Method for calibrating driving behavior of robot, electronic equipment and storage medium

Abstract

The invention relates to the field of vehicle driving robots, in particular to a method for calibrating robot driving behaviors, electronic equipment capable of implementing the scheme, a computer storage medium and a computer program product. The method comprises the steps of controlling a robot execution mechanism to execute a vehicle driving action according to a vehicle control instruction; receiving vehicle bus information, sensor information collected by a vehicle end sensor and position information of a robot execution mechanism; determining position information of the vehicle mechanism based on the vehicle bus information and the sensor information; closed-loop control is carried out according to the position information of the vehicle mechanism and the position information of the robot executing mechanism, so that the action of the robot executing mechanism is matched with the expected vehicle driving action; and storing the position information of the vehicle mechanism and the position information of the robot execution mechanism in an association table in an association manner.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving robots, and more specifically to a method for calibrating robot driving behavior, an electronic device capable of implementing the solution, a computer storage medium, and a computer program product. Background Art

[0002] In the field of vehicle research and development, vehicle road certification testing is an indispensable part to ensure that key indicators such as performance and durability of components and vehicles meet design expectations and to identify potential defects and failures in advance. However, the traditional manual driving test method is difficult to ensure the consistency and accuracy of the test process due to differences in driver operating habits and skill levels, which increases the uncertainty and risk of certification results.

[0003] To solve this problem, the introduction of robot driving technology has become a trend, which not only reduces the reliance on human resources, but also ensures a high degree of consistency and accuracy in test execution through automated control, thereby improving the quality and efficiency of the overall test certification. Given the diversification of the automotive market, different models have significant differences in mechanical design, electronic architecture, etc., which puts higher demands on the versatility and flexibility of test robots. In order to achieve seamless switching and compatibility across models and platforms, intelligent calibration and learning of robots has become the key.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In order to solve or at least alleviate one or more of the above problems, a method for calibrating robot driving behavior, an electronic device capable of implementing the solution, a computer storage medium and a computer program product are provided. The method has high versatility and flexibility, can support the testing requirements of various vehicle models and platforms, reduces the calibration difficulty and cost caused by differences in vehicle models, and improves the calibration accuracy and consistency.

[0006] According to a first aspect of the present application, a method for calibrating robot driving behavior is provided, the method comprising: controlling a robot actuator to perform a vehicle driving action according to a vehicle control instruction; receiving vehicle bus information, sensor information collected by a vehicle-side sensor, and position information of the robot actuator; determining the position information of the vehicle mechanism based on the vehicle bus information and the sensor information; performing closed-loop control according to the position information of the vehicle mechanism and the position information of the robot actuator so that the action of the robot actuator matches the expected vehicle driving action; and storing the position information of the vehicle mechanism and the position information of the robot actuator in an associated table in an associated manner.

[0007] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present application, controlling a robot actuator to perform a vehicle driving action according to a vehicle control instruction includes: determining an expected vehicle driving action based on the vehicle control instruction; determining an expected action of the robot actuator based on the expected vehicle driving action; converting the expected action of the robot actuator into a control signal; and sending the control signal to the robot actuator to perform the expected vehicle driving action.

[0008] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present application, closed-loop control is performed based on the position information of the vehicle mechanism and the position information of the robot actuator so that the action of the robot actuator matches the expected vehicle driving action, including: determining the deviation between the action of the robot actuator and the expected vehicle driving action; and adjusting the expected action of the robot actuator based on the real-time feedback of the position information of the vehicle mechanism to reduce the deviation.

[0009] As an alternative or supplement to the above solution, in a method according to an embodiment of the present application, the vehicle driving action includes one or a combination of the following: throttle control, brake control, steering control, and gear control.

[0010] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present application, the closed-loop control includes: performing zero-position learning by setting the corresponding vehicle mechanism to zero position and recording the position of the robot actuator to establish a zero-position reference point.

