CN-120533703-B - Data processing method, storage medium, electronic device, and program product

Abstract

The application provides a data processing method, a storage medium, electronic equipment and a program product, and relates to the technical field of robot control. The data processing method comprises the steps of carrying out safety inspection on a target control instruction of a target robot, wherein the safety inspection refers to whether the target robot is safe or not if the target robot is controlled based on the target control instruction, determining a movable structure of the target robot related to the target control instruction and a cross-structure cooperative limit condition corresponding to the movable structure under the condition that the target control instruction passes the safety inspection, and adjusting the target control instruction through a soft constraint strategy under the condition that the target control instruction does not meet the cross-structure cooperative limit condition.

Inventors

• Request for anonymity

Assignees

• 上海智元新创技术有限公司

Dates

Publication Date

20260508

Application Date

20250606

Claims (14)

1. 1. A method of data processing, comprising: Receiving first control data sent by a virtual reality end; Determining a delay time of the first control data in case the first control data is not outdated; Determining whether the received historical control data sent by the virtual reality end meets a prediction condition or not under the condition that the delay time is smaller than a target time threshold value, and predicting second control data of a target robot based on the historical control data under the condition that the historical control data meets the prediction condition; obtaining a target control instruction of the target robot based on the second control data; Performing safety check on a target control instruction of a target robot, wherein the safety check is to check whether the target robot is safe if the target robot is controlled based on the target control instruction; determining a movable structure of the target robot related to the target control instruction and a cross-structure cooperative limit condition corresponding to the movable structure under the condition that the target control instruction passes the safety inspection; and under the condition that the target control instruction does not meet the cross-structure cooperative limit condition, adjusting the target control instruction through a soft constraint strategy.
2. 2. The data processing method according to claim 1, wherein the target control command includes at least one of joint angle data, joint angular velocity data, and chassis velocity data, and the safety check is performed on the target control command of the target robot, including at least one of: checking whether the joint angle data falls into a first safety angle interval; Checking whether the difference value of the joint angular velocity data at adjacent moments is smaller than a target safe angular velocity difference value; Checking whether the chassis speed data is less than a target safe speed.
3. 3. The data processing method according to claim 2, characterized by further comprising: and if the joint angle data exceeds the first safety angle interval, processing the joint angle data by utilizing a soft saturation strategy so as to control the joint angle data to smoothly attenuate in a target buffer zone of the first safety angle interval.
4. 4. A data processing method according to claim 3, wherein said processing said joint angle data using a soft saturation strategy comprises: Determining a first target buffer zone positioned at the lower limit side and a second target buffer zone positioned at the upper limit side in the first safety angle interval according to boundary values at two sides of the first safety angle interval and preset buffer zone widths; Determining a lower limit value of the first target buffer zone and an upper limit value of the second target buffer zone; in the first target buffer zone, adjusting the joint angle data to be the result of adding the lower limit value and a first correction quantity, wherein the first correction quantity is used for representing a numerical value for carrying out smooth transition adjustment on the joint angle data in the first target buffer zone; And in the second target buffer zone, adjusting the joint angle data into a difference value result of the upper limit value and a second correction quantity, wherein the second correction quantity is used for representing a numerical value for carrying out smooth transition adjustment on the joint angle data in the second target buffer zone.
5. 5. The data processing method according to claim 4, further comprising: subtracting the lower limit value and the preset buffer zone width from the joint angle data to obtain a first difference value, determining the ratio of the first difference value to the sharpness control parameter as an input value of a soft saturation function to obtain a first transition value; And subtracting the preset buffer area width and the joint angle data from the upper limit value to obtain a second difference value, determining the ratio of the second difference value to the sharpness control parameter as an input value of the soft saturation function to obtain a second transition value, adding the second transition value and a second constant, and multiplying the second constant by the preset buffer area width to obtain the second correction amount.
6. 6. The data processing method according to claim 2, characterized by further comprising: if the difference value of the joint angular velocity data at the adjacent moment is greater than or equal to the target safe angular velocity difference value, determining acceleration limit data; And adjusting the joint angular velocity data of the adjacent moment so that the difference value of the joint angular velocity data of the adjacent moment is smaller than or equal to the product of the acceleration limit data and the time difference value of the adjacent moment.
7. 7. The method of any one of claims 1 to 6, wherein if the movable structure includes a chassis and a robotic arm joint, the cross-structure cooperative constraint comprises: In the event that the chassis speed data is greater than a motion stability threshold, the joint angle data falls within a second safe angle interval.
8. 8. The method according to any one of claims 1 to 6, wherein if the movable structure includes a chassis and a robot arm, the adjusting the target control command by the soft constraint strategy includes: determining target joint angle data and preset safety angle data of the mechanical arm; determining a first weight function and a second weight function based on chassis speed data of the chassis; determining a first product result of the first weight function and the target joint angle data and a second product result of the second weight function and the safety angle data; And adjusting the joint angle data of the mechanical arm based on the addition result of the first product result and the second product result.
9. 9. The data processing method according to claim 1, wherein the second control data of the target robot is predicted based on the history control data, including at least one of: Processing the historical control data by using an extended Kalman filtering algorithm to generate head posture data of the target robot, wherein the head posture data comprises a pitch angle and a yaw angle; processing the history control data by using a long and short-term memory neural network model to generate joint angle data of a mechanical arm of the target robot; processing the historical control data by utilizing a dynamics model based on differential drive and a Kalman filtering algorithm to obtain chassis speed data of the target robot; And processing the historical control data by using a sliding window average method and/or a uniform acceleration model to obtain waist state data of the target robot, wherein the waist state data comprises height data and pitch angle.
10. 10. The method according to claim 9, wherein the processing the history control data using a sliding window averaging method and/or a ramp-up model to obtain the waist state data of the target robot includes: Processing the history control data by using the uniform acceleration model to obtain first state data of the waist; processing the history control data by using the sliding window averaging method to obtain second state data of the waist; If the first state data meets the prediction accuracy condition, determining the first state data as the waist state data; if the first state data does not meet the prediction accuracy condition, respectively determining a first weight corresponding to the first state data and a second weight corresponding to the second state data; determining the sum of the product of the first state data and the first weight and the product of the second state data and the second weight, and determining the sum as the waist state data.
11. 11. The data processing method of claim 1, wherein the first control data comprises a transmission time stamp, and wherein the determining the delay time of the first control data comprises: determining an original delay time of the first control data based on the reception time of the first control data and the transmission time stamp; Determining system time offset data between the virtual reality end and the target robot; And determining the difference value between the original delay time and the system time offset data as the delay time of the first control data.
12. 12. A computer-readable storage medium, characterized in that the storage medium stores a computer program for executing the data processing method according to any one of the preceding claims 1 to 11.
13. 13. An electronic device, comprising: A processor; a memory for storing the processor-executable instructions; The processor being configured to perform the data processing method of any of the preceding claims 1 to 11.
14. 14. A computer program product, characterized in that it comprises instructions that, when executed on an electronic device, cause the electronic device to implement the data processing method of any of claims 1 to 11.

