ROBOT CONTROL DEVICE, ROBOT SYSTEM AND ROBOT CONTROL PROGRAM

Abstract

This robot control device controls a robot with one hand so that the robot picks objects from a randomly stacked pile. It includes a picking position calculation unit, a spatial information storage unit, a shape storage unit, and an operation path generation unit. The picking position calculation unit calculates a picking position of the object based on image information from an image pickup device that captures an image including the objects. The spatial information storage unit stores a movement range within which the robot can operate and a collision range within which the robot collides with the surroundings within the movement range.The shape storage unit stores the shapes of the robot and the hand, and the operation path generation unit generates an operation path of the hand based on the outputs of the picking position calculation unit, the spatial information storage unit, and the shape storage unit to prevent the robot from colliding with the surrounding environment. The shape storage unit stores a pre-grasping hand shape before the hand grasps the object and a post-grasping hand shape after the hand grasps the object.

Description

FIELD OF THE INVENTION

[0001] The present disclosure relates to a robot controller, a robot system and a robot control program. GENERAL STATE OF THE ART

[0002] In recent years, robots have been used in various industries to grasp and pick up an object (a workpiece). One of the applications of such a robot is the removal of individual workpieces from numerous workpieces randomly placed in a housing container (a bin), the so-called "bin picking" application.

[0003] In the bin picking application, for example, positions and locations of multiple workpieces in the container are detected based on image information from an image pickup device such as a stereo camera, and a workpiece can be picked using one hand of the robot.

[0004] For example, to retrieve a workpiece stacked in the container with the robot, a position of the hand for grasping the workpiece is taught at a position relative to a position of the workpiece. Furthermore, the hand approaches the taught position relative to the workpiece captured by the image pickup device to grasp and pick up the workpiece.

[0005] For example, with regard to the path along which the hand approaches the workpiece, information about devices arranged around the robot and information about the hand may be recorded in advance to generate a path that does not collide with peripheral devices and the like.

[0006] Specifically, the robot controller for controlling the robot is provided with a storage unit that stores a movement range of the robot and a collision range in which the hand (the robot) collides with peripheral devices, containers, and the like in the movement range of the robot.

[0007] Furthermore, the robot controller is also provided with a processing unit that calculates a removal position of a workpiece to be removed by the hand based on image information from the image pickup device and generates an operation path for the hand.

[0008] Heretofore, various techniques have been proposed for picking up stacked workpieces with one hand of a robot based on image information from an image pickup device without interference with peripheral devices and the like. LITERATURE LISTPATENT LITERATURE PTL 1: Japanese Patent Laid-Open Publication (kokai) No. 2022-017739 PTL 2: Japanese Patent Laid-Open Publication (kokai) No. 2022-017738 SUMMARY OF THE INVENTIONTECHNICAL PROBLEM

[0009] As described above, to retrieve a workpiece stacked in a container with a robot, for example, a posture of the hand for gripping the workpiece is taught at a position relative to a posture of the workpiece. Further, the hand approaches the taught position relative to the workpiece captured by the image pickup device to grip and retrieve the workpiece.

[0010] Incidentally, the shape before the robot grasps the workpiece is often different from the shape after the workpiece is grasped. However, when the robot picks up a workpiece in bulk, the operation path is usually generated based on a shape without the workpiece being grasped, and the shape before and after the workpiece is grasped by the hand is not considered.

[0011] If the shape of the hand assumed to create the operating path is too small compared to the shape of the hand after gripping, contact of the hand with the container, a peripheral device, and the like may occur. For example, if the hand changes during the operation to grip the workpiece and becomes larger than the assumed hand shape, the workpiece or hand may come into contact with an edge of the container or a peripheral device, and the like, resulting in breakage or damage.

[0012] On the other hand, if the hand shape assumed for generating the operating path is too large compared to the hand shape after grasping, the path will be longer than necessary, which may increase processing time and reduce work efficiency. Specifically, if the hand shape changes during the operation and becomes smaller than the assumed hand shape, this may increase processing time and reduce work efficiency because the hand moves along an unnecessary path. Furthermore, if the assumed hand shape is too large, there is a risk that a path cannot be found that allows the workpiece to be removed without collision.

