Man-machine co-driving control method and system for vehicle and storage medium

Abstract

The application discloses a kind of man-machine co-pilot control method, system and storage medium for vehicle, belong to automatic driving technical field.The method includes;Obtain vehicle speed and driver hand torque, and determine driver takeover condition according to the vehicle speed;In the case where the driver hand torque does not satisfy the driver takeover condition, obtain the first target steering angle planned by automatic driving system;According to the driver hand torque and the first target steering angle, determine target steering angle;According to the target steering angle control the vehicle steering.By the application, the technical problem that safety and reliability of man-machine co-pilot under automatic driving scene are not high is solved.

Description

Technical Field

[0001] This invention belongs to the field of autonomous driving technology, and in particular relates to a human-machine co-driving control method, system and storage medium for vehicles. Background Technology

[0002] In high-level autonomous driving scenarios, steer-by-wire is an essential technology for achieving human-machine decoupling, precise and rapid lateral control, and safety redundancy. Compared to traditional electric power steering (EPS), steer-by-wire (SBW) eliminates the mechanical connection between the steering wheel and the steering wheels. The driver rotates the upper rotor system (Handwheel Actuator, HWA, responsible for collecting driver input and simulating road feel), transmitting steering commands via electrical signals to the lower rotor system (Road Wheel Actuator, RWA, responsible for driving the wheels to achieve steering). The lower rotor system then executes the steering commands. In autonomous driving scenarios, steer-by-wire systems can meet the highest ASIL-D safety level, achieving full software and hardware redundancy to ensure safe operation of autonomous driving. How to achieve human-machine co-driving in autonomous driving scenarios is a pressing issue that needs to be addressed. Summary of the Invention

[0003] This invention provides a human-machine co-driving control method, device, system, and storage medium for vehicles, which addresses the technical problem of low safety and reliability of human-machine co-driving in autonomous driving scenarios in the prior art.

[0004] In a first aspect of the invention, a human-machine co-driving control method for a vehicle is provided, comprising: acquiring a current driving speed and a driver's hand torque, and determining a driver takeover condition based on the current driving speed; if the driver's hand torque does not meet the driver takeover condition, acquiring a first target steering angle planned by an autonomous driving system; determining a target steering angle based on the driver's hand torque and the first target steering angle; and controlling the vehicle steering based on the target steering angle.

[0005] In conjunction with the first aspect, in some embodiments, determining the driver takeover condition based on the current driving speed includes: if the current driving speed is less than a vehicle speed threshold, determining the driver takeover condition as follows: the absolute value of the driver's hand torque is greater than a first torque threshold and lasts for at least a first duration, or greater than a second torque threshold, wherein the second torque threshold is greater than the first torque threshold; if the current driving speed is greater than or equal to the vehicle speed threshold, determining the driver takeover condition as follows: the absolute value of the driver's hand torque is greater than a third torque threshold and lasts for at least a second duration, or greater than a fourth torque threshold, wherein the third torque threshold is greater than the first torque threshold, the fourth torque threshold is greater than the second torque threshold, and the third torque threshold is less than the fourth torque threshold.

[0006] In conjunction with the first aspect, in some embodiments, before determining the driver takeover condition based on the current driving speed, the method further includes: determining whether the driver's hand torque is greater than or equal to a fifth torque threshold, wherein the fifth torque threshold is less than the first torque threshold; if so, performing the step of determining the driver takeover condition based on the current driving speed.

[0007] In conjunction with the first aspect, in some embodiments, obtaining the driver's hand torque includes: detecting the driver's original hand force signal; performing low-pass filtering and moving average filtering on the driver's original hand force signal to obtain the driver's hand torque.

[0008] In conjunction with the first aspect, in some embodiments, determining the target steering angle based on the driver's hand torque and the first target steering angle includes: obtaining the driver's operation weight and the first target steering angle, wherein the driver's operation weight characterizes the degree of driver intervention in the vehicle steering; determining a superimposed steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque; and determining the target steering angle based on the superimposed steering angle.

[0009] In conjunction with the first aspect, in some embodiments, determining the superimposed steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque includes: calculating a base steering torque based on the first target steering angle; superimposing the driver's hand torque and the base steering torque based on the driver's operation weight to obtain a superimposed steering torque; and calculating the superimposed steering angle from the superimposed steering torque.

[0010] In conjunction with the first aspect, in some embodiments, the step of superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain a superimposed steering torque includes: determining an autonomous driving weight corresponding to the basic steering torque according to the driver's operation weight; multiplying the autonomous driving weight by the basic steering torque to obtain a first torque component; multiplying the driver's operation weight by the driver's hand torque to obtain a second torque component; and adding the first torque component to the second torque to obtain the superimposed steering torque.

[0011] In conjunction with the first aspect, in some embodiments, determining the superimposed steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque includes: calculating a second target steering angle based on the driver's hand torque; and superimposing the first target steering angle and the second target steering angle based on the driver's operation weight to obtain the superimposed steering angle.

[0012] In conjunction with the first aspect, in some embodiments, the step of superimposing the first target steering angle and the second target steering angle based on the driver's operation weight to obtain a superimposed steering angle includes: determining the autonomous driving weight corresponding to the first target steering angle according to the driver's operation weight; multiplying the autonomous driving weight by the first target steering angle to obtain a first steering angle component; multiplying the driver's operation weight by the driver's hand torque to obtain a second steering angle component; and adding the first steering angle component and the second steering angle component to obtain the superimposed steering angle.

[0013] In conjunction with the first aspect, in some embodiments, the method further includes: if it is detected that the driver is in a state where his hands are off the steering wheel, the driver operation weight is 0; if it is detected that the driver is in a state where his hands are on the steering wheel, the driver operation weight is in the range of 0-1.

[0014] In conjunction with the first aspect, in some embodiments, the human-machine co-driving control method further includes: when the driver's hand torque meets the driver takeover conditions, the automatic driving system disengages from steering control of the vehicle.

