An automatic driving parameter adjustment method, a terminal and a computer storage medium

Abstract

The application relates to an automatic driving parameter adjustment method, a terminal and a computer storage medium, wherein the adjustment method comprises the following steps: obtaining identity information and driving environment information of a target object; determining driving style information of the target object according to the identity information and the driving environment information of the target object; determining preset driving parameters according to the driving style information of the target object, and verifying the preset driving parameters; and adjusting the automatic driving parameters of a vehicle according to the preset driving parameters that pass the verification. The automatic driving parameter adjustment method, the terminal and the computer storage medium provided by the application can determine the preset driving parameters according to the driving style information of the target object, adjust the automatic driving parameters of the vehicle according to the preset driving parameters that pass the verification, and improve the automatic driving experience and safety.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to a method for adjusting autonomous driving parameters, a terminal, and a computer storage medium. Background Technology

[0002] Autonomous driving technology relies on environmental perception to sense the vehicle's surroundings and, based on this information, autonomously controls the vehicle's steering and speed through an onboard central computer. This enables the vehicle to travel safely and reliably to its destination. It plays a crucial role in reducing traffic accidents, improving transportation efficiency, completing special tasks, and in national defense and military applications. The key technologies for autonomous driving are environmental perception and vehicle control. Environmental perception is the foundation of autonomous vehicle operation, while vehicle control is its core, encompassing trajectory planning and control execution. These two technologies complement each other and together constitute the key technologies for autonomous vehicles.

[0003] Autonomous driving systems generally consist of vehicle-mounted hardware and onboard software; the vehicle-mounted hardware includes sensors, positioning components, and actuators; the onboard software performs predictive analysis, behavioral decision-making, and optimized control. For example... Figure 1 As shown, the interaction process between autonomous vehicles and the external environment is as follows: First, sensors receive external environment information, and the positioning component confirms the map information and the vehicle's current coordinate system position. Both send the external environment information to the prediction and extrapolation module and the behavior decision module. The prediction and extrapolation module performs prediction and extrapolation based on the vehicle information and the external environment information to predict the trajectory of external objects. Subsequently, the behavior decision module makes a behavior decision, determines the vehicle's current action, and plans an optimal trajectory, which is then sent to the optimization control module. The optimization control module implements optimized control of the vehicle through actuators.

[0004] However, with current autonomous driving technology, once the autonomous driving software is programmed into the chip, users cannot (or can only influence to a limited extent) the behavior of the autonomous driving system (such as following distance, aggressive acceleration, and lane-changing intentions). This is because the parameters that determine the behavior of the autonomous driving software are scattered across various modules, and the impact of adjusting these parameters cannot be fully predicted before testing, thus preventing users from having the initiative to adjust these parameters. Furthermore, once the autonomous driving software is programmed, the parameters cannot be directly modified; only simple adjustments can be made through limited options in the human-machine interface, which cannot meet the needs of all users. Summary of the Invention

[0005] To address the aforementioned technical problems, this application provides a method for adjusting autonomous driving parameters, a terminal, and a computer storage medium to improve the autonomous driving experience and safety.

[0006] This application provides a method for adjusting autonomous driving parameters, including: acquiring the identity information and driving environment information of a target object; determining the driving style information of the target object based on the identity information and driving environment information; determining preset driving parameters based on the driving style information of the target object, and verifying the preset driving parameters; and adjusting the autonomous driving parameters of the vehicle based on the verified preset driving parameters.

[0007] In one embodiment, the identity information of the target object includes any one of the target object's facial features, iris information, and fingerprint information; the driving environment information includes at least one of the driving route, driving time, and weather conditions.

[0008] In one embodiment, the driving style information of the target object includes at least one of: lane change aggressiveness, speed tendency, distance tendency, acceleration aggressiveness, and steering wheel steering aggressiveness.

[0009] In one embodiment, determining preset driving parameters based on the driving style information of the target object includes: determining the range of values ​​for the driving style parameters based on the driving style information; and combining the parameter values ​​of each driving style parameter within the corresponding range to determine multiple sets of preset driving parameters.