[0011] As an alternative or supplement to the above solution, in a method according to an embodiment of the present application, the closed-loop control includes: performing full-range learning to determine the correspondence between the position of the robot actuator and the vehicle mechanism within the entire motion range.

[0012] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present application, an out-of-limit judgment is performed during the zero-position learning and / or the full-range learning process, and if it is determined that the limit is exceeded, the zero-position learning process is stopped.

[0013] As an alternative or supplement to the above scheme, in a method according to an embodiment of the present application, the over-limit judgment includes one or more of the following items: judging whether the execution time of the zero-position learning exceeds a first threshold; judging whether the motor current exceeds a second threshold; judging whether the sensor information exceeds a third threshold; judging whether the position of the robot actuator exceeds the range of motion allowed by the vehicle mechanism.

[0014] According to a second aspect of the present application, an electronic device is provided, comprising: a memory; a processor; and a computer program stored on the memory and executable on the processor, wherein the execution of the computer program enables any one of the methods described in the first aspect to be executed.

[0015] As an alternative or supplement to the above solution, the electronic device according to an embodiment of the present application also includes: a communication interface for receiving vehicle control instructions from the upper control device of the robot.

[0016] According to a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium comprises instructions, and the instructions, when run, execute any one of the methods described in the first aspect of the present application.

[0017] According to a fourth aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements any one of the methods described in the first aspect of the present application.

[0018] The solution for calibrating the driving behavior of a robot according to one or more embodiments of the present application can at least achieve the following technical advantages:

[0019] Improve calibration accuracy and consistency: By combining vehicle bus information and real-time data collected by vehicle-side sensors, as well as the position information of the robot actuators, closed-loop control can achieve precise adjustment of the robot's driving behavior. This real-time feedback mechanism based on the actual vehicle state ensures that the robot actuator's actions can closely match the expected vehicle driving actions, thereby improving the accuracy and consistency of calibration.

[0020] Enhanced adaptability and versatility: This solution does not rely on specific vehicle models or hardware, but adapts to the control requirements of different vehicle models through universal processing of vehicle bus information and sensor information. This means that the calibration method has high versatility and flexibility, can support the testing requirements of multiple vehicle models and platforms, and reduces the difficulty and cost of calibration caused by differences in vehicle models.

[0021] Optimize calibration process and efficiency: By storing the position information of the vehicle mechanism and the position information of the robot actuator in an associated table, a data basis is provided for the subsequent calibration analysis and testing process. This data recording method facilitates the subsequent backtracking and evaluation of the calibration process, helps to quickly identify problems in the calibration process, and take corresponding improvement measures, thereby optimizing the calibration process and improving calibration efficiency.

[0022] Reduce human intervention and risks: The automated calibration process reduces the need for manual operation and reduces the impact of human factors on the calibration results. At the same time, by having robots perform driving tasks, it can also reduce risks such as driver fatigue and misoperation, ensuring the safety and stability of the test process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or other aspects and advantages of the present application will become clearer and easier to understand through the following description of various aspects in conjunction with the accompanying drawings, in which the same or similar units are represented by the same reference numerals. In the accompanying drawings:

[0024] Figure 1 is a schematic flow chart of a method 10 for calibrating a robot driving behavior according to one or more embodiments of the present application;

[0025] Figure 2 A schematic flow chart of closed-loop control for throttle learning according to one or more embodiments of the present application;

[0026] Figure 3 A schematic flow chart of closed-loop control for brake learning according to one or more embodiments of the present application;

[0027] Figure 4 is a schematic flow chart of closed-loop control for steering learning according to one or more embodiments of the present application;

[0028] Figure 5 A schematic flowchart of closed-loop control for gear learning according to one or more embodiments of the present application; and

[0029] Figure 6 is a schematic block diagram of an electronic device 60 according to one or more embodiments of the present application. DETAILED DESCRIPTION

[0030] The description of the following specific embodiments is merely exemplary in nature and is not intended to limit the disclosed technology or the application and use of the disclosed technology. In addition, it is not intended to be bound by any express or implied theory presented in the aforementioned technical field, background technology or the following specific embodiments.

