ROBOT CONTROL DEVICE, ROBOT CONTROL METHOD AND ROBOT CONTROL PROGRAM

Abstract

A robot control device (10) includes: an operation time prediction unit (11) that predicts a robot operation time, which is the time a robot needs to cause a hand of the robot to reach a target position, and a hand operation time, which is the time from the time an operation of the hand is commanded until the time the hand completes an operation to grasp an object at the target position; and a hand operation start instruction unit (13) that issues an instruction to start an operation of the hand at a time determined based on the predicted robot operation time and the predicted hand operation time. The operation time prediction unit (11) predicts the robot operation time by calculation that integrates robot control system information that specifies a property of a control system of the robot.

Description

Technical area

[0001] The present disclosure relates to a robot control apparatus that controls a robot, a robot control method, and a robot control program. State of the art

[0002] A robot is known which grasps a substance by a gripping device attached to a distal end portion of the robot, i.e., a hand, and transfers the grasped substance to a specified position. Such a robot is used for assembly work or work of removing a workpiece from a machine tool in the electrical and electronics engineering industry, dishwashing work in the food industry, transfer work in the logistics industry, or the like. Hereinafter, a substance to be grasped by the hand is referred to as an object. In transfer work by a robot, the robot is first positioned at a position of an object detected using a measuring device or a position determined in advance by a program. Then, when a hand executes a command, the hand starts an operation.After a predetermined waiting time has elapsed since the hand grasped the object, the robot starts the next operation. In such a series of grasping operations, it is desirable to optimize the timing at which the hand executes the command or the length of the waiting time, thereby shortening the operation time required for the grasping operation by the robot and the hand.

[0003] Patent Literature 1 discloses a robot control device that starts an operation of a hand before a robot reaches a target position, which is a position of an object. The robot control device of Patent Literature 1 starts an operation of the hand when a movement time until the robot reaches the target position becomes shorter than a hand operation time, which is a time required for the operation of the hand. Specifically, the robot control device of Patent Literature 1 predicts a movement time from a current position to the target position of the robot based on a robot operation command for operating the robot and compares the predicted movement time with the hand operation time. The robot control device of Patent Literature 1 outputs a command to the hand when the predicted movement time becomes shorter than the hand operation time. List of citationsPatent literature

[0004] Patent Literature 1: Japanese Patent Application Laid-Open No. 2000-787 Brief descriptionTechnical problem

[0005] The time until the robot moves the hand to the target position is not only determined by the robot operation command, but also varies due to a delay in the robot operation caused by characteristics of a robot control system. The length of a delay time due to the characteristics of the robot control system varies depending on a speed or acceleration of each axis of the robot. In a case where a parameter of the robot control system is made variable depending on a position or posture of the robot, the length of the delay time varies due to a change in the position or posture of the robot. The movement time predicted based on the robot operation command has an error with respect to an actual movement time.Therefore, in order to determine the timing for issuing an instruction for the hand operation, it is necessary to perform adjustment over a long period of time by a person skilled in the art. As described above, according to the conventional technique disclosed in Patent Literature 1, there is a problem in that it is difficult to accurately adjust the timing for issuing an instruction for the hand operation in order to shorten the time required for the grasping operation to grasp the object.

[0006] The present disclosure has been made in view of the foregoing, and an object thereof is to provide a robot control device which, in order to shorten a time required for a grasping operation by a robot and a hand, can accurately set a timing for giving an instruction for an operation of the hand. Solution to the problem

[0007] To solve the above problem and achieve an object, a robot control device according to the present disclosure includes: an operation time prediction unit for predicting a robot operation time, which is a time required for a robot to cause a hand of the robot to reach a target position, and a hand operation time, which is a time from the time an operation of the hand is commanded to the time the hand completes an operation of grasping an object at the target position; and a hand operation start instruction unit for issuing an instruction to start an operation of the hand at a time determined based on the predicted robot operation time and the predicted hand operation time.The operation time prediction unit predicts the robot operation time by calculation that integrates the robot control system information indicating a characteristic of a control system of the robot. Advantageous effects of the invention

[0008] A robot control device according to the present disclosure achieves an effect that, in order to shorten a time required for a grasping operation by a robot and a hand, it is possible to accurately set a timing for giving an instruction for an operation of the hand. Short description of the drawings Fig. 1 is a diagram illustrating an exemplary configuration of a robot control device according to a first embodiment. Fig. 2 is a diagram illustrating an exemplary configuration of a robot control system including the robot control device according to the first embodiment. Fig. 3 is a diagram for explaining a robot operation time predicted by an operation time prediction unit of the robot control device according to the first embodiment. Fig. 4 is a diagram for explaining an instruction for starting an operation of a hand and an instruction for starting an operation of a robot by the robot control device according to the first embodiment. Fig. 5 is a flowchart illustrating an operation procedure of the robot control device according to the first embodiment. Fig. 6 is a diagram illustrating an exemplary configuration of a robot control device according to a second embodiment. Fig. 7 is a diagram illustrating an exemplary configuration of a robot control device according to a third embodiment. Fig. 8 is a diagram illustrating an exemplary configuration of a robot control device according to a fifth embodiment. Fig. 9 is a diagram illustrating an exemplary configuration of a robot control device according to a sixth embodiment. Fig. 10 is a diagram illustrating a learning device and a learned model storage unit in a grip control parameter learning unit included in the robot control device according to the sixth embodiment. Fig. 11 is a diagram illustrating an exemplary configuration of a neural network used for machine learning in the sixth embodiment. Fig. 12 is a diagram illustrating an inference device and the learned model storage unit in the grip control parameter learning unit included in the robot control device according to the sixth embodiment. Fig. 13 is a diagram illustrating an exemplary configuration of a robot control device according to a seventh embodiment. Fig. 14 is a diagram illustrating an exemplary configuration of a control circuit according to the first to seventh embodiments. Fig. 15 is a diagram illustrating an exemplary configuration of a hardware circuit as a dedicated circuit according to the first to seventh embodiments. Description of embodiments

[0009] Hereinafter, a robot control apparatus, a robot control method, and a robot control program according to each embodiment will be described in detail with reference to the drawings. First embodiment.

[0010] Fig. 1 is a diagram illustrating an exemplary configuration of a robot control device 10 according to a first embodiment. Fig. 2 is a diagram illustrating an exemplary configuration of a robot control system 40 including the robot control device 10 according to the first embodiment.

[0011] The robot control system 40 includes the robot control device 10, a robot 30, and a hand 31. The hand 31 is attached to a distal end portion of an arm constituting the robot 30. The robot control device 10 controls the robot 30. The robot control system 40 grasps an object through operations of the robot 30 and the hand 31 and transports the grasped object to a specified position. Fig. The robot control system 40 illustrated in Figure 2 takes out an object placed in a box and transports the object to a specified position outside the box.

[0012] A detection device, such as an image sensor, is installed as a peripheral device of the robot control system 40. The detection device detects the position of the object. The robot control device 10 acquires information about the position of the object from the detection device and generates a robot command based on the acquired information. The robot control device 10 sends a robot operation command to a drive unit of the robot 30. The drive unit is not illustrated. The drive unit drives the robot 30 according to the robot operation command, so that the robot 30 operates according to the robot operation command.

[0013] The hand 31 is controlled by a hand controller. The hand controller is not illustrated. The hand 31 operates according to a hand operation command sent from the hand controller. In the robot control system 40, the robot control device 10 can control both the robot 30 and the hand 31 without using the hand controller.

[0014] In the first embodiment, the hand 31 includes two movable units that perform opening and closing operations. The hand 31 grips an object by gripping the object with two movable units facing each other. The hand 31 grips the object by a closing operation in which the movable units move in a direction approaching each other. The hand 31 releases the gripped object by an opening operation in which the movable units move in a direction away from each other from a state of gripping the object. Note that the hand 31 is not limited to one including two movable units. The number of movable units included in the hand 31 is not limited to two and is an arbitrary number. The hand 31 is not limited to one including such movable units.For example, the hand 31 may be one that includes a portion that generates a suction force and grasps an object by causing the portion to adsorb the object. In the following description, the movable units of the hand 31 are each referred to as a finger.

[0015] As in Fig. As illustrated in Figure 1, the robot control device 10 includes an operation time prediction unit 11, an adjustment time prediction unit 12, a hand operation start instruction unit 13, a follow-up operation instruction unit 14, and a storage unit 15. In addition, the robot control device 10 includes a command generation unit that generates a robot operation command. The command generation unit is not illustrated.

[0016] The operation time prediction unit 11 includes a robot operation time calculation unit 16 that calculates a robot operation time T1, and a manual operation time calculation unit 17 that calculates a manual operation time T gsp The robot operation time T1 is a time required by the robot 30 to cause the hand 31 of the robot 30 to reach a target position. The hand operation time T gspis a time from the time the operation of the hand 31 is commanded to the time the hand 31 finishes an operation of grasping the object at the target position. By the robot operation time calculation unit 16 calculating the robot operation time T1, the operation time prediction unit 11 predicts the robot operation time T1. The robot operation time calculation unit 16 calculates a remaining robot operation time T0 based on the robot operation time T1. The remaining robot operation time T0 is a time required from any time after the start of the operation of the robot 30 to the time the robot 30 reaches the target position. By the hand operation time calculation unit 17 calculating the hand operation time T gsp calculated, the operation time prediction unit 11 predicts the manual operation time T gsp previously.

[0017] The operation time prediction unit 11 outputs a value of the remaining robot operation time T0 and a value of the hand operation time T gsp to the hand operation start instruction unit 13. The hand operation start instruction unit 13 determines a time to start the operation of the hand 31 using the value of the remaining robot operation time T0, which is determined based on the value of the robot operation time T1 and the value of the hand operation time T gsp is calculated. The hand operation start instruction unit 13 instructs the hand control device to start the operation of the hand 31 at the specified time. That is, the hand operation start instruction unit 13 issues an instruction to start the operation of the hand 31 at the time determined based on the predicted robot operation time T1 and the predicted hand operation time T gspis determined. In addition, the hand operation start instruction unit 13 outputs to the follow-up operation instruction unit 14 information indicating a time Tk at which the instruction to start the operation of the hand 31 is given.

[0018] The adjustment time prediction unit 12 predicts an adjustment time T fit before. The adaptation time T fit is a time from the time the hand 31 starts to grasp the object until the time the hand 31 fits the object. "The hand 31 fits the object" means that the contact between the hand 31 and the object becomes stable to the extent that the hand 31 can maintain gripping the object even if the robot 30 moves the hand 31. The fitting time prediction unit 12 outputs a value of the predicted fitting time T fitto the follow-up operation instruction unit 14. In the first embodiment, the length of the predicted adjustment time T fit as the length of a waiting time from the time the hand 31 grasps the object until the time the robot 30 starts the next operation. After the elapse of the predicted adaptation time T fit Since the hand 31 starts gripping the object, the follow-up gripping operation instruction unit 14 issues an instruction for the operation of the robot 30 to be performed after the operation of gripping the object.