[0015] In conjunction with the first aspect, in some embodiments, the steer-by-wire system includes a main control MCU, an upper rotor system, and a lower rotor system; determining the target steering angle based on the driver's hand torque and the first target steering angle includes: calculating a basic steering torque based on the first target steering angle using the main control MCU, and superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain a superimposed steering torque; calculating the superimposed steering angle based on the superimposed steering torque using the upper rotor system's upper rotor controller, and determining the target steering angle based on the superimposed steering angle.

[0016] In conjunction with the first aspect, in some embodiments, controlling the vehicle steering according to the target steering angle includes: The upper rotor system's angle sensor acquires the actual steering angle of the wheel; the lower rotor system's controller adjusts the PID control parameters based on the error information between the target steering angle and the actual steering angle, as well as multiple preset fuzzy rules. Each fuzzy rule is a mapping relationship between various error states and parameter adjustment methods; the lower rotor system's controller outputs a correction torque based on the adjusted PID control parameters, which is superimposed on the execution torque of the steer-by-wire actuator in the steer-by-wire system to correct the angle deviation between the actual steering angle and the target steering angle.

[0017] In a second aspect of the invention, a human-machine co-driving control system for a vehicle is provided, comprising: an autonomous driving system and a steer-by-wire system communicatively connected to the autonomous driving system; the autonomous driving system being configured to acquire a current driving speed and a driver's hand torque, and to determine a driver takeover condition based on the current driving speed; the steer-by-wire system being configured to, when the driver's hand torque does not meet the driver takeover condition, acquire a first target steering angle planned by the autonomous driving system, determine a target steering angle based on the driver's hand torque and the first target steering angle, and control the vehicle steering based on the target steering angle.

[0018] In conjunction with the second aspect, in some embodiments, the steer-by-wire system includes an upper rotor system and a lower rotor system, the upper rotor system and the lower rotor system being connected via at least two CAN buses; and / or the key components in the upper rotor system and the lower rotor system each include at least two CAN buses; and / or the autonomous driving system and the steer-by-wire system are connected via at least two CAN buses; and / or the key components in the upper rotor system and the lower rotor system are each connected to two power grids, the two power grids being physically isolated from each other.

[0019] In a third aspect of the invention, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the human-machine co-driving control method for a vehicle as described in any embodiment of the first aspect.

[0020] The technical solutions provided by one or more embodiments of the present invention achieve at least the following technical effects or advantages: This invention provides an embodiment that acquires the current driving speed and driver's hand torque, and determines driver takeover conditions based on the current driving speed. If the driver's hand torque does not meet the driver takeover conditions, a first target steering angle planned by the autonomous driving system is acquired. A target steering angle is determined based on the driver's hand torque and the first target steering angle. The vehicle's steering is then controlled based on the target steering angle. This technical solution first determines the driver takeover conditions based on the current driving speed, accurately determining whether human-machine co-driving should be initiated, thereby improving the safety and reliability of entering human-machine co-driving scenarios in autonomous driving environments. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic diagram of the human-machine co-driving control system according to some embodiments of the present invention is shown; Figure 2 A flowchart of a human-machine co-driving control method for a vehicle according to some embodiments of the present invention is shown; Figure 3 The control logic for a human-machine co-driving control method for a vehicle according to some embodiments of the present invention is shown. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0024] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Numerous specific details are mentioned in the following detailed description to help understand the present invention. However, those skilled in the art should understand that the present invention can be implemented without these specific details. In other instances, detailed descriptions are not provided. The methods, processes, components, and circuits described below are intended to avoid unnecessarily obscuring the embodiments. Clearly, the embodiments described below are only a portion, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention. The terminology used in the embodiments of this invention is for the purpose of better describing particular embodiments and is not intended to limit the invention. The singular forms “a,” “described,” and “the” used in the embodiments of this invention and the appended claims are also intended to… The term "in many forms" is used unless the context clearly indicates otherwise. This description and the claims of the invention are as follows: The terms "first," "second," and "third," etc., used in the accompanying drawings are to distinguish different objects, not to describe a specific order. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more associated listed items. Furthermore, it should be understood that the term "comprising" as used herein specifies the presence of the stated feature, integral, step, operation, element, and / or component, without excluding the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof.

[0025] In autonomous driving scenarios, steer-by-wire systems, due to the elimination of mechanical linkages, present challenges. How can precise and rapid lateral control be guaranteed after this elimination? Can safety redundancy strategies meet the requirements of autonomous driving? Secondly, how can the smoothness and reliability of steering be ensured during the transition between human-driven and machine-driven modes to avoid safety hazards caused by signal delays, resulting in a poor user experience or misjudgments? Simultaneously, the fault tolerance of the steer-by-wire system under complex operating conditions needs to be addressed, and a multi-level redundancy mechanism needs to be constructed, covering the autonomous driving system, the steer-by-wire system, and the vehicle communication link, to meet the functional safety requirements of high-level autonomous driving functions. Figure 1 A schematic diagram of a human-machine co-driving control system according to some embodiments of the present invention is shown. Embodiments of the present invention provide a human-machine co-driving control method for a vehicle, applied in a human-machine co-driving control system equipped with an automatic driving system 110 and a steer-by-wire system 120, such as... Figure 1As shown. In the autonomous driving scenario, after the mechanical connection structure is eliminated, in order to improve the lateral control reliability and accuracy of the steer-by-wire system, the autonomous driving system 110 and the steer-by-wire system 120 are connected by at least two CAN (Controller Area Network) communication connections to ensure that the data transmission between the autonomous driving system 110 and the steer-by-wire system 120 is uninterrupted and error-free when a single CAN bus fails, thus ensuring communication safety.

