WO2024041577A1 - 机器人控制方法、装置、设备和机器人 - Google Patents

机器人控制方法、装置、设备和机器人 Download PDF

Info

Publication number
WO2024041577A1
WO2024041577A1 PCT/CN2023/114507 CN2023114507W WO2024041577A1 WO 2024041577 A1 WO2024041577 A1 WO 2024041577A1 CN 2023114507 W CN2023114507 W CN 2023114507W WO 2024041577 A1 WO2024041577 A1 WO 2024041577A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
conductor
electronic skin
virtual
control signal
Prior art date
Application number
PCT/CN2023/114507
Other languages
English (en)
French (fr)
Inventor
林炯辉
郎需林
刘培超
姜宇
黄睿
Original Assignee
深圳市越疆科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市越疆科技股份有限公司 filed Critical 深圳市越疆科技股份有限公司
Publication of WO2024041577A1 publication Critical patent/WO2024041577A1/zh

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/02—Programme-controlled manipulators characterised by movement of the arms, e.g. cartesian coordinate type
    • B25J9/04—Programme-controlled manipulators characterised by movement of the arms, e.g. cartesian coordinate type by rotating at least one arm, excluding the head movement itself, e.g. cylindrical coordinate type or polar coordinate type
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1602—Programme controls characterised by the control system, structure, architecture
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1602—Programme controls characterised by the control system, structure, architecture
    • B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • This application relates to a robot control method, device, equipment and robot, and belongs to the field of robot control technology.
  • an avoidance control scheme is generally adopted.
  • the robot's mechanical arm is controlled to avoid the human body.
  • the currently used avoidance control schemes are generally based on joint space algorithms, which plan the movements of each joint to control joint movements. This method often focuses on avoidance, which inevitably affects the normal operation of the robot and easily makes the robot unable to Or it may be more difficult to ultimately achieve its operational purpose.
  • the technical problem that this application needs to solve is to solve the problem that the avoidance scheme of the existing robot's joint space-based algorithm inevitably affects the normal operation of the robot and reduces the work efficiency.
  • the first aspect of the embodiment of the present application discloses a robot control method, including:
  • the conductor proximity information is associated with the sensing signal collected by the electronic skin provided on the robot, and the conductor proximity information indicates the degree of proximity of the conductor to the electronic skin;
  • control signal for the robot, where the control signal is generated based on the virtual repulsion field of the electronic skin to instruct the robot to avoid the conductor.
  • the second aspect of the embodiment of the present application discloses a robot control device, including
  • An information receiving module configured to receive conductor proximity information, where the conductor proximity information is associated with the sensing signal collected by the electronic skin provided on the robot, and the conductor proximity information indicates the degree to which the conductor is close to the electronic skin;
  • a repulsive force field establishment module configured to establish a virtual repulsive force field of the electronic skin, where the virtual repulsive force field is established based on the conductor proximity information
  • control signal generation module used to generate a control signal of the robot, the control signal
  • a virtual repulsive force field based on the electronic skin is generated to instruct the robot to avoid the conductor.
  • the third aspect of the embodiment of the present application discloses a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, the above is implemented.
  • Robot control methods Robot control methods.
  • the fourth aspect of the embodiment of the present application discloses a computer-readable storage medium.
  • the computer-readable storage medium stores a computer program.
  • the computer program is executed by a processor, the above-mentioned robot control method is implemented.
  • a fifth aspect of the embodiment of the present application discloses a robot.
  • the robot includes a processor, a terminal and a plurality of articulated arms. At least one articulated arm is provided with an electronic skin.
  • the processor executes a computer program, the above robot control method is implemented.
  • the sixth aspect of the embodiment of the present application discloses a robotic arm.
  • the robotic arm includes a processor, a terminal and a plurality of articulated arms. At least one articulated arm is provided with an electronic skin.
  • the processor executes a computer program, the above-mentioned robot control is realized. method.
  • a seventh aspect of the embodiment of the present application discloses a robot that includes a plurality of articulated arms, at least one articulated arm is provided with an electronic skin, the robot includes an avoidance mode, and in the avoidance mode, the articulated arm is configured to Avoidance of conductors approaching the electronic skin under direction of a control signal configured to be generated based at least in part on a virtual repulsion field of the electronic skin.
  • a virtual repulsion field of the electronic skin is established based on the conductor proximity information; the resultant end of the robot is determined based on the virtual repulsion field of the electronic skin.
  • Repulsion calculating the synthetic acceleration of the end of the robot according to the current motion information of the end of the robot and the synthetic repulsion, the current motion information indicating the current motion state of the end of the robot; generating according to the synthetic acceleration A control signal of the robot, the control signal instructs the robot to avoid the conductor.
  • the solution in the embodiment of the present application uses the sensing signal of the electronic skin provided on the robot. , transform and generate a virtual repulsion field, and use the virtual repulsion field to plan the robot's avoidance plan, thereby achieving reliable avoidance while also taking into account the original operation purpose of the robot, so that the robot's avoidance plan takes into account both avoidance and operation purposes.
  • the implementation reflects the intelligence of the avoidance plan.
  • the robot control method of the present application can also ensure that the position and posture of the end are controllable, so that the end avoids interference with the conductor and causes damage to the conductor or the robot, and enables its action purpose such as clamping the target object and transporting it to the target location.
  • This robot control method can ensure that the robot can plan the avoidance plan in real time during the operation process based on the constructed virtual repulsion field and the current motion information of the robot, thereby realizing intelligent avoidance during the operation process and realizing intelligent avoidance without affecting the operation.
  • the intelligence of robot control is greatly improved.
  • Figure 1 is a schematic structural diagram of the robot in the robot control method according to the embodiment of the present application.
  • Figure 2 is a flow chart of the robot control method according to the embodiment of the present application.
  • Figure 3 is another flow chart of the robot control method according to the embodiment of the present application.
  • Figure 4 is another flow chart of the robot control method according to the embodiment of the present application.
  • Figure 5 is another flow chart of the robot control method according to the embodiment of the present application.
  • Figure 6 is a schematic diagram of computer equipment in an embodiment of the present application.
  • Figure 7 is a block diagram of a robot according to an embodiment of the present application.
  • Figure 8 is a schematic diagram showing a robot performing an avoidance action according to an embodiment of the present application.
  • Robot 100 base 110, articulated arm 120, articulated arm 130, articulated arm 140, end 150, Electronic skin 21, electronic skin 22, electronic skin 23, electronic skin 24, joint driver 31, joint driver 32, joint driver 33, servo motor 41, servo motor 42, servo motor 43, joint part 51, joint part 52, joint part 53, processor 10.
  • the robot can be a robotic arm, a motion device including a robotic arm, or other intelligent machines that can work semi-autonomously or fully autonomously.
  • the robot can be a robotic arm, a motion device including a robotic arm, or other intelligent machines that can work semi-autonomously or fully autonomously.
  • the robot taking a robotic arm as an example, at least part of the surface of the moving parts of the robot (robot arm) 100, such as the articulated arm, is covered with electronic skin.
  • At least one electronic skin can be provided on the robot 100.
  • At least one electronic skin is provided on each articulated arm.
  • Electronic skins are installed on multiple articulated arms of the robot 100.
  • the robot 100 includes multiple articulated arms such as the articulated arm 120, the articulated arm 130, and the articulated arm 140 in Figure 1.
  • Each articulated arm is equipped with one or more electronic skins.
  • electronic skins 21, 22, 23 and 24 are installed on these articulated arms respectively.
  • These multiple electronic skins include Electrodes 3-a, 3-b, 3-e, 4-b, 4-a, 5-a, etc., according to the robot forward kinematics technology, it can be determined that the area where these electronic skins are located is in the robot 100-based coordinate system.
  • the spatial coordinate p i where i is 1, 2, 3...N, where N is the total number of electronic skins.
  • the electronic skin includes at least one sensing electrode, and the sensing electrode can be attached to the surface of the joint arm (such as the inner surface and/or the outer surface).
  • the robot is further provided with at least one detection circuit board, and each detection circuit board is connected to one or more electronic skins. Further, the detection circuit board is connected to the sensing electrodes in the electronic skin.
  • an external conductor for example, the human body
  • the sensing electrode of the electronic skin and the external conductor form a capacitance, and the capacitance value of the capacitor will change with the distance between the sensing electrode and the external conductor.
  • the oscillation frequency of the oscillation circuit set by the detection circuit changes, and the oscillation frequency is detected by other circuits of the detection circuit, thereby determining the distance between the external conductor and the sensing electrode based on the detected change in oscillation frequency.
  • the distance changes, thereby identifying the proximity between the external conductor and the electrode.
  • the detection circuit board uses the capacitance between the sensing electrode and the external conductor or its change to detect the distance between the sensing electrode and the external conductor or its change to obtain a representation of the distance between the sensing electrode and the external conductor. or its changing electrical signal.
  • a logic control board is also included, and the logic control board It is electrically connected to the detection circuit board to process the electrical signal output by the detection circuit board to output parameter information (conductor proximity information) representing the proximity between the electrode and the external conductor.
  • An embodiment of the present application provides a robot control method.
  • the robot control method can be applied in a processor.
  • the processor can be provided in the robot or in other devices other than the robot.
  • the robot control method in one embodiment of the present application includes:
  • S201 Receive conductor proximity information, the conductor proximity information is associated with the sensing signal collected by the electronic skin provided on the robot, and the conductor proximity information indicates the degree of proximity of the conductor to the electronic skin.
  • the conductor proximity information indicates the degree to which the conductor is close to the electronic skin.
  • the conductor proximity information may include the position of the conductor, the distance between the conductor and the electronic skin, or other information that represents the degree of proximity of the conductor to the electronic skin.
  • the sensing signal may be the capacitance value formed between the sensing electrode and the conductor in the electronic skin.
  • the conductor proximity information is associated with the sensing signal collected by the electronic skin provided on the robot, that is, the conductor proximity information can be obtained by converting the sensing signal.
  • the detection circuit board uses the capacitance between the sensing electrode and the external conductor or its change to detect the distance between the sensing electrode and the external conductor or its change, and obtains a representation of the distance between the electrode and the external conductor. or its changing electrical signal.
  • a logic control board is also included. The logic control board is electrically connected to the detection circuit board to process the electrical signal output by the detection circuit board to output a signal representing the relationship between the electrode and the detection circuit board. Parameter information about the proximity of external conductors (conductor proximity information), the processor then receives the conductor proximity information sent by the logic control board.
  • the robot 100 includes multiple articulated arms such as the articulated arm 120 , the articulated arm 130 , and the articulated arm 140 in FIG. 1 .
  • Each articulated arm is equipped with one or more electronic skins.
  • electronic skins 21, 22, 23 and 24 are installed on these articulated arms respectively.
  • These multiple electronic skins include Electrodes 3-a, 3-b, 3-e, 4-b, 4-a, 5-a, etc., according to the robot forward kinematics technology, it can be determined that the area where these electronic skins are located is in the robot 100-based coordinate system.
  • each electronic skin can generate a corresponding spatial coordinate p i , and its spatial coordinate p i changes with the current action of the robot 100 and the position of its joints.
