Humanoid robot control method, device, computer and program product

Abstract

The application relates to a humanoid robot control method and device, computer equipment, computer readable storage medium and computer program product. The method comprises: performing consistency calibration on a master control device and a humanoid robot; in the case that the consistency calibration is completed, collecting an operator's motion instruction through a sensor on the master control device, and sending the motion instruction to the humanoid robot; in the case that the humanoid robot executes the motion instruction, receiving end force data collected by a sensor of the humanoid robot; superimposing the end force data and initial force data of the master control device in a work coordinate system to obtain a resultant external force; and based on the resultant external force, torque feedback is provided to the operator. The method can achieve accurate control of the humanoid robot.

Description

Technical Field

[0001] This application relates to the field of robot control technology, and in particular to a humanoid robot control method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the continuous development of humanoid robot technology, remote-operated humanoid robots have become an important direction in fields such as industry, rescue, and medicine.

[0003] In related technologies, existing teleoperation mostly uses a handle to achieve end-effector control of a robot arm based on the end-effector posture. Simply achieving end-effector control cannot perform complex operations like an arm. Most existing remotely controlled humanoid robots lack the ability to perceive the force environment, making it difficult for operators to perceive the robot's contact state with the environment, resulting in insufficient precision operation and safety. Summary of the Invention

[0004] Therefore, it is necessary to provide a control method, device, computer equipment, computer-readable storage medium, and computer program product for humanoid robots that can accurately control the aforementioned technical problems.

[0005] In a first aspect, this application provides a control method for a humanoid robot, including:

[0006] Perform consistency calibration on the main control equipment and the humanoid robot;

[0007] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0008] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0009] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0010] Based on the resultant external force, torque feedback is provided to the operator.

[0011] In one embodiment, the consistency calibration of the main control device and the humanoid robot includes:

[0012] The main arm in the main control device and the slave arm in the humanoid robot are positioned in a preset initial configuration.

[0013] Adjust the attitude of the base coordinate system of the master arm and the slave arm so that the master arm and the slave arm are spatially aligned;

[0014] Based on the initial configuration and the spatial alignment of the main arm and the slave arm, a mapping relationship between the main arm and the slave arm is established.

[0015] In one embodiment, the step of superimposing the end force data with the initial force data of the main control device in the working coordinate system to obtain the resultant external force includes:

[0016] The vector sum of the end force data and the initial force data is taken as the resultant external force; the end force data is the humanoid robot, which is obtained by converting the initial end force data in the sensor coordinate system into the end force data in the working coordinate system according to the mapping relationship.

[0017] In one embodiment, providing torque feedback to the operator based on the resultant external force includes:

[0018] Based on the net external force, combined with the admittance control model or the current loop control model, a force feedback command is generated to provide torque feedback to the operator.

[0019] In one embodiment, the step of generating a force feedback command based on the resultant external force and in conjunction with an admittance control model to provide torque feedback to the operator includes:

[0020] The resultant external force is input into the admittance control model, and the target position compensation amount of the main control equipment is obtained by solving the model.

[0021] Based on the target position compensation amount, the position of the main arm in the main control device is adjusted.

[0022] In one embodiment, the step of generating a force feedback command based on the resultant external force and in conjunction with a current loop control model to provide torque feedback to the operator includes:

[0023] Based on the resultant external force and the Jacobian matrix, the joint torque of the main control device is calculated;

[0024] Dynamic compensation is performed on the main arm in the main control equipment, and the compensation torque is calculated;

[0025] The joint torque is superimposed with the compensation torque to obtain the total joint torque, and the total joint torque is converted into a motor current command for issuance.

[0026] Secondly, this application also provides a control device for a humanoid robot, comprising:

[0027] The calibration module is used to perform consistency calibration between the main control device and the humanoid robot.

[0028] The sending module is used to collect the operator's motion commands through the sensors on the main control device and send the motion commands to the humanoid robot after the consistency calibration is completed;

[0029] A receiving module is used to receive end-effector force data collected by the sensors of the humanoid robot when the humanoid robot executes the motion command;

[0030] The superposition module is used to superimpose the end force data with the initial force data of the main control device in the working coordinate system to obtain the resultant external force;

[0031] The feedback module is used to provide torque feedback to the operator based on the resultant external force.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0033] Perform consistency calibration on the main control equipment and the humanoid robot;

[0034] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0035] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0036] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0037] Based on the resultant external force, torque feedback is provided to the operator.