[0010] In one embodiment, verifying the preset driving parameters includes: acquiring a verification scenario library and verification priorities; and verifying the multiple sets of preset driving parameters one by one in different verification scenarios according to the verification priorities, until one set of preset driving parameters passes the verification of all verification scenarios.

[0011] In one embodiment, the adjustment method further includes: acquiring the operation information of the target object; and updating the driving style information of the target object based on the operation information of the target object and the driving environment information.

[0012] In one embodiment, before updating the driving style information of the target object, the method includes: acquiring a training dataset; training a driving style recognition model based on the training dataset; the step of updating the driving style information of the target object based on the operation information of the target object and the driving environment information includes: analyzing the operation information of the target object and the driving environment information using the trained driving style recognition model to determine the driving style information of the target object under the current driving environment; and updating the information in the driving style information table of the target object based on the driving style information of the target object under the current driving environment.

[0013] In one embodiment, updating the driving style information of the target object includes: determining the update direction and update range based on the operation information of the target object and the driving environment information; and updating the driving style information of the target object based on the update direction and the update range.

[0014] This application also provides a terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described adjustment method.

[0015] This application also provides a computer storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described adjustment method.

[0016] This application provides a method, terminal, and computer storage medium for adjusting autonomous driving parameters, which can determine preset driving parameters based on the driving style information of the target object, and adjust the autonomous driving parameters of the vehicle based on the verified preset driving parameters, thereby improving the autonomous driving experience and safety. Attached Figure Description

[0017] Figure 1 This is a schematic diagram illustrating the interaction between an autonomous vehicle and its external environment in a typical implementation.

[0018] Figure 2 This is a flowchart illustrating the adjustment method provided in Embodiment 1 of this application;

[0019] Figure 3 This is a scene interaction illustration of the adjustment method provided in Embodiment 1 of this application. Figure 1 ;

[0020] Figure 4 This is a scene interaction illustration of the adjustment method provided in Embodiment 1 of this application. Figure 2 ;

[0021] Figure 5 This is a schematic diagram of the terminal provided in Embodiment 2 of this application. Detailed Implementation

[0022] The technical solutions of this application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this application. The word "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] Figure 2 This is a flowchart illustrating the adjustment method provided in Embodiment 1 of this application. Figure 2 As shown, the adjustment method of this application may include the following steps:

[0024] Step S101: Obtain the target object's identity information and driving environment information;

[0025] Optionally, the target is the driver, and the driver's identity information is collected and verified through the in-vehicle human-machine interface; the target's identity information includes any one of the target's facial features, iris information, and fingerprint information.

[0026] Optionally, the driving environment information includes at least one of the following: driving route (e.g., city, highway, etc.), driving time (e.g., daytime, nighttime, etc.), and weather conditions (e.g., visibility, wind speed, rainfall, etc.); Optionally, the driving route of the vehicle is obtained through an on-board positioning device, the driving time of the vehicle is obtained through an on-board time device, and the weather conditions are obtained through on-board sensors.

[0027] Step S102: Determine the target's driving style information based on the target's identity information and driving environment information;

[0028] Optionally, the acquired identity information and driving environment information of the target object are matched with the information in the target object's driving style information table to determine the target object's driving style information under the current driving environment. The target object's driving style information includes at least one of the following: lane change aggressiveness, speed tendency, distance tendency, acceleration aggressiveness, and steering wheel steering aggressiveness. The target object's driving style information table is a correspondence table between driving environment information and driving style information.

[0029] Optionally, lane-change aggressiveness is used to characterize whether a driver likes to change lanes; speed tendency is used to characterize the driver's preferred vehicle speed; following distance tendency is used to characterize the driver's preferred following distance, including following distance and lateral distance from other vehicles; acceleration aggression is used to characterize the driver's acceptable acceleration cost, including lateral acceleration cost and longitudinal acceleration cost; steering aggression is used to characterize the driver's acceptable impact cost, including lateral impact cost and longitudinal impact cost. Optionally, the driving style information of the target object is quantified, using 1-10 to represent the level of each driving style, such as 1-3 indicating that the driver does not like to change lanes, i.e., low lane-change aggressiveness; 4-7 indicating that the driver likes to change lanes, i.e., moderate lane-change aggressiveness; 8-10 indicating that the driver very likes to change lanes, i.e., high lane-change aggressiveness.