[0026] To improve the reliability and accuracy of lateral control in steer-by-wire, in some embodiments, a main CAN bus and a backup CAN bus are connected between the autonomous driving system 110 and the steer-by-wire system 120. The main CAN bus and the backup CAN bus are composed of independent CAN controllers, transceivers, wiring harnesses, terminating resistors, etc., and the physical layer and data link layer of the main CAN bus and the backup CAN bus are completely isolated, realizing dual transmission and verification of safety-related key data. Among them, the safety-related key data include: steering signals sent by the autonomous driving system 110 to the steer-by-wire system 120, signals fed back by the steer-by-wire system 120 to the autonomous driving system 110, sensor status, etc.

[0027] To improve the reliability and accuracy of lateral control in steer-by-wire, in some embodiments, the steer-by-wire system 120 includes a main control MCU (Microcontroller Unit), an upper rotor system (also called a steering wheel assembly), and a lower rotor system (also called a steering actuator assembly), and the main control MCU, the upper rotor system, and the lower rotor system are connected via at least two CAN buses. Communication between the main control MCU, the upper rotor system, and the lower rotor system of the steer-by-wire system 120 uses dual CAN channels, and communication between the steer-by-wire system 120 and external systems also uses dual CAN channels, effectively preventing communication failures.

[0028] In some embodiments, the key components in both the upper and lower rotor systems include at least two paths. These key components include: a main control MCU (Microcontroller Unit), a road feel feedback motor, an upper controller, and a sensing sensor in the upper rotor system; and a sensing sensor, a steer-by-wire actuator, and a lower controller in the lower rotor system. Because both the upper and lower rotor systems have at least two key components, redundancy is achieved, and a single failure will not lead to a complete loss of steering function. Both the upper and lower rotor systems use dual-winding motors to prevent the failure of a single motor from causing the subsystem to lose functionality.

[0029] In some embodiments, the power supply of the steer-by-wire system 120 adopts a dual power supply. The key components of the upper rotor system and the lower rotor system are connected to two power grids, and the two power grids are physically isolated to avoid steer-by-wire failure caused by a single point power supply failure.

[0030] In some embodiments, the sensing sensors in the upper rotor system employ two sets of TAS (Torque Angle Sensors), each set of TAS sensors including two torque sensors and one angle sensor, while the sensing sensors in the lower rotor system employ two angle sensors.

[0031] Figure 2 A flowchart of a human-machine co-driving control method for a vehicle according to some embodiments of the present invention is shown. For example... Figure 2 As shown, this embodiment of the invention provides a human-machine co-driving control method for vehicles, applied to a human-machine co-driving control system, and implemented through the cooperation of an automatic driving system 110 and a steer-by-wire system 120. Figure 2 As shown, the human-machine co-driving control method for vehicles includes the following steps S201 to S204.

[0032] S201: Obtain the current driving speed and driver's hand torque, and determine the driver takeover conditions based on the current driving speed.

[0033] In some embodiments, step S201, obtaining the driver's hand torque, includes: detecting the driver's original hand force signal; filtering the detected original hand force signal to obtain the driver's hand torque, wherein the driver's hand torque characterizes the hand torque applied by the driver to the steering wheel. By detecting the driver's original hand force signal using a torque sensor and filtering the original hand force signal detected by the torque sensor, high-frequency noise and instantaneous spikes in the original hand force signal can be removed, resulting in a smooth, reliable, and effective driver's hand torque output, avoiding malfunctions of the steer-by-wire system 120 or abrupt torque superposition due to noise. High-frequency noise includes noise generated by driver hand tremors, electronic noise from sensors, etc., while instantaneous spikes are generated by driver mis-touch or sudden force application.

[0034] In some embodiments, filtering the detected raw hand force signal includes performing low-pass filtering and moving average filtering on the detected raw hand force signal.

[0035] In some embodiments, the original hand force signal is subjected to low-pass filtering and moving average filtering in sequence to first filter high-frequency noise and then smooth instantaneous spikes.

[0036] Understandably, the original hand force signal is low-pass filtered based on the first-order RC filtering principle, allowing only low-frequency effective signals (low-frequency effective signals are the driver's stable operating torque, which is a signal with a frequency of less than 5Hz) to pass through, while attenuating high-frequency noise (high-frequency noise is a signal with a frequency of more than 20Hz).

[0037] The key parameters for low-pass filtering of the original hand force signal based on the first-order RC filtering principle include: a cutoff frequency adapted to the driver's operating frequency and a sampling frequency synchronized with the torque sensor. The formula simplifies to: y(n) = α × x(n) + (1-α) × y(n-1), where α is the filtering coefficient calculated based on the cutoff frequency and the sampling frequency, y(n) is the torque value after low-pass filtering, x(n) is the original hand force signal detected by the torque sensor, and y(n) is the torque value after low-pass filtering. 1) is the torque value after the previous low-pass filtering. For example, if the cutoff frequency is 5Hz and the sampling frequency is 100Hz, then α≈0.1.

[0038] Understandably, the torque values ​​after the most recent N low-pass filtering are averaged to obtain the driver's hand torque. For example, with a window size of N=5, balancing real-time performance and smoothing effect, the formula simplifies to: y_avg(n) = [y(n)+y(n-1)+...+y(n-4)] / 5, where y_avg(n) is the driver's hand torque, and y(n), y(n-1), ..., y(n-4)] are the torque values ​​after the most recent N low-pass filtering.

[0039] In some embodiments, step S201 is performed by the autonomous driving system 110: acquiring the vehicle's current driving speed and driver's hand torque, and determining driver takeover conditions based on the current driving speed. Specifically, this includes: the autonomous driving system 110 receiving the driver's hand force signal fed back by the steer-by-wire system 120; and the autonomous driving system 110 performing low-pass filtering and moving average filtering on the received driver's hand force signal to obtain the driver's hand torque. It is understood that the driver's hand force signal fed back by the steer-by-wire system 120 is detected by the TAS sensor in the steer-by-wire system 120.

[0040] In some embodiments, the autonomous driving system 110 determines the driver's intervention state in vehicle steering based on the driver's hand torque. The driver's intervention state in vehicle steering is divided into: the state of hands off the steering wheel and the state of hands on the steering wheel.

