Wrist force sensor calibration method, device and equipment of humanoid robot and medium

Abstract

The invention relates to the technical field of robots and the technical field of information, and discloses a wrist force sensor calibration method, device, equipment and medium of a humanoid robot, and the method comprises the following steps: reading an external force measured by a wrist force sensor in a sensor fixed coordinate system, and reading an external torque measured by the wrist force sensor in the sensor fixed coordinate system; generating a calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and selecting the calibrated external force as a real external force; generating a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and a second calibration model, and selecting the calibrated external torque as a real external torque; and when the tail end executor of the mechanical arm makes contact with the object, the target action is executed on the object according to the real external force and the real external torque. The acquisition efficiency of the real external force and the real external torque can be improved.

Description

Technical Field

[0001] The present invention relates to the fields of robot technology and information technology, and in particular to a method, device, equipment and medium for calibrating a wrist force sensor of a humanoid robot. Background Art

[0002] With the continuous advancement of robotics and automation systems, humanoid robots have been widely used in many fields such as industrial manufacturing, medical care, and home services. When performing delicate operations in complex and changing working environments, higher requirements are placed on the accuracy and reliability of the wrist force sensors of humanoid robots.

[0003] However, the traditional offline calibration method is usually a one-time calibration process under specific conditions. Although it can provide relatively accurate measurement values ​​in the early stage, it cannot cope with real-time changes. Therefore, the traditional offline calibration method lacks a calibration mechanism and it is difficult to obtain the real external force and real external torque of the wrist force sensor. Therefore, how to obtain the real external force and real external torque of the wrist force sensor during the operation of the robot is an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a wrist force sensor calibration method, device, computer equipment and storage medium for a humanoid robot, so as to solve the technical problem of how to obtain the real external force and real external torque of the wrist force sensor.

[0005] In a first aspect, a method for calibrating a wrist force sensor of a humanoid robot is provided, comprising: A wrist force sensor connected to the humanoid robot, wherein the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; When the humanoid robot is in operation, sensor data generated by the wrist force sensor is recorded; In the sensor data, an external force measured by the wrist force sensor in the sensor fixed coordinate system is read, and an external torque measured by the wrist force sensor in the sensor fixed coordinate system is read to obtain a calibration result corresponding to the wrist force sensor; Generate the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and select the calibrated external force as the real external force; Generate a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and the second calibration model, and select the calibrated external torque as the real external torque; When the end effector of the robot arm contacts the object, the robot arm control system is controlled to perform a target action on the object according to the real external force and the real external torque.

[0006] Furthermore, when the humanoid robot is in the running state, recording the sensor data generated by the wrist force sensor includes: When the humanoid robot is in the running state, the sampling time interval is obtained; According to the sampling time interval, the sensor data generated by the wrist force sensor is read and the sensor data is recorded.

[0007] Further, in the sensor data, reading the external force measured by the wrist force sensor in the sensor fixed coordinate system, reading the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and obtaining the calibration result corresponding to the wrist force sensor include: Obtain a first read instruction and a second read instruction; In the sensor data, the first reading instruction is used to read the external force measured by the wrist force sensor in the sensor fixed coordinate system, and the second reading instruction is used to read the external torque measured by the wrist force sensor in the sensor fixed coordinate system to obtain the calibration result corresponding to the wrist force sensor.

[0008] Further, generating the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and selecting the calibrated external force as the real external force includes: In the calibration result, the rotation matrix from the manipulator end coordinate system to the robot base coordinate system, the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, and the gravity vector of the end effector in the robot base coordinate system are obtained, and the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system is selected as the installation matrix of the wrist force sensor; According to the rotation matrix from the robot arm end coordinate system to the robot base coordinate system, the installation matrix of the wrist force sensor, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, the gravity vector of the end effector in the robot base coordinate system and the first calibration model, the calibrated external force is generated and the calibrated external force is selected as the real external force.