[0030] Step S103: Determine the preset driving parameters based on the target object's driving style information, and verify the preset driving parameters;

[0031] In one embodiment, determining preset driving parameters based on the target object's driving style information includes:

[0032] Based on the driving style information, determine the range of values ​​for the driving style parameters;

[0033] The parameter values ​​of each driving style parameter within their corresponding range are combined to determine multiple sets of preset driving parameters.

[0034] For example, if the target object's driving style information is high lane change aggressiveness, short following distance, high longitudinal acceleration cost, and high lateral impact cost, then the range of values ​​for lane change frequency is determined to be a first preset frequency range, the range of values ​​for following distance is determined to be a first preset following distance range, the height distribution range of the longitudinal acceleration cost curve is determined to be a first preset longitudinal acceleration cost distribution range, and the height distribution range of the lateral impact cost curve is determined to be a first preset lateral impact cost distribution range; the above preset ranges can be obtained based on experimental calibration values.

[0035] Then, the lane change frequency included in the first preset frequency range, the following distance included in the first preset following distance range, the longitudinal acceleration cost curve included in the first preset longitudinal acceleration cost distribution range, and the lateral impact cost curve included in the first preset lateral impact cost distribution range are combined to obtain multiple sets of preset driving parameters including lane change frequency, following distance, longitudinal acceleration cost curve, and lateral impact cost curve.

[0036] In one embodiment, verifying preset driving parameters includes:

[0037] Obtain the verification scenario library and verification priority;

[0038] According to the verification priority, multiple sets of preset driving parameters are verified one by one in different verification scenarios until one set of preset driving parameters passes the verification of all verification scenarios.

[0039] Optionally, the verification scenario library includes a basic simulation scenario library and a special simulation scenario library; wherein, the basic simulation scenario library includes simulation scenarios of normal road conditions and normal weather; the special simulation scenario library includes simulation scenarios of extreme road conditions and / or extreme weather; wherein, extreme road conditions and / or extreme weather can be simulated by data collected by vehicles, or by simulation software through real-time rendering, modification of road adhesion coefficient, increase of perception error, etc.

[0040] Optionally, the verification priority of each set of preset driving parameters is set according to the degree of impact on driving safety; the verification priority is directly proportional to the degree of impact on driving safety, that is, the higher the degree of impact of the preset driving parameters on driving safety, the higher their verification priority. For example, if a set of preset driving parameters includes the maximum lane change frequency within the lane change frequency range, the highest acceleration cost curve within the acceleration cost distribution range, and the minimum following distance within the following distance range, then the verification priority of this set of preset driving parameters is the highest.

[0041] Optionally, according to the verification priority, multiple sets of preset driving parameters are verified one by one in different verification scenarios such as the basic simulation scenario library and the special simulation scenario library until one set of preset driving parameters passes the verification of all verification scenarios.

[0042] Step S104: Adjust the vehicle's automatic driving parameters according to the verified preset driving parameters.

[0043] Optionally, based on the lane change frequency, distance, acceleration cost curve, and impact cost curve in the preset driving parameters that have been verified, the vehicle's autonomous driving parameters are updated. Under the premise of ensuring autonomous driving safety, the driver's driving style is incorporated to improve the autonomous driving experience.

[0044] It is worth mentioning that the adjustment method provided in Embodiment 1 of this application further includes: obtaining the operation information of the target object; and updating the driving style information of the target object based on the operation information of the target object and the driving environment information.

[0045] In one embodiment, before updating the driving style information of the target object, the method includes: acquiring a training dataset; and training a driving style recognition model based on the training dataset.

[0046] Since extreme road conditions and extreme weather are rare occurrences, the training parameters can be adjusted by recording or analyzing existing datasets and combining parameter settings and learning results from normal scenarios to accelerate the convergence speed of the driving style recognition model for special scenarios.

[0047] In one embodiment, the step of updating the driving style information of the target object based on the target object's operation information and driving environment information includes: analyzing the target object's operation information and driving environment information using a trained driving style recognition model to determine the target object's driving style information under the current driving environment; and updating the information in the target object's driving style information table based on the target object's driving style information under the current driving environment.

