Robotic arm guidance method, device, computer equipment and storage medium

Abstract

The present application relates to a robot arm guidance method, device, computer equipment and storage medium. The method comprises: collecting external force information acting on the robot arm guidance component according to an external force sensor; decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system; adjusting the initial posture of the end of the robot arm according to the direction and size of the maximum decomposition vector, so that the position of the end of the robot arm is in the expected position. The method can be used to divide the guidance adjustment process into two modes: displacement adjustment and rotation adjustment according to the type of the maximum decomposition vector, thereby avoiding the probability of misjudgment of the adjustment direction, and improving the accuracy of manual force guidance adjustment in three-dimensional space, making it more suitable for high-precision working environments and reducing the risks brought by low-precision manual operations.

Description

Technical Field

[0001] The present application relates to the field of robot control technology, and in particular to a robot arm guidance method, device, computer equipment and storage medium. Background Art

[0002] With the development of intelligent control technology, robotic arms are widely used in various fields. In the application scenarios of robotic arms, it is sometimes necessary to manually drag the robotic arm according to actual needs so that the end position of the robotic arm reaches the expected position. However, in the process of manually dragging the robotic arm, the manual dragging accuracy is low, which is easy to cause operational errors or a large error between the manual dragging direction and the expected movement direction, resulting in a large position error between the end position of the robotic arm and the expected position. Summary of the invention

[0003] Based on this, it is necessary to provide a robot arm guidance method, device, computer equipment and storage medium that can improve the accuracy of manually guiding the adjustment of the position of the robot arm end in order to address the above technical problems.

[0004] In a first aspect, the present application provides a robot arm guidance method, the method comprising:

[0005] Collecting external force information acting on the guiding component of the robotic arm according to the external force sensor; the external force information includes a guiding force for guiding the translation of the robotic arm and / or a guiding torque for guiding the rotation of the robotic arm;

[0006] Decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system;

[0007] According to the direction and size of the maximum decomposition vector, the initial pose of the end of the robotic arm is adjusted so that the position of the end of the robotic arm is at the expected position.

[0008] In one embodiment, according to decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes:

[0009] If the external force sensor is a six-dimensional force sensor, the external force information is decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes a maximum guiding force vector and a maximum guiding moment vector;

[0010] If the external force sensor is a three-dimensional force sensor and a three-dimensional torque sensor, the external force information is decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector.

[0011] In one embodiment, adjusting the initial posture of the end of the robot arm according to the direction and size of the maximum decomposition vector so that the position of the end of the robot arm is at an expected position includes:

[0012] According to the direction and size of the maximum decomposition vector, the adjustment direction and adjustment amount of the end of the robot arm are determined;

[0013] According to the initial position of the end of the robot arm, the adjustment direction and adjustment amount of the end of the robot arm, determine the adjustment direction and adjustment amount required for each joint module of the robot arm;

[0014] According to the adjustment direction and amount of each joint module, the end of the robot arm is controlled to move until the position of the end of the robot arm is at the expected position.

[0015] In one embodiment, the maximum decomposition vector is a maximum guiding force vector, and the adjustment direction and adjustment amount of the end of the robot arm are determined according to the direction and magnitude of the maximum decomposition vector, including:

[0016] The direction of the maximum guiding force vector is used as the translation direction of the robot arm, and the modulus of the maximum guiding force vector is used as the translation distance of the end of the robot arm.

[0017] In one embodiment, the maximum decomposition vector is the maximum guiding torque vector, and the adjustment direction and adjustment amount of the end of the robot arm are determined according to the direction and magnitude of the maximum decomposition vector, including:

[0018] The coordinate axis of the maximum guiding torque vector located in the external force sensor coordinate system is taken as the rotation axis, the direction of the maximum guiding torque vector is taken as the rotation direction of the end of the robot arm, and the rotation acceleration of the end of the robot arm is determined according to the modulus value of the maximum guiding torque vector.

[0019] In one embodiment, the maximum decomposition vector includes a maximum guiding force vector and a maximum guiding torque vector, and the adjustment direction and adjustment amount of the end of the robot arm are determined according to the direction and magnitude of the maximum decomposition vector, including:

[0020] determining a weight ratio of a maximum guiding force vector and a maximum guiding moment vector;

[0021] According to the weight ratio, determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding force moment vector;

[0022] If the ratio is greater than 1, the direction of the maximum guiding force vector is used as the translation direction of the end of the robot arm, and the modulus of the maximum guiding force vector is used as the translation distance of the end of the robot arm;

[0023] If the ratio is less than 1, the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system is used as the rotation axis, and the direction of the maximum guiding torque vector is used as the rotation direction of the end of the robotic arm. The rotation acceleration of the end of the robotic arm is determined according to the modulus of the maximum guiding torque vector.

[0024] In one embodiment, according to the adjustment amount of each joint module, the end of the robot arm is controlled to move until the position of the end of the robot arm is at the expected position, including:

[0025] In the process of controlling the movement of the end of the robot arm according to the adjustment amount of each joint module, if the direction of the external force collected is inconsistent with the adjustment direction of the robot arm, the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated, and the step of determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector according to the weight ratio is returned and continued to be executed until the direction of the external force collected is consistent with the adjustment direction of the robot arm during the movement of the robot arm;

[0026] After the direction of the external force is consistent with the adjustment direction of the robotic arm, continue to control the movement of the end of the robotic arm until it reaches the expected position.

[0027] In one embodiment, updating the weight ratio of the maximum guidance force vector and the maximum guidance torque vector includes:

[0028] The magnitude and direction of the external force are input into a pre-trained prediction model, and the prediction model outputs the weight ratio of the updated maximum guiding force vector and the maximum guiding torque vector.

[0029] In a second aspect, the present application also provides a robot arm guiding device. The device comprises:

[0030] A collection module, used to collect external force information acting on the guiding component of the robotic arm according to the external force sensor; the external force information includes a guiding force for guiding the translation of the robotic arm and / or a guiding torque for guiding the rotation of the robotic arm;

[0031] A force decomposition module, which decomposes the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and determines the maximum decomposition vector in the axial direction of the external force sensor coordinate system;

[0032] The guiding module is used to adjust the initial posture of the end of the robot arm according to the direction and size of the maximum decomposition vector so that the position of the end of the robot arm is at the expected position.

[0033] In one embodiment, the force decomposition module is further used to determine the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system if the external force sensor is a six-dimensional force sensor, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes a maximum guiding force vector and a maximum guiding moment vector;

[0034] If the external force sensor is a three-dimensional force sensor and a three-dimensional torque sensor, the external force information is decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector.

[0035] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0036] The external force information acting on the guiding component of the robot arm is collected according to the external force sensor; the external force information includes the guiding force for guiding the translation of the robot arm and / or the guiding torque for guiding the rotation of the robot arm

[0037] Decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system;

[0038] According to the direction and size of the maximum decomposition vector, the initial pose of the end of the robotic arm is adjusted so that the position of the end of the robotic arm is at the expected position.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] The external force information acting on the guiding component of the robot arm is collected according to the external force sensor; the external force information includes the guiding force for guiding the translation of the robot arm and / or the guiding torque for guiding the rotation of the robot arm

[0041] Decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system;

[0042] According to the direction and size of the maximum decomposition vector, the initial pose of the end of the robotic arm is adjusted so that the position of the end of the robotic arm is at the expected position.