[0019] Information about a position P of the object and hand operation information are input to the robot controller 10. The position P is measured using a sensor such as an image sensor. The information about the position P to be input to the robot controller 10 is updated each time the object is grasped. The hand operation information is information about the operation of the hand 31 in grasping the object. In the first embodiment, the hand operation information includes values ​​of the insertion amount d, an opening width w, and a gripping force F. gsp .

[0020] Before starting the closing operation of grasping the object, a distal end of the hand 31, that is, a distal end of each finger, is inserted around the object. The insertion amount d represents the degree of insertion of each finger with respect to the object. Here, a state is defined as d=0, where, with the center position of the object as a reference, the distal end of each finger coincides with the center position of the object. By "the distal end of each finger coincides with the center position of the object," we mean that the position of the distal end of each finger in an insertion direction and the center position of the object in the insertion direction coincide with each other. The insertion direction is a direction in which each finger is moved by the operation of the robot 30 before the closing operation.In addition, a state is defined as d>0, where the center position of the object is located on a base side of each finger of the hand 31 compared to the case of d=0. A state is defined as d<0, where the center position of the object is located on a distal end side of each finger compared to the case of d=0. The opening width w is an interval between the distal end portions of the respective fingers at the start of the closing operation. The gripping force F. gsp is a force exerted by the hand 31 on the object in a state in which the hand 31 grasps the object.

[0021] The storage unit 15 stores robot control system information, hand property information, and object property information. The robot control system information is information indicating characteristics of a robot control system that controls the drive unit of the robot 30. The robot control system information includes at least one of a value of a control parameter used for feedforward control by the robot control system and a value of a control parameter used for feedback control by the robot control system. The control parameter included in the robot control system information is a parameter for determining the responsiveness of the robot control system.A control parameter is, for example, a parameter defined in control engineering, such as a proportional (P) gain, an integral (I) gain, and a derivative (D) gain of a proportional-integral-derivative (PID) controller, a time constant of a first-order delay element, or a dead time of a dead time element. The type of control parameter included in the robot control system information varies depending on the configuration of the robot control system.

[0022] The hand property information is information indicating operation characteristics of the hand 31. The hand property information includes at least one of an opening / closing command speed value, hand control system information, and a value of a mechanism parameter. The opening / closing command speed is a speed commanded by the hand control device and is a moving speed of each finger in the opening and closing operation of the hand 31. The hand control system information is information indicating characteristics of a hand control system that controls the opening and closing of the hand 31. The hand control system information includes a value of a control parameter of the hand control system.

[0023] The mechanism parameter is a value expressing a positional relationship of an element such as an actuator that drives the hand 31 or a reduction gear, or a dimension of each portion of the finger of the hand 31. Alternatively, the mechanism parameter is a value expressing a reduction ratio of an actuator or a reduction gear provided on the hand 31. The actuator provided on the hand 31 is a motor or a pneumatic actuator. Using the mechanism parameter makes it possible to calculate the position of the hand 31 or the position of each finger. The mechanism parameter is used to calculate a time point at which the hand 31 comes into contact with the object or a time point at which the hand 31 comes into contact with a substance around the object.

[0024] To improve the stability of the grip by the hand 31, a flexible material may be provided in a finger rest portion, which is a portion of each finger of the hand 31 that contacts the object. In this case, the object requires time to fit the finger rest portion through the deformation of the finger rest portion from the time the object starts to contact the finger rest portion until the object is stably grasped. To account for such properties of the finger rest portion, the hand property information may include information about physical properties of the finger rest portion, which is a portion of each finger of the hand 31 that contacts the object.The information about the physical properties of the finger rest portion includes a value of stiffness Kh of the finger rest portion, a value of viscosity Dh of the finger rest portion, or the like.

[0025] The object property information is information that specifies the physical properties of the object. The object property information is information about the deformation of the object and includes a stiffness value Kw, a viscosity value Dw, or the like.

[0026] One in Fig. 2 illustrated position P get is a target position at which the distal end of the hand 31 is caused to reach by the operation of the robot 30. Information about a position P of the object to be grasped next is input to the robot control device 10. The position P getis determined based on the position P of the object and the extent of insertion d. A Fig. 2 illustrated position P up is a position of the hand 31 when the operation of the robot 30 for moving the distal end of the hand 31 to the target position is started.

[0027] The detection device, which is a peripheral device of the robot control system 40, calculates the position P of the object and the insertion amount d based on a result of observing the object. The insertion amount d calculated here is the insertion amount d in a state where the distal end of the hand 31 is caused to reach the position P. get The command generation unit of the robot control device 10 generates a robot operation command based on the information about the position P of the object and the extent of insertion d.

[0028] The position Pup is a position that is a certain distance from the position P get upwards and is a position that can be defined by a user. The distance between the position P up and position P get A distance is set that prevents the distal end of the hand 31 from touching things around the object. A position of the hand 31 at position P up the same position is determined as the position that the hand 31 has at position P get By taking the position P up and the position at position P up as described above, a relative positional relationship between the object and the hand 31 can be made the same in each of the grasping operations, regardless of the operation of the robot 30 immediately before the hand 31 reaches the position P upSince the relative positional relationship between the object and the hand 31 is the same every time, the robot 30 can implement a reproducible operation. The robot operation command generated here is a robot operation command for causing the robot 30 to perform an operation of moving the hand 31 from the position P up to position P get where the position P get is obtained based on the position P of the object and the extent of insertion d and the position P up is obtained according to the above definition. As described above, the robot operation command is generated based on the information about the position P of the object and the value of the insertion amount d, which is the hand operation information.

[0029] Next, an operation of the robot control device 10 will be described. Fig. 3 is a diagram for explaining the robot operation time T1 predicted by the operation time prediction unit 11 of the robot control device 10 according to the first embodiment.

[0030] The robot operation time T1 is an operation time of the robot 30 in a case where the robot 30 performs the operation of moving the hand 31 from the position P up to position P get according to the robot operation command. A start point of the robot operation time T1 is a time at which the robot 30 starts the operation. An end point of the robot operation time T1 is a time at which an error between the position of the distal end of the hand 31 and the position P get falls within a predetermined range. The robot operation time calculation unit 16 calculates the robot operation time T1 based on the robot operation command.

[0031] A time Ta is an elapsed time since the start of the operation by the robot 30. The robot operation time calculation unit 16 measures the time Ta. The robot operation time calculation unit 16 calculates the remaining robot operation time T0 by subtracting the time Ta from the robot operation time T1. The operation time prediction unit 11 calculates the remaining robot operation time T0, thereby grasping a time required for the distal end of the hand 31 to reach the object, if necessary.

[0032] The robot operation time calculation unit 16 includes a robot operation simulation means. The robot operation simulation means simulates the generation of a robot operation command and simulates the operation of the robot 30 depending on the characteristics of the robot control system. The robot operation simulation means acquires information about the position P of the object input to the robot control device 10. The robot operation simulation means acquires the value of the insertion amount d from the hand operation information input to the robot control device 10. The robot operation simulation means simulates the generation of the robot operation command based on the position P of the object and the insertion amount d.

[0033] The robot operation simulation means includes filtering means for simulating the operation of the robot 30 depending on the characteristics of the robot control system. The filtering means is a mathematical model for simulating a behavior or response of a control system and a mechanical system with respect to a command value and expressing the state of the behavior or response. A transfer function, for example, can be used as the filtering means. By inputting the command value to the filtering means, the filtering means can obtain, with respect to a part of the mechanical system moving according to the command value, the amount of displacement due to an operation depending on the command value, the amount of change in speed in the operation depending on the command value, or the amount of change in acceleration in the operation depending on the command value.

[0034] The filtering means simulates the operation of the robot 30 based on the robot control system information stored in the storage unit 15. The robot operation simulation means simulates the operation of the robot 30 depending on the characteristics of the robot control system by passing the robot operation command through the filtering means. Note that the robot operation simulation means and the filtering means are not illustrated.

[0035] The robot operation time calculation unit 16 predicts the actual behavior of the distal end of the hand 31 based on the result of simulating the operation of the robot 30 by the robot operation simulation means. The robot operation time calculation unit 16 predicts the end point of the robot operation time T1 based on the predicted behavior of the hand 31 to calculate the robot operation time T1. As described above, the robot operation time calculation unit 16 calculates the robot operation time T1 by calculating the robot control system information. The operation time prediction unit 11 predicts the robot operation time T1 by calculating the robot control system information.

[0036] The robot operation time calculation unit 16 is not limited to one that simulates the operation of the robot 30 depending on the characteristics of the robot control system by the robot operation simulation means. The robot operation time calculation unit 16 may be one that calculates a delay time T rs of the operation of the robot 30 depending on the characteristics of the robot control system. The robot operation time calculation unit 16 uses an approximate function that calculates the delay time T rsbased on a command position specified by the robot operation command and a speed or acceleration at which the robot 30 is operated. By behaving the robot control system under a variety of operating conditions simulated in advance, a value of a parameter of the approximate function can be identified based on a result of the simulation. The value of the parameter of the approximate function is included in the robot control system information stored in the storage unit 15. The robot operation time calculation unit 16 calculates the delay time T rs Using the approximation function based on the value of the approximation function parameter included in the robot control system information. A polynomial equation or a neural network can be used for the approximation function.

[0037] The robot operation time calculation unit 16 calculates a time T1c based on the robot operation command. The time T1c is an operation time of the robot 30 in a case where the operation of moving the hand 31 from the position P up to position P get is performed. The robot operation time calculation unit 16 calculates the robot operation time T1 by adding the delay time T rsat time T1c. As described above, the robot operation time calculation unit 16 calculates the robot operation time T1 by calculation that integrates the robot control system information. That is, the operation time prediction unit 11 predicts the robot operation time T1 by calculation that integrates the robot control system information. In addition, the robot operation command used to calculate the robot operation time T1 is generated based on the information on the position P of the object and the value of the insertion amount d, which is the hand operation information, as described above. It can be said that the robot operation time calculation unit 16 calculates the robot operation time T1 by calculation that integrates the robot control system information, the information on the position P of the object, and the hand operation information.It can be said that the operation time prediction unit 11 predicts the robot operation time T1 by calculation that integrates the robot control system information, the information on the position P of the object, and the hand operation information.

[0038] The hand operation time calculation unit 17 includes a hand operation simulation means. The hand operation simulation means simulates the hand operation command and simulates the operation of the hand 31 depending on the characteristics of the hand control system. The hand operation simulation means acquires a value of an opening width w from the hand operation information input to the robot control device 10. The hand operation simulation means acquires a constant, which is a mechanism parameter, from the hand characteristic information stored in the storage unit 15. The hand operation simulation means calculates a stroke of the hand 31 by multiplying the value of the opening width w by the constant. The stroke of the hand 31 is a movement amplitude of the distal end of the hand 31 in each of the opening operation and the closing operation.The manual operation simulation means simulates the generation of the manual operation command based on the calculated stroke.

[0039] The hand operation simulation means includes filtering means for simulating the operation of the hand 31 depending on the characteristics of the hand control system. The filtering means simulates the operation of the hand 31 based on the hand control system information in the hand characteristic information stored in the storage unit 15. The hand operation simulation means simulates the operation of the hand 31 depending on the characteristics of the hand control system by passing the hand operation command through the filtering means. Note that the hand operation simulation means and the filtering means are not illustrated.