  • the real-time corresponding spatial coordinate p i of each electronic skin is its position parameter. It is understood that the position of any point in the electronic skin can be used as its spatial coordinate, for example, the midpoint (diagonal intersection) of the electronic skin, the position of any electrode in the electronic skin, or any endpoint of the electronic skin, etc.
  • S202 Establish a virtual repulsive field of the electronic skin, the virtual repulsive field is established based on the conductor proximity information.
  • the virtual repulsion field is a virtual force field established based on factors such as the proximity and direction of the conductor and the corresponding electronic skin, which can be used to guide subsequent avoidance actions of the robot.
  • the virtual repulsive force field may include factors such as the magnitude and direction of the repulsive force.
  • the conductor proximity information includes the distance d between the conductor and the electronic skin and the position information (spatial coordinates) p ob of the conductor; the virtual repulsion field can be determined by the following formula:
  • d can be determined through the capacitance calculation formula, and then through the sensing direction of the electrode in the electronic skin, the position information (space coordinate) p ob of the conductor can be located and determined.
  • the maximum distance between the conductor and the corresponding electronic skin that will generate capacitance can be determined as d max .
  • d max can also be an empirical value.
  • S203 Generate a control signal for the robot, where the control signal is generated based on the virtual repulsion field of the electronic skin to instruct the robot to avoid the conductor.
  • a control signal instructs the robot to avoid the conductor. Further, the control signal is sent to the servo motor of the robot, and the servo drives the robot to a designated position (ie, the position indicated by the control signal).
  • the control signal may be an angle value of each joint that reflects the position where the end of the robot needs to move.
  • the control signal is generated according to the virtual repulsive field of the electronic skin. Specifically, it can be determined by After determining the virtual repulsion field of the electronic skin, the robot's avoidance route/position/speed, etc. is determined based on the virtual repulsion field of the electronic skin on the joint arm. An avoidance route/position is determined based on factors such as the size and direction of the repulsion force in the virtual repulsion field. Move the robot away from approaching conductors, or move the articulated arm on the robot away from approaching conductors.
  • the robot control method in the embodiment of the present application establishes a virtual repulsion field of the electronic skin based on the conductor proximity information after receiving the conductor proximity information; generates a control signal for the robot based on the virtual repulsion field, and the control signal indicates The robot avoids the conductor.
  • the solution in the embodiment of the present application uses the sensing signal of the electronic skin provided on the robot.
  • This robot control method can ensure that the robot can plan the avoidance plan in real time during the operation process based on the constructed virtual repulsion field and the current motion information of the robot, thereby realizing intelligent avoidance during the operation process and realizing intelligent avoidance without affecting the operation.
  • the intelligence of robot control is greatly improved.
  • generating a control signal for the robot based on the virtual repulsive field of the electronic skin includes:
  • S301 Determine the synthetic repulsion of the end of the robot, and the synthetic repulsion of the end is determined based on the virtual repulsion field of the electronic skin.
  • the resultant repulsive force at the end of the robot is determined by the virtual repulsive force field of each electronic skin.
  • determining the resultant repulsion of the end of the robot may include:
  • S401 Convert the virtual repulsive field of the electronic skin into joint moments of each joint of the robot;
  • S402 Determine the combined repulsive force at the end of the robot, where the combined repulsive force is determined based on the joint moments of each joint of the robot.
  • the joint moment ⁇ j of each joint can be determined by the following formula:
  • ⁇ j is the joint moment of joint j in the robot.
  • the robot 100 includes a total of 6 joints, so the value of j can be 1, 2, 3, 4, 5, and 6. is the transpose of the Jacobian matrix of joint j, and f i is the virtual repulsion field of electronic skin i. Since multiple electronic skins can be installed on the robot, the joint torque of a joint is the virtual repulsion field corresponding to all electronic skins on the robot. It is obtained after Jacobian matrix conversion and then synthesis. From the above formula, it can be seen that the Jacobian matrix is first performed on the virtual repulsion field fi of each electronic skin. Conversion, i.e.
  • N is the number of electronic skins set on the robot. If a robot only installs one electronic skin, only the virtual repulsive field f i of the corresponding electronic skin participates in the Jacobian matrix conversion calculation, and N is 1 at this time.
  • the resultant repulsive force F at the end of the robot can be determined by the following formula:
  • ⁇ is the composite moment formed by the composite vector of the corresponding vectors of the above six joint moments ⁇ j .
  • the joint moment ⁇ j is a vector
  • ⁇ is obtained by synthesizing the vector of each joint moment ⁇ j
  • a vector for example, for a six-joint robot, is the synthesis of vectors of six joint moments.
  • the specific method of synthesis is the existing synthesis algorithm of multiple vectors, which will not be described again here. and is the inverse transposition of the Jacobian matrix of the resultant moments of the above six joints. If there is only one joint, ⁇ is simply the joint moment of that joint.
  • S302 Calculate the synthetic acceleration of the end of the robot.
  • the synthetic acceleration is calculated based on the current motion information of the end of the robot and the synthetic repulsion.
  • the current motion information indicates the current motion state of the end of the robot.
  • the current movement information indicates the current movement state of the end of the robot.
  • the current motion information may include position information of the end of the robot at the current moment (ie, current position information) and current speed.
  • the current position information can be reflected by the coordinates of the end in the robot's base coordinate system.
  • the current movement information includes the current position information, current speed, target position information and target speed of the end of the robot, where the target position information is the movement of the end of the robot in the working state.
  • Information corresponding to the end position, and the target speed is the speed of the end of the robot when it moves to the end position.
  • the robot needs to move the end from the current point A to point B.
  • point B is the target position.
  • the target position information can also be reflected by the coordinates of the end point to which the end needs to move in the robot's base coordinate system.
  • the robot control method can ensure that the robot plans an avoidance plan based on the constructed virtual repulsion field in real time during the operation, and can successfully complete the original operation task while ensuring avoidance.
  • the control method can use the avoidance plan
  • the original operating target original operating target position
  • Intelligent avoidance is realized without affecting the operation, which greatly improves the intelligence of the robot control.
  • the resultant acceleration of the end of the robot It can be determined by the following formula:
  • M, B, and K are positive definite virtual mass, damping, and stiffness matrices respectively, and these parameters are all greater than zero.
  • x is the current position of the end of the robot (can be determined by the Cartesian space point body now), is the current speed
  • x d is the target position of the end of the robot (can be reflected by Cartesian space points)
  • the target speed is 0.
  • S303 Generate a control signal of the robot, where the control signal is generated based on the synthetic acceleration.
  • the synthetic acceleration can be converted into a control signal for the robot to control the robot to avoid the approaching conductor.
  • the control signal instructs the robot to avoid the conductor.
  • the control signal is sent to the servo motor of the robot, and the servo drives the robot to a designated position (ie, the position indicated by the control signal).
  • the control signal may be an angle value of each joint that reflects the position where the end of the robot needs to move.
  • the synthetic repulsion of the end of the robot is first determined based on the virtual repulsion field of the electronic skin; and then the resultant repulsion of the end of the robot is calculated based on the current motion information of the end of the robot and the synthetic repulsion.
  • Synthetic acceleration the current motion information indicates the current motion state of the end of the robot; finally, a control signal of the robot is generated according to the synthetic acceleration.
  • the virtual repulsive force field and current motion information are comprehensively considered to generate the robot's control signal to more accurately instruct the robot to avoid.
  • generating a control signal of the robot based on the synthetic acceleration includes:
  • S501 Calculate the position of the end of the robot at the next moment.
  • the position of the end of the robot at the next moment is obtained by integrating the synthetic acceleration twice;
  • S502 Calculate the position of the end of the robot at the next moment.
  • the position of the end of the robot at the next moment is obtained by integrating the synthetic acceleration twice;
  • Cartesian position X of the end of the robot 100 at the next moment of production can be achieved by integrating the resultant acceleration twice through the following formula:
  • T is the control period of the controller of the robot 100 .
  • the angle value q j corresponding to each joint in the robot is determined according to the Cartesian position X of the end of the robot at the next moment.
  • the robot inverse kinematics algorithm is an algorithm that obtains joint variables (for example, angle values) of each joint of the robot through inverse operations after determining the position of the end of the robot.
  • the robot inverse kinematics algorithm can be implemented using numerical solutions, analytical solutions, or other existing implementation algorithms.
  • the angle values of each joint of the robot are converted into control signals of the robot, and then the control signals are output. For example, send this control signal to a robot's servo motor.
  • each joint is realized by the servo motor installed at the joint, and each A servo motor is connected to a corresponding driver, and the control center of the robot 100 can send the drive signals corresponding to the angle values q j corresponding to each joint to the corresponding driver, and then the driver controls the operation of the corresponding servo motor to control the final rotation of each joint. to the corresponding angle value q j . Since the corresponding angle values q j of the above-mentioned joints are derived based on the Cartesian target position The trajectory of the end is controllable so that it will not interfere with approaching conductors and ensures that the end of the robot 100 ultimately accurately completes its execution purpose.
  • the robot is in a working state. If during the process of controlling the end of the robot to move to the target position, a conductor approaches the electronic skin provided on the robot, then after receiving the relevant signal, the processor An avoidance plan will be planned (steps S201-S203). And repeated sensing and adjustment until the end of the robot moves to the target position, completing a complete motion control, can ensure that the robot can intelligently avoid approaching conductors during operation.
  • sequence number of each step in the above embodiment does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.
  • a robot control device which corresponds to the robot control method in the above embodiment.
  • the robot control device includes an information receiving module, a repulsive force field establishing module, a repulsive force determining module, a synthetic acceleration calculation module and a control signal generating module.
  • the detailed description of each functional module is as follows:
  • An information receiving module configured to receive conductor proximity information, where the conductor proximity information is associated with the sensing signal collected by the electronic skin provided on the robot, and the conductor proximity information indicates the degree to which the conductor is close to the electronic skin;
  • a repulsive field establishing module configured to establish a virtual repulsive field of the electronic skin based on the conductor proximity information
  • a control signal generation module configured to generate a control signal for the robot, where the control signal is generated based on the virtual repulsion field of the electronic skin to instruct the robot to avoid the conductor.
  • control signal generation module includes:
  • a repulsion determination unit configured to determine the resultant repulsion of the end of the robot, where the resultant repulsion of the end is determined based on the virtual repulsion field of the electronic skin;
  • a synthetic acceleration calculation unit used to calculate the synthetic acceleration of the end of the robot, the synthetic acceleration is calculated based on the current motion information of the end of the robot and the synthetic repulsion, the current motion information indicates the end of the robot current motion status;
  • a control signal generating unit configured to generate a control signal of the robot, where the control signal is generated based on the synthetic acceleration.
  • the repulsion determination unit is also used to convert the virtual repulsion field of the electronic skin into the The joint torque of each joint of the robot is determined; the synthetic repulsion force at the end of the robot is determined, and the synthetic repulsion force is determined according to the joint moment of each joint of the robot.
