WO2022074703A1 - ロボットの衝突検知装置 - Google Patents

ロボットの衝突検知装置 Download PDF

Info

Publication number
WO2022074703A1
WO2022074703A1 PCT/JP2020/037680 JP2020037680W WO2022074703A1 WO 2022074703 A1 WO2022074703 A1 WO 2022074703A1 JP 2020037680 W JP2020037680 W JP 2020037680W WO 2022074703 A1 WO2022074703 A1 WO 2022074703A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
calculation means
torque
drive torque
estimation error
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/JP2020/037680
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
清石 前川
暁生 斎藤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
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 Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to JP2022554978A priority Critical patent/JP7325656B2/ja
Priority to DE112020007659.8T priority patent/DE112020007659T5/de
Priority to PCT/JP2020/037680 priority patent/WO2022074703A1/ja
Priority to CN202080103192.2A priority patent/CN116018244B/zh
Publication of WO2022074703A1 publication Critical patent/WO2022074703A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1628—Program controls characterised by the control loop
    • B25J9/163—Program controls characterised by the control loop learning, adaptive, model based, rule based expert control
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1674—Program controls characterised by safety, monitoring, diagnostic
    • B25J9/1676—Avoiding collision or forbidden zones
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/40—Robotics, robotics mapping to robotics vision
    • G05B2219/40201—Detect contact, collision with human