[0040] The manual operation time calculation unit 17 calculates a time T gsp_obased on a result of the simulation of the operation of each finger of the hand 31 by the hand operation simulation means. The time T gsp_o is a time from the start of the operation of each finger to the end of the operation of each finger. The hand operation time calculation unit 17 adds a predicted value of a time required to transmit a signal, which is the hand operation command, to the time T gsp_o to set the manual operation time T gsp to calculate. With time T gsp_o A time that has elapsed before a difference between a simulated position of the finger and a target position of the finger becomes less than or equal to a predetermined value can be adopted.

[0041] So far, the example has been described in which the operation time prediction unit 11 calculates the robot operation time T1 and the hand operation time T gspusing the information about the position P of the object and the values ​​of the insertion amount d and the opening width w in the hand operation information. The operation time prediction unit 11 can predict the robot operation time T1 and the hand operation time T gsp predict by using only part of the information about the position P of the object and the values ​​of the insertion extent d and the opening width w. The operation time prediction unit 11 can use the value of the insertion extent d in the prediction of the robot operation time T1 and the hand operation time T gsp do not use.

[0042] The above description is an example of a case where the position of each finger of the hand 31 is fixed immediately before grasping near the object, and the hand 31 is moved at a low speed in a linear direction, and the hand 31 is positioned. In this case, the gripping stability can be improved, for example, it is possible to grasp the proximity of the center of gravity of the object simply by adjusting the amount of insertion d. On the other hand, in a case where no straight path is provided near the object and the hand 31 is positioned by high-speed movement of the hand 31 on a curved path, the amount of insertion d is used to predict the robot operation time T1 and the hand operation time T gsp unnecessary. In addition, in a case of a hand adsorbing the object, the value of the opening width w for predicting the hand operation time T gspunnecessary. In the case of the hand adsorbing the object, the hand action time T gsp a predicted value of the time required to transmit a signal.

[0043] Fig. 4 is a diagram for explaining an instruction to start the operation of the hand 31 and an instruction to start the operation of the robot 30 by the robot control device 10 according to the first embodiment. Fig. 4 illustrates a diagram illustrating a change in the position of the hand 31 and a diagram illustrating an open / closed state of the hand 31. In the diagram illustrating the change in the position of the hand 31, the vertical axis represents the position of the hand 31, and the horizontal axis represents time T. In the diagram illustrating the open / closed state of the hand 31, the vertical axis represents the open state or the closed state, and the horizontal axis represents time T.

[0044] The operation time prediction unit 11 detects a time at which the value of the remaining robot operation time T0 reaches a value corresponding to T0 <T gsp based on the value of the remaining robot operation time T0 and the value of the hand operation time T gsp When detecting the time, the operation time prediction unit 11 transmits the reaching of the time when TO <T gspis satisfied, to the manual operation start instruction unit 13. In addition, the operation time prediction unit 11 sends the value of the remaining robot operation time T0 at that time and the value of the manual operation time T gsp at that time to the manual operation start instruction unit 13.

[0045] When the time is reached when TO <T gsp is satisfied, the hand operation start instruction unit 13 instructs the hand controller to start the operation of grasping the object by the hand 31, that is, the closing operation. The hand operation start instruction unit 13 sends a closing operation command to the hand controller, thereby instructing the hand controller to start the closing operation. By sending the hand operation command to the hand 31 according to the instruction from the hand operation start instruction unit 13, the hand 31 starts the closing operation.

[0046] The hand operation start instruction unit 13 sends information indicating the time Tk, for example, time information indicating the time Tk, to the follow-up operation instruction unit 14. The time Tk is a time at which TO <T gsp is met, and a time at which the manual operation start instruction unit 13 instructs the manual control device to start the closing operation. Furthermore, the manual operation start instruction unit 13 sends T to the follow-up operation instruction unit 14 as needed. gsp -Tp, which is a difference between the value of the manual operation time T gsp and a value of an elapsed time Tp.

[0047] The operation time prediction unit 11 can set the amount of correction ΔT and detect a time point at which T0<(T gsp -AT) is fulfilled, instead of the time at which TO <T gspis fulfilled. Upon detecting the time, the operation time prediction unit 11 transmits the reaching of the time when T0<(T gsp -ΔT) is satisfied, to the manual operation start instruction unit 13. In addition, the operation time prediction unit 11 sends the value of the remaining robot operation time T0 at the time, the value of the manual operation time T gsp at the time and a value of the amount of correction ΔT to the manual operation start instruction unit 13.

[0048] Here, an example of the extent of the correction ΔT is described. Here, the outer shape of the object is approximated to a sphere with a radius R wapproximated. In addition, the object is slightly deformed by receiving an external force. An opening width of the hand 31 in the open state is denoted by w, and an opening width of the hand 31 in a state in which the hand 31 is closed to grasp the object is denoted by wc. If wa, which is an opening width in the process of closing the hand 31 from the open state, is 2R w the hand 31 comes into contact with the object.

[0049] Assume that hand 31 continues to move from the state of wa=2R w closes and the object is thereby deformed to the extent that the width of the object in a direction in which the fingers of the hand 31 face each other is 2R wc which is less than 2R wAt this time, a normal force Fn is generated between the object and the fingers of the hand 31. The hand 31 can grip the object by generating a frictional force against the normal force Fn and geometric constraints of the object between the fingers. As described above, the hand 31 closes further to the extent that the opening width becomes 2R wc after the hand 31 starts to close and the opening width becomes 2R w , resulting in a state where the fingers touch the object. In this case, the robot controller 10 instructs the hand controller to start the closing operation, so that the opening width of the hand 31 becomes 2R wcwhen T0=0. Consequently, when ΔT>0, the robot controller 10 can bring the fingers into contact with the object at a time when the operation of the robot 30 ends. In addition, the robot controller 10 can reduce grasp failure by preventing the fingers from touching the object during the operation of the robot 30.

[0050] It should be noted that in a case where the closing operation is started when it is first detected that T0≤T gsp is fulfilled, wa<2R wis satisfied during the operation of the robot 30. In this case, the gripping may fail because the fingers of the hand 31 begin to touch the object during the operation of the robot 30. On the other hand, by appropriately setting the amount of correction ΔT, a time at which the fingers begin to touch the object can coincide with a time at which the operation of the robot 30 ends. That is, by appropriately setting the amount of correction ΔT, the opening width when T0=0, 2R w Consequently, it is possible to improve the success rate of grasping by hand 31.

[0051] In the above description, the external shape of the object approximates a sphere, but the external shape of the object may be approximated to a rectangular parallelepiped. In this case, the success rate of grasping by the hand 31 can be improved by appropriately setting the amount of correction ΔT based on a length Lw of the object in the direction in which the fingers oppose each other.

[0052] The adaptation time prediction unit 12 includes a function for calculating the adaptation time T fit based on the opening width w and at least one of the hand property information and the object property information. The adaptation time prediction unit 12 calculates the adaptation time T fitby calculation that integrates at least one of the stiffness Kh value or the viscosity Dh value as the hand property information and the stiffness Kw value or the viscosity Dw value as the object property information. The adjustment time prediction unit 12 sends the adjustment time value T fit to the re-gripping operation instruction unit 14.

[0053] In a case where deformation of the object, if any, is insufficient, an inertial force is generated in the object due to the operation of the robot 30, and a portion of the object slides into contact with the fingers, whereby the object may fall from the hand 31. By integrating at least one of the information regarding the physical properties of the finger rest portions of the fingers of the hand 31 and the information regarding the deformation of the object into the calculation, the adaptation time prediction unit 12 can calculate the adaptation time Tfit , with which the object can be sufficiently deformed. Consequently, it is possible to improve the success rate of grasping by hand 31.

[0054] It should be noted that in the first embodiment, the deformation of the object includes a case where the entire object is deformed and a case where a part of the object is deformed. The deformation of the object also includes a case where only a protrusion or the like formed on the surface of the object is deformed. How the object is deformed is not limited to a specific appearance.

[0055] In the first embodiment, the function for calculating the adaptation time T fit a tabular database containing a relationship between the opening width w, the stiffness Kw of the object and the adaptation time T fitThe tabular database is not limited to a two-dimensional table of the opening width w and the stiffness Kw and can contain a table of the opening width w and the adaptation time T fit for each type of object. The relationship between the opening width w, the stiffness Kw of the object and the adaptation time T fit is obtained in advance by verifying the gripping operation by the robot 30 and the hand 31. The following describes the creation of a table by using as an example a table of the opening width w and the adjustment time T fit used for every type of object.

[0056] When collecting data to create a table, a plurality of objects of different sizes are prepared. For each of the plurality of objects, the success / failure of grasping is determined by verifying a series of operations in which the hand 31 grasps the object and the robot 30 lifts the object. Specifically, the robot 30 is caused to perform an operation in which the lifting of the object is started when a time T gsp +Tb has elapsed since the start of the closing operation by the hand 31, and the success rate of the grasp is calculated. A time Tb is gradually increased from 0 seconds in a predetermined step time. Verification is repeated a predetermined number of times for each of the times T gsp +Tb, where Tbs are different from each other, and the success rate is calculated for each of the times of T gsp+Tb is calculated based on the number of successful graspings. The robot 30 is stopped in a state where the object is lifted, and whether the object is grasped at the position where the robot 30 is stopped is determined using the image sensor.

[0057] Instead of the image sensor, a force sensor can be used to determine whether the object is grasped. The success / failure of the grasping is determined based on the output of the force sensor. The force sensor is attached to a wrist portion of the robot 30, which is a connecting part to the hand 31. Alternatively, a laser displacement sensor can be used instead of the image sensor, and the success / failure of the grasping can be determined based on the measurement result of the laser displacement sensor.

[0058] In a case where the calculated success rate is greater than or equal to a predetermined threshold or the time Tb exceeds a predetermined upper limit Tb lim is reached, the increase of the time Tb in each step is stopped. The values ​​of the opening width w and the adjustment time T are entered into the table to be generated. fit , when the increase in time Tb is completed, are written in conjunction with each other. The value of the opening width w is taken as the width of the object used for verification. The value of the adjustment time T fit a value of time Tb is adopted in a case where the success rate is greater than or equal to the threshold.

[0059] In a case where the table of opening width w, stiffness Kw and adaptation time T fit is generated, the value of the stiffness Kw of the object is calculated based on the value of the gripping force F gspderived when the hand 31 inserts the object with the opening width w, which is set to a predetermined width w0. The value of the gripping force F gsp is acquired from the hand operation information input to the robot controller 10. The table shows the values ​​of the stiffness Kw, the opening width w and the adaptation time T fit written in conjunction with each other for each value of stiffness Kw.