[0031] In the following detailed description of the embodiments, many specific details are set forth in order to provide a more thorough understanding of the disclosed technology. However, it is apparent to one of ordinary skill in the art that the disclosed technology can be practiced without these specific details. In other instances, well-known features are not described in detail to avoid unnecessarily complicating the description.

[0032] Terms such as "comprising" and "including" indicate that in addition to the units and steps directly and clearly stated in the specification, the technical solution of the present application does not exclude the situation of having other units and steps that are not directly or clearly stated. Terms such as "first" and "second" do not indicate the order of units in terms of time, space, size, etc., but are only used to distinguish between units.

[0033] Hereinafter, various exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings.

[0034] Referring to the accompanying drawings, Figure 1 It is a schematic flowchart of a method 10 for calibrating the driving behavior of a robot according to one or more embodiments of the present application.

[0035] like Figure 1 As shown, in step S110, according to the vehicle control instruction, the robot actuator is controlled to perform the vehicle driving action.

[0036] Vehicle control instructions refer to instructions issued by upper-level control devices such as autonomous driving systems to instruct vehicles to perform specific driving actions. These instructions usually include the specific types of actions that the vehicle needs to perform (for example, acceleration, deceleration, steering, etc.) and corresponding parameters (for example, acceleration magnitude, steering angle, etc.). Robot actuators refer to a part of the robot's motion system and execution control system, which is mainly used to realize the robot's motion control and mechanical movement. In this article, robot actuators generally refer to those mechanical and electronic components that can directly control the movement of the vehicle. Vehicle driving actions refer to various specific operations performed by the vehicle during driving, such as throttle control, brake control, steering control, gear control, etc. These actions are a direct reflection of the vehicle control instructions and are also the basis for the vehicle to achieve autonomous driving.

[0037] Optionally, step S110 can be decomposed into the following steps:

[0038] Parse the vehicle control command and determine the expected vehicle driving action. First, receive and parse the vehicle control command from the upper control device. After parsing the command, determine the expected vehicle driving action based on the command content. For example, if the command is to accelerate, the system needs to know the magnitude and duration of the acceleration; if it is to turn, the angle and speed of the turn need to be determined, etc.

[0039] Convert into action instructions for robot actuators. Specifically, convert the expected vehicle driving actions into instructions that the robot actuators can understand and execute. This usually involves converting vehicle-level driving actions (such as throttle opening, brake pressure, steering angle) into control parameters (such as voltage, current, position, etc.) of specific actuators (such as motors, hydraulic cylinders, steering gears, etc.).

[0040] Send control signals to the robot actuators. Once the action instructions of the robot actuators are determined, the system will generate corresponding control signals and send them to the robot actuators through appropriate interfaces. These control signals will guide the actuators to move or work in the expected manner.

[0041] Execute driving actions. After receiving the control signal, the robot actuator will perform the corresponding driving action according to the signal's instructions. For example, the motor may drive the wheel to rotate according to the change of voltage or current to achieve acceleration or deceleration; the servo may turn the steering wheel according to the position instruction to achieve the steering of the vehicle.

[0042] In step S120, vehicle bus information, sensor information collected by vehicle-side sensors, and position information of robot actuators are received.

[0043] While the robot actuator is performing driving actions, it receives real-time vehicle bus information (such as vehicle speed, engine speed, etc.) and sensor information collected by vehicle-side sensors (such as accelerometers, gyroscopes, cameras, etc.). At the same time, the system also receives the position information of the robot actuator (such as motor angle, steering gear position, etc.) to achieve comprehensive monitoring of the robot actuator status.