[0009] Further, generating a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, and selecting the calibrated external torque as the real external torque includes: In the calibration result, a rotation matrix from the robot end coordinate system to the robot base coordinate system, an installation matrix of the wrist force sensor, a center of gravity position of the wrist force sensor in the sensor fixed coordinate system, and a force offset measured by the wrist force sensor in the sensor fixed coordinate system are obtained; According to the rotation matrix from the robot arm end coordinate system to the robot base coordinate system, the installation matrix of the wrist force sensor, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, the center of gravity position of the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, a calibrated external torque is generated and the calibrated external torque is selected as the true external torque.

[0010] Further, when the end effector of the robotic arm contacts the object, controlling the robotic arm control system to perform a target action on the object according to the real external force and the real external torque includes: When the end effector of the robotic arm contacts the object, accessing the robotic arm control system of the humanoid robot, the robotic arm control system being the control system of the robotic arm; The real external force and the real external torque are transmitted to the robot control system, and the robot control system is controlled to perform a target action on the object according to the real external force and the real external torque.

[0011] Further, The sensor fixed coordinate system is a fixed coordinate system of a wrist force sensor, the robotic arm end coordinate system is an end coordinate system of the robotic arm, and the robot base coordinate system is a base coordinate system of the humanoid robot.

[0012] In a second aspect, a wrist force sensor calibration device for a humanoid robot is provided, comprising: A connection module, used for connecting a wrist force sensor of the humanoid robot, where the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; A recording module, used for recording sensor data generated by the wrist force sensor when the humanoid robot is in a running state; a reading module, used to read, from the sensor data, the external force measured by the wrist force sensor in the sensor fixed coordinate system, read the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and obtain a calibration result corresponding to the wrist force sensor; A first generating module, configured to generate the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and select the calibrated external force as the real external force; A second generating module is used to generate a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, and select the calibrated external torque as the real external torque; A control module is used to control the robotic arm control system to perform a target action on the object according to the real external force and the real external torque when the end effector of the robotic arm contacts the object.

[0013] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the wrist force sensor calibration method when executing the computer program.

[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the wrist force sensor calibration method are implemented.

[0015] The present application provides a wrist force sensor calibration method, device, computer equipment and storage medium of a humanoid robot, which are connected to the wrist force sensor of the humanoid robot, where the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; when the humanoid robot is in operation, the sensor data generated by the wrist force sensor is recorded; in the sensor data, the external force measured by the wrist force sensor in the sensor fixed coordinate system is read, and the external torque measured by the wrist force sensor in the sensor fixed coordinate system is read to obtain the calibration result corresponding to the wrist force sensor; according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and a first calibration model, the calibrated external force is generated, and the calibrated external force is selected as the real external force; according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and a second calibration model, the calibrated external torque is generated, and the calibrated external torque is selected as the real external force moment; when the end effector of the robotic arm contacts the object, the robotic arm control system is controlled to perform the target action on the object according to the real external force and the real external torque. The beneficial effects are in two aspects. On the one hand, according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, the calibrated external force is generated, and the calibrated external force is selected as the real external force. According to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, the calibrated external torque is generated, and the calibrated external torque is selected as the real external torque, thereby solving the problem of how to obtain the real external force and the real external torque of the wrist force sensor; on the other hand, when the robotic arm contacts the object, the robotic arm control system is controlled to perform the target action on the object according to the real external force and the real external torque, thereby helping to improve the accuracy of the robotic arm control system when performing tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 is a schematic diagram of an application environment of a wrist force sensor calibration method according to an embodiment of the present invention; Figure 2 A schematic flow chart of a wrist force sensor calibration method provided by an embodiment of the present invention; Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S23; Figure 4 yes Figure 2 A schematic flow chart of a specific implementation of step S25; Figure 5 yes Figure 2 A schematic flow chart of a specific implementation of step S26; Figure 6 is a structural schematic diagram of a wrist force sensor calibration device in one embodiment of the present invention; Figure 7 It is a structural diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 , Figure 1 FIG. 1 is a schematic diagram of an application environment of a wrist force sensor calibration method according to an embodiment of the present invention. The wrist force sensor calibration method provided by the embodiment of the present invention can be applied in the following embodiments: Figure 1 In an application environment, a client communicates with a server through a network.