[0041] In some embodiments, determining the driver's intervention state in vehicle steering based on the driver's hand torque includes: determining whether the driver's hand torque is greater than or equal to a fifth torque threshold, wherein the fifth torque threshold is less than a first torque threshold; if the driver's hand torque is less than the fifth torque threshold, it indicates that the driver is not operating the steering wheel, or the operation that generated the original hand force signal is a mistaken touch operation of the driver on the steering wheel, then determining that the driver is in a state of taking his hands off the steering wheel; if the driver's hand torque is greater than or equal to the fifth torque threshold, it indicates that the operation that generated the original hand force signal is the driver's true intention operation on the steering wheel, then determining that the driver is in a state of holding the steering wheel, triggering the automatic driving system 110 to execute the step of determining the driver takeover conditions based on the current driving speed, and determining whether the driver's hand torque meets the driver takeover conditions determined based on the current driving speed.

[0042] In some embodiments, if the driver's hand torque meets the driver takeover conditions determined based on the current driving speed, the vehicle is determined to be in a driver takeover state. The automatic driving system 110 exits control of the steer-by-wire system 120, so that the automatic driving system 110 exits steering control of the vehicle and the driver takes full control, controlling the steer-by-wire system 120 entirely based on the driver's operation of the steering wheel. If the driver's hand torque does not meet the driver takeover conditions determined based on the current driving speed, the automatic driving system 110 enters a human-machine co-driving state. In the human-machine co-driving state, the automatic driving system 110 and the driver jointly control the steer-by-wire system 120, thereby realizing human-machine co-driving.

[0043] In some embodiments, at least two speed ranges are divided based on at least one speed threshold, and corresponding driver takeover conditions are set for each speed range. The higher the speed range, the larger the torque threshold in the driver takeover conditions. Determining the driver takeover conditions based on the current driving speed includes: determining, from a variety of preset takeover conditions, a driver takeover condition that matches the current driving speed, based on the speed range in which the current driving speed falls.

[0044] In some embodiments, determining the driver takeover condition based on the current driving speed includes: if the current driving speed is less than a vehicle speed threshold, the determined driver takeover condition is: the driver's hand torque is greater than a first torque threshold and lasts for at least a first duration, or greater than a second torque threshold, wherein the second torque threshold is greater than the first torque threshold; if the current driving speed is greater than or equal to the vehicle speed threshold, the determined driver takeover condition is: the driver's hand torque is greater than a third torque threshold and lasts for at least a second duration, or greater than a fourth torque threshold, wherein the third torque threshold is greater than the first torque threshold, the fourth torque threshold is greater than the second torque threshold, and the third torque threshold is less than the fourth torque threshold.

[0045] For example, the vehicle speed threshold is 60 kph. When the current driving speed is less than 60 kph, the driver takeover condition is: the absolute value of the driver's hand torque is greater than the first torque threshold of 2.6 Nm for 300 ms, or the absolute value of the driver's hand torque is greater than the second torque threshold of 3 Nm. If either condition is met, the vehicle is determined to be in a driver takeover state, and the automatic driving system 110 disengages from steering control of the vehicle. When the current driving speed is greater than or equal to 60 kph, the driver takeover condition is: the absolute value of the driver's hand torque is greater than the third torque threshold of 3 Nm for 200 ms, or the absolute value of the driver's hand torque is greater than the fourth torque threshold of 3.5 Nm. If either condition is met, the vehicle is determined to be in a driver takeover state, and the automatic driving system 110 disengages from steering control of the vehicle. It should be noted that the values ​​of the above-mentioned vehicle speed threshold, the first to fourth torque thresholds, the first duration, and the second duration can be set according to actual needs, and this embodiment of the invention does not limit this.

[0046] S202: If the driver's hand torque does not meet the driver takeover conditions, obtain the first target steering angle planned by the automatic driving system 110.

[0047] In some embodiments, step S202 is performed by the steer-by-wire system 120, which receives a first target steering angle sent by the autonomous driving system 110. The first target steering angle is the steering angle that the autonomous driving system 110 plans based on the real-time status of the vehicle and the driving path.

[0048] S203: Determine the target steering angle based on the driver's hand torque and the first target steering angle.

[0049] In some embodiments, step S203 is performed by the steer-by-wire system 120: determining the target steering angle based on the driver's hand torque and the first target steering angle.

[0050] In some embodiments, determining a target steering angle based on the driver's hand torque and the first target steering angle includes: obtaining a driver's operation weight and the first target steering angle, wherein the driver's operation weight characterizes the degree of driver intervention in the vehicle's steering; and determining the target steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque.

[0051] In some embodiments, the steer-by-wire system 120 receives a first target steering angle and driver operation weight sent by the autonomous driving system 110, and then the steer-by-wire system 120 determines the target steering angle based on the driver operation weight, the first target steering angle and the driver's hand torque.

[0052] It is understandable that the driver's operation weight k ranges from 0 to 1. When the driver's hands are off the steering wheel, the driver's operation weight k sent by the autonomous driving system 110 to the steer-by-wire system 120 during operation is 0, so that the steer-by-wire system 120 does not have the driver's hand torque superimposed, and the autonomous driving system 110 completely controls the steer-by-wire system 120. When the driver's hands are on the steering wheel, the driver's operation weight k sent by the autonomous driving system 110 during operation satisfies 0 < k < 1, which meets the requirements of human-machine co-driving, realizing the joint control of the steer-by-wire system 120 by the driver and the autonomous driving system 110, as well as the hand feel control during human-machine co-driving.

