Method and device for controlling a simulated robot arm, and storage medium

Abstract

This application provides a control method, device, storage medium, and computer program product for a simulated robot's dual arms. It includes: receiving initial control commands for the robot's dual arms in a simulated environment; acquiring in real-time motion speed signals from the robot's end effector and contact pressure signals from the gripping mechanism; determining the current operation stage based on real-time signal changes, where the operation stage includes a movement stage, a grasping stage, and a placement stage; calling a corresponding preset weight parameter set according to the operation stage to adjust the response sensitivity to the initial control commands; wherein the preset weight parameter set includes at least one position sensitivity parameter and one rotation sensitivity parameter, and different values ​​for the position sensitivity parameter and rotation sensitivity parameter are configured for the movement stage, grasping stage, and placement stage respectively; and processing the initial control commands based on the position sensitivity parameter and rotation sensitivity parameter to generate joint or end effector motion commands for the robot.

Description

Technical Field

[0001] This application relates to the field of robot simulation control, specifically to a control method, device, storage medium, and computer program product for a simulated robot's dual arms. Background Technology

[0002] With the increasing application of robotics technology in industries such as manufacturing, healthcare, and services, there are growing demands for precise, efficient, and intuitive human-computer interaction methods for robot operation. As a key platform for robot research and development and training, the ease of control of simulation environments directly impacts the user experience and training effectiveness.

[0003] However, current interaction methods, which commonly rely on mice, gamepads, or force feedback devices, are often complex to operate, have high learning curves, and are difficult to intuitively map to real-world bi-arm collaborative tasks, such as grasping and assembly, which require precise coordination. Traditional keyboard control, while low-cost, typically only supports single-arm or simple movements, failing to meet the needs of multi-degree-of-freedom, multi-target coordinated operations, resulting in limited efficiency when performing complex tasks in simulation environments. On the other hand, voice or gesture control is susceptible to environmental interference and limitations in recognition accuracy, leading to insufficient stability. Immersive control methods such as VR / AR are complex and costly to implement, and system construction and logic mapping still face challenges, hindering widespread adoption. These methods generally lack the ability to adaptively adjust based on real-time states when dealing with dynamically changing operational scenarios, increasing the operational burden, making it difficult to guarantee bi-arm coordination and operational accuracy, and restricting the effective transfer of simulation training to real-world scenarios and further improvement in human-computer interaction efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a control method, device, storage medium, and computer program product for a simulated robot's dual arms. This aims to address the problems of existing dual-arm robot control methods in simulated environments, such as complex operation, high learning curve, poor arm coordination, lack of adaptive adjustment capabilities to real-time operating scenarios, and the difficulty in popularizing costly or unstable alternatives.

[0005] To achieve the above objectives, the first aspect of this application provides a control method for a dual-arm simulated robot, the method comprising: Receive initial control commands for the robot's dual arms in a simulated environment, triggered by an external input device; Real-time acquisition of motion speed signals from the robot's end effector and contact pressure signals from the gripping mechanism; Based on the real-time changes in motion speed and contact pressure signals, the current operation stage of the task is determined. The operation stages include the movement stage, the grasping stage, and the placement stage. The corresponding preset weight parameter set is invoked according to the current operation stage of the task to adjust the response sensitivity to the initial control command; wherein, the preset weight parameter set includes at least one position sensitivity parameter and one rotation sensitivity parameter, and different values ​​of position sensitivity parameter and rotation sensitivity parameter are configured for the movement stage, grasping stage and placement stage respectively. Based on position sensitivity parameters and rotation sensitivity parameters, the initial control commands are processed to generate joint or end effector motion commands for the robot.

[0006] In this embodiment of the application, determining the current operation stage of the task based on the real-time changes of the motion speed signal and the contact pressure signal includes: within a first preset time period, if the contact pressure signal values ​​are all lower than a first pressure threshold and the average value of the statistically obtained motion speed signal is higher than a first speed threshold, it is determined that the current stage is the movement stage.

[0007] In this embodiment of the application, determining the current operation stage of the task based on the real-time changes of the motion speed signal and the contact pressure signal further includes: within a second preset time period, if the contact pressure signal value changes from being continuously lower than the first pressure threshold to being continuously higher than the threshold, and the corresponding average motion speed signal value is lower than the second speed threshold, it is determined that the current stage is the grasping stage.