[0043] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] The external force information acting on the guiding component of the robot arm is collected according to the external force sensor; the external force information includes the guiding force for guiding the translation of the robot arm and / or the guiding torque for guiding the rotation of the robot arm

[0045] Decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system;

[0046] According to the direction and size of the maximum decomposition vector, the initial pose of the end of the robotic arm is adjusted so that the position of the end of the robotic arm is at the expected position.

[0047] The above-mentioned robot arm guidance method, device, computer equipment and storage medium decompose the external force information into decomposition vectors in each axial direction of the external force sensor coordinate system, and adjust the initial posture of the end of the robot arm according to the direction and size of the maximum decomposition vector in the axial direction of the external force sensor coordinate system, so that the position of the end of the robot arm is in the expected position. Among them, according to the type of the maximum decomposition vector, the guidance adjustment process is divided into two methods: displacement adjustment and rotation adjustment, thereby avoiding the probability of misjudgment of the adjustment direction, and improving the accuracy of manual force guidance adjustment in three-dimensional space, which is more suitable for high-precision working environment and reduces the risk brought by low-precision manual operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A diagram showing an application environment of a robot arm guiding method in an embodiment;

[0049] Figure 2 A schematic diagram of a flow chart of a robot arm guiding method in one embodiment;

[0050] Figure 3 This is a schematic diagram of installing a six-dimensional force sensor A on a robotic arm in an embodiment;

[0051] Figure 4 This is a schematic diagram of installing a three-dimensional force sensor B and a three-dimensional torque sensor C on a robotic arm in another embodiment;

[0052] Figure 5 A flowchart of filtering external force information data collected by an external force sensor in one embodiment;

[0053] Figure 6 A schematic diagram of Cartesian coordinate construction in one embodiment;

[0054] Figure 7 A schematic diagram of space coordinate conversion in one embodiment;

[0055] Figure 8 A flowchart of adjusting the initial position and posture of the end of a robotic arm in one embodiment;

[0056] Fig. 9 is a control flow chart of an admittance controller in one embodiment;

[0057] Fig.10A partial structural diagram of a three-dimensional force sensor B, a three-dimensional torque sensor C and a handle in one embodiment;

[0058] Fig.11 It is a schematic diagram of determining the guiding force and guiding torque of the external force sensor arranged separately in one embodiment;

[0059] Fig.12 A diagram showing the relationship between the positions of the sensor and the handle in one embodiment;

[0060] Fig.13 A schematic diagram of determining the guiding force and guiding torque of an external force sensor arranged integrally in one embodiment;

[0061] Fig.14 A flowchart of training a prediction model in one embodiment;

[0062] Fig.15 is a training flow chart of a perceptron model in one embodiment;

[0063] Fig.16 A training flow chart of a feedforward neural network for back-propagation learning in one embodiment;

[0064] Fig.17 A flowchart of updating the weight ratio of the maximum guidance force vector and the maximum guidance torque vector in one embodiment;

[0065] Fig.18 A schematic diagram of a process for determining the start and end of a control adjustment mode in an embodiment;

[0066] Fig.19 is a structural block diagram of a robot arm guiding device in one embodiment;

[0067] Fig. 20 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] The robot arm guiding method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the computer device 102 collects the external force acting on the guiding component of the robotic arm according to the external force sensor; decomposes the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and determines the maximum decomposition vector in the axial direction of the external force sensor coordinate system; according to the direction and size of the maximum decomposition vector, adjusts the initial posture of the end of the robotic arm so that the position of the end of the robotic arm is in the expected position. The computer device 102 communicates with the server 104 through the network. Among them, the computer device 102 can be but is not limited to various robots, personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0070] In one embodiment, Figure 2 As shown, a robot arm guidance method is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0071] Step 202 , collecting external force information acting on the guiding component of the robot arm according to the external force sensor; the external force information includes a guiding force for guiding the translation of the robot arm and / or a guiding torque for guiding the rotation of the robot arm.

[0072] The robot arm guide component is a component to which a force is applied manually, and guides the robot arm to move in the direction of the force under the force applied manually. For example, the robot arm guide component may be a control knob of the robot arm, or a control handle that drives the robot arm to move.

[0073] The external force sensor is installed on the guide part of the robot arm to achieve equivalent force transmission during the force conduction process, and is used to detect the external force acting on the guide part of the robot arm and output the external force information, wherein the external force information includes the direction and magnitude of the force. The external force sensor can be a six-dimensional force sensor A, or a three-dimensional force sensor B and a three-dimensional torque sensor C. The robot arm of this embodiment is a robot arm with a C-shaped structure, such as Figure 3 As shown in FIG. 1 , it is a schematic diagram of the installation of the six-dimensional force sensor A on the robotic arm. Figure 4 As shown, it is a schematic diagram of the installation of the three-dimensional force sensor B and the three-dimensional torque sensor C on the robotic arm.

[0074] Since the external force information collected by the external force sensor contains a lot of interference elements, it will greatly affect the judgment accuracy in the control. Figure 5 As shown, this embodiment performs filtering and rationality detection on all initial data, wherein the purpose of the rationality detection is to filter out data that is obviously illogical and ultimately output safe and reliable external force collection data.

[0075] Optionally, the computer device collects external force information acting on the guiding component of the robotic arm through an external force sensor installed on the guiding component of the robotic arm. If the external force sensor is a six-dimensional force sensor A, the collected external force information includes guiding force information and guiding torque information; if the external force sensor is a three-dimensional force sensor B and a three-dimensional torque sensor C, the three-dimensional force sensor B is used to collect the guiding force information applied by the operator on the guiding component of the robotic arm for translation, and the three-dimensional torque sensor C is used to collect the guiding torque information applied by the operator on the guiding component of the robotic arm for rotation.

[0076] Step 204 , determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system according to the decomposition vectors in each axial direction of the external force sensor coordinate system in accordance with the decomposition of the external force information.

[0077] Among them, the external force sensor coordinate system is based on Figure 6 The Cartesian coordinate system shown is established. Figure 6 is a side view of a robotic arm with a C-shaped structure. Figure 6 The robotic arm shown specifically includes a large C-arm and a small C-arm. Figure 6 In Chinese, sus means suspension, which is a rotating joint. sus represents the rotation axis of the suspension, X sus is obtained by MDH calibration and Z sus The direction of the axis is determined by the direction of the robot; LC represents the large C arm of the robot, Z LC Indicates the rotation axis of the large C-arm, X LC is obtained by MDH calibration and Z LC The direction of the axis is determined by the direction of the robot; SC represents the small C arm of the robot, Z SC Indicates the rotation axis of the small C-arm, X SC is obtained by MDH calibration and Z SC Since the force control adjustment effect is reflected in the flexible adjustment of the spatial position and spatial posture of the fixed point, the Cartesian coordinate system related position and posture of the robot arm moved during the adjustment process are established as follows: Figure 3 and Figure 4 The state shown in the figure, in which the Z-axis direction is determined according to the rotation axis direction of the robot arm, and the origin of the coordinate system is established at the fixed point, thereby achieving the effect of controlling the Cartesian coordinate system and simultaneously controlling the fixed point coordinate system. If the external force sensor is a six-dimensional force sensor A, the coordinate system corresponding to the six-dimensional force sensor A is as follows: Figure 3 If the external force sensors are three-dimensional force sensor B and three-dimensional torque sensor C, the coordinate systems corresponding to the three-dimensional force sensor B and the three-dimensional torque sensor C are as follows: Figure 4 As shown, the axes of the coordinate system of the three-dimensional force sensor B and the coordinate system of the three-dimensional torque sensor C are correspondingly parallel.