[0048] In one implementation, updating the driving style information of the target object includes:

[0049] Based on the target object's operational information and driving environment information, determine the update direction and update scope;

[0050] The driving style information of the target object is updated according to the update direction and update range.

[0051] Optionally, the target's operational information includes lane-changing operations (such as using turn signals, turning the steering wheel, etc.), distance radar data, accelerator pedal depth, accelerator pedal pressure, and steering wheel speed. Furthermore, based on the number of lane-changing operations performed by the driver within a preset time period and driving environment information, the driver's lane-changing aggressiveness level in the current driving environment can be determined; based on distance radar data and driving environment information, the driver's distance tendency level in the current driving environment can be determined; based on the average accelerator pedal depth and driving environment information, the driver's acceleration tendency level in the current driving environment can be determined; based on the average accelerator pedal pressure and driving environment information, the driver's acceleration aggression level in the current driving environment can be determined; and based on the average steering wheel speed and driving environment information, the driver's steering aggression level in the current driving environment can be determined.

[0052] For example, if the stored driver's lane change initiative level is 8 in the current driving environment, and the driver's lane change initiative level is determined to be 5 based on the driver's operation information and driving environment information, then the stored driver's lane change initiative level will be downgraded by 1 level, that is, the stored driver's lane change initiative level will be updated to 7; if the stored driver's lane change initiative level is 2 in the current driving environment, based on the driver's operation information and driving environment information, then the stored driver's lane change initiative level will be downgraded by 2 levels, that is, the stored driver's lane change initiative level will be updated to 6.

[0053] For example, if the driver's distance preference level is 6 in the current driving environment, and the driver's distance preference level is determined to be 9 based on the driver's operation information and driving environment information, then the driver's distance preference level is increased by 1 level, that is, the stored driver's distance preference level is updated to 7; if the driver's distance preference level is 1 in the current driving environment, that is, the driver's distance preference level is decreased by 1 level, that is, the stored driver's distance preference level is updated to 5.

[0054] Figure 3 This is a scene interaction illustration of the adjustment method provided in Embodiment 1 of this application. Figure 1 .like Figure 3As shown, the autonomous vehicle obtains the driver's identity information through a human-machine interface, acquires driving environment information through vehicle-side hardware such as sensors and positioning components, and performs identity authentication (ID authentication) on the driver. After the driver's identity authentication is successful, the driver's identity information and driving environment information are uploaded to the cloud and matched with the information in the driver's driving style information table stored in the cloud, or a new driving style information table for the driver is created (in the case of the driver using the vehicle for the first time). The cloud performs cyclic simulation verification on the driving style parameters in the matched or newly created driving style information table, and downloads the verified driving style parameters (driver model) to the vehicle. The vehicle's autonomous driving software automatically listens to and obtains the parameter table including the driving style parameters, and updates the autonomous driving parameters inside the software according to the driving style parameters.

[0055] In addition, based on the current autonomous driving system, a new takeover analysis software module is added to obtain the operations made by the driver when driving manually or taking over autonomous driving. Combined with driving environment information, the module analyzes driving expectations, determines the driver's driving style information in the current driving environment, and uploads the driver's driving style information in the current driving environment to the NetCloud to iteratively update the information in the driver style information table stored in the NetCloud.

[0056] Figure 4 This is a scene interaction illustration of the adjustment method provided in Embodiment 1 of this application. Figure 2 , Figure 4 and Figure 3 The difference lies in replacing the takeover analysis module with a shadow mode module. For example... Figure 4 As shown, the shadow mode module uploads the driver's operations, driving environment information, and vehicle data to NetCloud when the driver is manually driving or taking over autonomous driving. NetCloud analyzes the uploaded data to determine the driver's driving style information in the current driving environment and iteratively updates the information in the driver style information table stored in NetCloud.

[0057] It is worth mentioning that the adjustment method provided in this application also includes:

[0058] The driver's driving style information is displayed in the form of an intelligent assistant on the in-vehicle human-machine interface;

[0059] By combining non-fungible token (NFT) technology, after the driver successfully logs in to the smart assistant through identity authentication, a driver profile is automatically generated based on the driver's driving style information, making the driver more identified with and engaged with the vehicle brand. Furthermore, by combining decentralized finance (DeFi) technology, driving is treated as a form of gamified finance (Game Finance), making driving more interesting and engaging for drivers.