[0008] In this embodiment of the application, determining the current operation stage of the task based on the real-time changes of the motion speed signal and the contact pressure signal further includes: within a third preset time period, if the contact pressure signal value changes from continuously being higher than the first pressure threshold to continuously being lower than the threshold, it is determined that the task is currently in the placement stage.

[0009] In this embodiment, during the movement phase, the position sensitivity parameter is configured to be greater than the rotation sensitivity parameter; during the grasping phase, the rotation sensitivity parameter is configured to be less than the value configured during the movement phase; and during the placement phase, the absolute value of the difference between the position sensitivity parameter and the rotation sensitivity parameter is less than a preset equilibrium threshold.

[0010] In this embodiment, the initial control command is processed based on the position sensitivity parameter and the rotation sensitivity parameter, including: fusing the position increment component in the initial control command with the position sensitivity parameter to obtain a position command component; fusing the rotation increment component in the initial control command with the rotation sensitivity parameter to obtain a rotation command component; and generating joint or end effector motion commands for directly driving the robot based on the position command component and the rotation command component.

[0011] In this embodiment of the application, the control method further includes: after driving the robot to perform an action based on joint or end effector motion commands, returning to the execution of real-time acquisition of the motion speed signal of the robot end effector and the contact pressure signal of the gripping mechanism; updating the determination of the current operation stage of the task based on the newly acquired motion speed signal and contact pressure signal, and updating the preset weight parameter set called accordingly for processing the next received initial control command.

[0012] A second aspect of this application provides a control device for a simulated robot's dual arms, comprising: a memory configured to store instructions; a processor configured to retrieve instructions from the memory and, when executing the instructions, to implement any of the aforementioned control methods for the simulated robot's dual arms.

[0013] A third aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the control method for the simulated robot arms described above.

[0014] The fourth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the control method for the simulated robot's dual arms as described above.

[0015] This application proposes a control method for a simulated robot's dual arms. By receiving external input commands and simultaneously acquiring the motion speed of the robot's end effector and the contact pressure signals of the gripping mechanism, the current task stage is determined in real time. Based on different stages, a differentiated set of preset weight parameters is dynamically invoked to adaptively adjust the response sensitivity of the control commands, thereby achieving a seamless and intelligent switch from coarse movement to fine manipulation. This method fully leverages the ease of use and widespread availability of general-purpose input devices such as keyboards, significantly reducing operational complexity and learning costs, and effectively improving the intuitiveness, accuracy, and efficiency of dual-arm collaborative control. It provides a low-cost, high-efficiency, and easily scalable solution for robot operation training in a simulated environment.

[0016] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 A schematic flowchart illustrating a control method for a simulated robot's dual arms according to an embodiment of this application is shown. Figure 2A schematic flowchart illustrating a control method for a simulated robot dual-arm according to another embodiment of this application is shown. Figure 3 This illustration schematically depicts dynamic weight adjustment and instruction generation according to an embodiment of this application; Figure 4 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] Figure 1 The illustration schematically shows a flowchart of a control method for a simulated robot's dual arms according to an embodiment of this application. Figure 1 As shown in one embodiment of this application, a control method for a simulated robot's dual arms is provided, comprising the following steps: Step 101: Receive initial control commands for the robot's two arms in the simulation environment, triggered by an external input device.

[0020] Teleoperation is a remote control technology that allows operators to control a remote robot to complete specific tasks via a device. A simulation environment is a computer-simulated real-world scenario used to test and verify robot behavior. In the simulation environment, the user issues control commands via external input devices such as a keyboard. These commands are first captured by the system's built-in teleoperation agent. The agent parses the command content and determines its intent, such as specifying the left / right arm, instructing a joint movement, or controlling the end effector to translate or rotate in a specific direction. At this stage, the command is the unadjusted, raw command, called the initial control command. The system maintains real-time command reception to ensure immediate operational response.

[0021] Step 102: Real-time acquisition of the motion speed signal of the robot end effector and the contact pressure signal of the clamping mechanism.

[0022] Based on Isaac Lab's Python environment, a core control algorithm framework was built. Within this framework, a dynamic weight management module was introduced and integrated. This module receives and processes real-time data from the robot arm's velocity sensor and pressure sensor data from the gripper / finger.

[0023] Step 103: Based on the real-time changes in the motion speed signal and contact pressure signal, determine the current operation stage of the task. The operation stages include the movement stage, the grasping stage, and the placement stage.