[0078] This embodiment adopts the principle of decomposition force control guidance adjustment to ensure high-precision characteristics of posture adjustment. Therefore, it is necessary to decompose the external force information into each axis in the external force sensor coordinate system.

[0079] If the external force sensor is a six-dimensional force sensor A, the external force information is determined to be decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes the maximum guiding force vector and the maximum guiding torque vector; if the external force sensor is a three-dimensional force sensor B and a three-dimensional torque sensor C, the external force information is determined to be decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector, that is, the maximum decomposition vector decomposed into each axial direction in the three-dimensional force sensor B coordinate system is the maximum guiding force vector, and the maximum decomposition vector decomposed into each axial direction in the three-dimensional torque sensor C coordinate system is the maximum guiding torque vector.

[0080] It should be noted that: torque is a physical quantity that represents the rotational effect produced when a force acts on an object. The vector product of force and lever arm is torque. Torque is a vector. The magnitude of the torque of a force on a certain point is the length of the vertical line from the point to the line of action of the force (i.e., lever arm) multiplied by the magnitude of the force. The direction of the torque is perpendicular to the plane formed by the vertical line and the force, and is determined by the right-hand screw rule of the torque. The external force information output by the external force sensor includes information such as the magnitude and direction of the torque.

[0081] It should be noted that: decomposing the external force information into each axial direction in the external force sensor coordinate system specifically means: converting the external force into the external force sensor coordinate system, and determining the decomposition vector of the external force information into each axial direction in the external force sensor coordinate system based on the product of the cosine value of the angle between the external force and each axial direction in the external force sensor coordinate system and the modulus value of the external force.

[0082] like Figure 7 As shown, according to the force equivalence principle, this embodiment can equate the force F applied to the handle to the force F collected by the external force sensor, and the torque is converted according to the relative distance. However, for practical applications, it is necessary to convert the force and torque to the world coordinate system, so the following conversion is performed:

[0083] sen F bar = sen F sen ;

[0084] sen M bar = sen M sen + sen l bar × sen F sen ;

[0085]

[0086]

[0087] Among them, bar represents the handle, sen represents the external force sensor, sen F bar Indicates the magnitude and direction of the force of the handle relative to the external force sensor; sen F sen Indicates the force collected by the external force sensor; F represents force, M represents torque, sen M bar Represents the torque of the handle relative to the external force sensor, sen M sen represents the torque collected by the external force sensor, l represents the distance, sen l bar represents the distance between the handle and the external force sensor, w represents the world coordinate system, and R represents the rotation matrix Represents the transformation matrix between the handle coordinate system and the external force sensor coordinate system, Represents the transformation matrix between the handle coordinate system and the world coordinate system.

[0088] Optionally, the computer device equates the force F applied to the handle with the force F collected by the external force sensor, obtains the torque based on the relative distance conversion, decomposes the force and torque collected by the external force sensor into decomposition vectors in each axial direction in the external force sensor coordinate system according to the principle of force decomposition, and determines the maximum decomposition vector with the largest modulus value in the axial direction of the external force sensor coordinate system.

[0089] Step 206, adjusting the initial posture of the end of the robot arm according to the direction and size of the maximum decomposition vector, so that the position of the end of the robot arm is at the expected position.

[0090] Among them, the end of the robotic arm refers to the force-carrying part of the robotic arm used to load loads, pick up objects or the operator to drag the robotic arm.

[0091] In the process of the operator manually dragging the mechanical arm, the present embodiment adopts the superposition of the two motion modes of translation and rotation to achieve the purpose of adjusting the posture of the mechanical arm. Therefore, in the present embodiment, if the external force sensor is a six-dimensional force sensor A, the maximum decomposition vector of each axis in the coordinate system of the six-dimensional force sensor A includes the maximum guiding force vector and the maximum guiding torque vector. According to the weight ratio of the guiding force vector and the guiding torque vector, the vector with the largest proportion in the maximum decomposition vector is determined. If the vector with the largest proportion is the guiding force vector, the adjustment mode is determined to be the translation mode; if the vector with the largest proportion is the guiding torque vector, the adjustment mode is determined to be the rotation mode. If the external force sensor is a three-dimensional force sensor B, the maximum decomposition vector of each axis in the coordinate system of the three-dimensional force sensor B is the maximum guiding force vector, and the adjustment mode is determined to be the translation mode; if the external force sensor is a three-dimensional torque sensor C, the maximum decomposition vector of each axis in the coordinate system of the three-dimensional torque sensor C is the maximum guiding torque vector, and the adjustment mode is determined to be the rotation mode.

[0092] In displacement mode, ensure that the end point is along the coordinate system x established at the end h ,y h 、z h The direction is shifted successively, so there is no rotation in the process, so the direction of each axis of the coordinate system will not change. In the rotation mode, according to the structural characteristics of the robot arm, under the premise of ensuring that the spatial position of the end point remains unchanged, by rotating x h ,y h 、z h The axis adjusts the end coordinate system posture. The decomposed displacement process can ensure high-precision movement in all directions, while reducing the movement risk caused by misjudgment of displacement direction and complex movement trajectory.

[0093] Optionally, the computer device determines the adjustment direction of the robotic arm based on the direction of the maximum decomposition vector, determines the adjustment amount of the robotic arm based on the size of the maximum decomposition vector, and can determine the expected position of the end of the robotic arm based on the adjustment direction and the adjustment amount, and adjusts the initial posture of the end of the robotic arm based on the expected posture so that the position of the end of the robotic arm is at the expected position.

[0094] In the above-mentioned robot arm guidance method, the external force information is decomposed into decomposition vectors in each axial direction of the external force sensor coordinate system, and the initial posture of the end of the robot arm is adjusted according to the direction and size of the maximum decomposition vector in the axial direction of the external force sensor coordinate system, so that the position of the end of the robot arm is in the expected position. Among them, according to the type of the maximum decomposition vector, the guidance adjustment process is divided into two methods: displacement adjustment and rotation adjustment, thereby avoiding the probability of misjudgment of the adjustment direction, and improving the accuracy of manual force guidance adjustment in three-dimensional space, which is more suitable for high-precision working environment and reduces the risk brought by low-precision manual operation.

[0095] In one embodiment, Figure 8 As shown, according to the direction and size of the maximum decomposition vector, the initial position of the end of the robotic arm is adjusted so that the position of the end of the robotic arm is at the expected position, including:

[0096] Step 802, determining the adjustment direction and adjustment amount of the end of the robot arm according to the direction and size of the maximum decomposition vector.

[0097] Among them, the maximum decomposition vector includes three cases. The first case is that the maximum decomposition vector is the maximum guiding force vector, and the corresponding adjustment mode is the translation mode. The adjustment direction and adjustment amount of the robot arm are determined according to the direction and size of the maximum guiding force vector; the second case is that the maximum decomposition vector is the maximum guiding torque vector, and the corresponding adjustment mode is the rotation mode. The adjustment direction and adjustment amount of the robot arm are determined according to the direction and size of the guiding torque vector; the third case is that the maximum decomposition vector includes the maximum guiding force vector and the maximum guiding torque vector, and the corresponding adjustment mode needs to be determined according to the weighted ratio of the maximum guiding force vector and the maximum guiding torque vector.