  • control signal generation unit is also used to calculate the position of the end of the robot at the next moment.
  • the position of the end of the robot at the next moment is obtained by double integration of the synthetic acceleration; determine the position of the end of the robot at the next moment.
  • the angle value of each joint of the robot is obtained according to the position of the end of the robot at the next moment through the inverse kinematics algorithm of the robot; convert the angle value of each joint of the robot into the angle value of each joint of the robot. control signal.
  • the current movement information includes the current position information, current speed, target position information and target speed of the end of the robot, where the target position information is the movement of the end of the robot in the working state.
  • Information corresponding to the end position, and the target speed is the speed of the end of the robot when it moves to the end position.
  • the conductor proximity information includes the distance d between the conductor and the electronic skin and the position information p ob of the conductor; the virtual repulsion field of the electronic skin is established, and the repulsion field establishment module is also used to The virtual repulsion field f of the electronic skin is established through the following formula:
  • Each module in the above-mentioned robot control device can be realized in whole or in part by software, hardware and combinations thereof.
  • Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device which includes a processor, a memory, a network interface, and a database connected through a system bus.
  • the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes non-volatile storage media and internal memory.
  • the non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media.
  • the database of the computer device is used to store data used in the above robot control method.
  • the network interface of the computer device is used to communicate with external terminals through a network connection.
  • the computer program implements a robot control method when executed by the processor.
  • a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, it implements the methods described in any of the above embodiments. Robot control methods.
  • a computer-readable storage medium is provided with a computer program stored thereon.
  • the computer program is executed by a processor, the robot described in any of the above embodiments is implemented. Control Method.
  • Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous chain Synchlink DRAM
  • Rambus direct RAM
  • DRAM direct memory bus dynamic RAM
  • RDRAM memory bus dynamic RAM
  • the structure of the robot can be referred to Figure 1.
  • the robot includes a processor, a terminal and a plurality of articulated arms, at least one of which is provided with an electronic skin.
  • One or more electronic skins can be disposed on the surface of one articulated arm. Multiple electronic skins.
  • the robot also includes servo motors and joint drivers.
  • the servo motor is disposed at the joint portion at one end of the articulated arm of the robot 100 to drive the joint portion to rotate.
  • the joint driver is connected to the servo motor and is disposed in the joint part for driving the servo motor to operate as corresponding to the robot 100 in FIG. 1 .
  • It includes multiple joint parts, such as joint part 51 , joint part 52 , and joint part 53 .
  • multiple electronic skins, electronic skin 21, electronic skin 22 and electronic skin 23 in Figure 3 are respectively electrically connected to the processor 10, and the processor 10 is electrically connected to a plurality of joint drivers, namely the joint driver 31, the joint driver 31 and the joint driver 31.
  • the driver 32 and the joint driver 33 each drive a servo motor respectively, which are a servo motor 41, a servo motor 42 and a servo motor 43 respectively.
  • the processor 10 serves as a part of the controller of the robot 100 and is connected to each of the above-mentioned electronic skins and each joint driver.
  • the electronic skin includes:
  • Sensing electrode the sensing electrode can form a capacitance with a nearby external conductor
  • a detection circuit board is electrically connected to the sensing electrode to detect the distance between the sensing electrode and the external conductor or its change using the capacitance between the sensing electrode and the external conductor to obtain the characteristic value. The distance between the sensing electrode and the external conductor or the electrical signal of its change.
  • an electronic skin may include one or more sensing electrodes.
  • the detection circuit board can be connected to one sensing electrode or multiple sensing electrodes. There can be one detection circuit board or multiple detection circuit boards.
  • an external conductor e.g., human body
  • the sensing electrode of the electronic skin and the external conductor form a capacitance.
  • the capacitance value of the capacitor will change with the distance between the sensing electrode and the external conductor, and it will oscillate by detecting the oscillation circuit set on the circuit board.
  • the frequency changes, and the oscillation frequency is detected by other circuits on the circuit board, and the change in the distance between the external conductor and the sensing electrode is determined based on the detected change in oscillation frequency, thereby identifying the difference between the external conductor and the sensing electrode.
  • the detection circuit board uses the capacitance between the sensing electrode and the external conductor or its change to detect the distance between the sensing electrode and the external conductor or its change, and obtains a representation of the distance between the electrode and the external conductor or its change. Changing electrical signals.
  • a logic control board is also included. The logic control board is electrically connected to the detection circuit board to process the electrical signal output by the detection circuit board to output a signal representing the relationship between the electrode and the detection circuit board. Parameter information about the proximity of external conductors (conductor proximity information).
  • the robotic arm includes a processor, a terminal and a plurality of articulated arms. At least one articulated arm is provided with an electronic skin.
  • the processor executes a computer program, it implements any of the above embodiments. Robot control methods.
  • the electronic skin includes:
  • Sensing electrode the sensing electrode can form a capacitance with a nearby external conductor
  • a detection circuit board is electrically connected to the sensing electrode to detect the distance between the sensing electrode and the external conductor or its change using the capacitance between the sensing electrode and the external conductor to obtain the characteristic value. The distance between the sensing electrode and the external conductor or the electrical signal of its change.
  • This application also proposes a robot 100, as shown in Figure 1, including a base 110, a plurality of articulated arms and a terminal 150.
  • the robot 100 is also provided with the electronic skin-based avoidance control device of the robot 100 mentioned in the above embodiment.
  • the servo motor and joint driver are provided at one end of the articulated arm, the electronic skin is provided on the surface of the articulated arm, and a control cabinet of the robot 100 is provided at the base.
  • the control cabinet is provided with a controller of the robot, and a processor 10 is provided in the controller.
  • this application also proposes a robot that includes a plurality of articulated arms, at least one articulated arm is provided with an electronic skin, the robot includes an avoidance mode, and in the avoidance mode, at least one of the articulated arms Configured to avoid conductors approaching the electronic skin as directed by a control signal configured to be generated based at least in part on a virtual repulsive field of the electronic skin.
  • the avoidance mode at least one articulated arm in the robot will avoid the approaching conductor. It can be understood that in the avoidance mode, some of the articulated arms of the robot can avoid the approaching conductor, or all the articulated arms of the robot can avoid the approaching conductor.
  • the articulated arm that avoids the approaching conductor may be an articulated arm provided with an electronic skin, or may be an articulated arm without an electronic skin, or may include both an articulated arm provided with an electronic skin and an articulated arm without an electronic skin.
  • the robot avoids approaching conductors (hands) in avoidance mode. Specifically, the end 150 of the robot is clear of approaching conductors.
  • the control signal is configured to be generated based at least in part on the virtual repulsive field of the electronic skin.
  • the control signal can be a signal inside the robot or a signal sent to the robot by an external device.
  • the method of generating the control signal can be referred to the foregoing embodiments and will not be described again here.
  • the virtual repulsive force field is established based on conductor proximity information, which is associated with sensing signals collected by an electronic skin provided on the robot, and the conductor proximity information indicates that the conductor is close to the electronic skin. Degree.
  • the robot includes an avoidance mode
  • the control signal in the avoidance mode is configured to generate a virtual repulsion field based at least in part on the electronic skin, which can enable the robot to plan the avoidance plan of the robot through the virtual repulsion field, It can ensure that the robot can avoid intelligently.
  • the robot is configured to enter the avoidance mode from the working state after receiving the triggering instruction.
  • the working state means that the robot is working/moving, for example, clamping objects to a designated location, or performing other tasks.
  • the trigger command can be sent to the robot by an external device or generated by an internal trigger of the robot.
  • the triggering instruction can be embodied by a control signal. For example, when receiving or generating a control signal, the robot enters the avoidance mode, or an additional trigger signal can be used to cause the robot to enter the avoidance mode. For example, when receiving conductor approach information After that, a trigger signal is generated to cause the robot to enter the avoidance mode, and then after receiving the control signal, it avoids the conductor.
  • the robot is configured to enter the avoidance mode from a non-working state after receiving a triggering instruction.
  • the non-working state means that the robot is stationary or not performing tasks. For example, when the robot is in a stationary state, a conductor approaches the robot (electronic skin on the robot), which triggers the robot to enter the avoidance mode from a non-working state.
  • the trigger command can be sent to the robot by an external device or generated by an internal trigger of the robot.
  • the triggering instruction can be embodied by a control signal. For example, when receiving or generating a control signal, the robot enters the avoidance mode, or an additional trigger signal can be used to cause the robot to enter the avoidance mode. For example, when receiving conductor approach information After that, a trigger signal is generated to cause the robot to enter the avoidance mode, and then after receiving the control signal, it avoids the conductor.
  • the end of the articulated arm in the avoidance mode, is configured to avoid the conductor approaching the electronic skin and move toward a target position, the target position being the movement of the end in the working state. end position.
  • the robot is currently in working condition. For example, when the supporting object is moving to a key position, the robot enters the avoidance mode. In this avoidance mode, the end of the robot will move towards the approaching conductor while avoiding it.
  • the target position moves to achieve smooth command/task execution while ensuring avoidance of conductors, which better ensures the intelligence of robot control and improves efficiency.
  • control signal is configured to be generated based on a virtual repulsive field of the electronic skin and current motion information of a tip of the robot.
  • specific generation method please refer to the implementation method in any of the above embodiments, and will not be described again here.
  • the current motion information includes the current position information, current speed, target position information and target speed of the end of the robot, where the target position information is the machine The information corresponding to the end position of the movement of the end of the robot in the working state, and the target speed is the speed of the end of the robot when it moves to the end position.
  • first and second are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Therefore, features defined as “first” and “second” may explicitly or implicitly include at least one of these features.
  • “plurality” means at least two, such as two, three, etc., unless otherwise expressly and specifically limited.
  • connection In this application, unless otherwise clearly stated and limited, the terms “installation”, “connection”, “connection”, “fixing” and other terms should be understood in a broad sense. For example, it can be a fixed connection or a detachable connection. , or integrated into one; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be an internal connection between two elements or an interactive relationship between two elements, unless otherwise specified limitations. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.
  • a first feature being “on” or “below” a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediary. touch.
  • the terms “above”, “above” and “above” the first feature is above the second feature may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is higher in level than the second feature.
  • "Below”, “below” and “beneath” the first feature to the second feature may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature has a smaller horizontal height than the second feature.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Manipulator (AREA)