[0060] In a case where the opening width w is an intermediate value between the values ​​shown in the table, ie for the object whose width is the intermediate value, the adaptation time T fit by linear interpolation of a large number of values ​​of the adaptation time T fit calculated, which is shown in the table. Values ​​used for linear interpolation in this case are, for example, values ​​of the adaptation time T fit, which correspond to the respective values ​​of the opening width w, which are adjacent data points on both sides of the intermediate value. Even in a case where the stiffness Kw of the object is an intermediate value between the values ​​shown in the table, the adaptation time T fit for the object by linear interpolation of a large number of values ​​of the adaptation time T fit , which is shown in the table. Values ​​used in this case for linear interpolation are, for example, values ​​of the adaptation time T fit , which correspond to the respective values ​​of stiffness Kw, which are adjacent data points on both sides of the intermediate value.

[0061] The value of the adaptation time T fitis input to the follow-up gripping operation instruction unit 14. Information indicating the time Tk at which the instruction to start the gripping operation is given is input from the hand operation start instruction unit 13 to the follow-up gripping operation instruction unit 14. Furthermore, T gsp -Tp, which is a difference between the value of the manual operation time T gsp and the value of the elapsed time Tp is input from the manual operation start instruction unit 13 to the re-gripping operation instruction unit 14 as required.

[0062] The re-gripping operation instruction unit 14 compares an elapsed time since T gsp -Tp has reached 0, with the adaptation time T fit . The follow-up operation instruction unit 14 instructs at a time when the elapsed time since T gsp -Tp has reached 0, the adaptation time T fitexceeds, the command generation unit instructs the robot to issue the next robot operation command after gripping the object. In the manner described above, the re-gripping operation instruction unit 14 issues the next robot operation command after the elapse of the predicted adjustment time T fit Since the hand 31 starts grasping the object, an instruction to start the next operation of the robot 30 to be performed after the hand 31 has performed the operation of grasping the object. The drive unit drives the robot 30 according to the robot operation command, and thereby the robot 30 starts the next operation to be performed after grasping the object.

[0063] In a case where the robot operation time calculation unit 16 calculates the time T1c based on the robot operation command, the robot control device 10 can perform a process described below. In the above description, the robot operation time calculation unit 16 calculates the time T1c in the case where the robot 30 performs an operation according to the robot operation command. The time T1c may not be an operation time in the case where the robot 30 performs an operation according to the robot operation command, but may be a total number of operation times in a case where the robot 30 performs two consecutive operations according to the robot operation command. Here, in a case where the operation of moving the hand 31 from a point Ps to a point Pe corresponds to one operation, the two operations correspond to the one operation and a subsequent operation of moving the hand 31 from the point Pe to a point Pe2.The hand 31 is moved by the two processes at two consecutive locations Ps-Pe and Pe-Pe2.

[0064] For example, assume that through the two operations according to the robot operation command, the hand 31 is moved from the point Ps to the point Pe near the object and then the hand 31 is caused to perform a linear movement corresponding to the insertion amount d from the point Pe to the point Pe2. In this case, the robot operation time calculation unit 16 calculates the time T1c, which is a time from the start of the movement of the hand 31 from the point Ps to the end of the movement of the hand 31 to the point Pe2. The hand operation start instruction unit 13 sends the closing operation command to the hand control device at time Tk, where TO <T gsp is satisfied, regardless of whether before the start of the linear movement corresponding to the extent of insertion d or in the middle of the linear movement.

[0065] Next, an operation procedure of the robot control device 10 will be described. Fig. 5 is a flowchart illustrating an operation procedure of the robot control device 10 according to the first embodiment.

[0066] In step S1, the robot control device 10 acquires the information about the position P of the object and the hand operation information. In step S2, the robot control device 10 calculates the hand operation time T by the hand operation time calculation unit 17. gsp by calculation that integrates the hand property information. Step S2 is a step for predicting the hand operation time T gsp .

[0067] In step S3, the robot control device 10 calculates the adaptation time T fit by the adaptation time prediction unit 12. Step S3 is a step for predicting the adaptation time T fit . The adaptation time prediction unit 12 calculates the adaptation time Tfit by calculation that integrates the hand operation information and at least one of the hand property information and the object property information.

[0068] In step S4, the robot control device 10 calculates the remaining robot operation time T0 through the robot operation time calculation unit 16. Before calculating the remaining robot operation time T0, the operation time prediction unit 11 predicts the robot operation time T1 by performing a calculation that integrates the robot control system information, the position P information, and the hand operation information. The robot operation time calculation unit 16 calculates the remaining robot operation time T0 by subtracting the time Ta, which is an elapsed time, from the robot operation time T1. Note that step S2, step S3, and a step of predicting the robot operation time T1 can be performed in any order. The robot control device 10 can simultaneously perform two or more of the procedures of step S2, step S3, and the step of predicting the robot operation time T1.

[0069] In step S5, the robot control device 10 determines through the operation time prediction unit 11 whether T0 <T GSP is fulfilled. If TO <T gsp is not satisfied (step S5, No), the robot control device 10 returns the procedure to step S4 and recalculates the remaining robot operation time T0. If TO <T gsp is satisfied (step S5, Yes), the robot control device 10 advances the procedure to step S6.

[0070] In step S6, the robot control device 10 instructs the hand control device to start the operation of the hand 31 through the hand operation start instruction unit 13. Step S6 is a step of issuing an instruction to start the operation of the hand 31 at the time point determined based on the predicted robot operation time T1 and the predicted hand operation time T gsp is determined.

[0071] In step S7, the robot control device 10 determines through the re-gripping operation instruction unit 14 whether the adjustment time T fit has elapsed since the start of the grasping. If the adaptation time T fit has not elapsed since the start of gripping (step S7, No), the robot control device 10 repeats the procedure from step S7. If the adjustment time T fit has elapsed since the start of gripping (step S7, Yes), the robot controller 10 advances the procedure to step S8.

[0072] In step S8, the robot control device 10 issues an instruction for an operation of the robot 30 to be performed after the operation of grasping the object through the follow-up operation instruction unit 14. Step S8 is a step for issuing an instruction for the operation of the robot 30 to be performed after the operation of grasping the object after the predicted adaptation time T fithas elapsed since the start of grasping the object by the hand 31. Thus, the robot control device 10 ends the process of Fig. 5 illustrated procedure.

[0073] According to the first embodiment, by predicting the robot operation time T1 through calculation that integrates the robot control system information, the robot control device 10 can set a timing for issuing the instruction to start the operation of the hand 31, taking into account a delay in the operation of the robot 30 due to the characteristics of the robot control system. By predicting the robot operation time T1 through calculation that integrates the hand operation information, the robot control device 10 can set the timing for issuing the instruction to start the operation of the hand 31, taking into account the operation of the hand 31 depending on the size of the object. By predicting the hand operation time T gspThrough calculation that integrates the hand characteristic information, the robot control device 10 can adjust the timing for issuing the instruction to start the operation of the hand 31, taking into account the operation characteristics of the hand 31. The robot control device 10 can accurately adjust the timing for issuing the instruction for the operation of the hand 31 to shorten the time required for the grasping operation, even if the adjustment is not performed by a skilled person for a long period of time. Thus, the robot control device 10 achieves an effect that, in order to shorten the time required for the grasping operation by the robot 30 and the hand 31, it is possible to accurately adjust the timing for issuing the instruction for the operation of the hand 31.

[0074] Furthermore, the robot control device 10 according to the first embodiment predicts the adaptation time T fitand gives an instruction that the operation of the robot 30 after the gripping operation after the elapse of the predicted adaptation time T fit since the start of gripping the object by the hand 31. Even if trials for setting a timing to start the next operation of the gripping operation are not performed, the robot control device 10 can set the timing to start the next operation of the gripping operation appropriately.

[0075] Second embodiment. Fig. 6 is a diagram illustrating an exemplary configuration of a robot control device 10A according to a second embodiment. The robot control device 10A includes an operation time prediction unit 11A similar to the operation time prediction unit 11 described in the first embodiment. The robot control device 10A does not include the adjustment time prediction unit 12 described in the first embodiment. In the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals as therein, and configurations different from those of the first embodiment will be mainly described.

[0076] In the second embodiment, the re-gripping operation instruction unit 14 stores a value of a waiting time Tw, which is a time from the time the hand 31 grasps the object until the robot 30 starts the next operation. The value of the waiting time Tw is determined in advance by a program for controlling the robot 30. Alternatively, the value of the waiting time Tw is determined in advance as a parameter value of the robot control device 10A. The waiting time Tw corresponds to a predetermined adjustment time T fit .

[0077] Different times can be set as the waiting time Tw depending on the object. For example, in a case where a certain type of hand 31 is used, a time Tw1 can be set as the waiting time Tw in the case of gripping a metal object, and a time Tw2 can be set as the waiting time Tw in the case of gripping a resin object.

[0078] The re-gripping operation instruction unit 14 compares an elapsed time since T gsp -Tp has reached 0, with the waiting time Tw. The follow-up operation instruction unit 14 instructs at a time when the elapsed time since T gsp -Tp has reached 0, exceeds the waiting time Tw, the command generation unit 14 instructs the next robot operation command after grasping the object. In the manner described above, after the waiting time Tw has elapsed since the hand 31 started grasping the object, the follow-up grasping operation instruction unit 14 issues an instruction to start the operation of the robot 30 to be performed after the operation of grasping the object. The drive unit drives the robot 30 according to the robot operation command, and thereby the robot 30 starts the next operation to be performed after grasping the object.

[0079] According to the second embodiment, similar to the first embodiment, in order to shorten the time required for a grasping operation by the robot 30 and the hand 31, the robot control device 10A can accurately set the timing for issuing an instruction for the grasping operation. Furthermore, even if trial and error for setting the timing for starting the next grasping operation is not performed, the robot control device 10A can appropriately set the timing for starting the next grasping operation.

[0080] Third embodiment. Fig. 7 is a diagram illustrating an exemplary configuration of a robot control device 10B according to a third embodiment. The robot control device 10B includes a gripping control parameter update unit 18, which is different from the robot control device 10 according to the first embodiment. In addition, the robot control device 10B includes an operation time prediction unit 11B, which is different from the operation time prediction unit 11 described in the first embodiment, and an adjustment time prediction unit 12B, which is different from the adjustment time prediction unit 12 described in the first embodiment.In the third embodiment, the same components as those in the first or second embodiment are denoted by the same reference numerals as therein, and configurations different from those in the first or second embodiment will be mainly described.

[0081] The information about the position P of the object, the hand operation information, and the success / failure information are input to the gripping control parameter update unit 18. The success / failure information is information about the success / failure of gripping the object. The gripping control parameter update unit 18 updates a gripping control parameter. The gripping control parameter is a parameter for controlling the gripping operation. Here, the hand operation time T gsp and the adaptation time T fitSuch gripping control parameters. The gripping control parameter updating unit 18 acquires the success / failure information indicating a result of the determination of success / failure of gripping by verifying the operations of the robot 30 and the hand 31. It is possible to use information indicating a result of the determination of success / failure of gripping in a gripping operation that is the previous gripping operation as the success / failure information. Note that in a case where verification is performed a plurality of times using the same value as the value of each gripping control parameter, the success / failure information is a value indicating a success rate of gripping. A case where verification is performed a plurality of times using the same value as the value of each gripping control parameter will be described below as an example.