Definitions

  • the present disclosure relates to a robot collision detection device that detects that a robot collides with an object when the robot collides with an object around the robot.
  • the robot when a robot comes into contact with or collides with a device or a worker around the robot, the robot detects that the robot comes into contact with or collides with the device or the worker and stops the operation, thereby stopping the operation of the device around the robot. Or prevent the operator and the robot itself from being damaged.
  • the robot controller calculates the torque value required to perform the operation performed by the robot, and also calculates the torque based on the actual motor current value or the measured value of the torque sensor provided in the drive mechanism unit. Derive the measured value.
  • the robot controller compares the required torque value with the torque measurement value, and if the difference between the required torque value and the torque measurement value exceeds the threshold value, the robot collides with a device or a worker around the robot. Is determined.
  • a technique for reducing the threshold value as much as possible without causing false detection is required.
  • Patent Document 1 estimates parameters related to the inertial force and frictional force of the robot, and improves the accuracy of torque calculation or estimation required to perform the operation performed by the robot using the estimated parameters. The technology to make it is disclosed. Patent Document 1 also discloses a technique for reducing the influence of factors not modeled by the calculation unit for calculating the required torque by using a high-pass filter.
  • This disclosure has been made in view of the above, considering the effects of unmodeled factors, and when the robot collides with an object around the robot while preventing false positives, the robot becomes an object.
  • the purpose is to obtain a collision detection device for a robot that detects a collision with relatively high sensitivity.
  • the robot collision detection device uses a drive torque calculation means for calculating an estimated value of the drive torque of the robot and a motor current for driving the robot.
  • a torque estimation error model learning means that learns the difference and variation between the drive torque calculated based on the drive torque or the drive torque derived from the torque sensor provided in the drive unit and the estimated value calculated by the drive torque calculation means.
  • Torque estimation error model By the threshold calculation means that calculates the threshold based on the torque estimation error model learned by the learning means, and the drive torque and drive torque calculation means calculated based on the motor current for driving the robot. It has a collision discriminating means for discriminating a collision between a robot and an object by comparing the difference with the calculated estimated value and the threshold value calculated by the threshold calculation means.
  • the robot collision detection device considers the influence of unmodeled factors including its variation, and when the robot collides with an object around the robot while preventing false detection, the robot collides with the object. It has the effect of being able to detect what has been done with relatively high sensitivity.
  • At least a part of the drive torque calculation means, the operating state calculation means, the torque estimation error model learning means, the conversion means, the error calculation means, the threshold calculation means, and the collision determination means included in the collision detection device of the robot according to the first embodiment is a processor.
  • Diagram showing the processor when realized by At least a part of the drive torque calculation means, the operating state calculation means, the torque estimation error model learning means, the conversion means, the error calculation means, the threshold value calculation means, and the collision determination means included in the collision detection device of the robot according to the first embodiment are processed.
  • FIG. 1 is a diagram showing a configuration of a robot collision detection device 1 according to the first embodiment.
  • the collision detection device 1 of the robot may be referred to as a “collision detection device 1”.
  • the collision detection device 1 has a robot control device 2 that controls the robot. No robot is shown in FIG.
  • the robot control device 2 has a drive torque calculation means 3 that receives information indicating a motor position of each axis that drives the robot and calculates an estimated value of the drive torque of the robot.
  • the drive torque calculation means 3 calculates the motor speed and the motor acceleration of each axis by making a difference with respect to the motor position.
  • the drive torque calculation means 3 calculates the drive torque of the robot based on the motor position, the motor speed, the motor acceleration, and the following equation of motion (1) of the robot.
  • ⁇ M (q) a + h (q, v) + g (q) + f (v) ... (1)
  • ⁇ is a vector composed of the drive torque of each axis of the robot
  • q is the motor position of each axis of the robot converted into the output position of the transmission mechanism of each axis of the robot. It is a vector composed of positions.
  • A is a vector composed of the acceleration of each axis of the robot obtained by converting the motor acceleration into the output acceleration of each axis of the robot, and “v” is the output of the motor speed of each axis of the robot. It is a vector composed of the velocities of each axis of the robot converted into velocities.
  • M (q) a is the inertial force of each axis of the robot
  • h (q, v) is the centrifugal Coriolis force
  • g (q) is the gravity
  • f (v) is the frictional force. It is an element of drive torque.
  • the frictional force is the sum of the Coulomb frictional force determined in the direction of velocity and the viscous frictional force determined by the direction and magnitude of the velocity.
  • the simplest model of viscous frictional force is a speed-proportional model, and in the first embodiment, a speed-proportional viscous friction model is adopted.
  • the model of viscous frictional force may be a model of a polynomial of velocity or a model of exponentiation of velocity.
  • the collision detection device 1 further includes an operation state calculation means 4 located outside the robot control device 2.
  • the operation state calculation means 4 calculates a state quantity related to the operation state of the robot. Furthermore, the operating state calculation means 4 calculates a state quantity including all or a part of the information related to the motor speed, the information related to the motor acceleration, and a part of the elements of the driving torque of the robot. do.
  • Some of the elements of the driving torque of the robot are inertial force M (q) a, centrifugal Coriolis force h (q, v), gravity g (q), frictional force f (v), or M (q). ) It is the sum of drive torque elements such as a + h (q, v).
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference for the motor position, calculates the motor speed, and converts the motor speed into the output speed of the transmission mechanism of each axis of the robot. The amount of operating state indicating the speed of each axis of the robot is calculated.
  • the collision detection device 1 further includes a torque estimation error model learning means 5 located outside the robot control device 2.
  • the torque estimation error model learning means 5 determines the difference and variation between the drive torque calculated based on the motor current for driving the robot and the estimated value of the drive torque calculated by the drive torque calculation means 3. learn.
  • the operating state calculation means 4 outputs information indicating the operating state quantity to the torque estimation error model learning means 5.
  • the torque estimation error model learning means 5 learns using the state quantity calculated by the operating state calculation means 4 as an input signal of the correction function.
  • One or both of the operation state calculation means 4 and the torque estimation error model learning means 5 may be located inside the robot control device 2.
  • the robot control device 2 further includes a conversion means 6 that converts the motor current according to the torque constant of the motor and the speed ratio of the transmission mechanism to calculate the measured torque, which is the measured value of the drive torque of each axis of the robot.
  • the collision detection device 1 further includes an error calculation means 7 located outside the robot control device 2.