Abstract

本申请涉及一种机器人控制方法、装置、设备、计算机介质和机器人。通过接收导体接近信息之后，建立所述电子皮肤的虚拟斥力场，再生成所述机器人的控制信号。通过设置在机器人上的电子皮肤的感测信号，转化并生成虚拟斥力场，并且通过该虚拟斥力场规划机器人的避让方案，以此实现了在可靠的避让的同时，还兼顾机器人原有的运行目的，使得机器人的避让方案兼顾避让和运行目的的实现，体现了避让方案的智能化。

Description

机器人控制方法、装置、设备和机器人
本申请要求2022年8月23日向中国国家知识产权局递交的申请号为202211014994.3的在先申请的优先权。
技术领域
本申请涉及一种机器人控制方法、装置、设备和机器人，属于机器人控制技术领域。
背景技术
目前机器人运行过程中，为避免与接近的外界导体如人体干涉并对其造成伤害，一般采用避让控制方案，在检测到人体接近时控制机器人的机械臂避开人体。目前采用的避让控制方案一般基于关节空间的算法，其针对每个关节的动作进行规划以控制关节动作，此种方法往往偏重于避让，而不可避免地影响了机器人正常的运行，容易使得机器人无法或者较难最终实现其运行目的。
技术解决方案
本申请需要解决的技术问题是解决现有的机器人的基于关节空间的算法的避让方案不可避免地影响了机器人正常的运行，降低了工作效率的问题。
本申请实施例第一方面公开一种机器人控制方法，包括：
接收导体接近信息，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度；
建立所述电子皮肤的虚拟斥力场，所述虚拟斥力场基于所述导体接近信息建立；
生成所述机器人的控制信号，所述控制信号为基于所述电子皮肤的虚拟斥力场生成，以指示所述机器人避让所述导体。
本申请实施例第二方面公开一种机器人控制装置，包括
信息接收模块，用于接收导体接近信息，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度；
斥力场建立模块，用于建立所述电子皮肤的虚拟斥力场，所述虚拟斥力场基于所述导体接近信息建立；
控制信号生成模块，用于生成所述机器人的控制信号，所述控制信号 为基于所述电子皮肤的虚拟斥力场生成，以指示所述机器人避让所述导体。
本申请实施例第三方面公开一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述机器人控制方法。
本申请实施例第四方面公开一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述机器人控制方法。
本申请实施例第五方面公开一种机器人，所述机器人包括处理器、末端和多个关节臂，至少一个关节臂上设置有电子皮肤，所述处理器执行计算机程序时实现上述机器人控制方法。
本申请实施例第六方面公开一种机械臂，所述机械臂包括处理器、末端和多个关节臂，至少一个关节臂上设置有电子皮肤，所述处理器执行计算机程序时实现上述机器人控制方法。
本申请实施例第七方面公开一种机器人，包括多个关节臂，至少一个关节臂上设置有电子皮肤，所述机器人包括避让模式，在所述避让模式中，所述关节臂被配置为在控制信号的指示下避让接近所述电子皮肤的导体，所述控制信号被配置为至少部分基于所述电子皮肤的虚拟斥力场生成。
本申请实施例的机器人控制方法中，通过接收导体接近信息之后，根据所述导体接近信息建立所述电子皮肤的虚拟斥力场；根据所述电子皮肤的虚拟斥力场确定所述机器人的末端的合成斥力；根据所述机器人的末端的当前运动信息以及所述合成斥力，计算所述机器人的末端的合成加速度，所述当前运动信息指示所述机器人的末端的当前运动状态；根据所述合成加速度生成所述机器人的控制信号，所述控制信号指示所述机器人避让所述导体。不同于现有技术中的基于关节空间的算法中直接根据各个电子皮肤的避让的斥力来控制各个关节动作来进行避让，本申请实施例中的方案通过设置在机器人上的电子皮肤的感测信号，转化并生成虚拟斥力场，并且通过该虚拟斥力场规划机器人的避让方案，以此实现了在可靠的避让的同时，还兼顾机器人原有的运行目的，使得机器人的避让方案兼顾避让和运行目的的实现，体现了避让方案的智能化。
进一步地，本申请的机器人控制方法还可以保证了末端的位姿可控，使得末端避免与导体发生干涉对导体或者机器人造成伤害，且使得其动作目的如夹爪夹持目标物运输至目标位置的可靠实现。该机器人控制方法可以保证机器人在作业过程中实时根据构建的虚拟斥力场，结合机器人的当前运动信息规划避让方案，从而实现在作业过程中的智能避让，在不影响作业的前提下实现智能避让，大大提高了机器人控制的智能性。
附图说明
图1是本申请实施例的机器人控制方法中机器人的结构示意图；
图2是本申请实施例的机器人控制方法的一流程图；
图3是本申请实施例的机器人控制方法的另一流程图；
图4是本申请实施例的机器人控制方法的另一流程图；
图5是本申请实施例的机器人控制方法的另一流程图；
图6是本申请一实施例中计算机设备的一示意图；
图7是本申请实施例的机器人的框图；
图8为本申请实施例的机器人执行避让动作的演示示意图。
附图标记：
机器人100，底座110，关节臂120，关节臂130，关节臂140，末端150，
电子皮肤21、电子皮肤22、电子皮肤23、电子皮肤24、关节驱动器31，关节驱动器32，关节驱动器33，伺服电机41，伺服电机42，伺服电机43，关节部51，关节部52，关节部53，处理器10。
本申请的实施方式
需要说明的是，在结构或功能不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面根据实例来详细说明本申请。
本申请提出一种机器人控制方法。其中，机器人可以为机械臂、包括有机械臂的运动装置或者其他能够半自主或全自主工作的智能机器等。如图1所示，以机械臂为例，机器人(机械臂)100的运动部件如关节臂的至少部分表面覆盖电子皮肤，机器人100上可以设置至少一个电子皮肤，可选地，在机器人100的每一关节臂上设置至少一个电子皮肤。在机器人100的多个关节臂均安装有电子皮肤，如机器人100包括多个关节臂如图1中的关节臂120、关节臂130、关节臂140。每个关节臂安装了一个或者多个电子皮肤，如图1中在这些关节臂分别贴敷安装了电子皮肤21、电子皮肤22、电子皮肤23和电子皮肤24，这些多个电子皮肤共包含了电极3-a、3-b、3-e、4-b、4-a、5-a等，根据机器人正向运动学技术，可以确定出这些电子皮肤所在的区域在机器人100基坐标系下的空间坐标pi，其中i为1、2、3.....N，这里N为电子皮肤的总数量。电子皮肤中包括至少一个感测电极，感测电极可贴敷安装于关节臂的表面(如内表面和/或外表面)。在一个实施方式中，机器人中还设置有至少一个检测电路板，每一个检测电路板与一个或者多个电子皮肤连接。进一步地，检测电路板与电子皮肤中的感测电极连接。在外界导体(例如，人体)接近机器人的关节臂，即接近对应的电子皮肤时，电子皮肤的感测电极与外界导体构成电容，该电容的电容值会随着感测电极与外界导体的距离发生变化，通过检测电路设置的振荡电路使其振荡的频率发生改变，在通过检测电路的其他电路检测到振荡频率，以此根据检测到的振荡频率的变化确定出外界导体与感测电极之间的距离的变化，从而识别出外界导体与电极的接近程度。检测电路板利用所述感测电极与外界导体之间的电容或其变化检测所述感测电极与外界导体之间的距离或其变化，得到表征所述感测电极与外界导体之间的距离或其变化的电信号。可选地，还包括一逻辑控制板，所述逻辑控制板 与所述检测电路板电连接，以根据所述检测电路板输出的所述电信号进行处理，以输出表征所述电极与所述外界导体接近程度的参数信息(导体接近信息)。
进一步地，本申请实施例中关于电子皮肤的具体实现方式，可以参见由申请人在先提交的专利申请PCT/CN2019/106042，该在先提交的专利申请中关于电子皮肤的技术方案借此完全地引入本专利申请中。
本申请一实施例提出一种机器人控制方法，该机器人控制方法可以应用在一处理器中，该处理器可以设置在机器人中，或者设置在机器人之外的其他装置中。
如图2所示，本申请一实施例中的机器人控制方法包括：
S201：接收导体接近信息，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度。
其中，导体接近信息指示导体接近所述电子皮肤的程度。示例性地，该导体接近信息可以包括导体的位置、导体与电子皮肤的距离或者其他表征导体接近所述电子皮肤的程度的信息。感测信号可以为电子皮肤中感测电极和导体之间形成的电容值。导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，即导体接近信息可以为通过将感测信号转化得到。例如，检测电路板利用所述感测电极与外界导体之间的电容或其变化检测所述感测电极与外界导体之间的距离或其变化，得到表征所述电极与外界导体之间的距离或其变化的电信号。可选地，还包括一逻辑控制板，所述逻辑控制板与所述检测电路板电连接，以根据所述检测电路板输出的所述电信号进行处理，以输出表征所述电极与所述外界导体接近程度的参数信息(导体接近信息)，处理器再接收该逻辑控制板发送的导体接近信息。
如图1所示，在机器人100的多个关节臂均安装有电子皮肤，如机器人100包括多个关节臂如图1中的关节臂120、关节臂130、关节臂140。每个关节臂安装了一个或者多个电子皮肤，如图1中在这些关节臂分别贴敷安装了电子皮肤21、电子皮肤22、电子皮肤23和电子皮肤24，这些多个电子皮肤共包含了电极3-a、3-b、3-e、4-b、4-a、5-a等，根据机器人正向运动学技术，可以确定出这些电子皮肤所在的区域在机器人100基坐标系下的空间坐标pi，其中i为1、2、3.....N，这里N为电子皮肤的总数量。如图1所示，每一个电子皮肤都能生成对应的空间坐标pi，其空间坐标pi随着当前机器人100的动作，其关节的位置发生改变而变化。以此每个电子皮肤实时对应的空间坐标pi即为其位置参数。可以理解地，可以将电子皮肤中的任一点的位置作为其空间坐标，例如，电子皮肤的中点(对角线交点)、电子皮肤中任意一电极的位置或者电子皮肤的任一端点等。
S202：建立所述电子皮肤的虚拟斥力场，所述虚拟斥力场基于所述导体接近信息建立。
其中，虚拟斥力场为根据导体和对应的电子皮肤的接近程度、方向等因素而建立的一个虚拟力场，可以用来指引后续机器人的避让动作。该虚拟斥力场可以包括斥力的大小、方向等因素。在一个具体实施例中，所述导体接近信息包括所述导体与所述电子皮肤的距离d和所述导体的位置信息(空间坐标)pob；该虚拟斥力场可以通过如下公式确定：
其中，η为斥力场系数，η＞0，d＝|pob-pi|，dmax为虚拟斥力场的最大范围，pi为所述电子皮肤i的位置信息，i＝1，2，...，N，N为电子皮肤的数量。具体地，空间坐标pi确定之后，d可以通过电容计算公式确定，再通过电子皮肤中电极的感应方向，即可定位和确定该导体的位置信息(空间坐标)pob。
示例性地，可以将导体与对应的电子皮肤会产生电容的最大距离确定为dmax。或者，dmax也可以为一个经验值，例如，将导体与对应的电子皮肤会产生电容的最大距离做一定的增/减之后确定为dmax。因此，若d＞dmax，则f＝0。因此，虚拟斥力场还可以表示为：