[0044] In step S130 , the position information of the vehicle mechanism is determined based on the vehicle bus information and the sensor information.

[0045] Using vehicle bus information and sensor information, the system calculates the real-time position information of vehicle mechanisms (such as wheels, steering mechanisms, etc.) through algorithm processing (such as data fusion, filtering, etc.). This information provides an important basis for subsequent closed-loop control. For example, by analyzing the input of the steering system (such as the steering wheel angle) and the response of the vehicle (such as the wheel steering angle), the steering state of the vehicle can be determined.

[0046] In step S140, closed-loop control is performed based on the position information of the vehicle mechanism and the position information of the robot actuator, so that the action of the robot actuator matches the expected vehicle driving action.

[0047] Closed-loop control is a control method with a feedback mechanism that can compare the deviation between the actual output (i.e., the position information of the robot actuator) and the expected input (i.e., the position information corresponding to the expected vehicle driving action) to automatically adjust the control input (such as the driving signal of the robot actuator, which is used to indicate the expected action of the robot actuator) to eliminate or reduce this deviation, thereby achieving the desired control goal. The formulation of a specific closed-loop control strategy can be based on a predefined algorithm (such as a PID control algorithm) or on a machine learning model to achieve adaptation to complex dynamic environments.

[0048] During the action of the actuator, the sensor continues to collect the position information of the vehicle mechanism in real time and feeds it back to the system. The system recalculates the deviation based on the new feedback information and may adjust the control strategy again to achieve continuous optimization and fine-tuning of the robot actuator action. This process is a closed-loop iterative process until the action of the robot actuator fully matches the expected vehicle driving action or reaches the predetermined accuracy requirement.

[0049] Optionally, in closed-loop control, zero-position learning can be performed first. Zero-position learning is equivalent to an initialization step, which aims to establish a zero-position reference point by setting the corresponding vehicle mechanism to zero position and recording the position of the robot actuator for subsequent position control and calibration. Exemplarily, the specific implementation process of zero-position learning is as follows: First, the vehicle mechanism (such as the accelerator pedal, brake pedal, steering wheel, etc.) is set to a predetermined zero-position state, that is, their center or initial position. This zero position is the reference point for all subsequent position measurements; when the vehicle mechanism reaches the zero position, a high-precision sensor is used to record the exact position of the robot actuator at the zero position. This position will be regarded as the zero-position reference point for subsequent position calibration and calculation.

[0050] Optionally, in closed-loop control, full-range learning can also be performed. Full-range learning aims to determine the correspondence between the position of the robot actuator and the vehicle mechanism within the entire range of motion. Exemplarily, the specific implementation process of full-range learning is as follows: traversing the range of motion - controlling the robot actuator to traverse its entire range of motion in a predetermined path or pattern and at a predetermined scale, while recording the data of each position point; mapping the data of the robot actuator at each position point with the corresponding position information of the vehicle mechanism, and establishing a complete correspondence table or model. This mapping relationship will be used in subsequent testing processes to ensure that the robot actuator can accurately simulate all actions of the vehicle mechanism within the entire range of motion.

[0051] Optionally, during the process of zero-position learning and / or full-scale learning, an over-limit judgment mechanism can be added to prevent the robot actuator or vehicle mechanism from exceeding the safe operating range. Exemplarily, the over-limit judgment includes: time over-limit judgment - judging whether the execution time of zero-position learning and / or full-scale learning exceeds the first threshold. If it exceeds the set time threshold, it may mean that the learning process encounters a blockage or error and needs to be stopped and checked; current over-limit judgment - monitoring whether the motor current exceeds the second threshold. The abnormal increase in motor current may be caused by mechanical blockage, motor overload or other fault conditions. High current may indicate mechanical jamming, motor failure or load abnormality, and learning needs to be stopped immediately; sensor information over-limit judgment - judging whether the sensor information exceeds the third threshold. The abnormality of the sensor reading may be caused by sensor failure, external interference or abnormal position of the robot actuator. Abnormal data may mean sensor failure or inaccurate reading, affecting the accuracy of learning; position over-limit judgment - judging whether the position of the robot actuator exceeds the allowed range of motion of the vehicle mechanism. This is to prevent the robot actuator from pushing the vehicle mechanism beyond the design limit, which may cause damage or safety accidents. If any of the items in the over-limit judgment is judged as over-limit, the zero-position learning or full-scale learning process will be automatically stopped. The learning process is stopped to ensure the safety of the system and prevent further potential damage. After stopping, the system will record the current status and data for technicians to analyze the cause and take corresponding corrective measures.