[0038] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0039] Perform consistency calibration on the main control equipment and the humanoid robot;

[0040] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0041] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0042] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0043] Based on the resultant external force, torque feedback is provided to the operator.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0045] Perform consistency calibration on the main control equipment and the humanoid robot;

[0046] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0047] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0048] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0049] Based on the resultant external force, torque feedback is provided to the operator.

[0050] The aforementioned control method, device, computer equipment, computer-readable storage medium, and computer program product for the humanoid robot first perform consistency calibration on the main control device and the humanoid robot. After the consistency calibration is completed, the motion commands from the operator are collected by sensors on the main control device and sent to the humanoid robot. While the humanoid robot executes the motion commands, the system receives end-effector force data collected by the robot's sensors. This end-effector force data is then superimposed with the initial force data of the main control device in the working coordinate system to obtain the resultant external force. Based on this resultant external force, torque feedback is provided to the operator. In this way, control of the humanoid robot is achieved through multi-degree-of-freedom joint torque feedback, resulting in more precise control of the humanoid robot. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is an application environment diagram of the control method for a humanoid robot in one embodiment;

[0053] Figure 2 This is a schematic diagram of the main control device in one embodiment;

[0054] Figure 3 This is a flowchart illustrating a control method for a humanoid robot in one embodiment;

[0055] Figure 4 This is a schematic diagram of the humanoid robot in one embodiment;

[0056] Figure 5 This is a structural block diagram of the control device for a humanoid robot in one embodiment;

[0057] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0060] The humanoid robot control method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the main control device 102 communicates with the server 104 via a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104, or it can be located in the cloud or on another network server.

[0061] The main control device 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0062] In the embodiments of this application, the main control device includes an image display unit and a motion control unit. Motion control is accomplished through a 7-axis robotic arm and a control handle, as shown in the specific structural diagram. Figure 2 As shown.

[0063] In one exemplary embodiment, such as Figure 3 As shown, a control method for a humanoid robot is provided, which can be applied to... Figure 1 Taking the main control device 102 as an example, the explanation includes the following steps 302 to 310. Wherein:

[0064] Step 302: Perform consistency calibration on the main control device and the humanoid robot.

[0065] For example, before controlling the humanoid robot, the states of the main control device and the humanoid robot are first calibrated to ensure that the main arm of the main control device and the slave arm of the humanoid robot have the same angle and initial configuration.

[0066] The main arm is a 7-axis robotic arm that controls the main equipment, while the slave arm is a 7-axis robotic arm for humanoid robots.

[0067] Among them, the humanoid robot is a multi-degree-of-freedom wheeled humanoid robot, and the specific structural diagram is as follows. Figure 4 As shown, the humanoid robot body includes a microphone array, a 2-axis head, a fisheye camera, a 7-axis robotic arm, a depth camera, a hand, a 5-axis body, a lidar, and a mobile chassis.

[0068] The main control equipment and humanoid robot also include multiple sensors mounted on the robotic arm, such as a six-dimensional force sensor.

[0069] In one embodiment, the images captured by the humanoid robot camera can be displayed through the image display unit in the main control device.

[0070] The image transmission uses the RTC real-time image transmission protocol, which enables multi-channel image transmission.

[0071] Step 304: After the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0072] Optionally, once the consistency calibration is complete, the operator's motion commands are collected by sensors on the main control device and sent to the humanoid robot.

[0073] Step 306: When the humanoid robot executes motion commands, receive the end-effector force data collected by the humanoid robot's sensors.

[0074] For example, the operator executes motion commands through the main arm, and the humanoid robot executes the same motion commands synchronously. The current angle of the main arm is mapped to the slave arm through WebSocket to achieve control. The humanoid robot's torso / head / chassis is controlled by the control handle, and the force data of the slave arm end collected by the sensors is transmitted to the main control device through UDP (communication protocol).

[0075] Step 308: Superimpose the end force data with the initial force data of the main control device in the working coordinate system to obtain the resultant external force.