其中，只有d≤dmax时，才确定为外界导体处于接近机器人100的状态，此时才会生成虚拟斥力场f。上述公式中确定虚拟斥力场f的大小，确定虚拟斥力场f的方向。由于每一个电子皮肤的空间坐标pi不同，且不同导体距离电子皮肤的距离d也可能不同，因此通过上述公式最终计算出来的虚拟斥力场f的大小和方向都不同。通过上述构建的虚拟力场计算公式，可以较好地实现将感测信号进行精准转化，更好地保证了后续避让方案的实现。
其中，若机器人中设置的电子皮肤为多个，则只要任一电子皮肤与一个或者多个导体之间的距离小于dmax，都会产生该电子皮肤对应的虚拟斥力场。
S203：生成所述机器人的控制信号，所述控制信号为基于所述电子皮肤的虚拟斥力场生成，以指示所述机器人避让所述导体。
控制信号指示所述机器人避让所述导体。进一步地，将该控制信号发送至机器人的伺服电机，伺服驱动机器人达到指定位置(即该控制信号指示的位置)。可选地，该控制信号可以为体现该机器人末端需要移动的位置的各个关节的角度值。
该控制信号根据所述电子皮肤的虚拟斥力场生成，具体地，可以在确 定电子皮肤地虚拟斥力场之后，根据关节臂上电子皮肤的虚拟斥力场来确定机器人的避让路线/位置/速度等，通过虚拟斥力场中斥力的大小、方向等因素确定一个避让路线/位置，使得机器人远离接近的导体，或者，使得机器人上的关节臂远离接近的导体。
本申请实施例中的机器人控制方法，通过接收导体接近信息之后，根据所述导体接近信息建立所述电子皮肤的虚拟斥力场；根据虚拟斥力场生成所述机器人的控制信号，所述控制信号指示所述机器人避让所述导体。不同于现有技术中的基于关节空间的算法中直接根据各个电子皮肤的避让的斥力来控制各个关节动作来进行避让，本申请实施例中的方案通过设置在机器人上的电子皮肤的感测信号，转化并生成虚拟斥力场，并且通过该虚拟斥力场规划机器人的避让方案，以此实现了在可靠的避让的同时，还维持了末端的位姿不变，使得末端避免与导体发生干涉对导体或者机器人造成伤害，且使得其动作目的如夹爪夹持目标物运输至目标位置的可靠实现。该机器人控制方法可以保证机器人在作业过程中实时根据构建的虚拟斥力场，结合机器人的当前运动信息规划避让方案，从而实现在作业过程中的智能避让，在不影响作业的前提下实现智能避让，大大提高了机器人控制的智能性。
在一个实施例中，如图3所示，所述根据所述电子皮肤的虚拟斥力场生成所述机器人的控制信号，包括：
S301：确定所述机器人的末端的合成斥力，所述末端的合成斥力根据所述电子皮肤的虚拟斥力场确定。
在该步骤中，通过每一电子皮肤的虚拟斥力场来确定机器人的末端的合成斥力。
在一个实施方式中，确定所述机器人的末端的合成斥力可以包括：
S401：将所述电子皮肤的虚拟斥力场转化为所述机器人各个关节的关节力矩；
S402：确定所述机器人的末端的合成斥力，所述合成斥力根据所述机器人各个关节的关节力矩确定。
其中，各个关节的关节力矩τj可以通过如下公式确定：
其中τj为机器人中关节j的关节力矩，以图1中的机器人100为例，该机器人100总共包括6个关节，因此j的取值可以为1、2、3、4、5、6。为关节j的雅可比矩阵转置，fi电子皮肤i的虚拟斥力场，由于机器人上可以设置多个电子皮肤，因此一个关节的关节力矩是由该机器人上的所有电子皮肤对应的虚拟斥力场进行雅可比矩阵转换后再合成得到，从上述的公式可知，首先对其中的每个电子皮肤的虚拟斥力场fi进行雅可比矩阵 转换，即与相乘，然后通过累加公式∑进行累加，其中N为机器人上设置的电子皮肤的数量。如果一个机器人只安装一个电子皮肤，这只有对应的电子皮肤的虚拟斥力场fi参与雅可比矩阵转换计算，此时N为1。
在确定了每一关节的关节力矩之后，所述机器人的末端的合成斥力F可以通过如下公式确定：
其中，τ为上述六个关节力矩τj的对应的矢量的合成矢量而形成的合成力矩，具体而言关节力矩τj为矢量，τ是对每一个关节力矩τj的矢量进行合成后得到的一个矢量，如针对六关节机器人而言，是对六个关节力矩的矢量进行合成，合成的具体方法为现有的多个矢量的合成算法，在此不再赘述。而为上述六个关节的合成力矩的雅可比矩阵逆转置。如果只有一个关节，则τ仅为该关节的关节力矩。
S302：计算所述机器人的末端的合成加速度，所述合成加速度根据所述机器人的末端的当前运动信息以及所述合成斥力计算得到，所述当前运动信息指示所述机器人的末端的当前运动状态。
当前运动信息指示所述机器人的末端的当前运动状态。该当前运动信息可以包括当前时刻机器人的末端的位置信息(即当前位置信息)以及当前速度。该当前位置信息可以通过在机器人基坐标系下的末端的坐标来体现。
可选地，所述当前运动信息包括所述机器人的末端的当前位置信息、当前速度、目标位置信息和目标速度，其中，所述目标位置信息为所述机器人在工作状态下所述末端的移动终点位置对应的信息，所述目标速度为所述机器人的所述末端在移动到终点位置时的速度。例如，在工作状态下，机器人需要将末端从当前的A点移动到B点，此时B点即为目标位置。可以理解地，目标位置信息也可以通过在机器人基坐标系下的末端需要移到到的终点的坐标来体现。在该实施例中，该机器人控制方法可以保证机器人在作业过程中实时根据构建的虚拟斥力场规划避让方案，可以在保证避让的前提下顺利完成原有的作业任务，该控制方法可以在避让方案中考虑原有的作业目标(原有的运行目标位置)，从而实现在作业过程中的智能避让，在不影响作业的前提下实现智能避让，大大提高了机器人控制的智能性。
在一个实施方式中，机器人的末端的合成加速度可以通过如下公式确定：
其中，M、B、K分别为正定虚拟质量、阻尼和刚度矩阵，且这些参数都大于零。x为所述机器人的末端的当前位置(可以通过笛卡尔空间点体 现)，为当前速度，xd为所述机器人的末端的目标位置(可以通过笛卡尔空间点体现)，为目标速度。可以理解地，若此时该机器人的末端处于非工作状态(例如，静止状态)，则对应的目标位置和当前位置是同一位置，目标速度即为0。
S303：生成所述机器人的控制信号，所述控制信号根据所述合成加速度生成。
在得到机器人的末端的合成加速度之后，即可以将该合成加速度转化成对该机器人的控制信号，以控制该机器人对接近的导体进行避让。该控制信号指示所述机器人避让所述导体。进一步地，将该控制信号发送至机器人的伺服电机，伺服驱动机器人达到指定位置(即该控制信号指示的位置)。可选地，该控制信号可以为体现该机器人末端需要移动的位置的各个关节的角度值。
在该实施例中，先根据所述电子皮肤的虚拟斥力场确定所述机器人的末端的合成斥力；再根据所述机器人的末端的当前运动信息以及所述合成斥力，计算所述机器人的末端的合成加速度，所述当前运动信息指示所述机器人的末端的当前运动状态；最后根据所述合成加速度生成所述机器人的控制信号。综合考虑虚拟斥力场和当前运动信息来生成机器人的控制信号，更准确地指示机器人进行避让。
在一个实施方式中，根据所述合成加速度生成所述机器人的控制信号，包括：
S501：计算所述机器人的末端下一时刻的位置，所述机器人的末端下一时刻的位置为对所述合成加速度进行二次积分后得到；
S502：计算所述机器人的末端下一时刻的位置，所述机器人的末端下一时刻的位置为对所述合成加速度进行二次积分后得到；
S503：将所述机器人各个关节的角度值转化为所述机器人的控制信号。
具体地，可以通过以下公式对合成加速度进行两次积分实现生产下一个时刻的机器人100的末端的笛卡尔位置X：
其中，T为机器人100的控制器的控制周期。
进一步地，基于机器人逆运动学算法，根据下一个时刻机器人的末端的笛卡尔位置X来确定机器人中每个关节对应的角度值qj。其中，机器人逆运动学算法为确定机器人末端的位置后，通过逆运算获得机器人各个关节的关节变量(例如，角度值)的算法。可选地，该机器人逆运动学算法可以采用数值解法、解析解法或者其他现有的实现算法来实现。
再将该机器人各个关节的角度值转化为所述机器人的控制信号，而后输出该控制信号。例如，将该控制信号发送至机器人的伺服电机。
因为每一个关节的动作由安装于关节部位的伺服电机运行实现，而每 一个伺服电机连接对应的驱动器，可由机器人100的控制中心将这些每个关节对应的角度值qj对应的驱动信号发送至对应的驱动器，然后驱动器控制对应的伺服电机运行，以控制各个关节最终转动到对应的角度值qj。由于上述的关节的对应的角度值qj是基于末端的笛卡尔目标位置X推导生成的，因此在实现了对接近的导体进行避让的同时，还使得末端的位姿保持不变，以此使得末端的轨迹可控不会发生与接近的导体干涉并确保了机器人100的末端最终准确完成执行目的。
在一个实施例中，在所述机器人运行至下一个时刻的机器人100的末端的笛卡尔位置X之后，还包括如下步骤：
重复执行步骤S201-S203，直至所述机器人的末端移动至目标位置。
在该实施例中，该机器人处于工作状态中，若在控制机器人的末端运行至目标位置的过程中，有导体接近设置在机器人上的电子皮肤，则该处理器在接收到相关的信号之后，会规划避让的方案(步骤S201-S203)。并且重复感测和调整，直至该机器人的末端移动至目标位置，完成一个完整的运动控制，可以保证机器人在运行过程中可以对接近的导体进行智能避让。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在一实施例中，提供一种机器人控制装置，该机器人控制装置与上述实施例中机器人控制方法一一对应。该机器人控制装置包括信息接收模块、斥力场建立模块、斥力确定模块、合成加速度计算模块和控制信号生成模块。各功能模块详细说明如下：
信息接收模块，用于接收导体接近信息，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度；
斥力场建立模块，用于根据所述导体接近信息建立所述电子皮肤的虚拟斥力场；
控制信号生成模块，用于生成所述机器人的控制信号，所述控制信号为基于所述电子皮肤的虚拟斥力场生成，以指示所述机器人避让所述导体。
可选地，所述控制信号生成模块包括：
斥力确定单元，用于确定所述机器人的末端的合成斥力，所述末端的合成斥力根据所述电子皮肤的虚拟斥力场确定；
合成加速度计算单元，用于计算所述机器人的末端的合成加速度，所述合成加速度根据所述机器人的末端的当前运动信息以及所述合成斥力计算得到，所述当前运动信息指示所述机器人的末端的当前运动状态；
控制信号生成单元，用于生成所述机器人的控制信号，所述控制信号根据所述合成加速度生成。
可选地，斥力确定单元还用于将所述电子皮肤的虚拟斥力场转化为所 述机器人各个关节的关节力矩；确定所述机器人的末端的合成斥力，所述合成斥力根据所述机器人各个关节的关节力矩确定。
可选地，控制信号生成单元还用于计算所述机器人的末端下一时刻的位置，所述机器人的末端下一时刻的位置为对所述合成加速度进行二次积分后得到；确定所述机器人各个关节的角度值，所述机器人各个关节的角度值为通过机器人逆运动学算法，根据所述机器人的末端下一时刻的位置得到；将所述机器人各个关节的角度值转化为所述机器人的控制信号。
可选地，所述当前运动信息包括所述机器人的末端的当前位置信息、当前速度、目标位置信息和目标速度，其中，所述目标位置信息为所述机器人在工作状态下所述末端的移动终点位置对应的信息，所述目标速度为所述机器人的所述末端在移动到终点位置时的速度。
