Method and System for Smooth Handover of Autopilot Control Right Based on Dynamic Gradient Limitation

Abstract

The present invention is applicable to the field of automotive technology, and provides a method and system for smooth handover of autonomous driving control rights based on dynamic gradient limiting. The method includes: detecting the driver's operation intention, preventing false triggering through dual thresholds, and triggering a handover signal. Calculating dynamic limits according to the driver's torque, supporting multi-mode parameter selection to adapt to different scenarios. Limiting the smooth torque change rate, generating a compensation torque, and outputting the final torque through an attenuation function. Dynamically optimizing according to the real-time error, achieving iterative convergence, and ensuring a fast and stable switching process. The present invention solves the problem of uneven torque generated during manual takeover in the existing human-machine co-driving, and reduces the danger of human-machine co-driving. By designing an iterative optimization scheme, the present invention reduces jitter and error during the entire switching process, enhances the driver's sense of control, avoids the driver's nervousness caused by problems such as steering wheel response, and makes the driver more comfortable and safe when taking over autonomous driving.

Description

Technical Field

[0001] The present invention belongs to the technical field of automobiles, and particularly relates to a method and system for smooth handover of automatic driving control rights based on dynamic gradient limiting. Background Art

[0002] With the rapid development of autonomous driving technology, the safe and smooth handover of vehicle control rights has become one of the core challenges in realizing human-machine co-driving. Especially during the handover from the automatic mode to the manual driving mode, the sudden change in the torque of the steering wheel is likely to cause jitter, resulting in driver tension or misoperation, directly affecting the driving experience and safety.

[0003] Existing methods are difficult to solve the problem of uneven torque during manual takeover in human-machine co-driving of autonomous vehicles, and the tension and discomfort caused by the jerks will also become a precondition for danger. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for smooth handover of automatic driving control rights based on dynamic gradient limiting, aiming to solve the problem of the jerks of the hand torque felt by the driver due to the sudden change in the system torque during the handover from automatic driving to manual driving when the driver performs manual operations on autonomous vehicles.

[0005] The present invention is implemented as follows. The method for smooth handover of automatic driving control rights based on dynamic gradient limiting includes:

[0006] S1. Read the information collected by the steering wheel torque sensor in real time, identify the takeover state of the steering wheel, calculate the torque value applied by the driver and the takeover duration , set a torque threshold and a time threshold , and judge and to trigger the handover of control rights;

[0007] S2. According to the currently obtained torque value , calculate the maximum limit of the torque change rate :

[0008] ;

[0009] ;

[0010] Wherein, represents the basic change rate, represents the applied torque at the zero moment, and are both adjustment parameters;

[0011] S3. Set the sampling period and limit the torque change rate within the sampling period not exceeding the maximum limit of the torque change rate , and generate a compensation torque based on the smoothed torque and the target torque ; ;

[0012] S4. Combine the system torque and the compensation torque , and calculate the final output torque through an attenuation function ;

[0013] S5. Dynamically adjust the maximum limit of the torque change rate according to the error between the smoothed torque and the target torque , and calculate the dynamic limit change rate :

[0014] ;

[0015] wherein is an adjustment parameter

[0016] As a further aspect of the present invention, the takeover state of the steering wheel identified in S1 further includes that if the torque value applied by the driver does not continuously satisfy within the time threshold , it is determined as a mis-trigger, and the transfer of control right is not initiated

[0017] As a further aspect of the present invention, the values of the adjustment parameters and in S2 are set according to the switching mode, including

[0018] Fast switching mode: , ;

[0019] Normal switching mode: , ;

[0020] Slow switching mode: , .

[0021] As a further aspect of the present invention, generating the compensation torque based on the error between the smoothed torque and the target torque is specifically as follows

[0022] ;

[0023] Among them, represents the th sampling period, is an adjustment parameter, and .

[0024] As a further solution of the present invention, the final output torque is calculated by the attenuation function , specifically:

[0025] ;

[0026] Among them, , is a constant term.

[0027] As a further solution of the present invention, the method is optimized by dynamic gradient clipping and iterative compensation, including:

[0028] According to the error of the current sampling period, is updated to ;

[0029] Repeat steps S3 to S5 until the total switching time reaches 0.5 seconds.

[0030] As a further solution of the present invention, the method is optimized by dynamic gradient clipping and iterative compensation, including:

[0031] According to the error of the current sampling period, is updated to ;

[0032] Set a torque error threshold, and repeat steps S3 to S5 until the error between the output torque and the target torque is less than the torque error threshold.