[0076] Optionally, the force data at the end of the arm can be read via UDP and then transferred to the initial force data of the main arm in the working coordinate system to obtain the resultant external force.

[0077] Step 310: Based on the resultant external force, provide torque feedback to the operator.

[0078] For example, based on the obtained resultant external force and in conjunction with a preset feedback model, torque feedback is provided to the operator.

[0079] The preset feedback model includes an admittance control model and a current loop control model, or other models with feedback function. The operator can set these models according to the actual situation, and this application embodiment does not limit them.

[0080] In the aforementioned control method for the humanoid robot, consistency calibration is performed between the main control device and the humanoid robot. Once calibration is complete, the operator's motion commands are collected by sensors on the main control device and sent to the humanoid robot. As the humanoid robot executes the motion commands, the system receives end-effector force data collected by its sensors. This end-effector force data is then superimposed with the initial force data of the main control device in its working coordinate system to obtain the net external force. Based on this net external force, torque feedback is provided to the operator. Thus, by using multi-degree-of-freedom joint torque feedback, the humanoid robot is controlled more precisely.

[0081] In an exemplary embodiment, consistency calibration of the master control device and the humanoid robot includes: positioning the master arm in the master control device and the slave arm in the humanoid robot in a preset initial configuration; adjusting the attitude of the base coordinate system of the master arm and the slave arm so that the master arm and the slave arm are spatially aligned; and establishing a mapping relationship between the master arm and the slave arm based on the initial configuration and the premise that the master arm and the slave arm are spatially aligned.

[0082] In actual implementation, the master arm in the main control device and the slave arm in the humanoid robot are in a preset initial configuration; the attitude of the base coordinate system of the master arm and the slave arm is adjusted so that the master arm and the slave arm are aligned in space; based on the initial configuration and the master arm and the slave arm are aligned in space, a mapping relationship between the master arm and the slave arm is established.

[0083] In one embodiment, a six-dimensional force sensor on the slave arm is used to identify the load, which is similar to a gripper or the like. The center of mass and mass of the load, such as the gripper, are calibrated using the six-dimensional force sensor, and the influence caused by this part of the data is removed from the sensor data.

[0084] In the above embodiments, the base coordinate systems of the master arm and slave arm are aligned in space by calibration, and a consistent kinematic mapping relationship is established. This fundamentally ensures that the force / torque direction sensed by the six-dimensional force sensor at the end of the slave arm can be reproduced on the master arm without distortion or deviation.

[0085] In an exemplary embodiment, the end force data is superimposed with the initial force data of the main control device in the working coordinate system to obtain the resultant external force, including: taking the vector sum of the end force data and the initial force data as the resultant external force.

[0086] Among them, the end-effector force data is for the humanoid robot. According to the mapping relationship, the initial end-effector force data in the sensor coordinate system is converted into the end-effector force data in the working coordinate system.

[0087] In actual implementation, six-dimensional force sensors are installed at the end of both the main arm and the slave arm. The humanoid robot performs coordinate system transformation according to the mapping relationship, converting the initial end force data in the sensor coordinate system into the end force data in the working coordinate system. The end force data [fx,fy,fz,mx,my,mz] is added to the current initial force data [fx0,fy0,fz0,mx0,my0,mz0] in the working coordinate system to obtain the net external force [fx+fx0,fy+fy0,fz+fz0,mx+mx0,my+my0,mz+mz0].

[0088] In the above embodiments, by calculating the resultant external force, the operator's active applied force and the passive feedback force of the remote environment are physically integrated in real time, enhancing the operator's sense of immersion and realism.

[0089] In an exemplary embodiment, torque feedback to the operator is provided based on the net external force, including: generating a force feedback command based on the net external force, combined with an admittance control model or a current loop control model, and providing torque feedback to the operator.

[0090] In practice, based on the net external force and combined with the admittance control model or current loop control model, force feedback commands are generated to provide torque feedback to the operator.

[0091] In the above embodiments, torque feedback enables the operator to go from "only seeing" to "being able to touch," gaining a force perception dimension of the remote environment. The operator can directly perceive the contact state between the robot and the environment, the hardness of objects, the texture of surfaces, the resistance of assembly, and the force change trend during operation, making the operation of the humanoid robot more precise.