[0020] The server is connected to the wrist force sensor of the humanoid robot through the client, and the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; When the humanoid robot is in operation, sensor data generated by the wrist force sensor is recorded; In the sensor data, an external force measured by the wrist force sensor in the sensor fixed coordinate system is read, and an external torque measured by the wrist force sensor in the sensor fixed coordinate system is read to obtain a calibration result corresponding to the wrist force sensor; Generate the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and select the calibrated external force as the real external force; Generate a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and the second calibration model, and select the calibrated external torque as the real external torque; When the end effector of the robot arm contacts the object, the robot arm control system is controlled to perform a target action on the object according to the real external force and the real external torque.

[0021] In the scheme implemented by the above-mentioned wrist force sensor calibration method, device, equipment and medium, the beneficial effects are in two aspects. On the one hand, according to the calibration result, the external force measured by the wrist force sensor in the fixed coordinate system of the sensor and the first calibration model, the calibrated external force is generated, and the calibrated external force is selected as the real external force. According to the calibration result, the external torque measured by the wrist force sensor in the fixed coordinate system of the sensor and the second calibration model, the calibrated external torque is generated, and the calibrated external torque is selected as the real external torque, thereby solving the problem of how to obtain the real external force and the real external torque of the wrist force sensor; on the other hand, when the robotic arm contacts the object, the robotic arm control system is controlled to perform the target action on the object according to the real external force and the real external torque, thereby helping to improve the accuracy of the robotic arm control system when performing tasks.

[0022] The device running the client is referred to as a client device.

[0023] The device running the server is referred to as the server device.

[0024] Among them, client devices include but are not limited to smartphones, personal computers, Internet of Vehicles terminals, tablets and portable wearable devices.

[0025] The server device may be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments. Figure 2 , Figure 2 A schematic flow chart of a wrist force sensor calibration method provided in an embodiment of the present invention includes the following steps: S21, connecting a wrist force sensor of the humanoid robot, where the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; Among them, humanoid robots are intelligent robots that are highly designed to imitate human form and movements. Humanoid robots usually have basic human structures such as limbs, head and torso, and can achieve human-like abilities to walk, grasp and manipulate objects through complex sensor systems and advanced algorithms.

[0026] For example, the force sensor is a six-dimensional force sensor, which is a sensor capable of measuring three force components and three torque components simultaneously.

[0027] S22, when the humanoid robot is in a running state, recording sensor data generated by the wrist force sensor; Wherein, when the humanoid robot is in the running state, recording the sensor data generated by the wrist force sensor includes: When the humanoid robot is in the running state, the sampling time interval is obtained; According to the sampling time interval, the sensor data generated by the wrist force sensor is read and the sensor data is recorded.

[0028] Secondly, the sampling interval provides a reasonable balance, which can capture the details of the wrist force sensor changes without overburdening the system due to too frequent data collection. For most application scenarios, the sampling interval is sufficient to capture these changes while avoiding unnecessary data redundancy and storage.

[0029] For example, when the sampling time interval is 1 second, the sensor data generated by the wrist force sensor is read once every 1 second and the sensor data is recorded once.

[0030] For example, when the sampling time interval is 2 seconds, the sensor data generated by the wrist force sensor is read once every 2 seconds and the sensor data is recorded once.

[0031] For example, when the sampling time interval is 50 milliseconds, the sensor data generated by the wrist force sensor is read once every 50 milliseconds and the sensor data is recorded once.

[0032] S23, reading the external force measured by the wrist force sensor in the sensor fixed coordinate system from the sensor data, reading the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and obtaining a calibration result corresponding to the wrist force sensor; S24, generating the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system, and the first calibration model, and selecting the calibrated external force as the real external force; The step of generating the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system, and the first calibration model, and selecting the calibrated external force as the real external force includes: In the calibration result, the rotation matrix from the manipulator end coordinate system to the robot base coordinate system, the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, and the gravity vector of the end effector in the robot base coordinate system are obtained, and the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system is selected as the installation matrix of the wrist force sensor; According to the rotation matrix from the robot arm end coordinate system to the robot base coordinate system, the installation matrix of the wrist force sensor, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, the gravity vector of the end effector in the robot base coordinate system and the first calibration model, the calibrated external force is generated and the calibrated external force is selected as the real external force.