[0053] Understandably, when the driver's operating weight k is in the range of 0 < k < 1, the first steering angle planned by the autonomous driving system 110 and the actual steering angle of the vehicle will continuously deviate: as the value of k increases, the driver's steering wheel feel gradually softens, and the allowable deviation gradually increases. When k goes from 0 to a non-zero value or returns from a non-zero value to 0, the steering wheel will not turn too quickly or unexpectedly, causing a sudden steering wheel jolt. During human-machine co-driving, under the condition that the autonomous driving system 110 requests a steering angle of 0 degrees (i.e., the first target steering angle is 0 degrees), and the driver's hand torque is < 3.5 Nm when intervening, the relationship between the driver's operating weight k and the actual steering wheel angle is shown in the table below. Therefore, it is necessary to perform integral saturation on the first target steering angle.

[0054]

[0055] In some embodiments, the steer-by-wire system 120 determines the target steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque. This may include: calculating the basic steering torque planned by the autonomous driving system 110 based on the first target steering angle; superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain a superimposed steering torque; and calculating the superimposed steering angle based on the superimposed steering torque.

[0056] In some embodiments, superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain a superimposed steering torque may include: determining the autonomous driving weight corresponding to the first target steering angle according to the driver's operation weight, wherein the sum of the driver's operation weight and the autonomous driving weight is 1; multiplying the autonomous driving weight by the basic steering torque to obtain a first torque component; multiplying the driver's operation weight by the driver's hand torque to obtain a second torque component; and adding the first torque component and the second torque component to obtain the superimposed steering torque.

[0057] In some embodiments, the driver's hand torque and the basic steering torque are superimposed based on the driver's operation weight, as shown in the following formula: Tq Sum =(1-k)×Tq1+k×Tq2; Where k is the driver's operational weight, Tq1 is the basic steering torque planned by the autonomous driving system 110, Tq2 is the driver's hand torque, and Tq Sum To superimpose the steering torque.

[0058] Figure 3 The control logic for a human-machine co-driving control method for a vehicle according to some embodiments of the present invention is shown. See also Figure 3 As shown, the steer-by-wire system 120 superimposes the driver's hand torque Tq2 and the basic steering torque Tq1 based on the driver's operation weight k to obtain the superimposed steering torque Tq. Sum The steer-by-wire system 120 will superimpose the steering torque Tq. Sum The conversion is performed to determine the superimposed steering angle Ang corresponding to the superimposed steering torque. Cmd .

[0059] In other embodiments, the steer-by-wire system 120 determines the target steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque, which may include: calculating a second target steering angle based on the driver's hand torque; and superimposing the first target steering angle and the second target steering angle based on the driver's operation weight to obtain a superimposed steering angle.

[0060] Understandably, the second target steering angle is the steering angle that the driver expects, calculated by the steer-by-wire system 120 based on the driver's hand torque and vehicle state parameters. It represents the driver's desired steering demand expressed by the steering wheel torque. Among them, the vehicle state parameters include vehicle motion parameters such as current driving speed, yaw rate, lateral acceleration, and wheel speed.

[0061] It is understood that the superposition of the first target steering angle and the second target steering angle based on the driver operation weight to obtain the superimposed steering angle includes: determining the autonomous driving weight corresponding to the first target steering angle according to the driver operation weight, wherein the sum of the driver operation weight and the autonomous driving weight is 1; multiplying the autonomous driving weight by the first target steering angle to obtain the first steering angle component; multiplying the driver operation weight by the driver's hand torque to obtain the second steering angle component; and adding the first steering angle component and the second steering angle component to obtain the superimposed steering angle.

[0062] It is understood that the target steering angle is a given value for the closed-loop control steering angle of the steer-by-wire system 120, so that the actual steering angle is determined according to the superimposed steering torque in some embodiments. This can be achieved by directly converting the superimposed steering angle into a variable transmission ratio after obtaining the superimposed steering angle, thus obtaining the target steering angle for closed-loop control steering.

[0063] In other embodiments, the superimposed steering angle is sequentially corrected and the transmission ratio is converted to obtain the target steering angle for closed-loop control of vehicle steering.

[0064] In some embodiments, the correction of the superimposed steering angle may be achieved by adding multiple compensation terms to the superimposed steering angle. These multiple compensation terms may include one or more of the following: path error compensation angle, driver torque feedforward compensation angle, and steering angular velocity compensation angle.

[0065] In some embodiments, the path error compensation angle is obtained by multiplying the vehicle's current position by the lateral offset relative to the center line of the target lane using a preset adjustment coefficient, wherein the target lane line is the lane where the vehicle is located or the nearest adjacent lane.

[0066] In some embodiments, the driver's hand torque is input to the feedforward calculation function, and the driver's torque feedforward compensation angle is calculated by the feedforward calculation function.

[0067] In some embodiments, the calculation logic of the feedforward calculation function is as follows: the driver's hand torque relative to the maximum permissible operating torque of the steering wheel is normalized; the normalized torque is multiplied by the feedforward base gain and by the amplification factor to obtain the driver torque feedforward compensation angle. For example, the feedforward base gain is 0.3, used to control the overall strength of torque compensation, and the amplification factor is a constant 50, used to convert the normalized torque into the corresponding driver torque feedforward compensation angle.

[0068] In some embodiments, the negative differential coefficient is multiplied by the vehicle’s current steering angular velocity to obtain the steering angular velocity compensation angle, which is used to reduce rapid steering fluctuations and reduce oscillations.

[0069] In some embodiments, correcting the superimposed steering angle can be achieved by simply limiting the superimposed steering angle and returning the target steering angle after limiting and gear ratio conversion, thus restricting the target steering angle to the steering angle range formed by the negative maximum steering angle and the positive maximum steering angle. If the superimposed steering angle exceeds this steering angle range, the gear ratio is directly converted to a value closer to the boundary value (negative maximum steering angle or positive maximum steering angle) to obtain the target steering angle. If the superimposed steering angle does not exceed this steering angle range, the superimposed steering angle is converted to a gear ratio to obtain the target steering angle.

[0070] In other embodiments, correcting the superimposed steering angle may include: adding each compensation term to the superimposed steering angle to obtain the compensated steering angle, and performing amplitude limiting processing on the compensated steering angle.