[0092] In an exemplary embodiment, based on the resultant external force and combined with the admittance control model, a force feedback command is generated to provide torque feedback to the operator, including: inputting the resultant external force into the admittance control model to solve for the target position compensation amount of the main control equipment; and adjusting the position of the main arm in the main control equipment based on the target position compensation amount.

[0093] In actual implementation, the admittance control model is specifically as shown in formula (1). The dynamic relationship between external force and position is obtained through the admittance control model. Similar to a spring, the net external force fe is transmitted, and the position is adjusted to allow the main arm to output the net external force. The net external force is a force applied by a person dragging the main arm, part of which comes from the force data of the slave arm.

[0094]

[0095] Where M is the inertia parameter of the admittance control model, B is the damping parameter of the admittance control model, and K is the stiffness parameter of the admittance control model. This refers to the target position compensation amount that the main arm needs to adjust.

[0096] In the above embodiments, torque feedback is achieved through admittance control model, which realizes stable and smooth feedback, improves the naturalness and comfort of touch, and avoids the discomfort and device vibration caused by harsh feedback.

[0097] In an exemplary embodiment, based on the resultant external force and combined with the current loop control model, a force feedback command is generated to provide torque feedback to the operator, including: calculating the joint torque of the main control equipment based on the resultant external force and the Jacobian matrix; performing dynamic compensation on the main arm in the main control equipment and calculating the compensation torque; superimposing the joint torque and the compensation torque to obtain the total joint torque, and converting the total joint torque into a motor current command for issuance.

[0098] In actual implementation, the six-dimensional force sensor data [fx,fy,fz,mx,my,mz] of the working coordinate system of the arm is read, and the Jacobi matrix Jaco_work of the main arm in the working coordinate system is determined according to the angle of each joint of the main arm. According to formulas (2)-(5), the calculation formula of joint torque is derived as shown in formula (6).

[0099] Equation (2) is derived from the equation that work done in Cartesian space equals work done in joint space:

[0100]

[0101] The following are the basic kinematic equations based on linear differential mapping, and the specific formula is shown in (3):

[0102]

[0103] Substituting the above kinematic equations into the work equation, we obtain the following formula (4):

[0104]

[0105] The formula for mapping the end force to the joint torque can then be obtained as shown in formula (5):

[0106]

[0107] Furthermore, the formula for calculating the joint torque is shown in formula (6).

[0108]

[0109] in, The velocity in Cartesian space, For joint torque, This refers to the joint velocity.

[0110] Based on the current loop mode, the joint is required to work in the current servo mode. The main arm must also have the function of being dragged and remotely controlled by hand, just like the admittance model control mode mentioned above. Therefore, dynamic compensation of the robotic arm body is required.

[0111] The acceleration, velocity and position of the robotic arm joints are read in each control cycle and substituted into the dynamic model to obtain the compensation torque of the dynamic model. The specific calculation formula is shown in formula (7). The joint torque and the compensation torque are superimposed to obtain the total joint torque. The calculation formula is shown in formula (8).

[0112]

[0113]

[0114] Where M is the inertia matrix of the robotic arm, C is the Coriolis force matrix of the robotic arm, and G is the gravity matrix of the robotic arm. These three matrices are derived from the dynamic parameters of the robotic arm and represent the physical and kinematic characteristics of the robotic arm itself. The acceleration, velocity, and position of the robotic arm joints are measured separately.

[0115] Divide the total joint torque by the motor torque coefficient to obtain the motor output current, and then send the motor output current down.

[0116] In the above embodiments, torque feedback is achieved through a current loop control model, which is equivalent to compensating for the torque generated by the physical characteristics of the robotic arm itself, ensuring that the operator can easily drag the robotic arm.

[0117] To illustrate the control method of the humanoid robot in this application in detail, an embodiment is described below. For example, this application describes the control method of the humanoid robot in a specific scenario.

[0118] First, before controlling the humanoid robot, the states of the main control device and the humanoid robot are calibrated to ensure that the main arm of the main control device and the slave arm of the humanoid robot have the same angle and initial configuration.