[0033] Among them, the calibration results include the rotation matrix from the manipulator end coordinate system to the robot base coordinate system, the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, the gravity vector of the end effector in the robot base coordinate system, and the center of gravity position of the wrist force sensor in the sensor fixed coordinate system.

[0034] Exemplarily, the first calibration model is: ; It represents the real external force measured by the wrist force sensor in the robot base coordinate system; Represents the rotation matrix from the robot end coordinate system to the robot base coordinate system; represents the mounting matrix of the wrist force sensor; It represents the original external force measured by the wrist force sensor in the sensor fixed coordinate system; It represents the force offset measured by the wrist force sensor in the sensor fixed coordinate system; Represents the gravity vector of the end effector in the robot base coordinate system.

[0035] Among them, the end effector is a device in a humanoid robot that is directly used to operate or process a target object, and is usually installed at the end of the robotic arm of the humanoid robot.

[0036] Among them, the installation matrix of the wrist force sensor is the rotation matrix from the sensor fixed coordinate system to the robot end coordinate system.

[0037] Among them, the rotation matrix from the sensor fixed coordinate system to the robot end coordinate system can describe how the first reference point in the sensor fixed coordinate system rotates to reach the robot end coordinate system. By applying the rotation matrix from the sensor fixed coordinate system to the robot end coordinate system, the exact position and direction of the first reference point in the robot end coordinate system can be calculated without complex spatial geometry calculations. The rotation matrix not only simplifies the process of transforming between the sensor fixed coordinate system and the robot end coordinate system, but also ensures the accuracy and consistency of the transformation.

[0038] Among them, the rotation matrix from the robot end coordinate system to the robot base coordinate system can describe how the second reference point in the robot end coordinate system rotates to reach the robot base coordinate system. Through the rotation matrix from the robot end coordinate system to the robot base coordinate system, the exact position and direction of the second reference point in the robot base coordinate system can be calculated without complex spatial geometry calculations. The rotation matrix not only simplifies the process of transforming between the robot end coordinate system and the robot base coordinate system, but also ensures the accuracy and consistency of the transformation.

[0039] In an embodiment of the present invention, the first calibration model generates the calibrated external force, and the calibrated external force is selected as the real external force. Since there is no need to manually calibrate the real external force, the calibration time of the real external force is reduced, which is beneficial to improving the efficiency of obtaining the real external force.

[0040] S25, generating a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and the second calibration model, and selecting the calibrated external torque as the real external torque; Exemplarily, the second calibration model is: ; represents the actual external torque measured by the wrist force sensor in the robot base coordinate system; Represents the rotation matrix from the robot end coordinate system to the robot base coordinate system; represents the mounting matrix of the wrist force sensor; It represents the original external torque measured by the wrist force sensor in the sensor fixed coordinate system; Indicates the center of gravity position of the wrist force sensor in the sensor fixed coordinate system; It indicates the torque offset measured by the wrist force sensor in the sensor fixed coordinate system when there is no force acting.

[0041] The first calibration model and the second calibration model are different calibration models.

[0042] S26, when the end effector of the robot arm contacts the object, controlling the robot arm control system to perform a target action on the object according to the real external force and the real external torque.

[0043] The target action includes one of a grabbing action, a placing action, and an assembling action, or a combination thereof.

[0044] Among them, the sensor fixed coordinate system is the fixed coordinate system of the wrist force sensor, the robotic arm end coordinate system is the end coordinate system of the robotic arm, and the robot base coordinate system is the base coordinate system of the humanoid robot.