[0098] In this embodiment, due to the field of robot motion control, force control must be introduced. Simply using the joint target position as the control output is far from meeting the application requirements. It is necessary to introduce torque / force control output, or introduce torque / force as a closed-loop feedback quantity into the control. Therefore, in this embodiment, the adjustment direction and adjustment amount of the end of the robotic arm are collectively referred to as the auxiliary force of the end of the robotic arm. The auxiliary force refers to the force vector required by the end of the robotic arm when the end of the robotic arm is in a preset translation or rotation motion. The force vector includes a guiding force or a guiding torque. The direction of the auxiliary force is the same as the maximum decomposition vector, and the magnitude of the auxiliary force is the same as the modulus of the maximum decomposition vector, that is, the auxiliary force is in the same direction as the maximum decomposition vector and is proportional to the magnitude of the external force.

[0099] Optionally, the computer device determines the adjustment mode according to the maximum decomposition vector, and determines the auxiliary force required by the end of the robotic arm when the end of the robotic arm moves in a preset translation or rotation amount according to the direction and size of the maximum decomposition vector.

[0100] Step 804, determining the adjustment direction and adjustment amount required for each joint module of the robotic arm according to the initial position of the end of the robotic arm, and the adjustment direction and adjustment amount of the end of the robotic arm.

[0101] Among them, due to the field of robot motion control, force control must be introduced. Simply using the joint target position as the control output is far from meeting the application requirements. It is necessary to introduce torque / force control output, or introduce torque / force as a closed-loop feedback quantity into the control. Therefore, in this embodiment, the adjustment direction and adjustment amount required by the joint module are collectively referred to as the force vector required to be applied by the motor of the joint module. The force vector includes a guiding force or a guiding torque. After the force vector required to move the motor of each joint module acts, the binding force at the end position of the robotic arm is equal to the auxiliary force, that is, after the adjustment direction and adjustment amount of each joint module are moved, the posture presented by the end of the robotic arm is the same as the posture presented by the end of the robotic arm under the auxiliary force.

[0102] In this embodiment, the adjustment direction and adjustment amount of the robot arm are used as inputs of the admittance algorithm in the computer device, and the movement amount of each joint module is calculated according to the admittance algorithm. The admittance algorithm can realize the transformation of the maximum guiding force or the maximum guiding torque to position control, thereby realizing the transformation of the spatial position and posture of the fixed point according to the external force control.

[0103] It should be noted that the input of the admittance algorithm is the force vector of the operator's interaction with the robot arm, not the force vector applied or received by the motor of the joint module of the robot arm. The admittance algorithm is implemented in the admittance controller. Therefore, in this embodiment, the adjustment direction and adjustment amount of the robot arm determined according to the maximum decomposition vector are input to the admittance controller, and the admittance controller outputs the expected movement amount of the end of the robot arm.

[0104] Alternatively, if Fig. 9 As shown, the computer device uses the adjustment direction and adjustment amount of the robot arm as the input of the admittance controller in the computer device. The admittance controller analyzes according to the admittance algorithm and outputs the expected position of the end of the robot arm. The expected position of the end of the robot arm is input to each joint position ring controller, and each joint position ring controller outputs the required adjustment amount of each joint module, that is, the force vector required by the motor of each joint module, and determines the joint torque required for the motor of each joint module to rotate according to the force vector.

[0105] Step 806, controlling the movement of the end of the robotic arm according to the adjustment amount of each joint module until the position of the end of the robotic arm is at the expected position.

[0106] Among them, this embodiment is as follows Figure 3 Take the mechanical structure shown as an example. Figure 3 The mechanical structure shown has the characteristics of an end fixed point. The spatial position adjustment of the fixed point is determined by the six moving joints shown in the figure. The first joint 1, the second joint 2, and the third joint 3 control the spatial position of the fixed point. The fourth joint 4, the fifth joint 5, and the sixth joint 6 control the spatial posture of the fixed point. Figure 3The six-dimensional force sensor A shown in the figure senses the results and controls the six joints separately to realize the adjustment function of the spatial posture of the fixed point.

[0107] Alternatively, if Fig. 9 As shown, the computer device determines the torque required for the motor to rotate according to the adjustment amount of each joint module, that is, the force vector required to be applied by the motor of the joint module. The computer device controls the motor of the joint module to generate the same torque and controls the movement of the end of the robotic arm until the position of the end of the robotic arm is at the expected position.

[0108] In this embodiment, the maximum decomposition vector can be transformed into position control through the admittance algorithm, thereby realizing the transformation of the spatial position and posture of the fixed point according to the external force control, and the end of the robotic arm applies an auxiliary force in the same direction as the maximum decomposition vector and proportional to the magnitude of the external force. According to the auxiliary force, the force vector required by each joint module when the end of the robotic arm reaches the posture under the action of the auxiliary force is determined. Each joint module acts according to the force vector, which can reduce the force required for the operator to drag the robotic arm.

[0109] In one embodiment, the robot arm guide component is Fig.10 The two handles S shown in the figure, the external force sensors are a three-dimensional force sensor B and a three-dimensional torque sensor C, the three-dimensional force sensor B is used to detect the guiding force information acting on the guiding component of the robot arm, and the three-dimensional torque sensor C is used to detect the guiding torque information acting on the guiding component of the robot arm. Fig.10 The two handles in the middle apply external forces on the handles in sequence, that is, at the same time, the external force only acts on Fig.10 As shown in the figure, only the three-dimensional force sensor B or the three-dimensional torque sensor C can collect external force information at the same time.

[0110] like Figure 4 As shown in FIG. 1 , it is a schematic diagram of the installation of the three-dimensional force sensor B and the three-dimensional torque sensor C on the robotic arm. Fig.10 As shown, it is a partial structural diagram of a three-dimensional force sensor B, a three-dimensional torque sensor C and a handle. The three-dimensional force sensor B, which is subjected to greater force during the actual force control process, is installed at a structure with greater rigidity to meet the applied force size for controlling the spatial position of the fixed point during the adjustment process and protect the components from being damaged; the three-dimensional torque sensor C is installed at a structure near the fixed point to meet the operator's operating habits for adjusting the posture of the fixed point, making the adjustment process more intuitive and clear.

[0111] In this embodiment, when the operator manually drags the robot arm, the two motion modes of translation and rotation are superimposed to achieve the purpose of adjusting the posture of the robot arm. Therefore, a three-dimensional force sensor B and a three-dimensional torque sensor C are used in combination to ensure the separate measurement of force and torque. In the displacement stage and the rotation stage, external forces are applied to the handles corresponding to the three-dimensional force sensor B and the three-dimensional torque sensor C in turn to determine the dominant motion direction and the adjustment mode of the corresponding posture adjustment separation structure robot arm. When the external force sensors are the three-dimensional force sensor B and the three-dimensional torque sensor C, Fig.10 The handle structure in the embodiment has two handles S. The handle corresponding to the three-dimensional force sensor B is used to control the translation of the robot arm, and the handle corresponding to the three-dimensional torque sensor C is used to control the rotation of the robot arm. In order to facilitate the control mode recognition of the computer equipment and the precise guidance of the robot arm, when the external force is applied to the guiding component of the robot arm, only the Fig.10 If an external force is applied to one of the handles corresponding to the three-dimensional force sensor B, the external force is used to guide the translation of the robotic arm; if an external force is applied to the handle corresponding to the three-dimensional torque sensor C, the external force is used to guide the rotation of the robotic arm.