[0033] Another object of the present invention is to provide an automatic driving control right smooth handover system based on dynamic gradient clipping. The system includes:

[0034] A manual takeover intention recognition module, which is used to read the information collected by the steering wheel torque sensor in real time, identify the takeover state of the steering wheel, calculate the torque value applied by the driver and the takeover duration , set a torque threshold and a time threshold , and judge and to trigger the handover of control rights;

[0035] A maximum switching rate determination module, which is used to determine the maximum switching rate according to the currently obtained torque value , calculate the maximum limit of the torque change rate ;

[0036] The target gap compensation module is used to set the sampling period and limit the torque change rate within the sampling period not exceeding the maximum limit of the torque change rate , and based on the smoothed torque and the target torque generate a compensation torque for the error between them , combine the system torque and the compensation torque , and calculate the final output torque through an attenuation function ;

[0037] The switching rate dynamic adjustment module is used to dynamically adjust the maximum limit of the torque change rate according to the error between the smoothed torque and the target torque , calculate the dynamic limit change rate . .

[0038] The beneficial effects of the present invention are:

[0039] The present invention solves the problem of uneven torque generated during manual takeover in the existing human-machine co-driving, and reduces the danger of human-machine co-driving. By designing an iterative optimization scheme, the present invention reduces jitter and error during the entire switching process, enhances the driver's sense of control, avoids the driver's nervousness due to problems such as steering wheel response, and makes the driver more comfortable and safe when taking over autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flowchart of the autonomous driving control right smooth handover system based on dynamic gradient limiting described in the present invention;

[0041] Figure 2 is the torque change curve under three switching modes;

[0042] Figure 3 is a schematic diagram of the iterative optimization effect. DETAILED DESCRIPTION OF THE INVENTION

[0043] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0044] The autonomous driving control right smooth handover method based on dynamic gradient limiting, the method includes:

[0045] S1. Read the information collected by the steering wheel torque sensor in real time, identify the takeover state of the steering wheel, and calculate the torque value applied by the driver and the takeover duration , set the torque threshold and the time threshold , and judge and to trigger the handover of control rights when satisfied;

[0046] When the driver manually operates the steering wheel, takeover intention recognition is performed. To prevent misrecognition caused by slight steering wheel jitter and avoid overly sensitive switching, a torque threshold , time threshold is introduced and set . When it is determined that is 1, manual takeover starts, and the logic is as follows:

[0047] ;

[0048] If the torque value applied by the driver does not continuously satisfy within the time threshold , it is determined as a mis-trigger, and the handover of control rights is not initiated.

[0049] S2. Calculate the maximum limit of the torque change rate based on the currently obtained torque value :

[0050] ;

[0051] ; (The left turn of the steering wheel is positive)

[0052] The basic change rate is set so that no matter how the torque mutates, the time will be controlled within 0.5 s,

[0053] wherein, represents the basic change rate, represents the applied torque at the zero moment, and are both adjustment parameters;

[0054] The value of determines the average smooth speed of the torque during the entire switching process, The value of

[0055] determines the sense of control of the steering wheel felt by the driver when applying a sudden torque, that is, Figure 2As shown, the adjustment parameters and are set according to the switching mode, including:

[0056] Fast switching mode: , ;

[0057] Normal switching mode: , ;

[0058] Slow switching mode: , .

[0059] S3. Set the sampling period. According to the torque data collected by the torque sensor, calculate the real-time change rate of the torque with a sampling period of every 0.01 second, and limit the torque change rate not exceeding the maximum limit of the torque change rate , that is, limit . At this time, the change rate shows a non-linear step line over a 0.5s time span.

[0060] Since the change rate of the instantaneous torque mutation is very large, although limiting R max achieves the smoothing purpose to a certain extent, there are still certain errors. Adopt the target gap compensation method: Generate a compensation torque based on the error between the smoothed torque and the target torque , specifically:

[0061] ;

[0062] Among them, represents the th sampling period, is an adjustment parameter, and .

[0063] S4. Combine the system torque and the compensation torque , and calculate the final output torque through the attenuation function, specifically:

[0064] ;

[0065] ;

[0066] ;

[0067] ;

[0068] Among them, is the optimized system torque modulated by the attenuation function, and its function is to Through the attenuation characteristics of optimize the calculation process of the final output torque , is a constant term, taking , that is, it is hoped that the entire conversion process will be completed in about 0.5s. At this time, the optimized torque curve is both smooth and accurate, and greatly reduces the steering wheel jitter during the switching process.

[0069] S5. To further enhance the smoothing effect, dynamic adjustment is adopted. According to the smoothed torque and the target torque dynamically adjust the maximum limit of the torque change rate . The greater the final error, dynamically increases to accelerate convergence, and calculates the dynamic limit change rate :

[0070] ;

[0071] Among them, is the adjustment parameter, taking .

[0072] The method is optimized by dynamic gradient limiting and iterative compensation, including:

[0073] According to the error of the current sampling period, is updated to ;

[0074] Repeat steps S3 to S5 until the total switching time reaches 0.5 seconds, or the error between the output torque and the target torque is less than the torque error threshold.