[0082] The grasping control parameter update unit 18 inputs the success / failure information and the hand operation information from the previous grasping operation. The grasping control parameter update unit 18 outputs new hand operation information to the operation time prediction unit 11. The new hand operation information is updated information about an operation of the hand 31 in the next grasping operation. In addition, the grasping control parameter update unit 18 outputs the information about the position P of the object to the operation time prediction unit 11B.

[0083] Like the operation time prediction unit 11 of the first embodiment, the operation time prediction unit 11B includes the robot operation time calculation unit 16. The operation time prediction unit 11B does not include the manual operation time calculation unit 17 described in the first embodiment.

[0084] Next, an operation of the robot control device 10B will be described. The operations of the robot 30 and the hand 31 are verified while repeatedly updating each gripping control parameter. In the third embodiment, the gripping control parameter updating unit 18 determines the value of the hand operation time T. gsp based on the success / failure information acquired by performing the verification, while updating the manual operation time T gsp is repeated. In addition, the gripping control parameter updating unit 18 determines the value of the adaptation time T fit based on the success / failure information collected by performing the verification, while updating the adjustment time T fit is repeated.

[0085] The gripping control parameter updating unit 18 updates the hand operation time T gsp by increasing the manual operation time T gspby setting a value of the manual operation time T gsp with a certain step size Tg. The gripping control parameter update unit 18 stores a maximum value T gsp_ max of the manual operation time T gsp and a minimum value T gsp_ min of the manual operation time T gsp , if the manual operation time T gsp is repeatedly updated. In addition, the grip control parameter updating unit 18 stores a value of the step size Tg. It should be noted that a method in which the value of the hand operation time T gsp when updating the manual operation time T gsp is not limited to that described in the third embodiment and may be changed if necessary.

[0086] The gripping control parameter updating unit 18 updates the adaptation time T fit by setting the adaptation time T fit by specifying a value of the adaptation time Tfit with a certain step size Tf. The gripping control parameter update unit 18 stores a maximum value T fit_ max of the adaptation time T fit and a minimum value T fit_ min of the adaptation time T fit , if the adaptation time T fit is repeatedly updated. In addition, the gripping control parameter updating unit 18 stores a value of the step size Tf. It should be noted that a method in which the value of the adjustment time T fit when updating the adjustment time T fit is not limited to that described in the third embodiment and may be changed if necessary.

[0087] Here, the operation of the robot control device 10B when the value of the hand operation time T gsp and the value of the adaptation time T fitThe gripping control parameter updating unit 18 determines the value of the hand operation time T gsp and then determines the value of the adaptation time T fit . The robot control device 10B verifies the operations of the robot 30 and the hand 31 by setting the value of the adaptation time T fit to the maximum value T fit_ max and sequentially increasing the value of the manual operation time T gsp from the minimum value T gsp _min in steps of step size Tg. The robot control device 10B determines the value of the hand operation time T gsp through such verification.

[0088] When starting the process to determine the value of the manual operation time T gsp the gripping control parameter updating unit 18 sets the minimum value T gsp _min as the value of the manual operation time T gsp and sets the maximum value T fit_ max as the value of the adaptation time T fitThe gripping control parameter updating unit 18 outputs the value of the hand operation time T gsp , ie the minimum value T gsp_ min, to the operation time prediction unit 11B. The gripping control parameter updating unit 18 outputs the value of the adjustment time T fit , ie the maximum value T fit_ max, to the adjustment time prediction unit 12B.

[0089] Similar to the case of the first embodiment, the operation time prediction unit 11B calculates the robot operation time T1 by calculation that integrates the robot control system information, the position P information, and the hand operation information through the robot operation time calculation unit 16. The operation time prediction unit 11B predicts the robot operation time T1 by calculation that integrates the robot control system information, the position P information, and the hand operation information. The robot operation time calculation unit 16 calculates the remaining robot operation time T0 by subtracting the time Ta, which is an elapsed time, from the robot operation time T1.

[0090] The operation time prediction unit 11B compares a value of the remaining robot operation time T0 with a value of the inputted hand operation time T gsp. Similar to the case of the first embodiment, the operation time prediction unit 11B detects a time point at which the value of the remaining robot operation time T0 reaches a value corresponding to TO <T gsp When detecting the time, the operation time prediction unit 11B transmits the reaching of the time when TO <T gsp is satisfied, to the manual operation start instruction unit 13. In addition, the operation time prediction unit 11B sends the value of the remaining robot operation time T0 at that time and the value of the manual operation time T gsp at that time to the manual operation start instruction unit 13.

[0091] Similarly to the case of the first embodiment, the hand operation start instruction unit 13 sends information indicating the time Tk, for example, time information indicating the time Tk, to the follow-up gripping operation instruction unit 14. Further, the hand operation start instruction unit 13 sends to the follow-up gripping operation instruction unit 14 T as needed. gsp -Tp, which is a difference between the value of the manual operation time T gsp inputted from the operation time prediction unit 11B and the value of the elapsed time Tp.

[0092] Similar to the case of the first embodiment, the operation time prediction unit 11B may set the amount of correction ΔT and detect the time at which T0 <T gsp -ΔT is met, instead of the time at which TO <T gsp is met. Upon detecting the time, the operation time prediction unit 11B transmits the reaching of the time when T0 <Tgsp -ΔT is satisfied, to the manual operation start instruction unit 13. In addition, the operation time prediction unit 11B sends the value of the remaining robot operation time T0 at the time, the value of the manual operation time T gsp at the time and a value of the amount of correction ΔT to the manual operation start instruction unit 13.

[0093] Similar to the case of the first embodiment, the robot control device 10B instructs the hand control device to start the closing operation by the hand 31 so that the opening width of the hand 31 becomes 2R wc when T0=0. Consequently, when ΔT>0, the robot control device 10B can bring the fingers into contact with the object at a time when the operation of the robot 30 ends. In addition, the robot control device 10B can reduce grasp failure by preventing the fingers from touching the object during the operation of the robot 30.

[0094] The adjustment time prediction unit 12B outputs the value of the adjustment time T fit , which is input from the gripping control parameter updating unit 18, to the re-gripping operation instruction unit 14 as it is. Similar to the case of the first embodiment, the information indicating the time Tk and T gsp -Tp, which is a difference between the value of the manual operation time T gsp and the value of the elapsed time Tp. The follow-up operation instruction unit 14 instructs at a time when the elapsed time since T gsp -Tp has reached 0, the adaptation time T fitexceeds the limit, the command generation unit issues the next robot operation command after gripping the object. The drive unit drives the robot 30 according to the robot operation command, and thereby the robot 30 starts the next operation to be performed after gripping the object.

[0095] After the robot 30 performs its operation, it is determined using the image sensor whether the object is grasped at the position where the robot 30 is stopped. As described above, the success / failure of the grasping is determined by verifying a series of operations in which the hand 31 grasps the object and the robot 30 lifts the object. The success rate of the grasping is calculated by causing the robot 30 and the hand 31 to perform operations a predetermined number of times. Grasping information indicating a value of the success rate is input to the gripping control parameter update unit 18.

[0096] In a case where the success rate is greater than or equal to a predetermined threshold, the gripping control parameter updating unit 18 outputs to the operation time prediction unit 11B a value obtained by adding the step size Tg to the minimum value T gsp_min of the manual operation time T gsp The gripping control parameter updating unit 18 adds the step size Tg to the value of the hand operation time T gsp , thereby reducing the manual operation time T gsp The robot control device 10B repeats operations similar to those described above with respect to the updated hand operation time T gsp described to capture the value of the success rate.

[0097] The gripping control parameter updating unit 18 repeats the updating of the hand operation time T gsp and records the success rate until the success rate becomes less than or equal to the threshold or the value of the hand operation time T gsp the maximum value T gsp _max is reached. In a case where the success rate does not become less than or equal to the threshold and the hand operation time T gsp the maximum value T gsp_max is reached while the update and verification of the manual operation time T gsp are repeated, the gripping control parameter update unit 18 determines the maximum value T gsp _max as the value of the manual operation time T gsp . In a case where the success rate becomes less than or equal to the threshold while updating and verifying the manual operation time T gsp are repeated, the gripping control parameter updating unit 18 determines as the value of the hand operation time T gsp the value of the manual operation time T gsp , which is set in the verification immediately before the verification at which the success rate becomes less than or equal to the threshold.

[0098] In the manner described above, the grip control parameter updating unit 18 determines the value of the hand operation time T gspbased on the success / failure information acquired by performing the verification, while updating the manual operation time T gsp is repeated. The operation time prediction unit 11B outputs as a value of the predicted manual operation time T gsp , the value of the manual operation time T gsp which is determined by the gripping control parameter updating unit 18 based on the success / failure information.

[0099] Next, the robot control device 10B performs a process for determining the value of the adaptation time T fit The robot control device 10B verifies the operations of the robot 30 and the hand 31 by setting the value of the hand operation time T gsp to the specific value and sequentially decreasing the value of the adaptation time T fit from the maximum value T fit_max in steps of step size Tf. The robot control device 10B determines the value of the adaptation time T fit through such verification.

[0100] The gripping control parameter updating unit 18 sets the maximum value T fit_ max as the adaptation time T fit at the start of the process for determining the value of the adaptation time T fit The gripping control parameter update unit 18 outputs the value of the adaptation time T fit , ie the maximum value T fit_ max, to the adjustment time prediction unit 12B. Similar to the case of determining the value of the manual operation time T gsp , also in the case of determining the value of the adaptation time T fit, the grasping success rate is calculated by causing the robot 30 and the hand 31 to perform operations a predetermined number of times. Grasping information indicating a value of the success rate is input to the grasping control parameter update unit 18.

[0101] In a case where the success rate is greater than or equal to the predetermined threshold, the gripping control parameter updating unit 18 outputs to the adaptation time prediction unit 12B a value obtained by subtracting the step size Tf from the maximum value T fit_ max of the adaptation time T fit is obtained. The gripping control parameter updating unit 18 updates the adaptation time T fit by subtracting the step size Tf from the value of the adaptation time T fit . The robot control device 10B repeats operations corresponding to the above with respect to the updated adaptation time T fitdescribed in order to obtain a calculation result of the success rate.

[0102] The gripping control parameter updating unit 18 repeats the updating of the adaptation time T fit and records the success rate until the success rate becomes less than or equal to the threshold or the value of the adaptation time T fit the minimum value T fit_ min. In a case where the success rate is not less than or equal to the threshold and the value of the adaptation time T fit the minimum value T fit_ min, while the update and verification of the adaptation time T fit are repeated, the gripping control parameter update unit 18 determines the minimum value T fit_ min as the value of the adaptation time T fit. In a case where the success rate becomes less than or equal to the threshold while the update and verification of the adaptation time T fit are repeated, the gripping control parameter updating unit 18 determines as the value of the adaptation time T fit the value of the adaptation time T fit which is set during the verification immediately before the verification at which the success rate becomes less than or equal to the threshold.

[0103] In the manner described above, the gripping control parameter updating unit 18 determines the value of the adaptation time T fit based on the success / failure information collected by performing the verification, while updating the adjustment time T fit is repeated. The adaptation time prediction unit 12B outputs as a value of the predicted adaptation time T fit the value of the adaptation time T fitwhich is determined by the gripping control parameter updating unit 18 based on the success / failure information.