[0112] In this embodiment, if the robot arm guide component is Fig.10 In the handle shown in the figure, the external force sensors are a three-dimensional force sensor B and a three-dimensional torque sensor C, and the external force acts on the handle corresponding to the three-dimensional force sensor B. The maximum decomposition vector of each axis in the coordinate system of the three-dimensional force sensor B is the maximum guiding force vector, the direction of the maximum guiding force vector is used as the translation direction of the robot arm, and the modulus value of the maximum guiding force vector is used as the translation distance of the robot arm.

[0113] In this embodiment, if the robot arm guide component is Fig.10 For the handle shown in the figure, the external force sensors are a three-dimensional force sensor B and a three-dimensional torque sensor C, and the external force acts on the handle corresponding to the three-dimensional torque sensor C, then the maximum decomposition vector of each axis decomposed in the coordinate system of the three-dimensional torque sensor C is the maximum guiding torque vector, the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system is taken as the rotation axis, the direction of the maximum guiding torque vector is taken as the rotation direction of the robot arm, and the rotational acceleration of the robot arm is determined according to the modulus value of the maximum guiding torque vector.

[0114] The direction of the maximum guiding torque vector represents that the robot arm rotates in a preset direction under the action of the external force on the handle. The magnitude of the maximum guiding torque vector is equal to the moment of inertia multiplied by the angular acceleration, which further determines the rotational acceleration of the robot arm.

[0115] Alternatively, if Fig.11 As shown, the operator Fig.10An external force is applied to the handle corresponding to the three-dimensional force sensor B shown in the figure. The computer device decomposes the external force information into each axis in the three-dimensional force sensor B coordinate system, determines the maximum guiding force vector of each axis in the three-dimensional force sensor B coordinate system, and translates the robot arm in the direction of the maximum guiding force vector to reach a position with an equal distance from the modulus value of the maximum guiding force vector. The operator Fig.10 An external force is applied to the handle corresponding to the three-dimensional torque sensor C shown, and the computer device decomposes the external force information into each axis in the three-dimensional torque sensor C coordinate system, and determines the maximum guiding torque vector of each axis in the three-dimensional torque sensor C coordinate system. The computer device uses the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system as the rotation axis, and the direction of the maximum guiding torque vector as the rotation direction of the robotic arm. According to the modulus value of the maximum guiding torque vector, the rotation acceleration of the robotic arm is determined, and the end of the robotic arm is rotated according to the rotation acceleration until the robotic arm reaches the expected position.

[0116] In this embodiment, a three-dimensional force sensor B and a three-dimensional torque sensor C are used in combination to ensure separate measurement of force and torque. External forces are applied to the handles corresponding to the three-dimensional force sensor B and the three-dimensional torque sensor C in the displacement stage and the rotation stage respectively, so as to determine the dominant motion direction and the adjustment mode of the corresponding posture adjustment separation structure robot arm, so as to achieve only one guiding force or guiding torque at the same time, thereby ensuring movement or rotation along only one of the X, Y, and Z axes in the displacement mode or the rotation mode.

[0117] In one embodiment, the robot arm guide component is Fig.12 The external force sensor is a six-dimensional force sensor A, which is used to detect the external force acting on the guiding component of the robot arm and output the guiding force information and guiding torque information corresponding to the external force. Figure 3 As shown in FIG. 1 , it is a schematic diagram of the installation of the six-dimensional force sensor A on the robotic arm. Fig.12 As shown in the figure, it is a partial structure diagram of the six-dimensional force sensor A and the handle, where the two ends of the six-dimensional force sensor A are respectively fixed to the mechanical arm component and the handle, realizing equivalent force transmission in the force conduction process. The operator's force application point is the handle position, and the force parameters sensed by the six-dimensional force sensor A are equivalently converted to the handle. The sensed force parameters include the guiding force information and the guiding torque information. According to Fig.13The process shown in FIG. 1 decomposes the external force information into the guiding force in the X direction, the guiding force in the Y direction, the guiding force in the Z direction, the guiding torque in the X direction, the guiding torque in the Y direction, and the guiding torque in the Z direction, determines the maximum guiding force among the guiding force in the X direction, the guiding force in the Y direction, and the guiding torque in the Z direction, and determines the maximum guiding torque among the guiding torque in the X direction, the guiding torque in the Y direction, and the guiding torque in the Z direction, that is, decomposes the maximum decomposition vector of each axis in the A coordinate system of the six-dimensional force sensor, including the maximum guiding force vector and the maximum guiding torque vector, and determines the adjustment direction and adjustment amount of the robot arm according to the direction and size of the maximum decomposition vector, including the following steps:

[0118] Step 1, determine the weight ratio of the maximum guiding force vector and the maximum guiding torque vector.

[0119] The weight ratio of the maximum guiding force vector and the maximum guiding torque vector is obtained through empirical summary.

[0120] Step 2: Determine the ratio of the weighted maximum guiding force vector to the weighted maximum guiding force torque vector according to the weight ratio.

[0121] Among them, the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector is equal to the ratio of the maximum guiding force vector to the maximum guiding torque vector multiplied by the weight ratio of the maximum guiding force vector to the maximum guiding torque vector. If the ratio is greater than 1, the direction of the maximum guiding force vector is used as the translation direction of the manipulator, and the modulus of the maximum guiding force vector is used as the translation distance of the manipulator; if the ratio is less than 1, the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system is used as the rotation axis, and the direction of the maximum guiding torque vector is used as the rotation direction of the manipulator. According to the modulus of the maximum guiding torque vector, the rotation acceleration of the manipulator is determined.

[0122] It should be noted that: Fig.10 and Fig.12 The two handle structures are two independent components, and one of them can be used.

[0123] Optionally, the computer device determines the weight ratio of the maximum guiding force vector and the maximum guiding torque vector, and determines the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector based on the ratio of the maximum guiding force vector and the maximum guiding torque vector and the product of the weight ratio of the maximum guiding force vector and the maximum guiding torque vector. If the ratio is less than 1, the robotic arm is translated in the direction of the maximum guiding force vector to a position at an equal distance from the modulus of the maximum guiding force vector; if the ratio is greater than 1, the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system is used as the rotation axis, and the direction of the maximum guiding torque vector is used as the rotation direction of the robotic arm. According to the modulus of the maximum guiding torque vector, the rotational acceleration of the robotic arm is determined, and the end of the robotic arm is rotated according to the rotational acceleration until the robotic arm reaches the expected position.

[0124] In this embodiment, a six-dimensional force sensor A is used to collect the guiding force and guiding torque in the external force, and the guiding force and guiding torque are decomposed into each axial direction of the six-dimensional force sensor A coordinate system, and the maximum guiding force and the maximum guiding torque in the axial direction of the six-dimensional force sensor A coordinate system are determined. According to the preset maximum guiding force and maximum guiding torque weight ratio, the weighted results of the maximum guiding force and the maximum guiding torque are calculated, and the posture adjustment mode is selected according to the size of the weighted result, and the displacement or rotation axis direction is determined. The operator only needs to apply external force in the expected displacement direction. After the computer device makes a judgment, the robotic arm autonomously applies auxiliary force in the expected direction. When the external force is lower than the threshold, the auxiliary force is canceled and the robotic arm stops moving, thereby realizing a convenient, fast and high-precision initial posture adjustment function.