[0013] Therefore, it is desired to provide a robot controller, a robot system, and a robot control program that can generate an efficient operation path on which no contact and the like are caused before and after grasping a workpiece (an object) with a hand. SOLUTION TO THE PROBLEM

[0014] According to an embodiment of the present disclosure, there is provided a robot controller for controlling a robot to take out an object in bulk by the robot having a hand, comprising a taking-out position calculation unit, a space information storage unit, a shape information storage unit, and an operation path generation unit.

[0015] The picking position calculation unit is configured to calculate a picking position of the object based on image information from an image pickup device that captures an image including an object to be detected by the robot, and the space information storage unit is configured to store a movement range in which the robot can be operated and a collision range in which the robot collides with the surroundings in the movement range.

[0016] The shape storage unit is configured to store a shape of the robot and the hand, and the operation path generation unit is configured to generate an operation path of the hand based on outputs of the picking position calculation unit, the spatial information storage unit, and the shape storage unit so that the robot does not collide with the surrounding environment. The shape storage unit stores a pre-grasping hand shape before the hand grasps the object and a post-grasping hand shape after the hand grasps the object.

[0017] The objects and effects of the present invention will be realized and attained using the components and combinations specifically pointed out in the claims. Both the foregoing general description and the following detailed description are exemplary and explanatory, and are not limiting of the invention described in the claims. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1: Fig. Figure 1 is a diagram schematically illustrating an example of a robot system. Fig. 2: Fig. 2 is a diagram to explain the problem of the robot system used in Fig. 1 is shown. Fig. 3: Fig. 3 is a functional block diagram showing a structure of the main portion in one embodiment of the robot controller according to the present embodiment. Fig. 4: Fig. 4 is a diagram for explaining an example of processing in one embodiment of the robot system according to the present embodiment. Fig. 5: Fig. 5 is a diagram (part 1) for explaining an example of a method for generating a collision avoidance path applied to the robot system according to the present embodiment. Fig. 6: Fig. 6 is a diagram (part 2) for explaining an example of a method for generating a collision avoidance path applied to the robot system according to the present embodiment. Fig. 7: Fig. 7 is a functional block diagram showing the structure of a main portion in a modified example of the robot controller according to the present embodiment. Fig. 8: Fig. 8 is a diagram for explaining an example of processing in a modification example of the robot system according to the present embodiment. Fig. 9: Fig. 9 is a diagram for explaining an example of workpieces handled by the robot system according to the present embodiment. Fig. 10: Fig. 10 is a flowchart for explaining an example of processing in an embodiment of the robot control program according to the present embodiment. DESCRIPTION OF EMBODIMENTS

[0018] First, with reference to Fig. 1 and Fig. 2, an example of a robot system and its problem will be described before a robot controller, a robot system and a robot control program according to the present embodiment will be described in detail.

[0019] Fig. Figure 1 is a diagram schematically illustrating an example of a robot system used for so-called bin-picking applications. In Fig. 1, reference numeral 100 denotes a robot system, and 1 denotes a robot, 2 a robot controller, 3 an image pickup device, 4 a container, and W a workpiece.

[0020] As in Fig. As shown in Figure 1, the robot system 100 includes the robot 1, the robot controller 2, and the image pickup device 3. A hand 11 is provided at the tip of an arm 10 of the robot 1. Furthermore, the hand 11 can grasp and remove, for example, a single workpiece W from a plurality of workpieces W randomly arranged in the container 4.

[0021] It should be noted that the hand 11 in Fig. 1 is configured to grip the workpiece W by grasping the workpiece W, but the hand is not limited to gripping the workpiece W with claws, but may suck and grip the workpiece W, for example, by negative pressure. The robot 1 is not limited to the example of an industrial robot used in a factory and the like, but may be a robot used in various places.

[0022] The robot controller 2 includes a processing unit (21: arithmetic processing unit) and a storage unit (24), and the processing unit controls the robot 1 based on a program (a software program) and the like installed in advance in the storage unit. The storage unit also stores, for example, a shape of a hand or a workpiece, a movement range of the robot 1 (the hand 11), a collision range, and the like.

[0023] It should be noted that it is also possible to connect a teaching pendant to the robot controller 2 to perform teaching and the like of the robot 1. Furthermore, an external computer with excellent processing capacity may also be added to the robot controller 2 to assist or replace the processing unit for processing the image or the operation path.