  • the drive torque calculation means 3 outputs information indicating the estimated torque, which is an estimated value of the drive torque, to the error calculation means 7.
  • the conversion means 6 outputs information indicating the measured torque to the error calculation means 7.
  • the error calculating means 7 calculates the torque estimation error, which is the difference between the measured torque and the estimated torque, by subtracting the estimated torque calculated by the drive torque calculating means 3 from the measured torque obtained by the converting means 6.
  • the error calculation means 7 outputs information indicating the torque estimation error to the torque estimation error model learning means 5.
  • the torque estimation error model learning means 5 receives information indicating an operating state quantity output from the operating state calculating means 4 and information indicating a torque estimation error output from the error calculating means 7 when learning is performed.
  • the torque estimation error model learning means 5 has a learning means 5a that uses a nonparametric method for each axis.
  • the learning means 5a uses Gaussian process regression.
  • the nonparametric learning means 5a may use kernel density estimation or the K-nearest neighbor method.
  • the output of the operating state calculation means 4 is set to x1, x2, ..., Xn, and the measured torque corresponding to xi and the estimated torque calculated by the drive torque calculating means 3
  • y be the difference between.
  • n is an integer of 2 or more
  • i is an integer of 1 or more and n or less.
  • the Gaussian kernel and the Radial Basis Function (RBF) kernel are well known as the kernel function of the Gaussian process regression, and the torque estimation error model learning means 5 adopts the RBF as the kernel function.
  • the torque estimation error model learning means 5 may use a kernel function other than the RBF, for example, an exponential kernel or a periodic kernel.
  • the torque estimation error model learning means 5 obtains a torque estimation error model for calculating the predicted distribution of y * with respect to the new input x * after the learning is completed.
  • the following equation (2) shows an example of a torque estimation error model.
  • x * , D) N (k * TK -1 y, k ** -k * TK -1 k * ) ...
  • the k * of the formula (2) is represented by the following formula (3), and the k ** of the formula (2) is represented by the following formula (4).
  • k * (k (x * , x1), k (x * , x2), ..., k (x * , xn)) T ...
  • k ** k (x * , x * ) ⁇ ⁇ ⁇ (4)
  • k () is a kernel function.
  • K is a matrix called a kernel matrix, and the ij component of the matrix is k (xi, xj).
  • j is an integer of 1 or more and n or less.
  • N (b, ⁇ 2 ) is a probability density function of a Gaussian distribution with mean b and variance ⁇ 2 .
  • the robot control device 2 further includes a threshold value calculation means 8 for receiving information indicating a motor position.
  • the torque estimation error model learning means 5 outputs information indicating the torque estimation error model to the threshold value calculation means 8.
  • the threshold value calculation means 8 calculates a threshold value based on the torque estimation error model learned by the torque estimation error model learning means 5. Specifically, the threshold value calculation means 8 performs the same calculation as the calculation performed by the operation state calculation means 4.
  • the operating state calculation means 4 calculates the motor speed
  • the motor speed is calculated, when the motor acceleration is calculated, the motor acceleration is calculated, and some of the elements of the drive torque, for example, the inertial force M (q) a.
  • the calculation of the inertial force M (q) a is performed.
  • the threshold calculation means 8 calculates the motor speed by making a difference with respect to the motor position, and calculates the speed of each axis of the robot by converting the motor speed into the output speed of the transmission mechanism of each axis of the robot. ..
  • the threshold value calculation means 8 performs the calculation of the equation (2) with the speed of each axis as x * of the equation (2).
  • the robot control device 2 further includes a collision determination means 9.
  • the threshold value calculation means 8 sets the upper limit value and the lower limit value in the range of ⁇ 2 ⁇ as threshold values, and outputs information indicating the threshold value to the collision determination means 9.
  • the calculation may be performed as defined, or a method for reducing the calculation amount of Gaussian process regression such as the auxiliary variable method may be used.
  • the collision determination means 9 determines the difference between the drive torque calculated based on the motor current for driving the robot and the estimated value calculated by the drive torque calculation means 3 and the threshold value calculated by the threshold calculation means 8. By comparing, the presence or absence of a collision between the robot and the object is determined.
  • the drive torque calculation means 3 outputs information indicating the calculated estimated torque to the collision determination means 9.
  • the conversion means 6 outputs information indicating the measured torque to the collision determination means 9.
  • the collision determination means 9 receives the information output from the drive torque calculation means 3, the conversion means 6, and the threshold value calculation means 8.
  • the collision determining means 9 causes a collision between the robot and an object when the difference between the measured torque obtained by the converting means 6 and the estimated torque calculated by the drive torque calculating means 3 is equal to or greater than the upper limit value or equal to or less than the lower limit value. It is determined that it has occurred or has occurred, and the robot is stopped.
  • the robot collision detection device 1 has a difference between a drive torque calculated based on a motor current for driving the robot and an estimated value calculated by the drive torque calculation means 3 and a threshold calculation means. By comparing with the threshold value calculated by 8, the collision between the robot and the object is determined.
  • the threshold value calculation means 8 calculates a threshold value based on the torque estimation error model learned by the torque estimation error model learning means 5. Therefore, the collision detection device 1 of the robot takes into consideration the influence caused by the torque estimation error such as the elasticity or friction non-linearity of the transmission mechanism not modeled by the drive torque calculation means 3 and the variation of the torque estimation error. Can be set. As a result, the robot collision detection device 1 can determine with relatively high sensitivity that the robot has collided with the object when the robot collides with the object while preventing false detection.
  • the collision detection device 1 of the robot uses the operation state calculation means 4 for calculating the state amount related to the operation state of the robot and the state amount calculated by the operation state calculation means 4 as the input signal of the correction function. It has a torque estimation error model learning means 5 for learning, and a threshold calculation means 8 for calculating a threshold based on the torque estimation error model learned by the torque estimation error model learning means 5. Therefore, the collision detection device 1 of the robot has an influence due to a torque estimation error that is not modeled by the drive torque calculation means 3 and has a variation in the torque estimation error because it correlates with the state quantity related to the operation state of the robot. It is possible to set a threshold value in consideration of. As a result, the robot collision detection device 1 considers the influence of unmodeled factors and determines that the robot collides with an object when the robot collides with an object around the robot while preventing false detection. It can be detected with relatively high sensitivity.
  • the operation state calculation means 4 and the threshold value calculation means 8 calculate the speed of each axis obtained by converting the motor speed into the output speed of the transmission mechanism.
  • the collision detection device 1 of the robot may use the motor speed as x1, x2, ..., Xn and x * instead of the speed of each axis converted into the output speed of the transmission mechanism.
  • the collision detection device 1 of the robot does not have the motor speed of each axis, but the norm of the motor speed of each axis, or the norm of the speed of each axis obtained by converting the motor speed into the output speed of the transmission mechanism, x1, x2, ... , Xn and x * may be used.