[0125] In one embodiment, the weight ratio of the maximum guiding force vector and the maximum guiding torque vector of the above-mentioned embodiment is derived through experience summary, and the weight ratio is a fixed value, which causes the computer device to make an error in adjusting the mode during the stage of judging the translation mode and the rotation mode, and the adjustment direction of the end of the robot arm is inconsistent with the operator's intended direction, which increases the position accuracy error of the end of the robot arm. Therefore, in order to solve the above-mentioned problem, in this embodiment, in the process of controlling the movement of the end of the robot arm according to the adjustment amount of each joint module, the movement direction of the end of the robot arm is collected in real time. If an external force opposite to the initial external force is received within a short time after the end of the robot arm starts to move, it is determined that the adjustment mode of the end of the robot arm is wrong, and the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated through the prediction model, and a new adjustment mode is determined according to the new weight ratio. The movement of the end of the robot arm is controlled according to the new adjustment mode, so as to gradually master the operator's guidance adjustment control habits, reduce the misjudgment rate, and improve the guidance adjustment efficiency. Specifically, the following steps are included:

[0126] Step 1. In the process of controlling the movement of the end of the robot arm according to the adjustment amount of each joint module, if the direction of the external force collected is inconsistent with the adjustment direction of the robot arm, the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated, and the step of determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector according to the weight ratio is returned and continued until the direction of the external force collected is consistent with the adjustment direction of the robot arm during the movement of the robot arm.

[0127] Among them, since the adjustment direction of the end of the robot arm is determined according to the initial external force, the initial external force is the external force corresponding to the earliest time applied by the operator to the guide component of the robot arm. Therefore, after the computer equipment determines the adjustment direction of the end of the robot arm according to the initial external force, only after the end of the robot arm moves, can it be known whether the adjustment direction of the end of the robot arm is consistent with the intended direction corresponding to the operator's application of external force. If the adjustment direction of the end of the robot arm is consistent with the intended direction corresponding to the operator's application of external force, the direction of the external force applied by the operator to the guide component of the robot arm remains unchanged until the next adjustment link; if the adjustment direction of the end of the robot arm is inconsistent with the intended direction corresponding to the operator's application of external force, the operator changes the direction of the external force applied to the guide component of the robot arm, drags the end of the robot arm back to the position before movement, and continues to drag the position of the end of the robot arm until the position of the end of the robot arm is in the expected position.

[0128] This embodiment uses a prediction model to update the weight ratio of the maximum guiding force vector and the maximum guiding torque vector. The prediction model uses a supervised machine learning algorithm. The learning process updates the parameters of the weight ratio of the maximum guiding force vector and the maximum guiding torque vector used to determine the motion mode.

[0129] The input layer reference quantity and output layer reference quantity of the prediction model are shown in Table 1:

[0130] Table 1

[0131]

[0132] The training process of the prediction model is as follows Fig.14 As shown in the figure, it is stipulated that during the learning process, after the direction of the maximum guiding force vector is initially determined and moved, if an external force opposite to the direction of the initial external force is received in a short period of time, the movement mode is regarded as a displacement mode, which is correctly a rotation mode. It is manually corrected and recorded as a displacement misjudgment. At this time, the weight of the maximum guiding torque vector is increased and the weight of the maximum guiding force vector is reduced. The same is true for rotation misjudgment, and the result is to increase the weight of the maximum guiding force vector and reduce the weight of the maximum guiding torque vector. The output of the prediction model is a continuously updated weight ratio, which aims to improve the accuracy of the prediction model in judging the weighted size of the maximum guiding force vector and the maximum guiding torque vector, reduce the probability of misjudgment of the movement mode, and make the robot arm's response more in line with the operator's force habits.

[0133] In some embodiments, in order to be suitable for robotic arm control scenarios, this embodiment proposes a variety of adaptive neural network frameworks to build prediction model solutions based on different environmental requirements to be close to actual control requirements, specifically including perceptron models and feedforward neural networks with backpropagation learning.

[0134] The perceptron model is suitable for environments with insufficient computing power. The framework of the perceptron model algorithm is as follows: Fig.15 As shown, the input layer reference quantity of the prediction model is input into the stochastic gradient descent perceptron model, and the perceptron model outputs the maximum decomposition vector of successful classification and the maximum decomposition vector of misclassification. According to the maximum decomposition vector of misclassification, the perceptron model loss function is determined, and the parameters of the perceptron model are updated; according to the maximum decomposition vector of successful classification, the maximum decomposition vector after judgment by the perceptron model is output.

[0135] The feedforward neural network with backpropagation learning is suitable for situations where computing power is sufficient. The framework of the feedforward neural network is as follows: Fig.16 As shown, the input layer reference quantity of the prediction model is input into the feedforward neural network. After the feedforward neural network operation, the predicted maximum decomposition vector is output, and the prediction reference quantity error between the predicted maximum decomposition vector and the actual maximum decomposition vector is calculated. Back propagation is performed according to the prediction reference quantity error and the parameters of the feedforward neural network are updated to obtain a trained feedforward neural network. The trained feedforward neural network outputs the determined maximum decomposition vector.

[0136] Alternatively, if Fig.17 As shown, the computer device obtains the external force information collected by the six-dimensional force sensor A, performs zero-point compensation and gravity compensation and post-filtering processing, performs weighted calculation according to the initial weight ratio, determines whether the motion mode is a displacement mode or a rotation mode, and determines the auxiliary force of the end of the robotic arm according to the inverse kinematics solution of the robotic arm. The movement of the robotic arm is controlled according to the auxiliary force. In the process of controlling the movement of the end of the robotic arm according to the adjustment amount of each joint module, if the direction of the external force collected is inconsistent with the adjustment direction of the robotic arm, it is determined that the motion mode is misjudged, and the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated through the prediction model. The step of determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector according to the weight ratio is returned and continued to be executed to determine the new adjustment direction and adjustment amount of the end of the robotic arm, and control the movement of the robotic arm according to the new adjustment direction and adjustment amount until the direction of the external force collected is consistent with the adjustment direction of the robotic arm during the movement of the robotic arm.

[0137] Step 2: After the direction of the external force is consistent with the adjustment direction of the robotic arm, continue to control the movement of the end of the robotic arm until it reaches the expected position.

[0138] Optionally, after the direction of the external force is consistent with the adjustment direction of the robotic arm, the latest adjustment direction and adjustment amount of the end of the robotic arm are determined, and the robotic arm is controlled to continue moving according to the latest adjustment direction and adjustment amount of the end of the robotic arm until the end position of the robotic arm reaches the expected position.

[0139] In this embodiment, in the process of controlling the movement of the robot arm end according to the adjustment amount of each joint module, the movement direction of the robot arm end is collected in real time. If an external force opposite to the initial external force is received within a short time after the robot arm end starts to move, it is determined that the adjustment mode of the robot arm end is incorrect, and the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated through the prediction model, and a new adjustment mode is determined according to the new weight ratio. The movement of the robot arm end is controlled according to the new adjustment mode, so as to gradually master the operator's guidance adjustment control habits, gradually improve the reaction ability and judgment accuracy during use, reduce the misjudgment rate, and improve the guidance adjustment efficiency.