[0060] The autonomous driving parameter adjustment method provided in Embodiment 1 of this application obtains the driver's operation information and driving environment information, updates the driver's driving style information in real time, making the autonomous driving decision-making and behavior more human-like and closer to the current driver's habitual behavior patterns, reducing the autonomous driving takeover rate, and providing a more comfortable and personalized autonomous driving service; storing the driver's driving style information in the cloud and cyclically simulating and verifying it, while ensuring the adaptive adjustment of autonomous driving parameters, makes the impact of autonomous driving parameter adjustment predictable, greatly reducing the autonomous driving takeover rate and hidden risks, and effectively improving the autonomous driving experience and safety.

[0061] Figure 5 This is a schematic diagram of the terminal provided in Embodiment 2 of this application. The terminal of this application includes: a processor 110, a memory 111, and a computer program 112 stored in the memory 111 and executable on the processor 110. When the processor 110 executes the computer program 112, it implements the steps in the above-described adjustment method embodiments.

[0062] The terminal may include, but is not limited to, a processor 110 and a memory 111. Those skilled in the art will understand that... Figure 5 This is merely an example of a terminal and does not constitute a limitation on the terminal. It may include more or fewer components than shown, or combine certain components, or different components. For example, a terminal may also include input / output devices, network access devices, buses, etc.

[0063] The processor 110 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0064] The memory 111 can be an internal storage unit of the terminal, such as the terminal's hard drive or RAM. The memory 111 can also be an external storage device of the terminal, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 111 can include both internal and external storage units. The memory 111 is used to store computer programs and other programs and data required by the terminal. The memory 111 can also be used to temporarily store data that has been output or will be output.

[0065] This application also provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above-described adjustment method.

[0066] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0068] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for adjusting autonomous driving parameters, characterized in that, include: Obtain the target's identity information and driving environment information; Based on the target object's identity information and the driving environment information, determine the target object's driving style information; Based on the driving style information of the target object, multiple sets of preset driving parameters are determined; According to the verification priority, the multiple sets of preset driving parameters are verified one by one in different verification scenarios until one set of preset driving parameters passes the verification of all verification scenarios. Adjust the vehicle's autonomous driving parameters based on a set of verified preset driving parameters.

2. The adjustment method as described in claim 1, characterized in that, The identity information of the target object includes any one of the target object's facial features, iris information, and fingerprint information; the driving environment information includes at least one of the driving route, driving time, and weather conditions.

3. The adjustment method as described in claim 1, characterized in that, The driving style information of the target object includes at least one of the following: lane change aggressiveness, speed tendency, distance tendency, acceleration aggressiveness, and steering wheel steering aggressiveness.

4. The adjustment method as described in claim 1, characterized in that, Based on the driving style information of the target object, multiple sets of preset driving parameters are determined, including: Based on the driving style information, determine the range of values ​​for the driving style parameters; The parameter values ​​of each driving style parameter within their corresponding range are combined to determine multiple sets of preset driving parameters.

5. The adjustment method as described in claim 1, characterized in that, The adjustment method further includes: Obtain the operation information of the target object; Update the driving style information of the target object based on the operation information of the target object and the driving environment information.

6. The adjustment method as described in claim 5, characterized in that, Before updating the driving style information of the target object, the following steps are included: Obtain the training dataset; Based on the training dataset, train a driving style recognition model; The step of updating the driving style information of the target object based on the operation information of the target object and the driving environment information includes: By analyzing the operation information of the target object and the driving environment information through the trained driving style recognition model, the driving style information of the target object in the current driving environment is determined. Update the information in the target object's driving style information table based on the target object's driving style information under the current driving environment.

7. The adjustment method according to any one of claims 5-6, characterized in that, Updating the driving style information of the target object includes: Based on the operation information of the target object and the driving environment information, determine the update direction and update range; The driving style information of the target object is updated according to the update direction and the update magnitude.

8. A terminal, characterized in that, The terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the adjustment method as described in any one of claims 1 to 7.

9. A computer storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the adjustment method as described in any one of claims 1 to 7.

Images