  • FIG. 2 is a diagram showing a configuration of a robot collision detection device 1A according to a second embodiment.
  • the robot collision detection device 1A has components other than the conversion means 6 among all the components of the robot collision detection device 1 according to the first embodiment.
  • the robot collision detection device 1A has a robot control device 2A having a drive torque calculation means 3, a threshold value calculation means 8, and a collision determination means 9 but not a conversion means 6.
  • the differences from the first embodiment will be mainly described.
  • the measured torque which is the measured value of the drive torque of each axis of the robot, is measured by the torque sensor provided in the drive unit of the robot.
  • the drive unit and the torque sensor are not shown in FIG.
  • the information indicating the measured torque is received by the error calculating means 7 and the collision determining means 9.
  • the drive torque calculation means 3 calculates an estimated value of the drive torque excluding the friction torque of the drive unit and the acceleration / deceleration torque of the motor itself based on the following equation (5).
  • ⁇ ML (q) a + h (q, v) + g (q) ...
  • Equation (5) ML (q) is obtained by removing the inertia of each axis on the motor side from the torque sensor from the inertial matrix of the robot.
  • the above inertia includes the inertia of the motor itself.
  • the torque estimation error model learning means 5 learns the difference between the drive torque measured by the torque sensor and the estimated value of the drive torque calculated by the drive torque calculation means 3, and the variation in the difference.
  • the collision discriminating means 9 compares the difference between the drive torque measured by the torque sensor and the estimated value calculated by the drive torque calculation means 3 and the threshold value calculated by the threshold calculation means 8 between the robot and the object. Determine the collision.
  • the robot collision detection device 1A has the elasticity of the transmission mechanism and the tension from the cable attached to the robot based on the measured torque obtained by the torque sensor that is not affected by the motor and the transmission mechanism. It is possible to set a threshold value in consideration of the influence of the factor of the torque estimation error not modeled by the drive torque calculation means 3 and the variation of the torque estimation error. Therefore, the robot collision detection device 1A considers the influence of unmodeled factors, and while preventing false detection, has relatively high sensitivity that the robot collides with the object when the robot collides with the object. Can be determined.
  • FIG. 1 is also a diagram showing a configuration of a robot collision detection device according to the third embodiment.
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference for the motor position, calculates the motor speed, and then converts the motor speed into the output speed of the transmission mechanism. Is calculated as the operating state quantity.
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference twice with respect to the motor position, calculates the motor acceleration, and then converts the motor acceleration into the output acceleration of the transmission mechanism for each axis. The acceleration of is calculated as the operating state quantity.
  • the threshold value calculation means 8 When the threshold value calculation means 8 receives the information indicating the motor position, the threshold value calculation means 8 performs the same calculation as the calculation performed by the operation state calculation means 4. Specifically, the threshold value calculation means 8 calculates the motor acceleration by making a difference twice with respect to the motor position, and calculates the acceleration of each axis obtained by converting the motor acceleration into the output acceleration of the transmission mechanism. Next, the threshold value calculation means 8 performs the calculation of the equation (2) with the acceleration of each axis derived for each axis as x * of the equation (2). Since the matters other than the above-mentioned matters are the same as those in the first embodiment, the description of the matters other than the above-mentioned matters will be omitted.
  • the robot collision detection device can correct the influence of the torque estimation error of each axis, which has a correlation with the acceleration or the acceleration norm of each axis, with relatively high accuracy.
  • the operation state calculation means 4 and the threshold value calculation means 8 calculate the acceleration of each axis obtained by converting the motor acceleration into the output acceleration of the transmission mechanism.
  • the motor acceleration may be used for the calculation of the equation (2) or the learning by the torque estimation error model learning means 5.
  • the norm of the motor acceleration of each axis or the norm of the acceleration of each axis converted from the motor acceleration to the output acceleration of the transmission mechanism is used as x1, x2, ..., xn and x *. May be good.
  • FIG. 1 is also a diagram showing a configuration of a collision detection device for a robot according to a fourth embodiment.
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference for the motor position, calculates the motor speed, and then converts the motor speed into the output speed of the transmission mechanism. Is calculated as the operating state quantity.
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference for the motor position, calculates the motor speed and the motor acceleration, and then converts the motor speed into the output speed of the transmission mechanism.
  • the speed of the shaft is calculated, the acceleration of each shaft converted from the motor acceleration into the output acceleration of the transmission mechanism is calculated, and the operating state amount ⁇ is calculated based on the following equation (6).
  • the calculated operating state quantity ⁇ is used for learning by the torque estimation error model learning means 5.
  • ⁇ M (q) a + h (q, v) + g (q) ... (6)
  • the threshold value calculation means 8 Upon receiving the information indicating the motor position, the threshold value calculation means 8 calculates the motor speed and the motor acceleration in the same manner as the operation state calculation means 4. The threshold calculation means 8 calculates the speed of each axis in which the motor speed is converted into the output speed of the transmission mechanism and the acceleration of each axis in which the motor acceleration is converted into the output acceleration of the transmission mechanism, and is based on the equation (6). The calculation of the equation (2) is performed with the elements of each axis of the operating state quantity ⁇ calculated in the above as x * of the equation (2). Since the matters other than the above-mentioned matters are the same as those in the first embodiment, the description of the matters other than the above-mentioned matters will be omitted.
  • the robot collision detection device can correct the influence of the drive torque of each axis or the torque estimation error of each axis that correlates with the drive torque with relatively high accuracy.
  • the operating state calculation means 4 uses the sum of the elements M (q) a, h (q, v) and g (q) of the equation (6) as the operating state quantity. Since M (q) a, h (q, v) and g (q) are all part of the drive torque element and do not include the frictional force f (v), M (q) a, h ( The sum of q, v) and g (q) is also an example of some of the drive torque elements. However, the operating state calculation means 4 may use any one of M (q) a, h (q, v) and g (q) as the operating state quantity. In this case as well, it is an example of using a part of the drive torque element.
  • the threshold value calculation means 8 may carry out the calculation of the equation (6), or may use the calculation result of the drive torque calculation means 3. Further, the same as the calculation result of the equation (1) in which the frictional force f (v) is added instead of the sum of the elements M (q) a, h (q, v) and g (q) of the equation (6) is obtained. It may be an operating state quantity. When the same calculation result of the formula (1) is used as the operating state quantity, the threshold value calculation means 8 may perform the calculation of the formula (1) or may use the calculation result of the drive torque calculation means 3. good.
  • FIG. 3 is a diagram showing the configuration of the robot collision detection device 1B according to the fifth embodiment.
  • the robot collision detection device 1B has components other than the drive torque calculation means 3 among all the components of the robot collision detection device 1 according to the first embodiment.