[0140] In one embodiment, the corresponding reference values ​​for determination at the beginning and end of the robot arm end position control algorithm of this embodiment are shown in Table 2:

[0141] Table 2

[0142] Algorithm determination reference use Guiding force collected by external force sensor Determine the magnitude and direction of the guiding force at the end of the robot arm Guiding torque collected by the external force sensor Determine the magnitude and direction of the guiding torque at the end of the robot arm The sudden change of guiding force or guiding torque Determine the start and end time of a single control Duration of external force input and duration of no external force input Determine entry and exit of adjustment mode

[0143] The schematic diagram of the control adjustment mode start and end determination process of this embodiment is as follows Fig.18 As shown, the external force on the guiding component of the robot arm is obtained. If the duration of the external force does not exceed the response threshold of the computer device, the robot arm stops moving; if the duration of the external force exceeds the response threshold of the computer device, the timing starts from the time when the external force acts on the guiding component of the robot arm. If the duration of the external force reaches the starting threshold, the motion mode of the end of the robot arm and the auxiliary force of the end of the robot arm are determined according to the above embodiment, and the initial position and posture of the end of the robot arm are adjusted according to the auxiliary force.

[0144] In this embodiment, a series of determinations are made based on the maximum decomposition vector obtained after processing, thereby entering or exiting the adjustment mode, thereby realizing the function of making corresponding responses according to changes in external forces.

[0145] In one embodiment, this embodiment provides the most detailed steps of the robot arm guidance method, which specifically includes the following steps:

[0146] Step 1: Collect external force information acting on the guiding component of the robot arm according to the external force sensor; the external force information includes a guiding force for guiding the translation of the robot arm and / or a guiding torque for guiding the rotation of the robot arm.

[0147] Step 2: If the external force sensor is a six-dimensional force sensor A, determine the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes the maximum guiding force vector and the maximum guiding torque vector; if the external force sensor is a three-dimensional force sensor B and a three-dimensional torque sensor C, determine the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector.

[0148] Step 3, determine the type of the maximum decomposition vector. If the maximum decomposition vector is the maximum guiding force vector, execute step 4; if the maximum decomposition vector is the maximum guiding torque vector, execute step 5; if the maximum decomposition vector includes the maximum guiding force vector and the maximum guiding torque vector, execute step 6.

[0149] Step 4, taking the direction of the maximum guiding force vector as the translation direction of the robot arm, taking the modulus of the maximum guiding force vector as the translation distance of the robot arm, and executing step 9.

[0150] Step 5, take the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system as the rotation axis, take the direction of the maximum guiding torque vector as the rotation direction of the robot arm, determine the rotation acceleration of the robot arm according to the modulus of the maximum guiding torque vector, and execute step 9.

[0151] Step 6, determine the weight ratio of the maximum guiding force vector and the maximum guiding torque vector; according to the weight ratio, determine the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector; if the ratio is greater than 1, the direction of the maximum guiding force vector is used as the translation direction of the robot arm, and the modulus of the maximum guiding force vector is used as the translation distance of the robot arm; if the ratio is less than 1, the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system is used as the rotation axis, and the direction of the maximum guiding torque vector is used as the rotation direction of the robot arm, and the rotation acceleration of the robot arm is determined according to the modulus of the maximum guiding torque vector.

[0152] Step 7, determine the required adjustment amount of each joint module of the robot arm according to the initial posture of the end of the robot arm, the adjustment direction and adjustment amount of the end of the robot arm.

[0153] Step 8, according to the adjustment amount of each joint module, control the movement of the end of the robot arm. In the process of controlling the movement of the end of the robot arm according to the adjustment amount of each joint module, if the direction of the external force collected is inconsistent with the adjustment direction of the robot arm, update the weight ratio of the maximum guiding force vector and the maximum guiding torque vector, return to the step of determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector according to the weight ratio and continue to execute until in the process of the movement of the robot arm, the direction of the external force collected is consistent with the adjustment direction of the robot arm; after the direction of the external force is consistent with the adjustment direction of the robot arm, continue to control the movement of the end of the robot arm until it reaches the expected position, and end the adjustment process.

[0154] Step 9, determining the required adjustment amount of each joint module of the robot arm according to the initial posture of the end of the robot arm, the adjustment direction and adjustment amount of the end of the robot arm.

[0155] Step 10, according to the adjustment amount of each joint module, control the movement of the end of the robot arm until the position of the end of the robot arm is at the expected position, and end the adjustment process.

[0156] This embodiment provides two embodiments for collecting external force and two embodiments for controlling the movement of the end of the robot arm, which reduces the difficulty of adjusting the position and posture of the robot arm, simplifies the operation process, reduces the operator training cost, and improves the operability of the force-guided control adjustment function.

[0157] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0158] Based on the same inventive concept, the embodiment of the present application also provides a robot arm guiding device for implementing the robot arm guiding method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more robot arm guiding device embodiments provided below can refer to the limitations on the robot arm guiding method above, and will not be repeated here.

[0159] In one embodiment, Fig.19 As shown, a robot arm guiding device is provided, comprising:

[0160] The acquisition module 100 is used to acquire external force information acting on the guiding component of the robot arm according to the external force sensor; the external force information includes a guiding force for guiding the translation of the robot arm and / or a guiding torque for guiding the rotation of the robot arm;

[0161] A force decomposition module 200 is configured to decompose the external force information into decomposition vectors in each axial direction of the external force sensor coordinate system, and determine the maximum decomposition vector in the axial direction of the external force sensor coordinate system;

[0162] The guiding module 300 is used to adjust the initial posture of the end of the robot arm according to the direction and size of the maximum decomposition vector so that the position of the end of the robot arm is at an expected position.

[0163] In one embodiment, the force decomposition module 200 is also used for: if the external force sensor is a six-dimensional force sensor A, then determining the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes the maximum guiding force vector and the maximum guiding torque vector; if the external force sensor is a three-dimensional force sensor B and a three-dimensional torque sensor C, then determining the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector.

[0164] In one embodiment, the guiding module 300 is further used to: determine the adjustment direction and adjustment amount of the end of the robot arm according to the direction and size of the maximum decomposition vector;

[0165] According to the initial position of the end of the robot arm, the adjustment direction and adjustment amount of the end of the robot arm, determine the adjustment direction and adjustment amount required for each joint module of the robot arm;

[0166] According to the adjustment direction and amount of each joint module, the end of the robot arm is controlled to move until the position of the end of the robot arm is at the expected position.

[0167] In one embodiment, the maximum decomposition vector is the maximum guiding force vector, and the guiding module 300 is further used to: use the direction of the maximum guiding force vector as the translation direction of the robot arm, and use the modulus of the maximum guiding force vector as the translation distance of the end of the robot arm.

[0168] In one embodiment, the maximum decomposition vector is the maximum guiding torque vector, and the guiding module 300 is further used to: use the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system as the rotation axis, use the direction of the maximum guiding torque vector as the rotation direction of the end of the robot arm, and determine the rotational acceleration of the end of the robot arm according to the modulus of the maximum guiding torque vector.

[0169] In one embodiment, the maximum decomposition vector includes a maximum guiding force vector and a maximum guiding moment vector, and the guiding module 300 is further configured to:

[0170] determining a weight ratio of a maximum guiding force vector and a maximum guiding moment vector;

[0171] According to the weight ratio, determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding force moment vector;

[0172] If the ratio is greater than 1, the direction of the maximum guiding force vector is used as the translation direction of the end of the robot arm, and the modulus of the maximum guiding force vector is used as the translation distance of the end of the robot arm;

[0173] If the ratio is less than 1, the coordinate axis of the maximum guiding torque vector in the external force sensor coordinate system is used as the rotation axis, and the direction of the maximum guiding torque vector is used as the rotation direction of the end of the robotic arm. The rotation acceleration of the end of the robotic arm is determined according to the modulus of the maximum guiding torque vector.