[0119] Once the consistency calibration is complete, the operator's motion commands are collected by sensors on the main control device and sent to the humanoid robot.

[0120] The operator executes motion commands through the main arm, and the humanoid robot executes the same motion commands synchronously. The current angle of the main arm is mapped to the slave arm via WebSocket to achieve control. The humanoid robot's torso, head, chassis, etc. are controlled by the control handle, and the force data of the slave arm end collected by the sensors is transmitted to the main control device via UDP (communication protocol).

[0121] The force data at the end of the slave arm is read via UDP and compared with the initial force data of the master arm in the working coordinate system to obtain the resultant external force. Based on the obtained resultant external force and combined with the preset feedback model, torque feedback is provided to the operator.

[0122] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0123] Based on the same inventive concept, this application also provides a control device for a humanoid robot to implement the control method for the humanoid robot described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the humanoid robot control device provided below can be found in the limitations of the humanoid robot control method described above, and will not be repeated here.

[0124] In one exemplary embodiment, such as Figure 5 As shown, a control device for a humanoid robot is provided, comprising: a calibration module 501, a transmitting module 502, a receiving module 503, a superimposing module 504, and a feedback module 505, wherein:

[0125] The calibration module is used to perform consistency calibration between the main control device and the humanoid robot.

[0126] The sending module is used to collect the operator's motion commands through sensors on the main control device and send the motion commands to the humanoid robot after the consistency calibration is completed.

[0127] The receiving module is used to receive the end-effector force data collected by the humanoid robot's sensors when the humanoid robot executes the motion command.

[0128] The superposition module is used to superimpose the end force data with the initial force data of the main control device in the working coordinate system to obtain the resultant external force.

[0129] The feedback module is used to provide torque feedback to the operator based on the resultant external force.

[0130] In one exemplary embodiment, the calibration module is further configured to:

[0131] The main arm in the main control device and the slave arm in the humanoid robot are positioned in a preset initial configuration.

[0132] Adjust the attitude of the base coordinate system of the master arm and the slave arm so that the master arm and the slave arm are spatially aligned;

[0133] Based on the initial configuration and the spatial alignment of the main arm and the slave arm, a mapping relationship between the main arm and the slave arm is established.

[0134] In one exemplary embodiment, the above-described overlay module is further configured to:

[0135] The vector sum of the end force data and the initial force data is taken as the resultant external force; the end force data is the humanoid robot, which is obtained by converting the initial end force data in the sensor coordinate system into the end force data in the working coordinate system according to the mapping relationship.

[0136] In one exemplary embodiment, the feedback module described above is further configured to:

[0137] Based on the net external force, combined with the admittance control model or the current loop control model, a force feedback command is generated to provide torque feedback to the operator.

[0138] In one exemplary embodiment, the feedback module described above is further configured to:

[0139] The resultant external force is input into the admittance control model, and the target position compensation amount of the main control equipment is obtained by solving the model.

[0140] Based on the target position compensation amount, the position of the main arm in the main control device is adjusted.

[0141] In one exemplary embodiment, the feedback module described above is further configured to:

[0142] Based on the resultant external force and the Jacobian matrix, the joint torque of the main control device is calculated;

[0143] Dynamic compensation is performed on the main arm in the main control equipment, and the compensation torque is calculated;

[0144] The joint torque is superimposed with the compensation torque to obtain the total joint torque, and the total joint torque is converted into a motor current command for issuance.

[0145] The various modules in the control device of the aforementioned humanoid robot can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0146] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a control method for a humanoid robot.

[0147] The display unit of this computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of this computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad set on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0148] Those skilled in the art will understand that Figure 6 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.

[0149] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0150] Perform consistency calibration on the main control equipment and the humanoid robot;

[0151] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0152] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0153] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0154] Based on the resultant external force, torque feedback is provided to the operator.

[0155] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0156] Perform consistency calibration on the main control equipment and the humanoid robot;

[0157] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0158] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0159] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0160] Based on the resultant external force, torque feedback is provided to the operator.

[0161] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0162] Perform consistency calibration on the main control equipment and the humanoid robot;

[0163] Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot.

[0164] When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors.