[0071] In some embodiments, performing a variable gear ratio conversion on the superimposed steering angle or the corrected steering angle to obtain the target steering angle may include: determining the current gear ratio based on the current driving speed of the vehicle, and dividing the product of the current gear ratio and the driver's hand torque by the steering stiffness coefficient of the steer-by-wire system 120 to obtain the target steering angle.

[0072] like Figure 3 As shown, in some embodiments, the steer-by-wire system 120 includes a main control MCU, an upper rotor system, and a lower rotor system. The main control MCU of the steer-by-wire system 120 performs the following: calculating the basic steering torque based on the first target steering angle; and superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain a superimposed steering torque. The main control MCU then transmits the superimposed steering torque Tq. Sum The signal is sent to the upper rotor system's upper rotation controller, which then determines the superimposed steering torque Tq based on the signal. Sum Calculate the corresponding superimposed steering angle Ang Cmd And determine the target steering angle based on the superimposed steering angle.

[0073] S204: Control the vehicle steering according to the target steering angle.

[0074] In some embodiments, controlling vehicle steering according to the target steering angle includes: the upper steering controller sending the target steering angle to the lower steering controller of the lower rotor system; after receiving the target steering angle from the upper steering controller, the lower steering controller of the lower rotor system performs closed-loop control of the steering angle according to the target steering angle; and corrects the execution angle of the front wheels through closed-loop feedback so that the actual steering angle of the vehicle accurately tracks the target steering angle, so that the angle deviation between the actual steering angle of the vehicle and the target steering angle is less than or equal to 0.1°, thereby achieving vehicle steering control.

[0075] In some embodiments, the down-rotor controller performs closed-loop control of the steering angle based on the target steering angle, which may include: acquiring the actual steering angle of the wheels through an angle sensor in the down-rotor system of the steer-by-wire system 120; adjusting PID control parameters based on the error information between the target steering angle and the actual steering angle and multiple preset fuzzy rules, where each fuzzy rule is a mapping relationship between multiple error states and parameter adjustment methods; outputting a correction torque based on the adjusted PID control parameters, which is superimposed on the execution torque of the steer-by-wire actuator of the steer-by-wire system 120 to correct the execution angle of the front wheels, thereby correcting the angle deviation between the actual steering angle and the target steering angle, ensuring that the actual steering angle of the vehicle accurately tracks the target steering angle (deviation ≤ 0.1°).

[0076] In some embodiments, the PID control parameters include a proportional coefficient Kp, a derivative coefficient Kd, and an integral coefficient Ki, and the PID control parameters are initialized. For example, the initialization result is: proportional coefficient Kp = 1.2, derivative coefficient Kd = 0.1, and integral coefficient Ki = 0.05. The PID control parameters are adjusted based on the error information between the target steering angle and the actual steering angle, and multiple preset fuzzy rules. This includes: determining a target fuzzy rule from multiple preset fuzzy rules based on the error information between the target steering angle and the actual steering angle; and adjusting the PID control parameters based on the target simulation rule.

[0077] In some embodiments, the error information includes the angle error (e) between the target steering angle and the actual steering angle, and the error change rate (ec). Based on the magnitude of the angle error (range ±1°), it is divided into five fuzzy sets: negative large angle error, negative small angle error, zero angle error, positive small angle error, and positive large angle error. Based on the magnitude of the error change rate (range ±0.5° / ms), it is divided into five fuzzy sets: negative large change rate, negative small change rate, zero change rate, positive small change rate, and positive large change rate. Fuzzy rules are set according to the combination of fuzzy sets of angle error and error change rate, thereby setting several simulation rules. For example, among the preset fuzzy rules, one fuzzy rule is: "If the angle error e is positive large and the error change rate ec is positive small, then increase Kp and decrease Kd." Other similar fuzzy rules can be set with reference to this reference fuzzy rule to adapt to different driver intervention situations.

[0078] In some embodiments, based on the target simulation rules, the proportional coefficient Kp, integral coefficient Ki, and derivative coefficient Kd of the PID control parameters are dynamically adjusted: slight driver intervention (small positive e, small positive ec): decrease the proportional coefficient Kp and increase the integral coefficient Ki to avoid steering oscillation and maintain smoothness; strong driver intervention (large positive e, large positive ec): increase the proportional coefficient Kp and decrease the proportional coefficient Kd to quickly track the target steering angle and respond to the driver's intention.

[0079] In some embodiments, a correction torque is output based on the adjusted PID control parameters and the angle error between the target steering angle and the acquired actual steering angle, as shown in the following formula: u(t)=Kp×e+Ki×∫edt +Kd×de / dt. The correction torque u(t) is then added to the steering actuator's execution torque to drive the steering rack and correct the angle deviation between the actual steering angle and the target steering angle.

[0080] In some embodiments, the error change rate can be the difference between the current angle error e(n) and the previous angle error e(n-1): ec=e(n)-e(n-1), where the current angle error is the difference between the current actual steering angle and the previous target steering angle, and the previous angle error is the difference between the previous actual steering angle and the previous target steering angle.

[0081] Traditional autonomous driving control does not allow for human-machine co-driving; the autonomous driving system 110 disengages when the driver intervenes in steering. This embodiment of the invention utilizes the decoupling between the upper and lower rotor systems of the steer-by-wire system 120, allowing a certain degree of human-machine co-driving during autonomous driving operation. This adds more usage scenarios to the intelligent driving function while ensuring safety.

[0082] The human-machine co-driving control system for a vehicle provided in this embodiment of the invention includes: an automatic driving system 110, used to acquire the current driving speed of the vehicle and the driver's hand torque, and to determine the driver takeover conditions based on the current driving speed; and a steer-by-wire system 120, used to acquire a first target steering angle planned by the automatic driving system 110 when the driver's hand torque does not meet the driver takeover conditions, to determine a target steering angle based on the driver's hand torque and the first target steering angle, and to control the vehicle steering based on the target steering angle.