[0045] The fixed coordinate system of the wrist force sensor provides a stable and consistent reference frame, allowing the wrist force sensor to accurately locate and record changes in physical quantities relative to this fixed point. By establishing a fixed coordinate system, the wrist force sensor can distinguish between true changes in the measured value and errors caused by the sensor's own movement or tilt, thereby improving the accuracy and reliability of the data.

[0046] Among them, the end coordinate system of the robot arm defines a local reference frame with the end effector of the robot arm as the origin, so that the robot arm can accurately control and locate the position and posture of the end effector in space. By using the end coordinate system of the robot arm, the robot arm control system can calculate the precise position and orientation of the end effector relative to other objects or reference points in the working environment, thereby achieving precise grasping, placement, and assembly actions.

[0047] The base coordinate system of the humanoid robot serves as a fixed and global reference point, providing a unified and stable spatial coordinate frame for the entire humanoid robot. Through the base coordinate system of the humanoid robot, the humanoid robot can accurately determine the absolute position and direction of the manipulator and end effector in space. This not only enables the humanoid robot to perform precise operations according to preset paths and actions, but also enables self-navigation and obstacle avoidance in complex working environments.

[0048] In an embodiment of the present invention, beneficial effects lie in two aspects. On the one hand, according to the calibration result, the external force measured by the wrist force sensor in the fixed coordinate system of the sensor and the first calibration model, the calibrated external force is generated, and the calibrated external force is selected as the real external force. According to the calibration result, the external torque measured by the wrist force sensor in the fixed coordinate system of the sensor and the second calibration model, the calibrated external torque is generated, and the calibrated external torque is selected as the real external torque, thereby solving the problem of how to obtain the real external force and the real external torque of the wrist force sensor; on the other hand, when the robotic arm contacts the object, the robotic arm control system is controlled to perform the target action on the object according to the real external force and the real external torque, thereby helping to improve the accuracy of the robotic arm control system when performing tasks.

[0049] See also Figure 3 , Figure 3 yes Figure 2 A specific implementation flow diagram of step S23 is described in detail as follows: S31, obtaining a first read instruction and a second read instruction; S32, in the sensor data, using the first reading instruction to read the external force measured by the wrist force sensor in the sensor fixed coordinate system, using the second reading instruction to read the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and obtaining the calibration result corresponding to the wrist force sensor.

[0050] In the embodiment of the present invention, the external force measured by the wrist force sensor in the sensor fixed coordinate system is read, and the external torque measured by the wrist force sensor in the sensor fixed coordinate system is read. The external force and the external torque provide key basis for subsequent calibration.

[0051] See also Figure 4 , Figure 4 yes Figure 2 A specific implementation flow diagram of step S25 is described in detail as follows: S41, obtaining, from the calibration results, a rotation matrix from the manipulator end coordinate system to the robot base coordinate system, an installation matrix of the wrist force sensor, a center of gravity position of the wrist force sensor in the sensor fixed coordinate system, and a force offset measured by the wrist force sensor in the sensor fixed coordinate system; S42, based on the rotation matrix from the manipulator end coordinate system to the robot base coordinate system, the installation matrix of the wrist force sensor, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, the center of gravity position of the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, generates a calibrated external torque, and selects the calibrated external torque as the true external torque.

[0052] In an embodiment of the present invention, a calibrated external torque is generated according to the second calibration model, and the calibrated external torque is selected as the real external torque. Since there is no need to manually calibrate the real external torque, the calibration time of the real external torque is reduced, which is beneficial to improving the efficiency of obtaining the real external torque.

[0053] See also Figure 5 , Figure 5 yes Figure 2 A specific implementation flow diagram of step S26 is described in detail as follows: S51, when the end effector of the robotic arm contacts the object, accessing the robotic arm control system of the humanoid robot, the robotic arm control system being the control system of the robotic arm; S52, transmitting the real external force and the real external torque to the robot arm control system, and controlling the robot arm control system to perform a target action on the object according to the real external force and the real external torque.