[0052] In step S150, the position information of the vehicle mechanism and the position information of the robot actuator are stored in an association table in an associated manner.

[0053] During the calibration process, the correspondence between the position information of the vehicle mechanism and the position information of the robot actuator will be continuously recorded and stored. The association table is usually a data structure used to store the mapping relationship between the vehicle mechanism and the robot actuator. Exemplarily, each row of the association table can represent a specific state or action, including the following fields: the position information of the vehicle mechanism (such as throttle position, brake position, steering angle, etc.); the position information of the robot actuator (such as the corresponding control arm position, servo motor angle, etc.); possible timestamps or state identifiers to track data changes.

[0054] During each learning or operation, the system will record the current vehicle mechanism position information and robot actuator position information into the association table. As learning progresses, the association table will be continuously updated to reflect new learning results and optimized action parameters. The data stored in the association table will be used in subsequent control processes to ensure that the robot actuator can make corresponding actions according to the actual status of the vehicle.

[0055] Continue to refer to Figure 2 . Figure 2 The diagram is a schematic flowchart of closed-loop control for throttle learning according to one or more embodiments of the present application.

[0056] In S201, in response to the start of throttle learning, the absolute zero point of the motor is set. In S203, check whether the absolute zero point calibration is successful. If not, return to step S201. In S205, determine whether the vehicle power mode is ACC gear. If it is not ACC gear, a mode error occurs and the throttle learning is marked as failed. In S207, perform mechanism zero position learning. In S209, determine whether the zero position learning is successful. If not, determine in S211 whether the zero position learning has timed out (that is, whether it exceeds 5s). If the zero position learning times out, mark the throttle learning as failed. If not, continue with S207. In S213, perform point-by-point learning with the minimum division of the bus feedback signal (that is, the smallest unit of change that the feedback signal can distinguish). In S215, determine whether the throttle has reached the 100% position. If not, continue point-by-point learning and determine in S217 whether the motor current exceeds the limit value. If it exceeds the limit, then determine whether the throttle position is greater than 90% in S219. If it exceeds, mark the throttle learning failure. If everything is normal, then store the throttle learning data in S221 to complete the throttle learning.

[0057] Continue to refer to Figure 3 . Figure 3 The diagram is a schematic flow chart of closed-loop control for brake learning according to one or more embodiments of the present application.

[0058] In S301, in response to the start of brake learning, the absolute zero point of the motor is set. In S303, check whether the absolute zero point calibration is successful. If not, return to step S301. In S305, determine whether the vehicle power mode is in the ON gear. If it is not in the ON gear, a mode error occurs and the brake learning is marked as failed. In S307, the mechanism zero position learning is performed. In S309, determine whether the zero position learning is successful. If not, determine in S311 whether the zero position learning has timed out (that is, whether it exceeds 5s). If the zero position learning has timed out, the brake learning is marked as failed. If not, continue with S307. In S313, point-by-point learning is performed with the minimum division of the bus feedback signal. In S315, determine whether the braking 100% position has been reached. If not, continue point-by-point learning, and determine in S319 whether the motor current exceeds the limit value. If it exceeds the limit, determine in S323 whether the braking position is greater than 85%. If it is not exceeded, then in S321, it is determined whether the brake pedal force feedback value exceeds the limit value. If the brake pedal force feedback value exceeds the limit value, then in S323, it is determined whether the braking position is greater than 85%. If the braking position is greater than 85% or reaches the braking 100% position, then in S317, the braking learning data is stored to complete the braking learning.