[0174] In one embodiment, the guiding module 300 is further used for: in the process of controlling the movement of the end of the robot arm according to the adjustment amount of each joint module, if the direction of the external force collected is inconsistent with the adjustment direction of the robot arm, then the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated, and the step of determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector according to the weight ratio is returned and continued to be executed until the direction of the external force collected is consistent with the adjustment direction of the robot arm during the movement of the robot arm;

[0175] After the direction of the external force is consistent with the adjustment direction of the robotic arm, continue to control the movement of the end of the robotic arm until it reaches the expected position.

[0176] In one embodiment, the guidance module 300 is further used to input the magnitude and direction of the external force into a pre-trained prediction model, and the prediction model outputs the weight ratio of the updated maximum guidance force vector and the maximum guidance torque vector.

[0177] Each module in the above-mentioned robot arm guiding device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules 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 the operations corresponding to each of the above modules.

[0178] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 20As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. 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 input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for guiding a robotic arm is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0179] Those skilled in the art will understand that Fig. 20 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0180] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0181] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0182] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0183] 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, stored data, displayed data, 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 relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0184] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0185] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, 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 specification.

[0186] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A robot arm guiding method, characterized in that: The method comprises: The external force information acting on the guiding component of the robot arm is collected according to the external force sensor; the external force information includes a guiding force for guiding the translation of the robot arm and / or a guiding torque for guiding the rotation of the robot arm; the external force information is obtained after filtering and rationality detection of all initial data collected by the external force sensor; Determine the maximum decomposition vector in the axial direction of the external force sensor coordinate system according to the decomposition vectors in each ...; According to the direction and size of the maximum decomposition vector, the initial posture of the end of the robotic arm is adjusted so that the position of the end of the robotic arm is at the expected position; The step of adjusting the initial posture of the end of the robotic arm according to the direction and size of the maximum decomposition vector so that the end of the robotic arm is at an expected position includes: Determining the adjustment direction and adjustment amount of the end of the robotic arm according to the direction and size of the maximum decomposition vector; According to the initial position and adjustment amount of the end of the robot arm, determine the required adjustment direction and adjustment amount of each joint module of the robot arm; According to the adjustment direction and amount of each joint module, the end of the robot arm is controlled to move until the position of the end of the robot arm is at the expected position.

2. The method according to claim 1, characterized in that Decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system, comprises: If the external force sensor is a six-dimensional force sensor, determine the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes a maximum guiding force vector and a maximum guiding moment vector; If the external force sensor is a three-dimensional force sensor and a three-dimensional torque sensor, the external force information is decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector.

3. The method according to claim 1, characterized in that: The maximum decomposition vector is a maximum guiding force vector, and determining the adjustment direction and adjustment amount of the end of the robot arm according to the direction and magnitude of the maximum decomposition vector includes: The direction of the maximum guiding force vector is used as the translation direction of the end of the robot arm, and the modulus of the maximum guiding force vector is used as the translation distance of the end of the robot arm.

4. The method according to claim 1, characterized in that: The maximum decomposition vector is a maximum guiding torque vector, and determining the adjustment direction and adjustment amount of the end of the robot arm according to the direction and magnitude of the maximum decomposition vector includes: The coordinate axis of the maximum guiding torque vector located in the external force sensor coordinate system is taken as the rotation axis, the direction of the maximum guiding torque vector is taken as the rotation direction of the end of the robot arm, and the rotation acceleration of the end of the robot arm is determined according to the modulus value of the maximum guiding torque vector.

5. The method according to claim 1, characterized in that The maximum decomposition vector includes a maximum guiding force vector and a maximum guiding torque vector, and determining the adjustment direction and adjustment amount of the end of the robot arm according to the direction and magnitude of the maximum decomposition vector includes: Determine a weight ratio of a maximum guiding force vector and a maximum guiding moment vector; Determining, according to the weight ratio, a ratio of the weighted maximum guiding force vector to the weighted maximum guiding force torque vector; If the ratio is greater than 1, the direction of the maximum guiding force vector is used as the translation direction of the end of the robot arm, and the modulus of the maximum guiding force vector is used as the translation distance of the end of the robot arm; If the ratio is less than 1, the coordinate axis of the maximum guiding torque vector located in the external force sensor coordinate system is taken as the rotation axis, and the direction of the maximum guiding torque vector is taken as the rotation direction of the end of the robotic arm. The rotation acceleration of the end of the robotic arm is determined according to the modulus value of the maximum guiding torque vector.

6. The method according to claim 5, characterized in that According to the adjustment direction and adjustment amount of each joint module, the end of the robot arm is controlled to move until the end of the robot arm is at the expected position, including: In the process of controlling the movement of the end of the robot arm according to the adjustment amount of each joint module, if the direction of the external force collected is inconsistent with the adjustment direction of the end of the robot arm, the weight ratio of the maximum guiding force vector and the maximum guiding torque vector is updated, and the step of determining the ratio of the weighted maximum guiding force vector to the weighted maximum guiding torque vector according to the weight ratio is returned and continued to be executed until the direction of the external force collected is consistent with the adjustment direction of the end of the robot arm during the movement of the end of the robot arm; After the direction of the external force is consistent with the adjustment direction of the end of the robotic arm, continue to control the movement of the end of the robotic arm until it reaches the expected position.

7. The method according to claim 6, characterized in that The updating of the weight ratio of the maximum guiding force vector and the maximum guiding moment vector comprises: The magnitude and direction of the external force are input into a pre-trained prediction model, and the prediction model outputs an updated weight ratio of the maximum guiding force vector and the maximum guiding force torque vector.

8. A robot arm guiding device, characterized in that: The device comprises: A collection module, used for collecting external force information acting on the guiding component of the mechanical arm according to the external force sensor; the external force information includes a guiding force for guiding the translation of the mechanical arm and / or a guiding torque for guiding the rotation of the mechanical arm; the external force information is obtained after filtering and rationality detection of all initial data collected by the external force sensor; A force decomposition module, used for decomposing the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, and determining the maximum decomposition vector in the axial direction of the external force sensor coordinate system; A guiding module, used for adjusting the initial posture of the end of the robotic arm according to the direction and size of the maximum decomposition vector, so that the position of the end of the robotic arm is at an expected position; The guidance module is also used to determine the adjustment direction and adjustment amount of the end of the robot arm according to the direction and size of the maximum decomposition vector; determine the required adjustment direction and adjustment amount of each joint module of the robot arm according to the initial posture of the end of the robot arm and the adjustment amount of the end of the robot arm; control the movement of the end of the robot arm according to the adjustment direction and adjustment amount of each joint module until the position of the end of the robot arm is at the expected position.

9. The device according to claim 8, characterized in that The force decomposition module is further used for: if the external force sensor is a six-dimensional force sensor, determining the decomposition of the external force information into decomposition vectors in each axial direction in the external force sensor coordinate system, wherein the maximum decomposition vector in the axial direction of the external force sensor coordinate system includes a maximum guiding force vector and a maximum guiding moment vector; If the external force sensor is a three-dimensional force sensor and a three-dimensional torque sensor, the external force information is decomposed into decomposition vectors in each axial direction in the external force sensor coordinate system, and the maximum decomposition vector in the axial direction of the external force sensor coordinate system is the maximum guiding force vector or the maximum guiding torque vector.

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

Images