[0054] In an embodiment of the present invention, the robotic arm control system transmits the real external force and the real external torque, and controls the robotic arm control system to perform a target action on the object according to the real external force and the real external torque. By real-time monitoring of the real external force and the real external torque, the force state and mechanical response of the humanoid robot can be evaluated, and the stability and response speed of the humanoid robot can be improved, thereby helping to improve the accuracy and reliability of the robotic arm control system when performing tasks.

[0055] See also Figure 6 , Figure 6 FIG. 1 is a schematic diagram of a wrist force sensor calibration device according to an embodiment of the present invention. Figure 6 As shown, the wrist force sensor calibration device includes a connection module 101, a recording module 102, a reading module 103, a first generating module 104, a second generating module 105, and a control module 106. The functional modules are described in detail as follows: A connection module 101 is used to connect a wrist force sensor of the humanoid robot, where the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; A recording module 102, used for recording sensor data generated by the wrist force sensor when the humanoid robot is in operation; A reading module 103 is used to read the external force measured by the wrist force sensor in the sensor fixed coordinate system, read the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and obtain a calibration result corresponding to the wrist force sensor. A first generating module 104 is used to generate the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and select the calibrated external force as the real external force; A second generating module 105 is used to generate a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, and select the calibrated external torque as the real external torque; The control module 106 is used to control the robotic arm control system to perform a target action on the object according to the real external force and the real external torque when the end effector of the robotic arm contacts the object.

[0056] In an embodiment of the present invention, beneficial effects lie in two aspects. On the one hand, according to the calibration result, the external force measured by the wrist force sensor in the fixed coordinate system of the sensor and the first calibration model, the calibrated external force is generated, and the calibrated external force is selected as the real external force. According to the calibration result, the external torque measured by the wrist force sensor in the fixed coordinate system of the sensor and the second calibration model, the calibrated external torque is generated, and the calibrated external torque is selected as the real external torque, thereby solving the problem of how to obtain the real external force and the real external torque of the wrist force sensor; on the other hand, when the robotic arm contacts the object, the robotic arm control system is controlled to perform the target action on the object according to the real external force and the real external torque, thereby helping to improve the accuracy of the robotic arm control system when performing tasks.

[0057] For the specific limitations of the wrist force sensor calibration device, please refer to the limitations of the wrist force sensor calibration method above, which will not be repeated here.

[0058] Each module in the wrist force sensor calibration device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0059] See also Figure 7 , Figure 7 1 is another structural diagram of a computer device in one embodiment of the present invention. In one embodiment, a computer device is provided. The computer device is a server device or a client device. The internal structure diagram thereof can be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external device. When the computer program is executed by the processor, the functions or steps of a wrist force sensor calibration method of a humanoid robot can be realized.

[0060] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor.

[0061] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant description of the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0062] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), and a network processor (NP); it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0063] The above description and the accompanying drawings sufficiently illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. In this article, each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods and products disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0064] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0065] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for calibrating a wrist force sensor of a humanoid robot, characterized in that: include: A wrist force sensor connected to the humanoid robot, wherein the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; When the humanoid robot is in operation, sensor data generated by the wrist force sensor is recorded; In the sensor data, an external force measured by the wrist force sensor in the sensor fixed coordinate system is read, and an external torque measured by the wrist force sensor in the sensor fixed coordinate system is read to obtain a calibration result corresponding to the wrist force sensor; Generate the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and select the calibrated external force as the real external force; Generate a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and the second calibration model, and select the calibrated external torque as the real external torque; When the end effector of the robot arm contacts the object, the robot arm control system is controlled to perform a target action on the object according to the real external force and the real external torque.

2. The wrist force sensor calibration method according to claim 1, characterized in that: When the humanoid robot is in the running state, recording the sensor data generated by the wrist force sensor includes: When the humanoid robot is in the running state, the sampling time interval is obtained; According to the sampling time interval, the sensor data generated by the wrist force sensor is read and the sensor data is recorded.