  • the robot collision detection device 1B has a drive torque calculation means 3B instead of the drive torque calculation means 3.
  • the robot collision detection device 1B includes a robot control device 2B having a drive torque calculation means 3B, a conversion means 6, a threshold value calculation means 8, and a collision determination means 9.
  • the robot collision detection device 1B further includes a parameter identification means 10 located outside the robot control device 2B.
  • the parameter identification means 10 may be located inside the robot control device 2B.
  • the differences from the first embodiment will be mainly described.
  • the parameter identification means 10 identifies the value of the parameter of the equation of motion used by the drive torque calculation means 3B based on the pre-measured data. That is, the parameter identification means 10 identifies all or a part of the parameters of the equation of motion of the robot of the equation (1).
  • the parameter identification means 10 identifies all the parameters of the equation of motion of the robot in the equation (1), the calculation result using the parameters themselves such as the mass, the position of the center of gravity and the friction coefficient, or two or more parameters such as the mass ⁇ the position of the center of gravity.
  • the equation (1) is transformed into the following equation (7) by using the vector p composed of the new parameters.
  • the parameter identification means 10 uses the least squares method based on the vector Y p derived based on the position, velocity and acceleration at each time and the drive torque ⁇ when the vector Y p is derived, and the parameter p. Is calculated.
  • the calculated parameter p is used in the calculation performed by the drive torque calculation means 3B using the equation (1). That is, the drive torque calculation means 3B calculates the estimated value of the drive torque using the value of the parameter identified by the parameter identification means 10.
  • ⁇ 0 is defined by the following equation (9).
  • ⁇ 0 M 0 (q) a + h 0 (q, v) + g 0 (q) + f 0 (v) ...
  • the calculated parameter p 1 is used in the calculation performed by the drive torque calculation means 3B using the equation (1).
  • the difference between the drive torque calculation means 3B and the drive torque calculation means 3 is that the drive torque calculation means 3B uses the calculated parameter p or the calculated parameter p1.
  • the robot collision detection device 1B improves the accuracy of the parameter values of the model related to the dynamic characteristics of the robot, prevents false detection, and causes the robot to collide with the object. It is possible to detect a collision with relatively high sensitivity. Furthermore, the robot collision detection device 1B has relatively high sensitivity that the robot collides with the object when the robot collides with the object while preventing false detection even if the above parameter value is unknown. Can be detected.
  • FIG. 4 is a diagram showing the configuration of the robot collision detection device 1C according to the sixth embodiment.
  • the robot collision detection device 1C has components other than the drive torque calculation means 3 among all the components of the robot collision detection device 1 according to the first embodiment.
  • the robot collision detection device 1C has a drive torque calculation means 3C instead of the drive torque calculation means 3.
  • the robot collision detection device 1C further includes an online parameter identification means 11.
  • the robot collision detection device 1C includes a robot control device 2C having a drive torque calculation means 3C, a conversion means 6, a threshold value calculation means 8, a collision determination means 9, and an online parameter identification means 11.
  • the differences from the first embodiment will be mainly described.
  • the online parameter identification means 11 identifies the value of the parameter of the equation of motion used by the drive torque calculation means 3C based on the data during the operation of the robot. For example, the online parameter identification means 11 uses the adaptive identification method to set the values of the parameters of the equation of motion of the equation (1) whose values are unknown and the values of the parameters whose values fluctuate during the operation of the robot. Identified during robot movement. The online parameter identification means 11 identifies all or a part of the parameters of the equation of motion of the robot of the equation (1).
  • ⁇ of the equation (7) in the kth identification cycle is ⁇ [k] and Y p is Y p [k]. ]
  • the identification value of p in the kth identification cycle is p [k]
  • the identification cycle is moit, and the identification is performed based on the following equations (10), (11) and (12).
  • k is an integer of 1 or more and n or less.
  • R [k] R [k-1] + moit * (-k1 * R [k-1] + Y p [k] Y p [k] T ) ...
  • r [k] r [k-1] + moit * (-k1 * r [k-1] + ⁇ [k] * Y p [k]) ...
  • p [k] p [k-1] -mot * G1 ⁇ (R [k] ⁇ p [k-1] -r [k]) ...
  • k1 is a weighting coefficient for adjusting the speed of identification
  • G1 is a gain matrix for adjusting the speed of identification.
  • the online parameter identification means 11 When the online parameter identification means 11 identifies a part of the parameters of the equation of motion of the robot of the equation (1), in the equations (10), (11) and (12), ⁇ is replaced with ⁇ 1 and Y Replace p with Y p1 to identify the parameter p1 instead of p.
  • the online parameter identification means 11 outputs information indicating the identified parameter value to the drive torque calculation means 3C.
  • the drive torque calculation means 3C receives the information output from the online parameter identification means 11 and uses the parameter value indicated by the received information in the calculation of the equation of motion. That is, when the drive torque calculation means 3C calculates the estimated value of the drive torque, the value identified by the online parameter identification means 11 is used.
  • the difference between the drive torque calculation means 3C and the drive torque calculation means 3 is that the drive torque calculation means 3C uses the value identified by the online parameter identification means 11 when calculating the estimated value of the drive torque.
  • the online parameter identification means 11 outputs information indicating the sequentially updated parameter values to the drive torque calculation means 3C.
  • the robot collision detection device 1C determines the accuracy of the value of the parameter of the model related to the dynamic characteristic of the robot even when the value of the parameter related to the dynamic characteristic of the robot fluctuates during the operation of the robot. It is possible to detect that the robot collides with the object with relatively high sensitivity when the robot collides with the object while improving and preventing false detection.
  • FIG. 1 is also a diagram showing a configuration of a robot collision detection device according to the seventh embodiment.
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference for the motor position, calculates the motor speed, and then converts the motor speed into the output speed of the transmission mechanism. Is calculated as the operating state quantity.
  • the operating state calculation means 4 receives information indicating the motor position, performs a difference with respect to the motor position, calculates the motor speed and the motor acceleration, and then converts the motor speed into the output speed of the transmission mechanism. The speed of the shaft and the acceleration of each shaft obtained by converting the motor acceleration into the output acceleration of the transmission mechanism are calculated.
  • the operating state calculation means 4 calculates a vector composed of the velocity of each axis and the acceleration of each axis as the operating state quantity.
  • the input element of the kernel function used by the torque estimation error model learning means 5 and the threshold calculation means 8 is a scalar quantity, but in the seventh embodiment, the element is a vector quantity.
  • the robot collision detection device according to the seventh embodiment can correct the influence of the torque estimation error of each axis, which correlates with both the acceleration and the velocity of each axis, with relatively high accuracy.
  • the vector acceleration may be replaced with a value obtained by multiplying the acceleration of each axis obtained by converting the motor acceleration into the output acceleration of the transmission mechanism by the weighting coefficient.