[0104] So far, the example has been described in which the grip control parameter updating unit 18 updates the hand operation time T gsp and the adaptation time T fit updated and the value of the manual operation time T gsp and the value of the adaptation time T fit based on the success / failure information. In the third embodiment, the gripping control parameter update unit 18 can determine the delay time T rs of the operation of the robot 30 instead of the manual operation time T gsp update and a value of the delay time T rs based on the success / failure information. In the third embodiment, the gripping control parameters may determine the delay time T rs, which is the robot control system information, and the adaptation time T fit be.

[0105] The gripping control parameter updating unit 18 determines the value of the delay time T rs based on the success / failure information collected by performing the verification, while updating the delay time T rs is repeated. The operation time prediction unit 11B calculates the robot operation time T1 by the robot operation time calculation unit 16 by calculating the value of the determined delay time T rs integrated. The operation time prediction unit 11B predicts the robot operation time T1 by calculation, which determines the value of the determined delay time T rs integrated.

[0106] The gripping control parameter updating unit 18 updates the delay time T rs by setting the delay time T rsby changing a value of the delay time T rs with a certain step size Tr. The gripping control parameter updating unit 18 stores a maximum value T rs_ max of the delay time T rs and a minimum value T rs_ min of the delay time T rs , if the delay time T rs is repeatedly updated. In addition, the gripping control parameter updating unit 18 stores a value of the step size Tr. It should be noted that a method in which the value of the delay time T rs when updating the delay time T rs is not limited to that described in the third embodiment and may be changed if necessary.

[0107] Here, the operation of the robot control device 10B when the value of the delay time T rsThe gripping control parameter updating unit 18 determines the value of the delay time T rs and then determines the value of the adaptation time T fit . The robot control device 10B verifies the operations of the robot 30 and the hand 31 by setting the value of the adaptation time T fit to a fixed value and changing the value of the delay time T rs from the maximum value T rs_ max or the minimum value T rs_ min with the step size Tr. The robot control device 10B determines the value of the delay time T rs through such verification.

[0108] When starting the process of determining the value of the delay time T rs the gripping control parameter updating unit 18 sets the maximum value T rs_ max or the minimum value T rs_ min as the value of the delay time T rsThe gripping control parameter update unit 18 outputs the value of the delay time T rs to the operation time prediction unit 11B. Similar to the case of the first embodiment, the robot operation time calculation unit 16 calculates the time T1c based on the robot operation command. The robot operation time calculation unit 16 calculates the robot operation time T1 by adding the delay time T rs at time T1c. The robot operation time calculation unit 16 calculates the remaining robot operation time T0 by subtracting the time Ta, which is an elapsed time since the start of the operation by the robot 30, from the robot operation time T1.

[0109] The gripping control parameter updating unit 18 repeats the update of the delay time T rsand records the success rate until the success rate becomes less than or equal to the threshold or the value of the delay time T rs the maximum value T rs _max or the minimum value T rs _min is reached. In the manner described above, the gripping control parameter updating unit 18 determines the value of the delay time T rs based on the success / failure information collected by performing the verification, while updating the delay time T rs is repeated. The operation time prediction unit 11B predicts the robot operation time T1 by calculation, which determines the value of the determined delay time T rs integrated.

[0110] According to the third embodiment, the robot control device 10B updates each of the hand operation time T gsp and the adaptation time T fit and determines the value of the manual operation time T gspand the value of the adaptation time T fit based on the success / failure information acquired by the verification. Alternatively, the robot control device 10B updates each of the delay times T rs , which is the robot control system information, and the adaptation time T fit and determines the value of the delay time T rs and the value of the adaptation time T fit based on the success / failure information acquired through the verification. Consequently, the robot control device 10B can improve the grasping success rate and shorten the time required for the grasping operation by the robot 30 and the hand 31.

[0111] In the third embodiment, the gripping control parameter updating unit 18 can update the correction amount ΔT and determine a value of the correction amount ΔT based on the success / failure information. In this case, the gripping control parameters include the correction amount ΔT. The gripping control parameter updating unit 18 determines the value of the correction amount ΔT based on the success / failure information acquired by performing the verification while repeating the update of the correction amount ΔT. The gripping control parameter updating unit 18 updates the correction amount ΔT by adjusting the correction amount ΔT by changing a value of the correction amount ΔT with a certain step size.The operation time prediction unit 11B calculates the robot operation time T1 through the robot operation time calculation unit 16 by calculating the value of the determined correction amount ΔT. Even in a case of determining the value of the correction amount ΔT based on the success / failure information, the robot control device 10B can slightly improve the success rate of grasping compared to a manual setting method by the user and can shorten the time required for the grasping operation by the robot 30 and the hand 31.

[0112] In the third embodiment, the gripping control parameter updating unit 18 can update the insertion amount d and determine a value of the insertion amount d based on the success / failure information. In this case, the gripping control parameters include the insertion amount d. The gripping control parameter updating unit 18 determines the value of the insertion amount d based on the success / failure information acquired by performing the verification while repeating the insertion amount update. The gripping control parameter updating unit 18 updates the insertion amount d by adjusting the insertion amount d by changing a value of the insertion amount d with a certain step size.The operation time prediction unit 11B calculates the robot operation time T1 through the robot operation time calculation unit 16 by calculating the value of the determined insertion amount d. Even in a case of determining the value of the insertion amount d based on the success / failure information, the robot control device 10B can slightly improve the success rate of grasping compared to a manual setting method by the user and can shorten the time required for the grasping operation by the robot 30 and the hand 31.

[0113] Fourth Embodiment. In a fourth embodiment, a modification of how the grip control parameters are updated in the third embodiment will be described. An operation of the robot control device 10B according to the fourth embodiment differs from that of the third embodiment in the method for setting the grip control parameters. Here, the operation of the robot control device 10B according to the fourth embodiment will be described with reference to Fig. 7. In the fourth embodiment, the same components as those in the above-described first to third embodiments are denoted by the same reference numerals as therein, and configurations different from those in the first to third embodiments will be mainly described.

[0114] In the fourth embodiment, the gripping control parameters similar to the third embodiment are the hand operation time T gspand the adaptation time T fit or the delay time T rs , which is the robot control system information and the adaptation time T fit The grip control parameters may include the amount of correction ΔT or the amount of insertion d. Here, a description is given by using as an example a case where the grip control parameters include the hand operation time T gsp and the adaptation time T fit are.

[0115] In the third embodiment, the robot control device 10B updates the hand operation time T gsp or updates the adjustment time T fit by setting a value of the manual operation time T gsp and the value of the adaptation time T fitto a fixed value and changing the other of them with the determined step size Tg or Tf. In the fourth embodiment, the robot control device 10B searches for a combination of the value of the hand operation time T gsp and the value of the adaptation time T fit using a search method such as particle swarm optimization, Bayesian optimization, or a genetic algorithm.

[0116] As an evaluation function used for the search, a function for evaluating the brevity of an operation time is used. The operation time is a time required for the grasping operation by the robot 30 and the hand 31, and is a time from the time the robot 30 starts moving to the target position to the time the hand 31 finishes the operation of grasping the object. In a case where the grasping fails, a large penalty is added to an evaluation result. The grasping control parameter update unit 18 uses the evaluation function to search for an optimal combination of the value of the hand operation time T gsp and the value of the adaptation time T fitto search for a position that can succeed in grasping and shorten the operation time. The grasp control parameter update unit 18 stops the search when the number of times the search is performed reaches a predetermined number of times, and outputs a combination of the value of the hand operation time T gsp and the value of the adaptation time T fit with the minimum rating function in the searches performed so far.

[0117] It should be noted that in a case where the gripping control parameters exceed the delay time T rs and the adaptation time T fit are, the gripping control parameter updating unit 18 uses the evaluation function to search for an optimal combination of the value of the delay time T rs and the value of the adaptation time T fit to look for a solution that can be successful in gripping and shorten the process time.

[0118] According to the fourth embodiment, the robot control device 10B uses the evaluation function to search for the optimal combination of the value of the hand operation time T gsp and the value of the adaptation time T fit which can succeed in gripping and shorten the operation time. Alternatively, the robot control device 10B uses the evaluation function to search for the optimal combination of the value of the delay time T rs and the value of the adaptation time T fit to search for a method that can succeed in grasping and shorten the operation time. Consequently, the robot control device 10B can improve the grasping success rate and shorten the time required for the grasping operation by the robot 30 and the hand 31. Fifth embodiment.

[0119] Fig. 8 is a diagram illustrating an exemplary configuration of a robot control device 10C according to a fifth embodiment. The robot control device 10C includes an operation time prediction unit 11C similar to the operation time prediction unit 11B described in the third embodiment. The robot control device 10C does not include the adjustment time prediction unit 12B described in the third embodiment. In the fifth embodiment, the same components as those in the above-described first to fourth embodiments are denoted by the same reference numerals as therein, and configurations different from those in the first to fourth embodiments will be mainly described.

[0120] The robot control device 10C includes a gripping control parameter updating unit 18C, which is different from the gripping control parameter updating unit 18 described in the third embodiment. In the fifth embodiment, the gripping control parameter is the hand operation time T gsp or the delay time T rs .

[0121] Similar to the case of the third embodiment, the grip control parameter updating unit 18C updates the hand operation time T gsp and records the success / failure information. The gripping control parameter update unit 18C determines the value of the hand operation time T gsp based on the success / failure information acquired by performing the verification, while updating the manual operation time T gspis repeated. Similarly to the case of the third embodiment, the gripping control parameter updating unit 18C alternatively updates the delay time T rs , which is the robot control system information, and acquires the success / failure information. The gripping control parameter update unit 18C determines the value of the hand operation time T gsp based on the success / failure information acquired by performing the verification, while updating the manual operation time T gsp is repeated. In the fifth embodiment, the gripping control parameter updating unit 18C does not update the adaptation time T fit or determines the value of the adaptation time T fit .

[0122] The operation of the robot control device 10C for determining the value of the hand operation time T gsp or the value of the delay time T rsis similar to the case of the third embodiment, and according to the fifth embodiment, the robot control device 10C can improve the grasping success rate and shorten the time required for the grasping operation by the robot 30 and the hand 31. Note that, similar to the case of the third or fourth embodiment, the grasping control parameters may include the amount of correction ΔT or the amount of insertion d. Sixth embodiment.

[0123] In a sixth embodiment, an example is described in which a value of a gripping control parameter is determined by machine learning. Fig. 9 is a diagram illustrating an exemplary configuration of a robot control device 10D according to the sixth embodiment. The robot control device 10D includes a gripping control parameter learning unit 20. The robot control device 10D does not include the gripping control parameter updating unit 18 described in the third embodiment. The robot control device 10D includes an operation time prediction unit 11D similar to the operation time prediction unit 11B described in the third embodiment. The robot control device 10D includes an adjustment time prediction unit 12D similar to the adjustment time prediction unit 12B described in the third embodiment.In the sixth embodiment, the same components as those in the above-described first to fifth embodiments are denoted by the same reference numerals as therein, and configurations different from those in the first to fifth embodiments will be mainly described.