可选地，所述导体接近信息包括所述导体与所述电子皮肤的距离d和所述导体的位置信息pob；所述建立所述电子皮肤的虚拟斥力场，斥力场建立模块还用于通过以下公式建立所述电子皮肤的虚拟斥力场f：
其中，η为斥力场系数，η＞0，d＝|pob-pi|，dmax为虚拟斥力场的最大范围，pi为所述电子皮肤i的位置信息，i＝1，2，...，N，N为电子皮肤的数量。
关于机器人控制装置的具体限定可以参见上文中对于机器人控制方法的限定，在此不再赘述。上述机器人控制装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，如图6所示，提供了一种计算机设备，该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储上述机器人控制方法中所使用到的数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种机器人控制方法。
在一个实施例中，提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行计算机程序时实现上述任一实施例中所述的机器人控制方法。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述任一实施例中所述的机器人 控制方法。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
本申请还提出一种机器人，如图7所示，其机器人的结构可参考图1，所述机器人包括处理器、末端和多个关节臂，至少一个关节臂上设置有电子皮肤。其中电子皮肤可以为多个，分别设置于机器人100的多个关节臂的表面，具体可以设置与其内表面或外表面，可与关节臂的表面结合成一体，一个关节臂的表面可以设置一个或者多个电子皮肤。所述处理器执行计算机程序时实现上述任一实施例所述的机器人控制方法。
进一步地，该机器人还包括伺服电机和关节驱动器。伺服电机设置于机器人100的关节臂的一端的关节部，以带动关节部的转动。关节驱动器与伺服电机连接，其设置于关节部内，用于驱动伺服电机运行如对应图1中的机器人100，其包括多个关节部，如关节部51、关节部52、关节部53。如图3所示，多个电子皮肤如图3中年的电子皮肤21、电子皮肤22和电子皮肤23分别电连接处理器10，处理器10电连接多个关节驱动器分别是关节驱动器31、关节驱动器32、关节驱动器33，每个关节驱动器分别对应驱动伺服电机，分别是伺服电机41、伺服电机42、伺服电机43。处理器10做为机器人100的控制器的一部分，与上述各个电子皮肤和各个关节驱动器连接。
在一个实施方式中，所述电子皮肤包括：
感测电极，所述感测电极能够与接近的外界导体构成电容；
检测电路板，与所述感测电极电连接，以利用所述感测电极与外界导体之间的电容或其变化检测所述感测电极与外界导体之间的距离或其变化，得到表征所述感测电极与外界导体之间的距离或其变化的电信号。
可以理解地，一个电子皮肤可以包括一个或者多个感测电极。检测电路板可以与一个感测电极连接，也可以与多个感测电极连接。检测电路板可以为一个，也可以为多个。在外界导体(例如，人体)接近机器人的关节臂， 即接近对应的电子皮肤时，电子皮肤的感测电极与外界导体构成电容，该电容的电容值会随着感测电极与外界导体的距离发生变化，通过检测电路板设置的振荡电路使其振荡的频率发生改变，在通过检测电路板的其他电路检测到振荡频率，以此根据检测到的振荡频率的变化确定出外界导体与感测电极之间的距离的变化，从而识别出外界导体与感测电极的接近程度。检测电路板利用所述感测电极与外界导体之间的电容或其变化检测所述感测电极与外界导体之间的距离或其变化，得到表征所述电极与外界导体之间的距离或其变化的电信号。可选地，还包括一逻辑控制板，所述逻辑控制板与所述检测电路板电连接，以根据所述检测电路板输出的所述电信号进行处理，以输出表征所述电极与所述外界导体接近程度的参数信息(导体接近信息)。
本申请还提出一种机械臂，该机械臂包括处理器、末端和多个关节臂，至少一个关节臂上设置有电子皮肤，所述处理器执行计算机程序时实现上述任一实施例所述的机器人控制方法。
可选地，所述电子皮肤包括：
感测电极，所述感测电极能够与接近的外界导体构成电容；
检测电路板，与所述感测电极电连接，以利用所述感测电极与外界导体之间的电容或其变化检测所述感测电极与外界导体之间的距离或其变化，得到表征所述感测电极与外界导体之间的距离或其变化的电信号。
本申请还提出一种机器人100，如图1所示，包括底座110、多个关节臂和末端150，机器人100还设置了上述实施例中提到的基于电子皮肤的机器人100避让的控制装置，其中伺服电机和关节驱动器设置于关节臂的一端，电子皮肤设置于关节臂的表面，在底座设置有机器人100的控制柜，控制柜设置有机器人的控制器，控制器中设置了处理器10。通过设置该控制装置，使得机器人100在实现了在可靠的避让的同时，还维持了末端的位姿不变，使得末端避免与人体发生干涉对人体造成伤害，且使得其动作目的如夹爪夹持目标物运输至目标位置的可靠实现。
在一个实施例中，本申请还提出一种机器人，包括多个关节臂，至少一个关节臂上设置有电子皮肤，所述机器人包括避让模式，在所述避让模式中，至少一个所述关节臂被配置为在控制信号的指示下避让接近所述电子皮肤的导体，所述控制信号被配置为至少部分基于所述电子皮肤的虚拟斥力场生成。
其中，在避让模式中，该机器人中的至少一个关节臂会避让该接近的导体。可以理解地，在该避让模式中，可以为该机器人中的部分关节臂避让该接近的导体，也可以为该机器人的全部关节臂避让该接近的导体。避让该接近的导体的关节臂可以为设置有电子皮肤的关节臂，也可以为没有设置有电子皮肤的关节臂，也可以同时包括设置有电子皮肤的关节臂和没有设置有电子皮肤的关节臂。如图8所示，该机器人在避让模式下，避让接近的导体(手部)。具体地，该机器人的末端150避让接近的导体。
控制信号被配置为至少部分基于所述电子皮肤的虚拟斥力场生成。该控 制信号可以为机器人内部的信号，也可以为外部装置发送至机器人的信号。该控制信号的生成方式可以参见前述实施例，在此不再赘述。
在一个实施例中，所述虚拟斥力场根据导体接近信息建立，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度。
在本实施例中，该机器人包括避让模式，该避让模式中的控制信号被配置为至少部分基于所述电子皮肤的虚拟斥力场生成，可以使得该机器人通过该虚拟斥力场规划机器人的避让方案，可以保证机器人进行智能避让。
在一个实施方式中，所述机器人被配置为在接收到触发指令之后，从工作状态进入所述避让模式。其中，工作状态是指该机器人处于工作/运动中，例如，夹持物件到指定位置，或者执行其他任务。该触发指令可以为外部装置发送至该机器人，也可以为该机器人内部触发生成。该触发指令可以通过控制信号体现，示例性地，在接收或者生成控制信号时，该机器人即进入避让模式，或者通过一个额外的触发信号，使得机器人进入避让模式，例如，在接收到导体接近信息之后，即生成一个触发信号使得机器人进入避让模式，后续在接收到控制信号之后，在避让所述导体。
在一个实施方式中，所述机器人被配置为在接收到触发指令之后，从非工作状态进入所述避让模式。非工作状态是指该机器人处于静止或者未执行任务的状态。例如，该机器人处于静止状态时，有导体接近该机器人(机器人上的电子皮肤)，即触发该机器人从非工作状态进入所述避让模式。该触发指令可以为外部装置发送至该机器人，也可以为该机器人内部触发生成。该触发指令可以通过控制信号体现，示例性地，在接收或者生成控制信号时，该机器人即进入避让模式，或者通过一个额外的触发信号，使得机器人进入避让模式，例如，在接收到导体接近信息之后，即生成一个触发信号使得机器人进入避让模式，后续在接收到控制信号之后，在避让所述导体。
在一个实施方式中，在所述避让模式中，所述关节臂的末端被配置为避让接近所述电子皮肤的导体且向目标位置移动，所述目标位置为在工作状态下所述末端的移动终点位置。
该机器人此时正处于工作状态中，例如，加持物件往重点位置移动的过程中，此时，机器人进入避让模式，在该避让模式中，该机器人的末端会在避让接近的导体的过程中向目标位置移动，从而在保证避让导体的前提下实现顺利的命令/任务执行，更好地保证了机器人控制的智能性，提高效率。
在一个实施例中，所述控制信号被配置为基于所述电子皮肤的虚拟斥力场和所述机器人的末端的当前运动信息生成。具体生成方式可参见上述任一实施例中的实现方式，在此不再赘述。
可选地，所述当前运动信息包括所述机器人的末端的当前位置信息、当前速度、目标位置信息和目标速度，其中，所述目标位置信息为所述机 器人在工作状态下所述末端的移动终点位置对应的信息，所述目标速度为所述机器人的所述末端在移动到终点位置时的速度。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本申请的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
在本申请的描述中，需要理解的是，术语“中心”、“纵向”、“横向”、“长度”、“宽度”、“厚度”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”“内”、“外”、“顺时针”、“逆时针”、“轴向”、“径向”、“周向”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本申请的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
在本申请中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”、“固定”等术语应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或成一体；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通或两个元件的相互作用关系，除非另有明确的限定。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本申请中的具体含义。
在本申请中，除非另有明确的规定和限定，第一特征在第二特征“上”或“下”可以是第一和第二特征直接接触，或第一和第二特征通过中间媒介间接接触。而且，第一特征在第二特征“之上”、“上方”和“上面”可是第一特征在第二特征正上方或斜上方，或仅仅表示第一特征水平高度高于第二特征。第一特征在第二特征“之下”、“下方”和“下面”可以是第一特征在第二特征正下方或斜下方，或仅仅表示第一特征水平高度小于第二特征。
尽管上面已经示出和描述了本申请的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本申请的限制，本领域的普通技术人员在本申请的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (19)