  • the operating state calculation means 4 may calculate not only the velocity and acceleration of the axis to be learned but also a vector composed of the velocities and accelerations of all the axes as the operating state quantity.
  • the operating state calculation means 4 may calculate a vector composed of the positions of all the axes, the velocities of all the axes, and the result of multiplying the accelerations of all the axes by weights as the operating state quantity.
  • FIG. 5 is a diagram showing the configuration of the robot collision detection device 1D according to the eighth embodiment.
  • the robot collision detection device 1D has components other than the threshold value calculation means 8 among all the components of the robot collision detection device 1 according to the first embodiment.
  • the robot collision detection device 1D has a threshold value calculation means 8D instead of the threshold value calculation means 8.
  • the robot collision detection device 1D includes a robot control device 2D having a drive torque calculation means 3, a conversion means 6, a threshold value calculation means 8D, and a collision determination means 9.
  • the robot collision detection device 1D further includes an approximate function learning means 12 located outside the robot control device 2D.
  • the differences from the first embodiment will be mainly described.
  • the approximate function learning means 12 learns an approximate function based on the torque estimation error model learned by the torque estimation error model learning means 5. Specifically, the approximate function learning means 12 receives the equation (2) for calculating the predicted distribution and the data used for deriving the equation (2). When data is added, the approximation function learning means 12 also receives the output of the operating state calculation means 4. The approximate function learning means 12 combines the functions and parameters built in the equation (2), the data used for learning by the torque estimation error model learning means 5, and the data newly added from the operating state calculation means 4. By using this, an approximate function whose output is the upper limit value and the lower limit value in the range of ⁇ 2 ⁇ of the estimated value of the torque estimation error is acquired by learning.
  • the approximation function is a feedforward type neural network or a recurrent type neural network.
  • the approximate function learning means 12 outputs information indicating the learned approximate function to the threshold value calculation means 8D.
  • the threshold value calculation means 8D calculates the threshold value using the approximation function learned by the approximation function learning means 12. That is, the threshold value calculation means 8D calculates the threshold value using the approximation function derived by the approximation function learning means 12. Specifically, when the threshold calculation means 8D receives the information indicating the motor position, the threshold calculation means 8D performs the same calculation as the operation state calculation means 4, inputs the calculation result into the approximation function obtained from the approximation function learning means 12, and inputs the approximation function. The calculation result in is output to the collision determination means 9 as the + side and-side thresholds.
  • the threshold on the + side is the above-mentioned upper limit value, and the threshold on the-side is the above-mentioned lower limit value. Since the matters other than the above-mentioned matters are the same as those in the first embodiment, the description of the matters other than the above-mentioned matters will be omitted.
  • the robot collision detection device 1D uses an approximate function instead of using the torque estimation error model for the calculation of the threshold value, the amount of calculation of the threshold value can be relatively small, and therefore, the threshold value can be calculated. The calculation can be performed in a relatively short time.
  • FIG. 6 is a diagram showing a configuration of the robot collision detection device 1E according to the ninth embodiment.
  • the robot collision detection device 1E has components other than the torque estimation error model learning means 5 and the threshold value calculation means 8 among all the components of the robot collision detection device 1 according to the first embodiment.
  • the robot collision detection device 1E has a torque estimation error model learning means 5E instead of the torque estimation error model learning means 5, and has a threshold calculation means 8E instead of the threshold calculation means 8.
  • the robot collision detection device 1E further includes a temperature measuring means 13 for measuring the temperature.
  • the temperature measuring means 13 is a temperature sensor attached to an encoder that measures the angle of the motor of each axis of the robot.
  • the robot collision detection device 1E includes a robot control device 2E having a drive torque calculation means 3, a conversion means 6, a threshold value calculation means 8E, a collision determination means 9, and a temperature measuring means 13.
  • a robot control device 2E having a drive torque calculation means 3, a conversion means 6, a threshold value calculation means 8E, a collision determination means 9, and a temperature measuring means 13.
  • the differences from the first embodiment will be mainly described.
  • the temperature measuring means 13 outputs information indicating the measured temperature to the torque estimation error model learning means 5E.
  • the torque estimation error model learning means 5E performs learning using the temperature measured by the temperature measuring means 13.
  • the torque estimation error model learning means 5 uses the speed of each axis of the robot as an input of Gaussian process regression when learning.
  • the torque estimation error model learning means 5E uses a vector composed of the velocity of each axis and the temperature of each axis as an input of Gaussian process regression of each axis of the robot.
  • the torque estimation error model learning means 5E and the torque estimation error are that the torque estimation error model learning means 5E uses a vector composed of the speed of each axis and the temperature of each axis as the input of the Gaussian process regression of each axis of the robot. This is a difference from the model learning means 5.
  • the temperature of each of the above axes may be replaced with a value obtained by multiplying the temperature of each of the above axes by a weighting factor.
  • the temperature measuring means 13 When the robot collision detection device 1E determines whether or not there is a collision between the robot and an object while the robot is operating, the temperature measuring means 13 outputs information indicating the measured temperature to the threshold value calculating means 8E.
  • the threshold value calculation means 8E calculates the threshold value using the temperature measured by the temperature measuring means 13.
  • the input element of the kernel function used by the threshold value calculation means 8 is the velocity of each axis.
  • the threshold value calculation means 8E uses a vector composed of the velocity of each axis and the temperature of each axis.
  • the threshold value calculation means 8E calculates the threshold value using the temperature measured by the temperature measuring means 13.
  • the difference between the threshold value calculation means 8E and the threshold value calculation means 8 is that the threshold value calculation means 8E calculates the threshold value using the temperature measured by the temperature measurement means 13.
  • the threshold calculation means 8E uses the weight coefficient for the speed of each axis and the temperature of each axis. Use a vector composed of the values obtained by multiplying by. Since the matters other than the above-mentioned matters are the same as those in the first embodiment, the description of the matters other than the above-mentioned matters will be omitted.
  • the robot collision detection device 1E can correct the influence of the torque estimation error of each axis, which correlates with the temperature of each axis, with relatively high accuracy, and thus prevents erroneous detection.
  • the robot collides with an object it can be detected with relatively high sensitivity that the robot collides with the object.
  • FIG. 7 shows the drive torque calculation means 3, the operating state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, and the threshold value calculation means included in the collision detection device 1 of the robot according to the first embodiment. It is a figure which shows the processor 71 when at least a part of 8 and the collision determination means 9 is realized by a processor 71. That is, at least a part of the functions of the drive torque calculation means 3, the operation state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, the threshold calculation means 8, and the collision determination means 9 are stored in the memory 72. It may be realized by a processor 71 that executes a program stored in.
