses the adaptive driving assistance system for the first time, they need to register their personal biometric information, such as facial features and fingerprints, through a camera sensor and a fingerprint sensor. Vehicle component positions refer to the positions of components such as rearview mirrors and seats. In this embodiment, the positions of vehicle components such as the exterior rearview mirrors and seats are adjusted according to personal preferences and bound to the driver's identity information. Thus, the next time the driver drives, the corresponding vehicle component position information can be directly retrieved, and the positions of vehicle components such as the rearview mirrors and seats can be automatically adjusted. This achieves automatic adjustment of vehicle component positions according to personal preferences and habits, realizing personalized customization.

[0040] In step S103, each driving scenario and its corresponding driving parameters are input into a pre-trained deep learning model to obtain the assist curve.

[0041] In this embodiment, various driving scenarios and corresponding driving parameters are input into a pre-trained deep learning model. Based on this data, calculations are performed to adjust the assist curves for pressing the accelerator, pressing the brake, and turning the steering wheel in different scenarios.

[0042] In one embodiment of this application, step S103 specifically includes: obtaining all driving scenarios and corresponding driving parameters within a preset time period; inputting all driving scenarios and corresponding driving parameters into a pre-trained deep learning model to obtain the assist curve, and establishing a second correspondence between the assist curve and the driver's identity information.

[0043] In this embodiment, the system can learn from historical and current data, continuously calculate and adjust the power assist curves for different positions of the accelerator, brake, and steering wheel to increase the accuracy of the power assist curves. Upon initial login, there is no historical data available for the driver. The driver can select data from various modes provided by the system, i.e., driving parameters such as accelerator, brake, and steering wheel operation for different scenarios such as starting, accelerating, cruising, braking, and steering. The selected driving scenario and corresponding driving parameters are then bound to the driver's identity information.

[0044] This application embodiment acquires historical data based on driver identity information and updates the power assist curve using all driving scenarios and corresponding driving parameters within a preset time period, thereby improving the accuracy of updating the power assist curve.

[0045] In one embodiment of this application, after receiving the login instruction for the adaptive driving assistance system, the method further includes: if it is not the first login, collecting driver identity information, searching for a first correspondence and a second correspondence based on the driver identity information; obtaining vehicle component position information corresponding to the driver identity information based on the first correspondence, obtaining the assistance curve corresponding to the driver identity information based on the second correspondence; and adjusting the position of the vehicle components according to the vehicle component position information.

[0046] In this embodiment, when the driver uses the vehicle again, the driver's identity information will be automatically recognized, and the relevant settings will be adjusted to the memory position to achieve adaptive interaction with the user, bringing the user a convenient and fast operating experience.

[0047] In step S104, when a confirmation command for the assist curve is received, the vehicle is assisted and controlled according to the assist curve.

[0048] In this embodiment, the driver is given feedback on the changes in the power assist curve at certain time intervals, and can choose whether to confirm the modification, thereby meeting the driver's personalized driving needs.

[0049] In one embodiment of this application, before performing power assist control on the vehicle according to the power assist curve when a confirmation instruction for the power assist curve is received, the method further includes: if a power assist curve adjustment instruction is received, adjusting the power assist curve according to the power assist curve adjustment instruction.

[0050] The embodiments of this application can also prompt the driver to update the adaptive driving assistance system after obtaining the assistance curve, and manually confirm and adjust the details on the new assistance curve, further improving the personalization and convenience of assistance control.

[0051] In one embodiment of this application, the deep learning model is a convolutional neural network or a recurrent neural network. The deep learning model employs a convolutional neural network (CNN) or a recurrent neural network (RNN). For training the deep learning model, historical data from the past year and current input data can be used as the training dataset. This allows the deep learning model to continuously optimize and adjust the fitting parameters of the accelerator pedal, brake pedal, and steering wheel steering assist curves under different vehicle speeds, turning, and braking scenarios, thereby generating an adaptive steering assist curve.

[0052] In the embodiments of this application, such as Figure 2As shown, step A1 involves collecting driving environment and driving parameter information during vehicle operation using the data acquisition module; step A2 involves identifying the driver's identity information in the driver identification system; step A3 involves switching between vehicle preferred position and driving preference; step A4 involves using the assist curve for assist control in the vehicle execution control module; and step A5 involves inputting the data into a pre-trained deep learning model to train the vehicle assist curve.

[0053] In one embodiment, such as Figure 3 As shown, step B1 is identity verification; Step B2: Determine if the driver is a new driver; if yes, proceed to steps C1 and C2; if no, proceed to step B3. Step B3: Adjust the rearview mirrors and seats to the memory positions; Step B4: Adjust the power assist sensitivity for pressing the accelerator, pressing the brake, and turning the steering wheel in different scenarios; where power assist sensitivity refers to the acceleration of pressing the accelerator, the acceleration of pressing the brake, and the steering wheel rotation angle. Step B5: During the journey, collect road condition and scene information; Step B6: During driving, collect data on accelerator pedal pressure, brake pedal pressure, and steering wheel rotation angle; and then proceed to step B7. Step C1: Set the rearview mirror and seat positions; Step C2: Select different scenarios and test the power steering sensitivity when pressing the accelerator, pressing the brake, and turning the steering wheel; then proceed to step B7. Step B7: Calculate the boost curve using deep learning algorithms such as convolutional neural networks (CNN).