[0124] The gripping control parameter learning unit 20 includes a learning device 21, an inference device 22, and a learned model storage unit 23. The learning device 21 learns a relationship between the position P of the object, the hand operation information, and the gripping control parameters. The relationship is a relationship in which the grasping success rate is greater than or equal to a predetermined threshold and the operation time, which is the time required for the grasping operation by the robot 30 and the hand 31, is the shortest. The gripping control parameters are at least one of the hand operation time T gsp , the adaptation time T fit and the delay time T trs , which is the robot control system information. Here, as an example, a case is described in which a relationship between the position P of the object, the hand operation information, the hand operation time T gsp, the adaptation time T fit and the delay time T rs is learned. The hand operation information includes a value of the extent of insertion d and a value of the opening width w. The hand operation information may include a value of the width of the object instead of the value of the opening width w.

[0125] The learning device 21 generates a learned model indicating the relationship between the position P of the object, the hand operation information, and the gripping control parameters. The learned model storage unit 23 stores the learned model. The inference device 22 uses the learned model to determine the values ​​of the hand operation time T. gsp , the adaptation time T fit and the delay time T rs to derive.

[0126] Fig. 10 is a diagram illustrating the learning device 21 and the learned model storage unit 23 in the grip control parameter learning unit 20 included in the robot control device 10D according to the sixth embodiment. The learning device 21 includes a data acquisition unit 24 and a model generation unit 25. The values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fit , the position P information, the manual operation information, the success / failure information and the operation time information are input into the data acquisition unit 24.

[0127] The information about success / failure is obtained by verifying the gripping process when updating the values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fitfor each combination of the position P, the insertion amount d, and the opening width w. In the sixth embodiment, the success / failure information is a value indicating the success rate of grasping. The operation time information is a value indicating the length of time from the time the robot 30 starts moving to the target position to the time the hand 31 completes the operation of grasping the object. The operation time is measured when the grasping operation is verified.

[0128] The data acquisition unit 24 generates learning data using combinations of the values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fit, the position information P, the manual operation information, the success / failure information, and the operation time information. The data acquisition unit 24 extracts from the combinations of the input values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fit a combination where the success rate is greater than or equal to the threshold and the operation time is the shortest. The data acquisition unit 24 generates learning data in which the information about the position P, the hand operation information, and the extracted combination of the values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fit are associated with each other. In the manner described above, the data acquisition unit 24 acquires the learning data.

[0129] Using the learning data, the model generation unit 25 generates a learned model for deriving the values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fit based on the position P and the hand operation information. The learned model storage unit 23 stores the generated learned model.

[0130] As a learning algorithm used by the model generation unit 25, a known algorithm such as supervised learning, unsupervised learning, or reinforcement learning can be used. As an example, a case in which a neural network is applied will be described. The model generation unit 25 learns combinations from the values ​​of the delay time T. rs , the manual operation time T gsp and the adaptation time T fitthrough so-called supervised learning according to a neural network model. Here, supervised learning is a method in which sets of data, each containing an input and a result, are given to the learning device 21, and thereby properties in the learning data are learned and results are derived from inputs. The learning data includes an input and a label, which is a result associated with the input. The information about the position P and the hand operation information correspond to inputs, and the values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fit correspond to markings.

[0131] Fig. 11 is a diagram illustrating an exemplary configuration of a neural network used for machine learning in the sixth embodiment. The neural network includes an input layer including a plurality of neurons, a hidden layer that is an intermediate layer including a plurality of neurons, and an output layer including a plurality of neurons. The intermediate layer may be one layer or two or more layers. Each of a plurality of values ​​input to the input layer is multiplied by a weight and input to the intermediate layer. Each of a plurality of values ​​input to the intermediate layer is multiplied by a weight and output from the output layer.An output result output from the output layer changes according to the value of the weight used for multiplication in the input layer and the value of the weight used for multiplication in the intermediate layer.

[0132] The neural network adjusts the values ​​of the weights so that results output by the output layer after the information about the position P and the hand operation information are input to the input layer approach the values ​​of the delay time Ts, the hand operation time Tgsp and the adaptation time Tfit, thereby obtaining combinations of the values ​​of the delay time T rs , the manual operation time T gsp and the adaptation time T fitThe model generation unit 25 generates a learned model by performing learning as described above. The model generation unit 25 can read a learned model that has already been generated from the learned model storage unit 23 and update the learned model by relearning according to the learning data.

[0133] Fig. 12 is a diagram illustrating the inference device 22 and the learned model storage unit 23 in the gripping control parameter learning unit 20 included in the robot control device 10D according to the sixth embodiment. The inference device 22 includes a data acquisition unit 26 and an inference unit 27.

[0134] The information about the position P and the hand operation information are input to the data acquisition unit 26, and thereby the data acquisition unit 26 acquires the information about the position P and the hand operation information, which are inference data. The inference unit 27 reads a learned model from the learned model storage unit 23. The inference unit 27 inputs the information about the position P and the hand operation information into the learned model, thereby determining the values ​​of the delay time T. rs , the manual operation time T gsp and the adaptation time T fit be issued.

[0135] The gripping control parameter learning unit 20 outputs the values ​​of the delay time T rs and the manual operation time T gsp to the operation time prediction unit 11D. The gripping control parameter learning unit 20 outputs the value of the adjustment time T fitto the adaptation time prediction unit 12D.

[0136] Similar to the case of the first embodiment, the robot operation time calculation unit 16 calculates the time T1c based on the robot operation command. The robot operation time calculation unit 16 calculates the robot operation time T1 by adding the delay time T rsat time T1c. The robot operation time calculation unit 16 calculates the remaining robot operation time T0 by subtracting the time Ta, which is an elapsed time since the start of the operation by the robot 30, from the robot operation time T1. Similar to the case of the first embodiment, the operation time prediction unit 11D calculates the robot operation time T1 by calculation that integrates the robot control system information, the information on the position P of the object, and the hand operation information by the robot operation time calculation unit 16. The operation time prediction unit 11D predicts the robot operation time T1 by calculation that integrates the robot control system information, the information on the position P of the object, and the hand operation information.

[0137] The operation time prediction unit 11D compares the value of the remaining robot operation time T0 with the value of the input hand operation time Tgsp . Similar to the case of the first embodiment, when the time is detected at which the value of the remaining robot operation time T0 reaches a value that T0< Tgsp fulfilled, the operation time prediction unit 11D transmits the reaching of the time T0 <T gsp is fulfilled, to the manual operation start instruction unit 13. In addition, the operation time prediction unit 11D sends the value of the remaining robot operation time T0 at that time and the value of the manual operation time T gsp at that time to the manual operation start instruction unit 13.

[0138] It should be noted that, similarly to the case of the first embodiment, the operation time prediction unit 11D may set the amount of correction ΔT and detect the time point at which T0 <T gsp -ΔT is met, instead of the time at which T0 <T gspis met. The robot control device 10D instructs the hand control device to start the gripping operation so that the opening width of the hand 31 becomes 2R wc when T0=0. Consequently, when ΔT>0, the robot control device 10D can bring the fingers into contact with the object at a time when the operation of the robot 30 ends. In addition, the robot control device 10D can reduce grasp failure by preventing the fingers from touching the object during the operation of the robot 30.

[0139] The adjustment time prediction unit 12D outputs the value of the adjustment time T fit input from the grip control parameter learning unit 20 to the re-gripping operation instruction unit 14 as it is. Note that the operation of each of the hand operation start instruction unit 13 and the re-gripping operation instruction unit 14 is similar to that in the case of the first embodiment.

[0140] In the sixth embodiment, the case where supervised learning is applied to the learning algorithm used by the model generation unit 25 was described, but learning other than supervised learning may be applied to the learning algorithm. The model generation unit 25 may perform machine learning using a learning algorithm such as reinforcement learning, unsupervised learning, or semi-supervised learning. The model generation unit 25 may perform machine learning using a learning algorithm such as deep learning, genetic programming, inductive logic programming, or a support vector machine.

[0141] In the sixth embodiment, the learning device 21 is included in the robot control device 10D. The learning device 21 may be a device external to the robot control device 10D. The learning device 21 may be a device connected to the robot control device 10D via a network or a device located on a cloud server.

[0142] The learning device 21 is not limited to the one that learns the values ​​of the gripping control parameters according to the learning data generated for one robot control device 10D. The learning device 21 may learn the values ​​of the gripping control parameters according to the learning data generated for a plurality of robot control devices 10D. The learning device 21 may acquire the learning data from a plurality of robot control devices 10D used at the same location, or may acquire the learning data from a plurality of robot control devices 10D used at different locations. The learning data may be acquired from the robot control devices 10D operating independently of each other at a plurality of locations. After starting the acquisition of the learning data from the plurality of robot control devices 10D, a new robot control device 10D may be added as a target from which the learning data is acquired.In addition, after the acquisition of the learning data from the plurality of robot control devices 10D is started, a part of the plurality of robot control devices 10D may be excluded from targets from which the learning data is acquired.

[0143] The learning device 21 that has learned a robot control device 10D can learn another robot control device 10D that is not the robot control device 10D. The learning device 21 can update the learned model by relearning the other robot control device 10D.

[0144] The learning device 21 only needs to establish a relationship between the position P of the object, the hand operation information and at least one of the values ​​of the hand operation time T gsp , the adaptation time T fit and the delay time T rsUsing the learned model, the inference device 22 derives at least one of the values ​​of the hand operation time T gsp , the adaptation time T fit and the delay time T rs depends on the position P of the object and the hand operation information.

[0145] The manual operation information to be inputted to the learning device 21 only needs to include at least one of the value of the insertion amount d and the value of the opening width w. The manual operation information to be inputted to the learning device 21 may include information about speed or acceleration when the robot 30 is caused to operate at a specified position by the insertion amount d, instead of the value of the insertion amount d.

[0146] According to the sixth embodiment, the robot control device 10D learns the relationship between the position P of the object, the hand operation information, and the gripping control parameters. This relationship is a relationship where the gripping success rate is greater than or equal to a predetermined threshold and the operation time, which is the time required for the gripping operation by the robot 30 and the hand 31, is the shortest. The robot control device 10D uses the learned model to derive the values ​​of the gripping control parameters based on the position P of the object and the hand operation information. Consequently, the robot control device 10D can improve the gripping success rate and shorten the time required for the gripping operation by the robot 30 and the hand 31. Seventh embodiment.

[0147] Fig. 13 is a diagram illustrating an exemplary configuration of a robot control device 10E according to a seventh embodiment. Similar to the robot control device 10D according to the sixth embodiment, the robot control device 10E includes the grip control parameter learning unit 20. The robot control device 10E includes an operation time prediction unit 11E similar to the operation time prediction unit 11D described in the sixth embodiment. The robot control device 10E does not include the adjustment time prediction unit 12D described in the sixth embodiment. In the seventh embodiment, the same components as those in the above-described first to sixth embodiments are denoted by the same reference numerals as therein, and configurations different from those of the first to sixth embodiments will be mainly described.