  • the processor 71 is a CPU (Central Processing Unit), a processing device, an arithmetic unit, a microprocessor, or a DSP (Digital Signal Processor).
  • FIG. 7 also shows the memory 72.
  • the processor 71 realizes at least a part of the functions of the drive torque calculation means 3, the operation state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, the threshold calculation means 8, and the collision determination means 9. If so, at least some of the functions are realized by the processor 71 and software, firmware, or a combination of software and firmware.
  • the software or firmware is described as a program and stored in the memory 72. By reading and executing the program stored in the memory 72, the processor 71 reads and executes a drive torque calculation means 3, an operating state calculation means 4, a torque estimation error model learning means 5, a conversion means 6, an error calculation means 7, and a threshold calculation. At least a part of the functions of the means 8 and the collision determination means 9 are realized.
  • the robot collision detection device 1 is driven by a drive torque calculation means 3, an operating state calculation means 4, a torque estimation error model learning means 5, a conversion means 6, an error calculation means 7, a threshold calculation means 8, and a collision determination means 9. It has a memory 72 for storing a program for which at least a part of the steps to be executed will be executed as a result.
  • the program stored in the memory 72 is executed by the drive torque calculation means 3, the operation state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, the threshold calculation means 8, and the collision determination means 9. It can also be said to cause a computer to perform at least a part of a procedure or method.
  • the memory 72 is, for example, non-volatile such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (registered trademark) (Electrically Erasable Programmable Read-Only Memory).
  • RAM Random Access Memory
  • ROM Read Only Memory
  • flash memory EPROM (Erasable Programmable Read Only Memory)
  • EEPROM registered trademark
  • it is a volatile semiconductor memory, magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disk), or the like.
  • FIG. 8 shows a drive torque calculation means 3, an operating state calculation means 4, a torque estimation error model learning means 5, a conversion means 6, an error calculation means 7, and a threshold value calculation means included in the collision detection device 1 of the robot according to the first embodiment. It is a figure which shows the processing circuit 81 when at least a part of 8 and a collision discriminating means 9 is realized by a processing circuit 81. That is, at least a part of the drive torque calculation means 3, the operation state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, the threshold value calculation means 8, and the collision determination means 9 is provided by the processing circuit 81. It may be realized.
  • the processing circuit 81 is dedicated hardware.
  • the processing circuit 81 is, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. Is.
  • a part of the drive torque calculation means 3, the operation state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, the threshold calculation means 8, and the collision determination means 9 are dedicated hardware separate from the rest. It may be realized by hardware.
  • the part may be realized by software or firmware, and the rest of the plurality of functions may be realized by dedicated hardware.
  • the plurality of functions of the drive torque calculation means 3, the operating state calculation means 4, the torque estimation error model learning means 5, the conversion means 6, the error calculation means 7, the threshold calculation means 8, and the collision determination means 9 are hardware. , Software, firmware, or a combination thereof.
  • Some functions may be realized by a processor that executes a program stored in memory.
  • the memory is the same memory as the memory 72, and the processor is the same processor as the processor 71.
  • At least a part of the above-mentioned drive torque calculation means 3, operating state calculation means 4, torque estimation error model learning means 5, error calculation means 7, threshold value calculation means 8, and collision determination means 9 may be realized by a processing circuit. ..
  • the processing circuit is the same processing circuit as the processing circuit 81.
  • At least some of the functions of the means 8 and the collision determination means 9 may be realized by a processor that executes a program stored in the memory.
  • the memory is the same memory as the memory 72, and the processor is the same processor as the processor 71.
  • At least a part of the means 8 and the collision determination means 9 may be realized by a processing circuit.
  • the processing circuit is the same processing circuit as the processing circuit 81.
  • At least some of the functions of means 9 and parameter identification means 10 may be realized by a processor that executes a program stored in memory.
  • the memory is the same memory as the memory 72, and the processor is the same processor as the processor 71.
  • At least a part of the above-mentioned drive torque calculation means 3B, operation state calculation means 4, torque estimation error model learning means 5, conversion means 6, error calculation means 7, threshold value calculation means 8, collision determination means 9, and parameter identification means 10. May be realized by a processing circuit.
  • the processing circuit is the same processing circuit as the processing circuit 81.
  • At least some of the functions of means 9 and online parameter identification means 11 may be realized by a processor that executes a program stored in memory.
  • the memory is the same memory as the memory 72, and the processor is the same processor as the processor 71.
  • At least a part of the above-mentioned drive torque calculation means 3C, operation state calculation means 4, torque estimation error model learning means 5, conversion means 6, error calculation means 7, threshold value calculation means 8, collision determination means 9, and online parameter identification means 11. May be realized by a processing circuit.
  • the processing circuit is the same processing circuit as the processing circuit 81.
  • At least some of the functions of the means 9 and the approximate function learning means 12 may be realized by a processor that executes a program stored in the memory.
  • the memory is the same memory as the memory 72, and the processor is the same processor as the processor 71.
  • At least a part of the above-mentioned drive torque calculation means 3, operating state calculation means 4, torque estimation error model learning means 5, conversion means 6, error calculation means 7, threshold calculation means 8D, collision discrimination means 9, and approximation function learning means 12. May be realized by a processing circuit.
  • the processing circuit is the same processing circuit as the processing circuit 81.
  • At least some of the functions of the means 9 and the temperature measuring means 13 may be realized by a processor that executes a program stored in the memory.
  • the memory is the same memory as the memory 72, and the processor is the same processor as the processor 71.
  • At least a part of the above-mentioned drive torque calculation means 3, operating state calculation means 4, torque estimation error model learning means 5E, conversion means 6, error calculation means 7, threshold value calculation means 8E, collision determination means 9, and temperature measurement means 13. May be realized by a processing circuit.
  • the processing circuit is the same processing circuit as the processing circuit 81.
  • the configuration shown in the above embodiments is an example, and can be combined with another known technique, can be combined with each other, and does not deviate from the gist. It is also possible to omit or change a part of the configuration.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)
PCT/JP2020/037680 2020-10-05 2020-10-05 ロボットの衝突検知装置 Ceased WO2022074703A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2022554978A JP7325656B2 (ja) 2020-10-05 2020-10-05 ロボットの衝突検知装置
DE112020007659.8T DE112020007659T5 (de) 2020-10-05 2020-10-05 Roboterkollisionsdetektionsvorrichtung
PCT/JP2020/037680 WO2022074703A1 (ja) 2020-10-05 2020-10-05 ロボットの衝突検知装置
CN202080103192.2A CN116018244B (zh) 2020-10-05 2020-10-05 机器人的碰撞检测装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/037680 WO2022074703A1 (ja) 2020-10-05 2020-10-05 ロボットの衝突検知装置