[0024] In one embodiment, determining the current operational stage of the task based on real-time changes in motion speed and contact pressure signals includes: within a first preset time period, if all contact pressure signal values ​​are below a first pressure threshold and the average value of the statistically obtained motion speed signal is above a first speed threshold, the system determines that it is currently in the movement stage. The system sets a first preset time period. Within this time range, the system continuously compares the contact pressure signal of the gripping mechanism with a preset pressure trigger lower limit, i.e., the first pressure threshold. If, within this time window, the pressure signal values ​​of all sampling points are below the pressure threshold, it indicates that the gripping mechanism has not made effective contact or is only in a state of slight contact, and no grasping or placing force action is performed. Simultaneously, the system calculates the average value of the end effector's motion speed signal within the same time window. If this average speed is above a preset movement speed determination threshold, i.e., the first speed threshold, it indicates that the robot is in a significant positional movement process. Combining the two conditions of no effective contact and significant movement, the system determines the current task stage as the movement stage. In this stage, the control strategy will focus on maintaining the smoothness and efficiency of the coordinated movement of both arms.

[0025] In one embodiment, determining the current operational stage of the task based on the real-time changes in the motion speed signal and the contact pressure signal further includes: within a second preset time period, if the contact pressure signal value changes from being consistently below a first pressure threshold to consistently above the threshold, and the corresponding average motion speed signal is below a second speed threshold, the system determines that it is currently in the grasping stage. The system enters the second preset time period. Within this time range, the system focuses on the changing trend of the contact pressure signal and the average level of the motion speed. The system continuously monitors the pressure value. When the pressure signal changes from being consistently below the first pressure threshold to being consistently and stably above the threshold, it indicates that the gripping mechanism has established effective contact with the manipulated object and has begun to apply force. The system calculates the average motion speed of the end effector within the corresponding time window and compares it with a lower speed judgment threshold, namely the second speed threshold. If the average speed is below this threshold, it indicates that the robot end effector has basically positioned itself at the target location, and the movement has significantly slowed down or tended to stop. At this time, the main operational intention shifts to stably gripping the object. When the system simultaneously detects that the pressure has stably exceeded the threshold from low to high and the movement speed has dropped to a lower level, it comprehensively determines that the current task has transitioned from the movement stage to the grasping stage.

[0026] In one embodiment, determining the current operational stage of the task based on real-time changes in the motion speed signal and contact pressure signal further includes: within a third preset time period, if the contact pressure signal value changes from consistently above a first pressure threshold to consistently below that threshold, the system determines that it is currently in the placement stage. After the grasping action is completed, the system enters the third preset time period. Within this time range, the system continuously monitors the contact pressure signal of the gripping mechanism. The system detects that the pressure signal changes from being consistently above the first pressure threshold to consistently below that threshold. This change indicates that the gripped object has left the gripping mechanism, completing the transition from the gripping state to the release state. When the pressure signal is consistently and stably below the first pressure threshold for the third preset time period, the system determines that the current task has entered the placement stage. This determination indicates that the object has been successfully placed, and the robot can prepare to perform subsequent removal or resetting actions.

[0027] In one embodiment, the system uses 500 milliseconds as the time range for each judgment stage, with the first, second, and third preset times all set to 0.5 seconds. Within these three consecutive time ranges, the system samples the contact pressure signal of the gripping mechanism and the motion speed signal of the end effector in real time. Movement Stage Judgment: In the first 500 milliseconds, the system samples the pressure value every 100 milliseconds, collecting a total of 5 pressure data points. If all 5 pressure values ​​are below 10N, and the calculated average motion speed exceeds 0.1 m / s, the system determines that it is currently in the movement stage. At this time, the robot has not made effective contact with the object and is in a rapid positioning and movement state. Grasping Stage Judgment: In the second 500 millisecond window, the system continuously monitors pressure changes. When the system detects that the pressure value changes from a state continuously below 10N to a state continuously above 10N, and the average motion speed within these 500 milliseconds is below 0.02 m / s, the system determines that it is currently in the grasping stage. This indicates that the robot has completed positioning and begun to stably grip the object. Placement Phase Determination: Within the third 500-millisecond window, when the pressure value changes from consistently above 10N to consistently below 10N, the system is determined to be in the placement phase. This indicates that the clamping mechanism has completely released the object, completing the placement operation. Through time range settings and threshold judgment mechanisms, the system can accurately switch between different operation phases, providing precise timing basis for subsequent dynamic weight adjustments.

[0028] Step 104: According to the current operation stage of the task, call the corresponding preset weight parameter set to adjust the response sensitivity to the initial control command; wherein, the preset weight parameter set includes at least one position sensitivity parameter and one rotation sensitivity parameter, and the position sensitivity parameter and rotation sensitivity parameter are configured with different values ​​for the movement stage, the grasping stage and the placement stage respectively.