  1. 一种机器人控制方法，其特征在于，包括：
    接收导体接近信息，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度；
    建立所述电子皮肤的虚拟斥力场，所述虚拟斥力场基于所述导体接近信息建立；
    生成所述机器人的控制信号，所述控制信号为基于所述电子皮肤的虚拟斥力场生成，以指示所述机器人避让所述导体。
  2. 根据权利要求1所述的机器人控制方法，其特征在于，所述生成所述机器人的控制信号，包括：
    确定所述机器人的末端的合成斥力，所述末端的合成斥力根据所述电子皮肤的虚拟斥力场确定；
    计算所述机器人的末端的合成加速度，所述合成加速度根据所述机器人的末端的当前运动信息以及所述合成斥力计算得到，所述当前运动信息指示所述机器人的末端的当前运动状态；
    生成所述机器人的控制信号，所述控制信号根据所述合成加速度生成。
  3. 根据权利要求2所述的机器人控制方法，其特征在于，所述确定所述机器人的末端的合成斥力，包括：
    将所述电子皮肤的虚拟斥力场转化为所述机器人各个关节的关节力矩；
    确定所述机器人的末端的合成斥力，所述合成斥力根据所述机器人各个关节的关节力矩确定。
  4. 根据权利要求2所述的机器人控制方法，其特征在于，所述生成所述机器人的控制信号，所述控制信号根据所述合成加速度生成，包括：
    计算所述机器人的末端下一时刻的位置，所述机器人的末端下一时刻的位置为对所述合成加速度进行二次积分后得到；
    确定所述机器人各个关节的角度值，所述机器人各个关节的角度值为通过机器人逆运动学算法，根据所述机器人的末端下一时刻的位置得到；
    将所述机器人各个关节的角度值转化为所述机器人的控制信号。
  5. 根据权利要求2所述的机器人控制方法，其特征在于，所述当前运动信息包括所述机器人的末端的当前位置信息、当前速度、目标位置信息和目标速度，其中，所述目标位置信息为所述机器人在工作状态下所述末 端的移动终点位置对应的信息，所述目标速度为所述机器人的所述末端在移动到终点位置时的速度。
  6. 根据权利要求1所述的机器人控制方法，其特征在于，所述导体接近信息包括所述导体与所述电子皮肤的距离d和所述导体的位置信息pob；所述建立所述电子皮肤的虚拟斥力场，包括：
    通过以下公式建立所述电子皮肤的虚拟斥力场f：
    其中，η为斥力场系数，η＞0，d＝|pob-pi|，dmax为虚拟斥力场的最大范围，pi为所述电子皮肤i的位置信息，i＝1，2，...，N，N为电子皮肤的数量。
  7. 一种机器人控制装置，其特征在于，包括
    信息接收模块，用于接收导体接近信息，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度；
    斥力场建立模块，用于建立所述电子皮肤的虚拟斥力场，所述虚拟斥力场基于所述导体接近信息建立；
    控制信号生成模块，用于生成所述机器人的控制信号，所述控制信号为基于所述电子皮肤的虚拟斥力场生成，以指示所述机器人避让所述导体。
  8. 一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至6任一项所述的机器人控制方法。
  9. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述的机器人控制方法。
  10. 一种机器人，其特征在于，所述机器人包括处理器、末端和多个关节臂，至少一个关节臂上设置有电子皮肤，所述处理器执行计算机程序时实现如权利要求1至6任一项所述的机器人控制方法。
  11. 根据权利要求10所述的机器人，其特征在于，所述电子皮肤包括：
    感测电极，所述感测电极能够与接近的外界导体构成电容；
    检测电路板，与所述感测电极电连接，以利用所述感测电极与外界导体之间的电容或其变化检测所述感测电极与外界导体之间的距离或其变 化，得到表征所述感测电极与外界导体之间的距离或其变化的电信号。
  12. 一种机械臂，其特征在于，所述机械臂包括处理器、末端和多个关节臂，至少一个关节臂上设置有电子皮肤，所述处理器执行计算机程序时实现如权利要求1至6任一项所述的机器人控制方法。
  13. 一种机器人，其特征在于，包括多个关节臂，至少一个关节臂上设置有电子皮肤，所述机器人包括避让模式，在所述避让模式中，至少一个所述关节臂被配置为在控制信号的指示下避让接近所述电子皮肤的导体，所述控制信号被配置为至少部分基于所述电子皮肤的虚拟斥力场生成。
  14. 根据权利要求13所述的机器人，其特征在于，所述虚拟斥力场根据导体接近信息建立，所述导体接近信息与设置在机器人上的电子皮肤采集到的感测信号关联，所述导体接近信息指示导体接近所述电子皮肤的程度。
  15. 根据权利要求13所述的机器人，其特征在于，所述机器人被配置为在接收到触发指令之后，从工作状态进入所述避让模式。
  16. 根据权利要求13所述的机器人，其特征在于，所述机器人被配置为在接收到触发指令之后，从非工作状态进入所述避让模式。
  17. 根据权利要求13所述的机器人，其特征在于，在所述避让模式中，所述关节臂的末端被配置为避让接近所述电子皮肤的导体且向目标位置移动，所述目标位置为在工作状态下所述末端的移动终点位置。
  18. 根据权利要求13所述的机器人，其特征在于，所述控制信号被配置为基于所述电子皮肤的虚拟斥力场和所述机器人的末端的当前运动信息生成。
  19. 根据权利要求18所述的机器人，其特征在于，所述当前运动信息包括所述机器人的末端的当前位置信息、当前速度、目标位置信息和目标速度，其中，所述目标位置信息为所述机器人在工作状态下所述末端的移动终点位置对应的信息，所述目标速度为所述机器人的末端在移动到终点位置时的速度。
PCT/CN2023/114507 2022-08-23 2023-08-23 机器人控制方法、装置、设备和机器人 WO2024041577A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211014994.3A CN115229772B (zh) 2022-08-23 2022-08-23 机器人及其控制方法、装置、设备、存储介质、机械臂
CN202211014994.3 2022-08-23