[0054] like Figure 4 As shown, the adaptive driving assistance control device 10 includes: a data acquisition module 100, a recognition module 200, an input module 300, and a control module 400.

[0055] Specifically, the data acquisition module 100 is used to acquire driver identity information and to collect driving environment information and driving parameter information during vehicle operation; The recognition module 200 is used to identify various driving scenarios in the driving environment information and obtain the driving parameters corresponding to each driving scenario based on the driving parameter information. The input module 300 is used to input various driving scenarios and corresponding driving parameters into a pre-trained deep learning model to obtain the assist curve; The control module 400 is used to perform power assist control on the vehicle according to the power assist curve when a confirmation command for the power assist curve is received.

[0056] Optionally, the driver identity information includes the driver's facial information and / or the driver's fingerprint information; the driving environment information includes vehicle road condition information, traffic flow information and obstacle information; the driving scenario includes one or more of the following: starting scenario, acceleration scenario, cruising scenario, braking scenario and steering scenario; and the driving parameter information includes accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle.

[0057] Optionally, the adaptive driving assistance control device 10 further includes: an adjustment module for receiving an adaptive driving assistance system login command; if it is the first login, collecting and storing driver identity information; when receiving a vehicle component position adjustment command, obtaining vehicle component position information based on the current vehicle component position, and establishing a first correspondence between driver identity information and vehicle component position information.

[0058] Optionally, the input module 300 includes: The acquisition unit is used to acquire all driving scenarios and corresponding driving parameters within a preset time period; The input unit is used to input all driving scenarios and corresponding driving parameters into a pre-trained deep learning model to obtain the assist curve and establish a second correspondence between the assist curve and the driver's identity information.

[0059] Optionally, the input module 300 also includes: The lookup unit is used to collect driver identity information if it is not the first login, and to look up the first and second correspondences based on the driver identity information; The information acquisition unit is used to obtain vehicle component location information corresponding to the driver's identity information according to the first correspondence relationship, and to obtain the power assist curve corresponding to the driver's identity information according to the second correspondence relationship. The position adjustment unit is used to adjust the position of vehicle components according to the vehicle component position information.

[0060] Optionally, the adaptive driving assist control device 10 also includes: The curve adjustment module is used to adjust the assist curve according to the assist curve adjustment command if an assist curve adjustment command is received.

[0061] Alternatively, the deep learning model can be a convolutional neural network or a recurrent neural network.

[0062] It should be noted that the foregoing explanation of the adaptive driving assistance control method embodiment also applies to the adaptive driving assistance control device of this embodiment, and will not be repeated here.

[0063] According to the adaptive driving assistance control device proposed in this application, the device acquires driver identity information and collects driving environment information and driving parameter information during vehicle operation; identifies various driving scenarios in the driving environment information and obtains driving parameters corresponding to each driving scenario based on the driving parameter information; inputs each driving scenario and its corresponding driving parameters into a pre-trained deep learning model to obtain an assistance curve; and when a confirmation command for the assistance curve is received, assist control is applied to the vehicle according to the assistance curve. This application, by collecting driving environment information and driving parameter information during vehicle operation and updating the assistance curve using a pre-trained deep learning model, updates the assistance curve based on the driver's driving data. Different drivers can obtain different assistance curves, and targeted assistance control improves the convenience of driving the vehicle, solving the problem that using the same assistance curve for all vehicle assistance control leads to inconvenient driving.

[0064] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0065] When the processor 502 executes the program, it implements the adaptive driving assistance control method provided in the above embodiments.

[0066] Furthermore, the vehicle also includes: Communication interface 503 is used for communication between memory 501 and processor 502.

[0067] The memory 501 is used to store computer programs that can run on the processor 502.

[0068] The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0069] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The symbol is represented by only one line, but this does not mean that there is only one bus or one type of bus.

[0070] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0071] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0072] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described adaptive driving assistance control method.

[0073] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0074] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0075] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0076] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can read and execute instructions from or in conjunction with such an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). In addition, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically by optically scanning paper or other media, then editing, interpreting or otherwise processing them as necessary, and then storing them in computer memory.