[0075] As Figure 3 shown, continuously output the optimized and . From the entire 0.5s optimization process, it can be known that when takes 0 to 25, the number of optimizations is more and the response speed is faster. When

[0076] As Figure 1As shown, a smooth handover system for autonomous driving control rights based on dynamic gradient clipping, the system includes:

[0077] A manual takeover intention recognition module, which is used to read the information collected by the steering wheel torque sensor in real time, identify the takeover state of the steering wheel, and calculate the torque value applied by the driver and the takeover duration , set a torque threshold and a time threshold , and judge and to trigger the handover of control rights when;

[0078] A maximum switching rate determination module, which is used to calculate the maximum limit of the torque change rate according to the currently obtained torque value ; ;

[0079] A target gap compensation module, which is used to set a sampling period and limit the torque change rate within the sampling period not exceeding the maximum limit of the torque change rate , and generate a compensation torque based on the error between the smoothed torque and the target torque , combine the system torque and the compensation torque and the compensation torque , and calculate the final output torque through an attenuation function ;

[0080] A switching rate dynamic adjustment module, which is used to dynamically adjust the maximum limit of the torque change rate according to the error between the smoothed torque and the target torque , and calculate the dynamic limit change rate ; ;

[0081] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0082] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0083] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0084] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

[0085] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for smooth handover of autonomous driving control rights based on dynamic gradient clipping, characterized in that, The method includes: S1. Read the information collected by the steering wheel torque sensor in real time, identify the takeover state of the steering wheel, and calculate the torque value applied by the driver and the takeover duration , set the torque threshold and the time threshold , and judge and to trigger the handover of control rights when S2. According to the currently obtained torque value , calculate the maximum limit of the torque change rate : ； ； Among them, represents the basic change rate, represents the applied torque at the zero moment, and are both adjustment parameters; S3. Set the sampling period and limit the torque change rate within the sampling period not exceeding the maximum limit of the torque change rate , and generate a compensation torque based on the smoothed torque and the target torque ; ; S4. Combine the system torque and the compensation torque , and calculate the final output torque through the attenuation function ; S5. Dynamically adjust the maximum limit of the torque change rate according to the error between the smoothed torque and the target torque to calculate the dynamic limit change rate : : ； Among them, is an adjustment parameter.

2. The method according to claim 1, wherein The recognition of the takeover state of the steering wheel described in S1 further includes that if the torque value applied by the driver does not continuously meet within the time threshold , it is determined as a false trigger and the transfer of control right is not initiated. ​ 3. The method according to claim 1, wherein The adjustment parameters described in S2 and are set according to the switching mode and include: Quick switching mode: , ; Normal switching mode: , ; Slow switching mode: , .

4. The method according to claim 1, characterized in that, The error between the smoothed torque and the target torque is used to generate a compensation torque , specifically as follows: ； Among them, represents the th sampling period, is an adjustment parameter, and .

5. The method according to claim 1, characterized in that, The final output torque is calculated through the attenuation function , specifically as follows: ； Among them, , is the constant term.

6. The method according to claim 1, wherein The method is optimized by dynamic gradient clipping and iterative compensation, and includes: Update according to the error in the current sampling period to ; to ; Repeat steps S3 to S5 until the total switching time reaches 0.5 seconds.

7. The method according to claim 1, characterized in that, The method is optimized by dynamic gradient clipping and iterative compensation, and includes: Update according to the error of the current sampling period to ; Set a torque error threshold, and repeatedly execute S3 to S5 until the output torque and the target torque have an error less than the torque error threshold.

8. An automatic driving control right smooth handover system based on dynamic gradient clipping, characterized in that, The system includes: The manual takeover intention recognition module is used to read in real time the information collected by the steering wheel torque sensor, identify the takeover state of the steering wheel, and calculate the torque value applied by the driver and the takeover duration , set the torque threshold and the time threshold , and judge and trigger the transfer of control right when; The maximum switching rate determination module is used to calculate the maximum limit of the torque change rate according to the currently obtained torque value , and calculate the maximum limit of the torque change rate ; ； ； Among them, represents the basic change rate, represents the applied torque at the zero moment, and are both adjustment parameters; The target gap compensation module is used to set the sampling period and limit the torque change rate within the sampling period not exceeding the maximum limit of the torque change rate , and generate a compensation torque based on the smoothed torque and the target torque ; combine the system torque and the compensation torque to calculate the final output torque through an attenuation function ; ; The switching rate dynamic adjustment module is used to dynamically adjust the maximum limit of the torque change rate according to the error between the smoothed torque and the target torque and calculate the dynamic limit change rate ; ; ； Among them, is an adjustment parameter.

Images