[0029] The system maintains a pre-configured weight parameter database. This database stores a set of preset weight parameters for each operation stage. Each parameter set contains at least two core parameters: position sensitivity parameter (pos_sensitivity) and rotation sensitivity parameter (rot_sensitivity). After step 103 determines the current operation stage, this step retrieves the parameter set corresponding to that stage from the database.

[0030] In one embodiment, during the movement phase, the position sensitivity parameter is configured to be greater than the rotation sensitivity parameter; during the grasping phase, the rotation sensitivity parameter is configured to be less than the value configured during the movement phase; and during the placement phase, the absolute value of the difference between the position sensitivity parameter and the rotation sensitivity parameter is less than a preset equilibrium threshold.

[0031] In one embodiment, the weight parameter set settings can be as shown in Table 1 below: Table 1

[0032] In the movement phase, the position sensitivity parameter is set to 0.5 and the rotation sensitivity parameter to 0.2 to provide stable movement, avoid jitter caused by oversensitivity, and reduce unnecessary posture adjustments by minimizing rotation weight. In the grasping phase, the position sensitivity parameter is set to 0.2 and the rotation sensitivity parameter to 0.1 to precisely adjust position and posture, reduce rotation weight, avoid impact on the object, and ensure the stability and accuracy of gripping. In the placement phase, the position sensitivity parameter is set to 0.4 and the rotation sensitivity parameter to 0.4 to increase the sensitivity weight for position adjustment and necessary posture adjustments, ensuring that the object can be placed quickly and smoothly at the target location.

[0033] Step 105: Based on the position sensitivity parameters and rotation sensitivity parameters, process the initial control commands to generate joint or end effector motion commands for the robot.

[0034] In one embodiment, the initial control command is processed based on the position sensitivity parameter and the rotation sensitivity parameter, including: fusing the position increment component in the initial control command with the position sensitivity parameter to obtain a position command component; fusing the rotation increment component in the initial control command with the rotation sensitivity parameter to obtain a rotation command component; and generating joint or end effector motion commands for directly driving the robot based on the position command component and the rotation command component.

[0035] In one embodiment, keyboard commands are converted into incremental pose control commands for the robot, and the specific processing is as follows: Each valid keyboard key press generates an incremental pose command. This command consists of three-axis position increments and three-axis rotation increments, and can be expressed as:

[0036] Where Δx, Δy, and Δz represent the positional changes of the robot's end effector in the X, Y, and Z directions, respectively; Δrx, Δry, and Δrz represent the rotational changes around the X, Y, and Z axes, respectively. Different keys on the keyboard are mapped to incremental inputs in different directions, and their magnitudes are controlled by the weighting parameters corresponding to the current stage. Position control section: W / S key: controls the X direction; each press increases or decreases Δx by an amount related to the position sensitivity parameter pos_sensitivity, i.e. A / D key: Controls the Y direction, corresponding to... Q / E keys: Control the Z direction, corresponding to... Rotation control section: Z / X keys: control rotation around the X-axis. T / G key: Controls rotation about the Y-axis. C / V key: Controls rotation about the Z-axis. Of the parameters mentioned above, `pos_sensitivity` represents the position weight parameter, measured in meters per press, used to control the magnitude of the position change corresponding to each button press. `rot_sensitivity` represents the rotation weight parameter, measured in radians per press, used to control the magnitude of the rotation change corresponding to each button press. The values ​​of these two parameters are dynamically set by the dynamic weight management module based on the current operation stage (movement, grasping, placement). Since the rotation increments Δrx, Δry, and Δrz are given in Euler angles, they need to be converted into a rotation vector form that can be directly used by the robot controller before generating the final control command.

[0037] In one embodiment, the `spatial.transform.Rotation` module from the Python scientific computing library `scipy` is used to convert the rotation represented by Euler angles into a corresponding rotation vector. This rotation vector describes the motion of rotating around a fixed axis by a certain angle. After the conversion, the final generated control command is a 6-dimensional vector: [Δx, Δy, Δz, rx, ry, rz]. Here, Δx, Δy, and Δz are the position increment components, typically in meters; rx, ry, and rz are the components of the rotation vector along the three coordinate axes, describing the pose change of the robot's end effector, in radians. This vector, after dynamic weighting, is the incremental pose command, which can be directly sent to the robot joint controller or end effector controller to drive the robot to complete the corresponding action.