[0165] The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system;

[0166] Based on the resultant external force, torque feedback is provided to the operator.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0168] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0169] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0170] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A control method for a humanoid robot, characterized in that, Applied to a main control device, the method includes: The consistency calibration of the main control device and the humanoid robot includes: positioning the main arm in the main control device and the slave arm in the humanoid robot in a preset initial configuration; adjusting the base coordinate system orientation of the main arm and the slave arm to align them spatially; establishing a kinematic mapping relationship between the main arm and the slave arm based on the initial configuration and the spatial alignment of the main arm and the slave arm, and performing load identification on the six-dimensional force sensor of the slave arm to reproduce the force and torque directions sensed by the six-dimensional force sensor at the end of the slave arm onto the main arm; and positioning the main arm in the main control device and the slave arm in the humanoid robot in a preset initial configuration. Once the consistency calibration is completed, the operator's motion commands are collected by the sensors on the main control device and sent to the humanoid robot to remotely control the humanoid robot. When the humanoid robot executes the motion command, the system receives end-effector force data collected by the humanoid robot's sensors. The resultant external force is obtained by superimposing the end force data with the initial force data of the main control device in the working coordinate system; Based on the net external force, combined with the admittance control model or the current loop control model, a force feedback command is generated to provide torque feedback to the operator.

2. The method according to claim 1, characterized in that, The step of superimposing the end force data with the initial force data of the main control device in the working coordinate system to obtain the resultant external force includes: The vector sum of the end force data and the initial force data is taken as the resultant external force; the end force data is the humanoid robot, which is obtained by converting the initial end force data in the sensor coordinate system into the end force data in the working coordinate system according to the mapping relationship.

3. The method according to claim 1, characterized in that, The process of generating force feedback commands based on the resultant external force and in conjunction with the admittance control model to provide torque feedback to the operator includes: The resultant external force is input into the admittance control model, and the target position compensation amount of the main control equipment is obtained by solving the model. Based on the target position compensation amount, the position of the main arm in the main control device is adjusted.

4. The method according to claim 1, characterized in that, Based on the resultant external force and combined with the current loop control model, a force feedback command is generated to provide torque feedback to the operator, including: Based on the resultant external force and the Jacobian matrix, the joint torque of the main control device is calculated; Dynamic compensation is performed on the main arm in the main control equipment, and the compensation torque is calculated; The joint torque is superimposed with the compensation torque to obtain the total joint torque, and the total joint torque is converted into a motor current command for issuance.

5. A control device for a humanoid robot, characterized in that, The device includes: The calibration module is used to perform consistency calibration between the main control device and the humanoid robot. The calibration module is further configured to: position the main arm in the main control device and the slave arm in the humanoid robot in a preset initial configuration; adjust the attitude of the base coordinate system of the main arm and the slave arm so that the main arm and the slave arm are spatially aligned; based on the initial configuration and the spatial alignment of the main arm and the slave arm, establish the kinematic mapping relationship between the main arm and the slave arm, and perform load identification on the six-dimensional force sensor of the slave arm so that the force and torque directions sensed by the six-dimensional force sensor at the end of the slave arm are reproduced on the main arm; The sending module is used to collect the operator's motion commands through the sensors on the main control device after the consistency calibration is completed, and send the motion commands to the humanoid robot to remotely control the humanoid robot. A receiving module is used to receive end-effector force data collected by the sensors of the humanoid robot when the humanoid robot executes the motion command; The superposition module is used to superimpose the end force data with the initial force data of the main control device in the working coordinate system to obtain the resultant external force; The feedback module is used to generate force feedback commands based on the resultant external force and in combination with the admittance control model or the current loop control model, and to provide torque feedback to the operator.

6. The apparatus according to claim 5, characterized in that, The superposition module is further configured to: take the vector sum of the end force data and the initial force data as the resultant external force; the end force data is the humanoid robot, and is obtained by converting the initial end force data in the sensor coordinate system into the end force data in the working coordinate system according to the mapping relationship.

7. The apparatus according to claim 5, characterized in that, The feedback module is also used to: input the resultant external force into the admittance control model to solve for the target position compensation amount of the main control equipment; and adjust the position of the main arm in the main control equipment based on the target position compensation amount.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images