3. The wrist force sensor calibration method according to claim 1, characterized in that: The method of reading the external force measured by the wrist force sensor in the sensor fixed coordinate system and the external torque measured by the wrist force sensor in the sensor fixed coordinate system in the sensor data, and obtaining the calibration result corresponding to the wrist force sensor includes: Obtain a first read instruction and a second read instruction; In the sensor data, the first reading instruction is used to read the external force measured by the wrist force sensor in the sensor fixed coordinate system, and the second reading instruction is used to read the external torque measured by the wrist force sensor in the sensor fixed coordinate system to obtain the calibration result corresponding to the wrist force sensor.

4. The wrist force sensor calibration method according to claim 1, characterized in that: The step of generating the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system, and the first calibration model, and selecting the calibrated external force as the real external force includes: In the calibration result, the rotation matrix from the manipulator end coordinate system to the robot base coordinate system, the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, and the gravity vector of the end effector in the robot base coordinate system are obtained, and the rotation matrix from the sensor fixed coordinate system to the manipulator end coordinate system is selected as the installation matrix of the wrist force sensor; According to the rotation matrix from the robot arm end coordinate system to the robot base coordinate system, the installation matrix of the wrist force sensor, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the external force measured by the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system, the gravity vector of the end effector in the robot base coordinate system and the first calibration model, the calibrated external force is generated and the calibrated external force is selected as the real external force.

5. The wrist force sensor calibration method according to claim 1, characterized in that: The step of generating a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and the second calibration model, and selecting the calibrated external torque as the real external torque includes: In the calibration result, a rotation matrix from the robot end coordinate system to the robot base coordinate system, an installation matrix of the wrist force sensor, a center of gravity position of the wrist force sensor in the sensor fixed coordinate system, and a force offset measured by the wrist force sensor in the sensor fixed coordinate system are obtained; According to the rotation matrix from the robot arm end coordinate system to the robot base coordinate system, the installation matrix of the wrist force sensor, the external torque measured by the wrist force sensor in the sensor fixed coordinate system, the center of gravity position of the wrist force sensor in the sensor fixed coordinate system, the force offset measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, a calibrated external torque is generated and the calibrated external torque is selected as the true external torque.

6. The wrist force sensor calibration method according to claim 1, characterized in that: When the end effector of the robot arm contacts the object, controlling the robot arm control system to perform a target action on the object according to the real external force and the real external torque includes: When the end effector of the robotic arm contacts the object, accessing the robotic arm control system of the humanoid robot, the robotic arm control system being the control system of the robotic arm; The real external force and the real external torque are transmitted to the robot control system, and the robot control system is controlled to perform a target action on the object according to the real external force and the real external torque.

7. The wrist force sensor calibration method according to claim 1, characterized in that: The sensor fixed coordinate system is a fixed coordinate system of a wrist force sensor, the robotic arm end coordinate system is an end coordinate system of the robotic arm, and the robot base coordinate system is a base coordinate system of the humanoid robot.

8. A wrist force sensor calibration device for a humanoid robot, characterized in that: include: A connection module, used for connecting a wrist force sensor of the humanoid robot, where the wrist force sensor is a force sensor installed or fixed on the wrist of the mechanical arm of the humanoid robot; A recording module, used for recording sensor data generated by the wrist force sensor when the humanoid robot is in a running state; a reading module, used to read, from the sensor data, the external force measured by the wrist force sensor in the sensor fixed coordinate system, read the external torque measured by the wrist force sensor in the sensor fixed coordinate system, and obtain a calibration result corresponding to the wrist force sensor; A first generating module, configured to generate the calibrated external force according to the calibration result, the external force measured by the wrist force sensor in the sensor fixed coordinate system and the first calibration model, and select the calibrated external force as the real external force; A second generating module is used to generate a calibrated external torque according to the calibration result, the external torque measured by the wrist force sensor in the sensor fixed coordinate system and the second calibration model, and select the calibrated external torque as the real external torque; A control module is used to control the robotic arm control system to perform a target action on the object according to the real external force and the real external torque when the end effector of the robotic arm contacts the object.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the wrist force sensor calibration method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the wrist force sensor calibration method according to any one of claims 1 to 7 are implemented.

Images