[0038] In one embodiment, the control method further includes: after driving the robot to perform an action based on joint or end-effector motion commands, returning to the execution of real-time acquisition of the motion speed signal of the robot's end effector and the contact pressure signal of the gripping mechanism; updating the determination of the current task's operational stage based on the newly acquired motion speed signal and contact pressure signal, and accordingly updating the preset weight parameter set to be invoked for processing the next received initial control command. The above control method does not end the process after executing the current command and driving the robot to move. The system continuously acquires updated end-effector motion speed signals and gripping mechanism contact pressure signals from the robot's sensors. Subsequently, the dynamic weight management module will re-determine the robot's current working stage (movement, gripping, or placement) based on this latest sensor data, and accordingly update the position sensitivity parameters and rotation sensitivity parameters to be used in the next round of control commands. Thus, when the operator presses a keyboard key again, the system uses the updated weight parameters to weight the input command, thereby realizing a closed-loop teleoperation process that dynamically adjusts the control response according to the robot's real-time state.

[0039] Figure 1 This is a flowchart illustrating a control method for the dual arms of a simulated robot in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0040] In one embodiment, Figure 2This diagram illustrates a flowchart of a control method for a simulated robot's dual arms according to another embodiment of this application. Upon system startup, using the Python environment and infrastructure provided by Isaac Lab, a class specifically responsible for dual-arm keyboard control mapping is created. At this stage, not only is the control mapping logic initialized, but a dynamic weight management module is also integrated and initialized. This module is responsible for determining in real-time whether the current operation is in one of three different stages and scenarios—movement, grasping, or placement—based on the robot arm's movement speed and pressure information obtained from contact sensors mounted on the grippers or fingers, and setting initial control weight parameters for the left and right arms. Then, a teleoperation proxy class is created to receive input from the keyboard and convert it into robot control commands. This proxy class needs to be compatible with the dual-arm keyboard control logic. After receiving keyboard input, the teleoperation proxy class calls the action command preprocessing method. This method not only performs basic command parsing but also actively calls the dynamic weight management module. The module determines the current task stage (movement, grasping, placement) based on the current robot arm speed and pressure sensor feedback from the grippers / fingers. Based on the judgment result of the dynamic weight management module, the priority and sensitivity of the left and right arm control commands are dynamically adjusted. Furthermore, in the higher-level task logic or generalized control class, the system can receive and correctly process the dual-arm control commands after dynamic weight adjustment, maintaining the compatibility and flexibility of the control logic. In the specific task implementation class, a corresponding arm motion controller and gripper / finger controller are explicitly configured for the right arm. The arm controller and gripper controller will receive the final control commands after preprocessing and dynamic weight adjustment, driving the robot in the simulation environment to perform actions. After completing the above configuration, the system enters the running state. The user operates via keyboard, and the control signals pass through proxy connections, command preprocessing, dynamic weight adjustment, and other stages, ultimately driving the robot's dual arms in the simulation environment to perform tasks. The dynamic weight management module continuously monitors sensor information and motion status throughout the entire operation, optimizing the control effect in real time.

[0041] In one embodiment, Figure 3This diagram illustrates the dynamic weight adjustment and instruction generation according to an embodiment of this application. After receiving keyboard input, the teleoperation agent class calls the action instruction preprocessing method. This method not only performs basic instruction parsing but also actively calls the dynamic weight management module. The module determines the current task stage (movement, grasping, placement) based on the current robot arm speed and pressure sensor feedback from the gripper / finger. Based on the dynamic weight management module's determination, the priority and position and attitude sensitivity of the left and right arm control instructions are dynamically adjusted. For example, during the movement stage, emphasis is placed on maintaining the stability of coordinated movement of both arms, reducing the sensitivity of fine operations of a single arm, and increasing the weight of movement instructions. During the grasping stage, when the pressure sensor begins to contact the object and reaches a preset threshold, it is determined to be a grasping stage. The button sensitivity of the current operating arm is reduced to allow for precise gripping adjustments, and the weight of disruptive actions of the non-grasping arm may be reduced. During the placement stage, when the pressure sensor pressure decreases or reaches the placement target area, it is determined to be a placement stage. The precise control weight of the placement arm needs to be increased, in conjunction with stability control. The adjusted weights will be applied to subsequent instruction generation logic. The original motion amplitude is directly amplified or reduced using the adjusted weights to generate the final dual-arm control commands, which are then sent to the robot for execution.