[0077] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0078] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0079] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0080] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. An adaptive driving assistance control method, characterized in that, Includes the following steps: Obtain driver identification information and collect driving environment and driving parameter information while the vehicle is in motion; Identify each driving scenario in the driving environment information, and obtain the driving parameters corresponding to each driving scenario based on the driving parameter information; Each driving scenario and its corresponding driving parameters are input into a pre-trained deep learning model to obtain the assist curve; When a confirmation command for the assist curve is received, assist control is applied to the vehicle according to the assist curve. The driver identity information includes driver facial information and / or driver fingerprint information; the driving environment information includes vehicle road condition information, traffic flow information and obstacle information; the driving scenario includes one or more of the following: starting scenario, acceleration scenario, cruising scenario, braking scenario and steering scenario; and the driving parameter information includes accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle. Before obtaining the driver's identity information and collecting driving environment information and driving parameter information during vehicle operation, the method further includes: receiving an adaptive driving assistance system login command; if it is the first login, collecting and storing the driver's identity information; when receiving a vehicle component position adjustment command, obtaining vehicle component position information based on the current vehicle component position, and establishing a first correspondence between the driver's identity information and the vehicle component position information. The process involves inputting each driving scenario and its corresponding driving parameters into a pre-trained deep learning model to obtain an assistance curve, including: acquiring all driving scenarios and their corresponding driving parameters within a preset time period; inputting all driving scenarios and their corresponding driving parameters into a pre-trained deep learning model to obtain an assistance curve; and establishing a second correspondence between the assistance curve and the driver's identity information. After receiving the login command for the adaptive driving assistance system, the method further includes: if it is not the first login, collecting driver identity information, searching for the first correspondence and the second correspondence based on the driver identity information; obtaining vehicle component position information corresponding to the driver identity information based on the first correspondence, obtaining the assistance curve corresponding to the driver identity information based on the second correspondence; and adjusting the vehicle component position according to the vehicle component position information. Identifying each driving scenario in the driving environment information and obtaining the driving parameters corresponding to each driving scenario based on the driving parameter information includes: cleaning the real-time collected driving environment information to obtain the corresponding driving scenario. Both the driving environment information and the driving parameter information are time-series data, and the driving scenario corresponds to the current driving parameters. Each driving scenario and its corresponding driving parameters are input into a pre-trained deep learning model to obtain the assist curve, including: selecting the accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle under different scenarios, and calculating the assist curve through the pre-trained deep learning model.

2. The adaptive driving assistance control method as described in claim 1, characterized in that, Before performing power assist control on the vehicle according to the power assist curve when a confirmation command for the power assist curve is received, the procedure further includes: If a power assist curve adjustment instruction is received, the power assist curve is adjusted according to the instruction.

3. The adaptive driving assistance control method as described in claim 1, characterized in that, The deep learning model is a convolutional neural network or a recurrent neural network.

4. An adaptive driving assistance control device, characterized in that, include: The data acquisition module is used to obtain driver identity information and collect driving environment information and driving parameter information during vehicle operation; The identification module is used to identify each driving scenario in the driving environment information and obtain the driving parameters corresponding to each driving scenario based on the driving parameter information. The input module is used to input each driving scenario and the corresponding driving parameters into a pre-trained deep learning model to obtain the assist curve; The control module is used to perform power assist control on the vehicle according to the power assist curve when a confirmation command for the power assist curve is received. Driver identity information includes driver facial information and / or driver fingerprint information; driving environment information includes vehicle road condition information, traffic flow information and obstacle information; driving scenario includes one or more of the following: starting scenario, acceleration scenario, cruising scenario, braking scenario and steering scenario; driving parameter information includes accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle. The adaptive driving assistance control device also includes: an adjustment module, used to receive the adaptive driving assistance system login command; if it is the first login, it collects and stores the driver's identity information; when it receives the vehicle component position adjustment command, it obtains the vehicle component position information based on the current vehicle component position, and establishes a first correspondence between the driver's identity information and the vehicle component position information; The input module includes: an acquisition unit for acquiring all driving scenarios and corresponding driving parameters within a preset time period; and an input unit for inputting all driving scenarios and corresponding driving parameters into a pre-trained deep learning model to obtain the assist curve and establish a second correspondence between the assist curve and the driver's identity information. The lookup unit is used to collect driver identity information if it is not the first login, and look up the first and second correspondences based on the driver identity information; the information acquisition unit is used to obtain the vehicle component position information corresponding to the driver identity information based on the first correspondence, and obtain the power assist curve corresponding to the driver identity information based on the second correspondence; the position adjustment unit is used to adjust the position of the vehicle components according to the vehicle component position information. Identifying each driving scenario in the driving environment information and obtaining the driving parameters corresponding to each driving scenario based on the driving parameter information includes: cleaning the real-time collected driving environment information to obtain the corresponding driving scenario. Both the driving environment information and the driving parameter information are time-series data, and the driving scenario corresponds to the current driving parameters. Each driving scenario and its corresponding driving parameters are input into a pre-trained deep learning model to obtain the assist curve, including: selecting the accelerator pedal acceleration, brake pedal acceleration and steering wheel rotation angle under different scenarios, and calculating the assist curve through the pre-trained deep learning model.

5. A vehicle, characterized in that, The vehicle includes a memory, a processor, and an adaptive driving assistance control program stored in the memory and executable on the processor. When the processor executes the adaptive driving assistance control program, it implements the steps of the adaptive driving assistance control method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an adaptive driving assistance control program, which, when executed by a processor, implements the steps of the adaptive driving assistance control method as described in any one of claims 1-3.

Images