Publications (1)

Publication Number Publication Date
WO2022074703A1 true WO2022074703A1 (ja) 2022-04-14

Family

ID=81126753

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/037680 Ceased WO2022074703A1 (ja) 2020-10-05 2020-10-05 ロボットの衝突検知装置

Country Status (4)

Country Link
JP (1) JP7325656B2 (https=)
CN (1) CN116018244B (https=)
DE (1) DE112020007659T5 (https=)
WO (1) WO2022074703A1 (https=)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220152821A1 (en) * 2020-11-16 2022-05-19 Techman Robot Inc. Robot safety weight compensation system and method capable of compensating weight of robot
JP7398024B1 (ja) 2023-07-04 2023-12-13 株式会社ユーシン精機 衝突検知方法及び衝突検知システム

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013066965A (ja) * 2011-09-21 2013-04-18 Toshiba Corp ロボット制御装置、外乱判定方法およびアクチュエータ制御方法
JP2014018941A (ja) * 2012-07-23 2014-02-03 Daihen Corp 制御装置、及び制御方法
CN107253196A (zh) * 2017-08-01 2017-10-17 中科新松有限公司 一种机械臂碰撞检测方法、装置、设备及存储介质
JP2019012392A (ja) * 2017-06-30 2019-01-24 ファナック株式会社 制御装置及び機械学習装置
JP2020019117A (ja) * 2018-08-02 2020-02-06 株式会社神戸製鋼所 ロボット制御装置、ロボット制御方法及びプログラム

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4055090B2 (ja) * 1997-07-08 2008-03-05 株式会社安川電機 ロボットの制御装置
JP3878054B2 (ja) * 2001-05-08 2007-02-07 三菱電機株式会社 ロボット制御装置
JP4223911B2 (ja) * 2003-09-25 2009-02-12 株式会社神戸製鋼所 衝突検知方法及び衝突検知装置
FR3002048B1 (fr) 2013-02-14 2016-07-01 Commissariat Energie Atomique Procede de detection amelioree de collision d'un robot avec son environnement, systeme et produit programme d'ordinateur mettant en œuvre le procede
EP3351356B1 (en) * 2015-09-16 2020-11-18 Panasonic Intellectual Property Management Co., Ltd. Robot collision detection method
CN106826819B (zh) * 2017-01-15 2019-07-30 上海新时达电气股份有限公司 桁架机器人防碰撞检测方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013066965A (ja) * 2011-09-21 2013-04-18 Toshiba Corp ロボット制御装置、外乱判定方法およびアクチュエータ制御方法
JP2014018941A (ja) * 2012-07-23 2014-02-03 Daihen Corp 制御装置、及び制御方法
JP2019012392A (ja) * 2017-06-30 2019-01-24 ファナック株式会社 制御装置及び機械学習装置
CN107253196A (zh) * 2017-08-01 2017-10-17 中科新松有限公司 一种机械臂碰撞检测方法、装置、设备及存储介质
JP2020019117A (ja) * 2018-08-02 2020-02-06 株式会社神戸製鋼所 ロボット制御装置、ロボット制御方法及びプログラム

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220152821A1 (en) * 2020-11-16 2022-05-19 Techman Robot Inc. Robot safety weight compensation system and method capable of compensating weight of robot
JP7398024B1 (ja) 2023-07-04 2023-12-13 株式会社ユーシン精機 衝突検知方法及び衝突検知システム
JP2025008219A (ja) * 2023-07-04 2025-01-20 株式会社ユーシン精機 衝突検知方法及び衝突検知システム

Also Published As

Publication number Publication date
JPWO2022074703A1 (https=) 2022-04-14
DE112020007659T5 (de) 2023-08-03
JP7325656B2 (ja) 2023-08-14
CN116018244A (zh) 2023-04-25
CN116018244B (zh) 2025-08-05

Similar Documents

Publication Publication Date Title
US8442685B2 (en) Robot control apparatus
CN109219738B (zh) 异常诊断装置及异常诊断方法
CN107458466B (zh) 用于确定在车辆的方向盘处的驾驶员手力矩的方法和装置
CN113365788A (zh) 作业判别装置及作业判别方法
CN113748597B (zh) 电动机控制装置
JP6688962B2 (ja) 判定装置、判定方法、および判定プログラム
JP7325656B2 (ja) ロボットの衝突検知装置
US9952249B2 (en) Inertia estimating method and inertia estimation apparatus of position control apparatus
KR102193914B1 (ko) 위치 추정 상태 진단 방법 및 이를 수행하는 자율주행로봇
US20110166763A1 (en) Apparatus and method detecting a robot slip
JP6906711B1 (ja) 摩擦補償装置、衝突検知装置、トルクフィードフォワード演算装置およびロボット制御装置並びに摩擦補償方法
KR101262277B1 (ko) 로봇의 충돌검지 방법
US20230286150A1 (en) Robot control device
JP5740858B2 (ja) 光位相差検出式の物体検知センサ
CN113737453B (zh) 洗衣机的转速检测方法、装置和系统
JP4390539B2 (ja) 負荷特性演算装置及びモータ制御装置
JP7485302B2 (ja) 信頼性評価装置
CN116127284B (zh) 一种测量信号野值的检测及修复方法、装置及设备
JPWO2022074703A5 (https=)
US20200308751A1 (en) Washing machine and control method thereof
CN117669661A (zh) 用于训练生成对抗网络的方法
JP2020203330A (ja) 直接教示装置及び直接教示方法
WO2021245916A1 (ja) サーボ制御装置
KR101862111B1 (ko) 스텝모터의 스톨 감지 방법 및 장치
JP3402017B2 (ja) 速度検出制御装置

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: 20956652

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022554978

Country of ref document: JP

Kind code of ref document: A

122 Ep: pct application non-entry in european phase

Ref document number: 20956652

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 202080103192.2

Country of ref document: CN