[0042] In one embodiment, a control device for a simulated robotic dual arm (not shown in the figure) is provided, comprising: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement any of the aforementioned control methods for the robotic arms.

[0043] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and the control method for the simulated robot's dual arms can be implemented by adjusting the kernel parameters.

[0044] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0045] This application provides a storage medium storing a program that, when executed by a processor, implements the aforementioned control method for the dual arms of a simulated robot.

[0046] This application provides a processor for running a program, wherein the program executes the above-described control method for the dual arms of a simulated robot.

[0047] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The network interface A02 is used for communication with external terminals via a network connection. When executed by the processor A01, the computer program B02 implements a control method for simulating the dual arms of a robot.

[0048] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0049] This application provides a computer (electronic) device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements any of the above-mentioned control methods for the dual arms of a simulated robot.

[0050] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing control method steps for initializing the dual arms of a simulated robot.

[0051] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0053] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0054] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0055] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0056] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0057] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0058] It should also be noted that the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0059] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A control method for a simulated robot's dual arms, characterized in that, The control method includes: Receive initial control commands for the robot's dual arms in a simulated environment, triggered by an external input device; Real-time acquisition of motion speed signals from the robot's end effector and contact pressure signals from the gripping mechanism; Based on the real-time changes in the motion speed signal and the contact pressure signal, the current operation stage of the task is determined, including the movement stage, the grasping stage, and the placement stage. The corresponding preset weight parameter set is invoked according to the current operation stage of the task to adjust the response sensitivity to the initial control command; wherein the preset weight parameter set includes at least one position sensitivity parameter and one rotation sensitivity parameter, and different position sensitivity parameters and rotation sensitivity parameters are configured for the movement stage, the grasping stage and the placement stage respectively. Based on the position sensitivity parameters and rotation sensitivity parameters, the initial control command is processed to generate joint or end effector motion commands for the robot.

2. The method according to claim 1, characterized in that, The step of determining the current operational stage of the task based on the real-time changes in the motion speed signal and the contact pressure signal includes: If, within a first preset time period, the contact pressure signal values ​​are all below a first pressure threshold and the average value of the statistically obtained motion speed signal is above a first speed threshold, it is determined that the current movement phase is being performed.

3. The method according to claim 1, characterized in that, The step of determining the current operational stage of the task based on the real-time changes in the motion speed signal and the contact pressure signal further includes: Within a second preset time period, if the contact pressure signal value changes from being continuously below the first pressure threshold to being continuously above the threshold, and the average value of the corresponding motion speed signal is lower than the second speed threshold, it is determined that the current stage is the grasping stage.

4. The method according to claim 1, characterized in that, The step of determining the current operational stage of the task based on the real-time changes in the motion speed signal and the contact pressure signal further includes: If, within a third preset time period, the contact pressure signal value changes from being continuously higher than the first pressure threshold to being continuously lower than the threshold, it is determined that the current stage is the placement stage.

5. The method according to claim 1, characterized in that, During the movement phase, the position sensitivity parameter is configured to be greater than the rotation sensitivity parameter; During the grasping phase, the rotational sensitivity parameter is configured to be less than the value configured during the moving phase; During the placement phase, the absolute value of the difference between the position sensitivity parameter and the rotation sensitivity parameter is less than a preset equalization threshold.

6. The method according to claim 1, characterized in that, The processing of the initial control command based on the position sensitivity parameter and rotation sensitivity parameter includes: The position increment component in the initial control command is fused with the position sensitivity parameter to obtain the position command component; The rotation increment component in the initial control command is fused with the rotation sensitivity parameter to obtain the rotation command component; Based on the position command component and the rotation command component, joint or end effector motion commands for directly driving the robot are generated.

7. The method according to claim 1, characterized in that, The control method further includes: After the robot is driven to perform an action based on the joint or end effector motion command, the process returns to acquiring the motion speed signal of the robot end effector and the contact pressure signal of the gripping mechanism in real time. Based on the newly acquired motion speed signal and contact pressure signal, the determination of the current operation stage of the task is updated, and the preset weight parameter set is updated accordingly to process the next received initial control command.

8. A control device for a simulated robot's dual arms, characterized in that, include: The memory is configured to store instructions; The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the control method for the simulated robot's dual arms according to any one of claims 1 to 7.

9. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, the instruction causes the processor to be configured to perform the control method for the dual arms of a simulated robot according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the control method for the dual arms of the simulated robot according to any one of claims 1 to 7.

Images