Publications (1)

Publication Number Publication Date
WO2024041577A1 true WO2024041577A1 (zh) 2024-02-29

Family

ID=83680552

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/114507 WO2024041577A1 (zh) 2022-08-23 2023-08-23 机器人控制方法、装置、设备和机器人

Country Status (2)

Country Link
CN (1) CN115229772B (zh)
WO (1) WO2024041577A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115229772B (zh) * 2022-08-23 2023-07-18 深圳市越疆科技股份有限公司 机器人及其控制方法、装置、设备、存储介质、机械臂

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012011498A (ja) * 2010-06-30 2012-01-19 Toshiba Corp ロボットアーム操作システムおよびその操作方法
CN104317292A (zh) * 2014-09-16 2015-01-28 哈尔滨恒誉名翔科技有限公司 一种复杂形状机器人避碰路径的方法
CN111906778A (zh) * 2020-06-24 2020-11-10 深圳市越疆科技有限公司 基于多重感知的机器人安全控制方法及装置
CN113070881A (zh) * 2021-04-02 2021-07-06 深圳市优必选科技股份有限公司 机器人运动控制方法、装置和机器人
CN113733089A (zh) * 2021-05-27 2021-12-03 深圳市越疆科技有限公司 机械臂控制方法、装置、设备、系统、存储介质及机械臂
CN115229772A (zh) * 2022-08-23 2022-10-25 深圳市越疆科技有限公司 机器人及其控制方法、装置、设备、存储介质、机械臂

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2610443B2 (ja) * 1987-09-09 1997-05-14 富士通株式会社 ロボットの姿勢制御方法
US5502638A (en) * 1992-02-10 1996-03-26 Honda Giken Kogyo Kabushiki Kaisha System for obstacle avoidance path planning for multiple-degree-of-freedom mechanism
US6004016A (en) * 1996-08-06 1999-12-21 Trw Inc. Motion planning and control for systems with multiple mobile objects
JP5173958B2 (ja) * 2009-07-29 2013-04-03 株式会社東芝 移動体姿勢生成方法および移動体姿勢生成装置
KR101664575B1 (ko) * 2014-11-07 2016-10-10 재단법인대구경북과학기술원 모바일 로봇의 장애물 회피 시스템 및 방법
CN105629974B (zh) * 2016-02-04 2018-12-04 重庆大学 一种基于改进型人工势场法的机器人路径规划方法及系统
CN108287469B (zh) * 2017-11-28 2021-02-26 上海师范大学 基于人工势场引力因子的机械臂最优避障控制方法及装置
CN108555911A (zh) * 2018-04-22 2018-09-21 北京工业大学 基于虚拟推力的遥操作机械臂三维避障方法
JP6992719B2 (ja) * 2018-09-27 2022-01-13 オムロン株式会社 制御装置
CN113119096B (zh) * 2019-12-30 2022-10-28 深圳市优必选科技股份有限公司 机械臂空间位置调整方法、装置、机械臂及存储介质
CN112140102A (zh) * 2020-06-08 2020-12-29 深圳市越疆科技有限公司 一种工业机器人的避障方法、装置和系统
CN112008721B (zh) * 2020-08-19 2021-11-19 亿嘉和科技股份有限公司 一种高空带电作业挂线检测方法
KR20220061821A (ko) * 2020-11-06 2022-05-13 삼성전자주식회사 로봇 및 그 제어 방법
CN112507520A (zh) * 2020-11-12 2021-03-16 深圳慧拓无限科技有限公司 一种基于强化学习的路径规划方法及装置
CN114643576B (zh) * 2020-12-17 2023-06-20 中国科学院沈阳自动化研究所 一种基于虚拟力引导的人机协同目标抓取方法
CN112605998A (zh) * 2020-12-21 2021-04-06 深圳市越疆科技有限公司 电子皮肤主模块、子模块、系统、机械臂和机器人
CN112828359B (zh) * 2021-01-27 2022-02-01 华中科技大学 基于势场法多约束的机器人铣削加工姿态规划方法和系统
CN113084811B (zh) * 2021-04-12 2022-12-13 贵州大学 一种机械臂路径规划方法
CN113352331B (zh) * 2021-08-11 2022-04-22 苏州艾利特机器人有限公司 一种机器人与外部对象力协作的方法及协作机器人
CN114564009A (zh) * 2022-01-21 2022-05-31 首都医科大学 一种手术机器人路径规划方法及系统
CN114442628B (zh) * 2022-01-24 2023-12-01 南京工程学院 基于人工势场法的移动机器人路径规划方法、装置及系统
CN114571469B (zh) * 2022-05-05 2022-07-26 北京科技大学 一种机械臂零空间实时避障控制方法及系统
CN114924565A (zh) * 2022-05-26 2022-08-19 华东理工大学 一种焊接机器人路径规划方法、电子设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012011498A (ja) * 2010-06-30 2012-01-19 Toshiba Corp ロボットアーム操作システムおよびその操作方法
CN104317292A (zh) * 2014-09-16 2015-01-28 哈尔滨恒誉名翔科技有限公司 一种复杂形状机器人避碰路径的方法
CN111906778A (zh) * 2020-06-24 2020-11-10 深圳市越疆科技有限公司 基于多重感知的机器人安全控制方法及装置
CN113070881A (zh) * 2021-04-02 2021-07-06 深圳市优必选科技股份有限公司 机器人运动控制方法、装置和机器人
CN113733089A (zh) * 2021-05-27 2021-12-03 深圳市越疆科技有限公司 机械臂控制方法、装置、设备、系统、存储介质及机械臂
CN115229772A (zh) * 2022-08-23 2022-10-25 深圳市越疆科技有限公司 机器人及其控制方法、装置、设备、存储介质、机械臂

Also Published As

Publication number Publication date
CN115229772B (zh) 2023-07-18
CN115229772A (zh) 2022-10-25

Similar Documents

Publication Publication Date Title
US9862090B2 (en) Surrogate: a body-dexterous mobile manipulation robot with a tracked base
WO2022165973A1 (zh) 三维扫描方法、系统、电子装置和计算机设备
WO2024041577A1 (zh) 机器人控制方法、装置、设备和机器人
WO2002085581A2 (en) A hybrid robot motion task level control system
JP2013180380A (ja) 制御装置、制御方法及びロボット装置
CN111515928B (zh) 机械臂运动控制系统
CN109807933B (zh) 一种能力图点云更新方法、装置、设备及存储介质
CN111496798B (zh) 机器人传送带跟踪方法、设备及存储装置
CN113858189A (zh) 机器人的控制方法及机器人系统
JP7263987B2 (ja) 制御装置、制御方法、及び制御プログラム
JP2018167333A (ja) ロボット制御装置、ロボットおよびロボットシステム
CN114800505B (zh) 一种机器人作业控制方法及装置
CN114952838B (zh) 一种基于末端测量反馈的机械臂关节轨迹规划方法
CN116214510A (zh) 一种机械臂导纳控制方法和系统
CN114851207A (zh) 一种双机器人的防碰撞控制方法、系统和多机器人系统
CN112589786A (zh) 机器人与外部轴协同运动的控制方法和装置
JP2737325B2 (ja) ロボットの軌道生成方式
KR101334356B1 (ko) 로봇 제어 장치
Huang et al. CEASE: Collision-Evaluation-based Active Sense System for Collaborative Robotic Arms
CN116330303B (zh) Scara机器人运动控制方法、装置、终端设备及介质
JP2023023193A (ja) 制御システム及び制御方法
EP4241930A1 (en) Robot control in working space
EP4205916A1 (en) Learning device, learning method, learning program, control device, control method, and control program
WO2024045091A1 (zh) 执行机构的运动规划方法、装置、系统及存储介质
CN118061169A (zh) 通过奇异点的机器人控制系统和机器人

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23856665

Country of ref document: EP

Kind code of ref document: A1