Description

Data processing method, storage medium, electronic device, and program product Technical Field The present application relates to the field of robot control technologies, and in particular, to a data processing method, a storage medium, an electronic device, and a program product. Background During the operation of the robot, the control instructions (such as joint angle, chassis speed, head posture, etc.) received by the robot may have potential safety hazards, and if the unverified control instructions are directly executed, the problems of mechanical structure overrun, impact or environmental safety hazard may be caused, for example, the robot joint overload, end effector collision obstacle or dynamic instability of the system may be caused. Disclosure of Invention In view of this, the embodiments of the present application provide a data processing method, a storage medium, an electronic device, and a program product. In a first aspect, an embodiment of the present application provides a data processing method, including performing security check on a target control instruction of a target robot, where the security check refers to checking whether the target robot is safe if the target robot is controlled based on the target control instruction, determining a movable structure of the target robot related to the target control instruction and a cross-structure cooperative constraint condition corresponding to the movable structure if the target control instruction passes the security check, and adjusting the target control instruction through a soft constraint policy if the target control instruction does not satisfy the cross-structure cooperative constraint condition. With reference to the first aspect, in certain implementation manners of the first aspect, the target control instruction includes at least one of joint angle data, joint angular velocity data, and chassis velocity data, and the safety check is performed on the target control instruction of the target robot, including at least one of checking whether the joint angle data falls within a first safety angle interval, checking whether a difference value of the joint angular velocity data at adjacent moments is smaller than a target safety angular velocity difference value, and checking whether the chassis velocity data is smaller than a target safety velocity. With reference to the first aspect, in some implementations of the first aspect, the method further includes processing the joint angle data with a soft saturation policy if the joint angle data exceeds the first safe angle interval, so as to control the joint angle data to attenuate smoothly within a target buffer of the first safe angle interval. With reference to the first aspect, in some implementations of the first aspect, the processing of the joint angle data by using a soft saturation strategy includes determining a first target buffer area located on a lower limit side and a second target buffer area located on an upper limit side in the first safety angle interval according to a boundary value and a preset buffer area width on both sides of the first safety angle interval, determining a lower limit value of the first target buffer area and an upper limit value of the second target buffer area, adjusting the joint angle data to be a sum result of the lower limit value and a first correction amount in the first target buffer area, wherein the first correction amount is used for representing a value for performing smooth transition adjustment on the joint angle data in the first target buffer area, and adjusting the joint angle data to be a difference result of the upper limit value and the second correction amount in the second target buffer area, wherein the second correction amount is used for representing a value for performing smooth transition adjustment on the joint angle data in the second target buffer area. With reference to the first aspect, in some implementations of the first aspect, the method further includes subtracting the lower limit value and the preset buffer width from the joint angle data to obtain a first difference value, determining a ratio of the first difference value to the sharpness control parameter as an input value of the soft saturation function to obtain a first transition value, adding the first transition value to the first constant, multiplying the preset buffer width and the first coefficient to obtain a first correction amount, subtracting the preset buffer width and the joint angle data from the upper limit value to obtain a second difference value, determining a ratio of the second difference value to the sharpness control parameter as an input value of the soft saturation function to obtain a second transition value, adding the second transition value to the second constant, multiplying the preset buffer width and the second coefficient to obtain a second correction amount. With reference to the first aspect, in certain implementations of