[0059] Continue to refer to Figure 4 . Figure 4 It is a schematic flowchart of closed-loop control for steering learning according to one or more embodiments of the present application.

[0060] In S401, in response to the start of steering learning, the absolute zero point of the motor is set. In S403, check whether the absolute zero point calibration is successful. If not, return to step S401. In S405, determine whether the vehicle power mode is ON gear. If not ON gear, a mode error occurs and the steering learning is marked as failed. In S407, determine whether the steering bus feedback signal is less than 5°. If greater than or equal to 5°, the mechanical zero position deviation is large and the steering learning is marked as failed. If less than 5°, the mechanism zero position learning is performed in S409. In S411, determine whether the zero position learning is successful. If not, determine whether the zero position learning has timed out (that is, whether it exceeds 10s) in S413. If the zero position learning has timed out, the steering learning is marked as failed. If not, continue with S409. In S415, perform left limit learning. In S417, determine whether the limited left limit has been reached. If the limited left limit has been reached, continue to perform right limit learning in S423. If the defined left limit is not reached, determine whether the motor current exceeds the limit value in S419. If it exceeds, continue to S423; if it does not exceed, determine whether the steering wheel torque feedback value exceeds the limit value in S421. If it exceeds, continue to S423; if it does not exceed, continue to learn the left limit. Similarly, as shown in the flowchart, perform S425-429 for right limit learning. If the defined right limit value is reached, or the motor current does not exceed the limit value, or the steering wheel torque feedback value does not exceed the limit value, then store the steering learning data in S431 and complete the steering learning.

[0061] Continue to refer to Figure 5 . Figure 5 The present invention is a schematic flowchart of closed-loop control for gear learning according to one or more embodiments of the present application.

[0062] In S501, in response to the start of gear learning, determine whether the gear is in P gear. If not in P gear, mark the gear learning failure; if in P gear, set the motor absolute zero point in S503. In S505, check whether the absolute zero point calibration is successful. If not, return to step S503. In S507, determine whether the vehicle power mode is ON gear. If not in ON gear, a mode error occurs and the gear learning failure is marked. In S509, teach each gear position. In S511, determine whether the learning completion button is pressed. If not, continue S509. If pressed, store the gear learning data in S513 to complete the gear learning.

[0063] Figure 66 is a schematic block diagram of an electronic device 60 according to one or more embodiments of the present application. The electronic device 60 includes a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620. The execution of the computer program 630 enables the following Figure 1-Figure 5 Any of the methods shown in is executed. Exemplarily, the electronic device 60 may be a robot control mechanism or a robot including the control mechanism. Optionally, the electronic device 60 further includes a communication interface for receiving vehicle control instructions from an upper control device of the robot.

[0064] In addition, as described above, the present application can also be implemented as a computer storage medium, in which there is stored a program for causing a computer to execute the following steps: Figure 1-Figure 5 Here, as the computer storage medium, various computer storage media such as disks (e.g., magnetic disks, optical disks, etc.), cards (e.g., memory cards, optical cards, etc.), semiconductor memories (e.g., ROMs, nonvolatile memories, etc.), and tapes (e.g., magnetic tapes, cassette tapes, etc.) can be used.

[0065] The present application may also be implemented as a computer program product, which includes a computer program. When the computer program is executed by a processor, the following Figure 1-Figure 5 The procedure of any of the methods shown in .