[0083] In some embodiments, the autonomous driving system 110 is specifically configured to: if the current driving speed is less than a vehicle speed threshold, determine the driver takeover condition as follows: the absolute value of the driver's hand torque is greater than a first torque threshold and lasts for at least a first duration, or is greater than a second torque threshold, wherein the second torque threshold is greater than the first torque threshold; if the current driving speed is greater than or equal to the vehicle speed threshold, determine the driver takeover condition as follows: the absolute value of the driver's hand torque is greater than a third torque threshold and lasts for at least a second duration, or is greater than a fourth torque threshold, wherein the third torque threshold is greater than the first torque threshold, the fourth torque threshold is greater than the second torque threshold, and the third torque threshold is less than the fourth torque threshold.

[0084] In some embodiments, the autonomous driving system 110 is further configured to: determine whether the driver's hand torque is greater than or equal to a fifth torque threshold, wherein the fifth torque threshold is less than the first torque threshold; if so, execute the step of determining the driver takeover conditions based on the current driving speed.

[0085] In some embodiments, the autonomous driving system 110 is specifically configured to: detect the driver's raw hand force signal; perform low-pass filtering and moving average filtering on the driver's raw hand force signal to obtain the driver's hand torque.

[0086] In some embodiments, the steer-by-wire system 120 is specifically configured to: acquire driver operation weights and a first target steering angle, wherein the driver operation weights characterize the degree of driver intervention in the vehicle steering; determine a superimposed steering angle based on the driver operation weights, the first target steering angle, and the driver's hand torque; and determine the target steering angle based on the superimposed steering angle.

[0087] In some embodiments, the steer-by-wire system 120 is specifically used for: calculating a basic steering torque based on the first target steering angle; superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain a superimposed steering torque; and calculating the superimposed steering angle from the superimposed steering torque.

[0088] In some embodiments, the steer-by-wire system 120 is specifically configured to: determine an autonomous driving weight corresponding to the basic steering torque based on the driver's operation weight; multiply the autonomous driving weight by the basic steering torque to obtain a first torque component; multiply the driver's operation weight by the driver's hand torque to obtain a second torque component; and add the first torque component to the second torque to obtain the superimposed steering torque.

[0089] In some embodiments, the steer-by-wire system 120 is specifically used to: calculate a second target steering angle based on the driver's hand torque; and superimpose the first target steering angle and the second target steering angle based on the driver's operation weight to obtain the superimposed steering angle.

[0090] In some embodiments, the steer-by-wire system 120 is specifically configured to: determine the autonomous driving weight corresponding to the first target steering angle based on the driver's operation weight; multiply the autonomous driving weight by the first target steering angle to obtain a first steering angle component; multiply the driver's operation weight by the driver's hand torque to obtain a second steering angle component; and add the first steering angle component and the second steering angle component to obtain the superimposed steering angle.

[0091] In some embodiments, the autonomous driving system 110 is specifically configured to: if it detects that the driver is in a state where his hands are off the steering wheel, send the driver operation weight as 0; if it detects that the driver is in a state where his hands are on the steering wheel, send the driver operation weight in the range of 0-1.

[0092] In some embodiments, the autonomous driving system 110 is further configured to: disengage steering control of the vehicle when the driver's hand torque satisfies the driver takeover conditions.

[0093] In some embodiments, the steer-by-wire system 120 includes a main control MCU, an upper rotor system, and a lower rotor system; The main control MCU is used to calculate the basic steering torque based on the first target steering angle, and to superimpose the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain the superimposed steering torque; The upper rotor system's upper rotor controller is used to calculate the superimposed steering angle from the superimposed steering torque, and to determine the target steering angle based on the superimposed steering angle.

[0094] In some embodiments, the angle sensor of the upper rotor system is used to collect the actual steering angle of the wheel; The lower-turn controller of the upper rotor system is used to adjust the PID control parameters according to the error information between the target steering angle and the actual steering angle, as well as multiple preset fuzzy rules. Each fuzzy rule is a mapping relationship between multiple error states and parameter adjustment methods. The lower-turn controller of the upper rotor system is used to output a correction torque based on the adjusted PID control parameters, which is superimposed on the execution torque of the steer-by-wire actuator of the steer-by-wire system 120 to correct the angle deviation between the actual steering angle and the target steering angle.

[0095] More details on the real-time implementation of the autonomous driving system 110 and the steer-by-wire system 120 can be found in the descriptions in the foregoing method embodiments, and will not be repeated here for the sake of brevity.

[0096] Based on the same inventive concept, embodiments of the present invention provide a vehicle including the human-machine co-driving control system described in any of the foregoing embodiments of the present invention.

[0097] Based on the same inventive concept, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the human-machine co-driving control method provided in any embodiment of the present invention.

[0098] The human-machine co-driving control system provided by one or more embodiments of the present invention provides dual transmission and verification in multiple aspects, including hardware redundancy in the steer-by-wire system and autonomous driving system, vehicle power redundancy, vehicle communication redundancy, and autonomous driving system software redundancy, fully ensuring the safety of human-machine co-driving in L3 and above autonomous driving scenarios. Utilizing the decoupling property of steer-by-wire, it attempts to allow a certain degree of human-machine co-driving during autonomous driving operation, ensuring the safety of human-machine co-driving while adding more usage scenarios for intelligent driving functions.

[0099] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0101] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0103] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A human-machine co-driving control method for vehicles, characterized in that, include; The vehicle's current speed and the driver's hand torque are obtained, and the driver takeover conditions are determined based on the current speed. If the driver's hand torque does not meet the driver takeover conditions, obtain the first target steering angle planned by the autonomous driving system; The target steering angle is determined based on the driver's hand torque and the first target steering angle; The vehicle steering is controlled according to the target steering angle.