[0148] In the seventh embodiment, the gripping control parameters are at least one of the hand operation time T gsp and the delay time T rs , which is the robot control system information. The learning device 21 learns a relationship between the position P of the object, the hand operation information, and at least one of the values ​​of the hand operation time T gsp and the delay time T rs . In the seventh embodiment, the value of the adaptation time T fit not input into the learning device 21. The inference device 22 uses the learned model to calculate the values ​​of the hand operation time T gsp and the delay time T rs The inference device 22 derives the value of the adaptation time T fit not off.

[0149] Similar to the sixth embodiment, the robot control device 10E learns the relationship between the position P of the object, the hand operation information, and the gripping control parameters. This relationship is a relationship where the gripping success rate is greater than or equal to a predetermined threshold and the operation time, which is the time required for the gripping operation by the robot 30 and the hand 31, is the shortest. Similar to the sixth embodiment, the robot control device 10E uses the learned model to derive values ​​of the gripping control parameters from the position P and the hand operation information. Consequently, the robot control device 10E can improve the gripping success rate and shorten the time required for the gripping operation by the robot 30 and the hand 31.

[0150] Next, a hardware configuration implementing the robot control devices 10, 10A, 10B, 10C, 10D, and 10E according to the first to seventh embodiments will be described. The robot control devices 10, 10A, 10B, 10C, 10D, and 10E are each implemented by a processing circuit. The processing circuit may be a circuit in which a processor executes software or may be a dedicated circuit.

[0151] In a case where the processing circuit is implemented by software, the processing circuit is, for example, a Fig. 14 illustrated control circuit. Fig. 14 is a diagram illustrating an exemplary configuration of a control circuit 50 according to the first to seventh embodiments. The control circuit 50 includes an input unit 51, a processor 52, a memory 53, and an output unit 54.

[0152] The input unit 51 is an interface circuit that receives data input from outside the control circuit 50 and outputs the data to the processor 52. The output unit 54 is an interface circuit that sends data from the processor 52 or the memory 53 to outside the control circuit 50. In a case where the processing circuit Fig. 14, the processor 52 reads and executes a robot control program stored in the memory 53, thereby implementing each component of the robot control devices 10, 10A, 10B, 10C, 10D, and 10E. The robot control program is a program corresponding to each component of the robot control devices 10, 10A, 10B, 10C, 10D, and 10E. In addition, the processor 52 outputs data such as a calculation result to a volatile memory of the memory 53. The memory 53 is also used as a temporary storage in each process performed by the processor 52. The processor 52 may output and store data such as a calculation result in the memory 53 or may store data such as a calculation result in an auxiliary storage device via the volatile memory of the memory 53.A function of storing information in each component is implemented by the memory 53 or the auxiliary storage device.

[0153] The processor 52 is a central processing unit (CPU, also referred to as a central processing device, a processing device, an arithmetic device, a microprocessor, a microcomputer, a processor, or a digital signal processor (DSP), or the like). The memory 53 corresponds, for example, to a non-volatile or volatile semiconductor memory such as a random access memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable ROM (EPROM), or an electrically erasable programmable read-only memory (EEPROM (registered trademark)), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a digital versatile disk (DVD).

[0154] Fig. 14 is an example of hardware in a case where each component is implemented by the processor 52 and the memory 53 for general-purpose use, but each component may be implemented by a dedicated hardware circuit. Fig. 15 is a diagram illustrating an exemplary configuration of a hardware circuit 55 as a dedicated circuit according to the first to seventh embodiments.

[0155] The hardware circuit 55, as a dedicated circuit, includes an input unit 51, an output unit 54, and a processing circuit 56. The processing circuit 56 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination thereof. Each component can be implemented by combining the control circuit 50 and the hardware circuit 55.

[0156] It should be noted that the robot control program may be stored on a recording medium such as a compact disc (CD)-ROM or a DVD-ROM, and the recording medium may be provided to implement each embodiment.

[0157] The configurations described in the respective embodiments above are merely examples of the content of the present disclosure. The configurations of the respective embodiments can be combined with other known techniques. The configurations of the respective embodiments can be combined as appropriate. Part of the configurations of the respective embodiments may be omitted or modified without departing from the gist of the present disclosure. List of reference symbols

[0158] 10, 10A, 10B, 10C, 10D, 10E Robot control device; 11, 11A, 11B, 11C, 11D, 11E Operation time prediction unit; 12, 12B, 12D Adjustment time prediction unit; 13 Hand operation start instruction unit; 14 Re-grasping operation instruction unit; 15 Storage unit; 16 Robot operation time calculation unit; 17 Hand operation time calculation unit; 18, 18C Gripping control parameter update unit; 20 Gripping control parameter learning unit; 21 Learning device; 22 Inference device; 23 Learned model storage unit; 24, 26 Data acquisition unit; 25 Model generation unit; 27 Inference unit; 30 Robot; 31 Hand; 40 Robot control system; 50 Control circuit; 51 Input unit; 52 Processor; 53 Memory; 54 Output unit; 55 Hardware circuit; 56 Processing circuit. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] 2000-787

[0004]

Claims

[1] Robot control device comprising: an operation time prediction unit for predicting a robot operation time, which is a time required for a robot to cause a hand of the robot to reach a target position, and a hand operation time, which is a time from the time an operation of the hand is commanded to the time the hand completes an operation of grasping an object at the target position; and a hand operation start instruction unit for issuing an instruction to start an operation of the hand at a time determined based on the predicted robot operation time and the predicted hand operation time, wherein the operation time prediction unit predicts the robot operation time by calculation that integrates the robot control system information indicating a characteristic of a control system of the robot. [2] The robot control device according to claim 1, wherein the operation time prediction unit predicts the robot operation time by calculation that integrates the robot control system information, information about a position of the object, and hand operation information which is information about an operation of the hand in grasping the object. [3] The robot control device according to claim 1 or 2, wherein the operation time prediction unit predicts the hand operation time by calculation integrating hand property information indicating a property of a control system of the hand or a property of a mechanism constituting the hand. [4] Robot control device according to one of claims 1 to 3, comprising: a gripping control parameter updating unit for updating the hand operation time, which is a gripping control parameter for controlling a gripping operation by the robot and the hand, and for acquiring success / failure information indicating a result of determining success / failure of the gripping by verifying operations of the robot and the hand, wherein the gripping control parameter updating unit determines a value of the hand operation time based on the success / failure information acquired by performing the verification while repeating an update of the hand operation time, and the operation time prediction unit outputs a value of the manual operation time determined based on the success / failure information as a value of the predicted manual operation time. [5] Robot control device according to one of claims 1 to 3, comprising: a gripping control parameter updating unit for updating the robot control system information, which is a gripping control parameter for controlling a gripping operation by the robot and the hand, and for acquiring success / failure information indicating a result of determining success / failure of the gripping by verifying operations of the robot and the hand, wherein the gripping control parameter updating unit determines the robot control system information based on the success / failure information acquired by performing the verification while repeating an update of the hand operation time, and the operation time prediction unit predicts the robot operation time by calculation that integrates the robot control system information determined based on the success / failure information. [6] The robot control device according to any one of claims 1 to 3, comprising a gripping control parameter learning unit for learning a relationship between information about a position of the object, hand operation information which is information about an operation of the hand and which is obtained based on information about the object, and a gripping control parameter which is at least one of the hand operation time and the robot control system information, the relationship being a relationship in which a success rate of gripping is equal to or greater than a predetermined threshold and an operation time which is a time required for a gripping operation to grip the object is the shortest. [7] Robot control device according to claim 1, comprising: a fitting time prediction unit for predicting a fitting time, that is, a time from the time the hand starts to grasp the object to the time the hand fits the object; and a follow-up grasping operation instruction unit for giving an instruction for an operation of the robot to be performed after an operation of grasping the object after a lapse of the adaptation time predicted from the start of grasping the object by the hand. [8] The robot control device according to claim 7, wherein the adjustment time prediction unit predicts the adjustment time by calculation that integrates at least one of hand property information and object property information, the hand property information indicating a property of a control system of the hand or an operation property of the hand, the object property information indicating a property of the object, and hand operation information which is information about an operation of the hand and which is obtained based on information about the object. [9] Robot control device according to claim 7 or 8, comprising: a gripping control parameter updating unit for updating each of the hand operation time and the adjustment time, each of which is a gripping control parameter for controlling a gripping operation by the robot and the hand, and for acquiring success / failure information indicating a result of determining success / failure of the gripping by verifying operations of the robot and the hand, wherein the gripping control parameter updating unit determines a value of the hand operation time based on the success / failure information acquired by performing the verification while repeating an update of the hand operation time, and determines a value of the adjustment time based on the success / failure information acquired by performing the verification while repeating the update of the adjustment time, the operation time prediction unit outputs a value of the manual operation time determined based on the success / failure information as a value of the predicted manual operation time, and the adaptation time prediction unit outputs a value of the adaptation time determined based on the success / failure information as a value of the predicted adaptation time. [10] Robot control device according to claim 7 or 8, comprising: a gripping control parameter updating unit for updating each of the robot control system information and the adaptation time, each of which is a gripping control parameter for controlling a gripping operation by the robot and the hand, and for acquiring success / failure information indicating a result of determining success / failure of the gripping by verifying operations of the robot and the hand, wherein the gripping control parameter updating unit determines the robot control system information based on the success / failure information acquired by performing the verification while repeating the updating of the robot control system information, and determines the adjustment time based on the success / failure information acquired by performing the verification while repeating the updating of the adjustment time, the operation time prediction unit predicts the robot operation time by calculation that integrates the robot control system information determined based on the success / failure information, and the adaptation time prediction unit outputs a value of the adaptation time determined based on the success / failure information as a value of the predicted adaptation time. [11] The robot control device according to claim 7 or 8, comprising a gripping control parameter learning unit for learning a relationship between a position of the object, hand operation information which is information about an operation of the hand and which is obtained based on information about the object, and a gripping control parameter which is at least one of the hand operation time, the adaptation time, and the robot control system information, wherein the relationship is a relationship in which a success rate of gripping is greater than or equal to a predetermined threshold, and an operation time which is a time required for a gripping operation to grip the object is the shortest. [12] Robot control method, comprising: a step of predicting a robot operation time, that is, a time required for a robot to cause a hand of the robot to reach a target position, by calculation integrating robot control system information indicating a characteristic of a control system of the robot; a step of predicting a hand operation time, that is, a time from the time an operation of the hand is commanded to the time the hand completes an operation of grasping an object at the target position; and a step of issuing an instruction to start an operation of the hand at a timing determined based on the predicted robot operation time and the predicted hand operation time. [13] Robot control program that causes a computer system to perform the following: a step of predicting a robot operation time, that is, a time required for a robot to cause a hand of the robot to reach a target position, by calculation integrating robot control system information indicating a characteristic of a control system of the robot; a step of predicting a hand operation time, that is, a time from the time an operation of the hand is commanded to the time the hand completes an operation of grasping an object at the target position; and a step of issuing an instruction to start an operation of the hand at a timing determined based on the predicted robot operation time and the predicted hand operation time.

Images