[0066] In the applicable situation, hardware, software or a combination of hardware and software can be used to realize the various embodiments provided by the application. Moreover, in the applicable situation, without departing from the scope of the application, the various hardware components and / or software components set forth herein can be combined into a composite component comprising software, hardware and / or both. In the applicable situation, without departing from the scope of the application, the various hardware components and / or software components set forth herein can be divided into subcomponents comprising software, hardware or both. In addition, in the applicable situation, it is contemplated that the software component can be implemented as a hardware component, and vice versa.

[0067] Software (such as program code and / or data) according to the present application can be stored on one or more computer storage media. It is also contemplated that the software identified herein can be implemented using one or more general or special-purpose computers and / or computer systems, networked and / or otherwise. Where applicable, the order of the various steps described herein can be changed, combined into composite steps, and / or divided into sub-steps to provide the features described herein.

[0068] The embodiments and examples set forth herein are provided to best illustrate embodiments according to the present application and its specific applications, and thereby enable those skilled in the art to implement and use the present application. However, those skilled in the art will appreciate that the above description and examples are provided only for ease of illustration and example. The description set forth is not intended to cover all aspects of the present application or to limit the present application to the precise form disclosed.

Claims

1. A method for calibrating robot driving behavior, characterized in that: The method comprises: According to the vehicle control instructions, control the robot actuator to perform vehicle driving actions; Receive vehicle bus information, sensor information collected by vehicle-side sensors, and position information of robot actuators; determining position information of a vehicle mechanism based on the vehicle bus information and the sensor information; Performing closed-loop control based on the position information of the vehicle mechanism and the position information of the robot actuator so that the action of the robot actuator matches the expected vehicle driving action; and The position information of the vehicle mechanism and the position information of the robot actuator are stored in an association table in an associated manner.

2. The method according to claim 1, characterized in that According to the vehicle control instructions, the robot actuator is controlled to perform the vehicle driving actions including: Determining an expected vehicle driving action based on the vehicle control command; Determining an expected action of the robot actuator based on the expected vehicle driving action; converting the expected movement of the robot actuator into a control signal; and The control signal is sent to the robot actuator to execute the expected vehicle driving action.

3. The method according to claim 1, characterized in that Performing closed-loop control according to the position information of the vehicle mechanism and the position information of the robot actuator so that the action of the robot actuator matches the expected vehicle driving action includes: determining deviations between the actions of the robotic actuators and expected vehicle driving actions; and According to the position information of the vehicle mechanism fed back in real time, the expected action of the robot actuator is adjusted to reduce the deviation.

4. The method according to claim 1, characterized in that: The vehicle driving action includes one of the following items or a combination thereof: throttle control, brake control, steering control, and gear control.

5. The method according to claim 1, characterized in that: The closed-loop control comprises: Zero position learning is performed to establish a zero position reference point by setting the corresponding vehicle mechanism to the zero position and recording the position of the robot actuator.

6. The method according to claim 5, characterized in that The closed-loop control comprises: Full-range learning is performed to determine the correspondence between the positions of the robot actuator and the vehicle mechanism within the entire range of motion.

7. The method according to claim 6, characterized in that During the zero-position learning and / or the full-scale learning process, an over-limit judgment is performed. If an over-limit is determined, the zero-position learning process is stopped.

8. The method according to claim 7, characterized in that The over-limit judgment includes one or more of the following: Determining whether the execution time of the zero-position learning exceeds a first threshold; Determining whether the motor current exceeds a second threshold; determining whether the sensor information exceeds a third threshold; It is determined whether the position of the robot actuator exceeds the allowed range of motion of the vehicle mechanism.

9. An electronic device, characterized in that: The method comprises: a memory; a processor; and a computer program stored in the memory and executable on the processor, wherein the execution of the computer program causes the method according to any one of claims 1 to 8 to be executed.

10. The electronic device according to claim 9, characterized in that: The electronic device further comprises: Communication interface, used to receive vehicle control instructions from the upper control device of the robot.

11. A computer storage medium, characterized in that: The computer storage medium comprises instructions which, when executed, perform the method according to any one of claims 1-8.

12. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images