2. The human-machine co-driving control method as described in claim 1, characterized in that, The step of determining the driver takeover conditions based on the current driving speed includes: If the current driving speed is less than the vehicle speed threshold, the driver takeover condition is determined to be: the absolute value of the driver's hand torque is greater than the first torque threshold and lasts for at least the first duration, or it is greater than the second torque threshold, wherein the second torque threshold is greater than the first torque threshold; If the current driving speed is greater than or equal to the vehicle speed threshold, the driver takeover condition is determined to be: the absolute value of the driver's hand torque is greater than the third torque threshold and lasts for at least the second duration, or greater than the fourth torque threshold, wherein the third torque threshold is greater than the first torque threshold, the fourth torque threshold is greater than the second torque threshold, and the third torque threshold is less than the fourth torque threshold.

3. The human-machine co-driving control method as described in claim 2, characterized in that, Before determining the driver takeover conditions based on the current driving speed, the method further includes: Determine whether the driver's hand torque is greater than or equal to a fifth torque threshold, wherein the fifth torque threshold is less than the first torque threshold; If so, proceed with the step of determining the driver takeover conditions based on the current driving speed.

4. The human-machine co-driving control method as described in claim 1, characterized in that, To obtain the driver's hand torque, the following is included: Detect the driver's original hand force signal; The driver's original hand force signal is subjected to low-pass filtering and moving average filtering to obtain the driver's hand torque.

5. The human-machine co-driving control method as described in claim 1, characterized in that, Determining the target steering angle based on the driver's hand torque and the first target steering angle includes: The driver's operational weight and the first target steering angle are obtained, wherein the driver's operational weight characterizes the degree of driver intervention in the vehicle's steering; The superimposed steering angle is determined based on the driver's operation weight, the first target steering angle, and the driver's hand torque; The target steering angle is determined based on the superimposed steering angle.

6. The human-machine co-driving control method as described in claim 5, characterized in that, Determining the superimposed steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque includes: The basic steering torque is calculated based on the first target steering angle; The driver's hand torque and the basic steering torque are superimposed based on the driver's operation weight to obtain the superimposed steering torque; The superimposed steering angle is calculated from the superimposed steering torque.

7. The human-machine co-driving control method as described in claim 6, characterized in that, The step of superimposing the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain the superimposed steering torque includes: Based on the driver operation weights, determine the autonomous driving weights corresponding to the basic steering torque; Multiply the autonomous driving weight by the basic steering torque to obtain the first torque component, and multiply the driver operation weight by the driver hand torque to obtain the second torque component; The first torque component is added to the second torque component to obtain the superimposed steering torque.

8. The method as described in claim 5, characterized in that, Determining the superimposed steering angle based on the driver's operation weight, the first target steering angle, and the driver's hand torque includes: The second target steering angle is calculated based on the driver's hand torque. The first target steering angle and the second target steering angle are superimposed based on the driver's operating weight to obtain the superimposed steering angle.

9. The human-machine co-driving control method as described in claim 8, characterized in that, The step of superimposing the first target steering angle and the second target steering angle based on the driver's operation weight to obtain the superimposed steering angle includes: Based on the driver operation weights, determine the autonomous driving weights corresponding to the first target steering angle; Multiply the autonomous driving weight by the first target steering angle to obtain the first steering angle component, and multiply the driver operation weight by the driver hand torque to obtain the second steering angle component; The first steering angle component and the second steering angle component are added together to obtain the superimposed steering angle.

10. The human-machine co-driving control method as described in any one of claims 5-9, characterized in that, Also includes: If it is detected that the driver has taken their hands off the steering wheel, the driver's operation weight is 0; If the driver is detected to be holding the steering wheel, the driver's operation weight is in the range of 0-1.

11. The human-machine co-driving control method as described in claim 1, characterized in that, Also includes: When the driver's hand torque meets the driver takeover conditions, the automatic driving system disengages from steering control of the vehicle.

12. The human-machine co-driving control method as described in claim 6, characterized in that, The steer-by-wire system includes a main control MCU, an upper rotor system, and a lower rotor system; determining the target steering angle based on the driver's hand torque and the first target steering angle includes: The main control MCU calculates the basic steering torque based on the first target steering angle, and then superimposes the driver's hand torque and the basic steering torque based on the driver's operation weight to obtain the superimposed steering torque. The superimposed steering angle is calculated by the upper rotor system's upper rotation controller, and the target steering angle is determined based on the superimposed steering angle.

13. The human-machine co-driving control method as described in claim 12, characterized in that, The step of controlling the vehicle steering according to the target steering angle includes: The actual steering angle of the wheel is acquired by the angle sensor of the upper rotor system; The PID control parameters are adjusted by the lower rotation controller of the upper rotor system based on the error information between the target steering angle and the actual steering angle, as well as multiple preset fuzzy rules. Each fuzzy rule is a mapping relationship between multiple error states and parameter adjustment methods. The lower rotor controller of the upper rotor system outputs a correction torque based on the adjusted PID control parameters, which is superimposed on the execution torque of the steer-by-wire actuator of the steer-by-wire system to correct the angle deviation between the actual steering angle and the target steering angle.

14. A human-machine co-driving control system for vehicles, characterized in that, include: An autonomous driving system, and a steer-by-wire system communicatively connected to the autonomous driving system; The autonomous driving system is used to acquire the vehicle's current driving speed and the driver's hand torque, and to determine the conditions for driver takeover based on the current driving speed. The steer-by-wire system is used to obtain a first target steering angle planned by the autonomous driving system when the driver's hand torque does not meet the driver takeover conditions, determine a target steering angle based on the driver's hand torque and the first target steering angle, and control the vehicle steering based on the target steering angle.

15. The human-machine co-driving control system as described in claim 14, characterized in that: The steer-by-wire system includes an upper rotor system and a lower rotor system, which are connected via at least two CAN buses; and / or The key components in both the upper rotor system and the lower rotor system include at least two paths; and / or The autonomous driving system and the steer-by-wire system are connected via at least two CAN buses; and / or The key components of both the upper rotor system and the lower rotor system are connected to two power grids, which are physically isolated from each other.

16. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, implements the human-machine co-driving control method for a vehicle as described in any one of claims 1-13.

Images