[0024] The image pickup device 3 is provided above the container 4 and captures images of a plurality of workpieces W in the container 4 or a hand 11 of the robot 1 holding the workpiece W. In this case, image information captured by the image pickup device 3 is input to the robot control device 2. The image pickup device 3 is not limited to being provided above the container 4, for example, on the ceiling, but may be installed near the hand and the like.

[0025] The image pickup device 3 can capture a three-dimensional image using multiple cameras such as a stereo camera, but may also be a TOF (Time-of-Flight) image sensor, for example. Furthermore, the image pickup device can be variously modified or altered depending on the type of robot 1 used, required processing, and the like.

[0026] It should be noted that Fig. 1 shows a state in which the hand 11 comes into contact with a wall of the container 4 when the hand 11 is moved along the shortest path when the hand 11 grasps a predetermined workpiece W. Here, the robot controller 2 can generate the operation path of the robot 1 based on, for example, the image information acquired by the image pickup device 3 and the movement range, collision range, and the like of the robot 1 stored in the storage unit.

[0027] Specifically, for example, the robot controller 2 sets an escape point above the wall of the container 4 and generates the operating path such that the hand 11 passes through the escape point. This allows the hand 11 to approach and grasp the workpiece W without coming into contact with the wall of the container 4.

[0028] Fig. 2 is a diagram to explain the problem of the robot system used in Fig. 1, and to explain the generation of an operating path of the hand 11 (of the robot 1). In this case, Fig. 2(a) describe the events before the gripping (grasping) of a workpiece W by the hand 11 and Fig. 2(b) describe what happens after the workpiece W is grasped (captured) by the hand 11.

[0029] As in Fig. As shown in Fig. 2(a), when the hand 11 grips the workpiece W, the hand 11 approaches the posture of the workpiece W, for example, based on image information acquired by the image pickup device 3 and the like, so as to arrive at a relative position taught to the hand 11. In this case, since the shape of the hand 11 is in the state before the workpiece W is gripped, if the shape of the hand 11 is stored in advance in the storage unit, for example, the operation path of the hand 11 can be generated based on the shape of the hand 11.

[0030] Specifically, the hand 11 approaches the position of the workpiece W based on the shape of only the hand 11 so as to reach a relative position taught to the hand 11, avoiding the wall of the container 4, and the workpiece W is grasped by the hand 11. Since the shape of the hand 11 does not change and is constant, the hand 11 does not come into contact with the wall of the container 4, for example.

[0031] On the other hand, if, as in Fig. 2(b), the hand 11 that has gripped the workpiece W is moved on the operation path based on the shape of the hand 11, the workpiece W may come into contact with, for example, the wall of the container 4. Concretely, since the shape of the hand 11 that has gripped the workpiece W has changed to be larger than the shape of only the hand 11, the workpiece gripped by the hand 11 may come into contact with, for example, the wall of the container 4 even if the hand 11 itself does not come into contact therewith.

[0032] This may occur not only when the shape after the workpiece W is gripped by the hand 11 becomes larger than the shape before the workpiece W is gripped; the same problem may be caused when the shape changes before and after the workpiece W is gripped by the hand 11.

[0033] Specifically, when the shape of the hand assumed for generating the operation path is too small compared to the hand shape after grasping, the hand 11 (the robot 1) or the workpiece W comes into contact with the container 4, a peripheral device, and the like. For example, if the shape of the hand changes during the operation and becomes larger than the assumed hand shape, the workpiece or hand may come into contact with an edge of the container or a peripheral device, and the like, resulting in breakage or damage.

[0034] On the other hand, if the hand shape assumed for generating the operating path is too large compared to the hand shape after grasping, the path will become longer than necessary, which may increase processing time and decrease work efficiency. For example, if the hand shape changes during the operation and becomes smaller than the assumed hand shape, processing time may increase and decrease work efficiency because the hand moves along an unnecessary path. Furthermore, if the assumed hand shape is too large, there is a risk that it will not be possible to find a path that allows the workpiece to be removed without a collision.

[0035] Examples of a robot controller, a robot system, and a robot control program according to the present embodiment will be described in detail below with reference to the accompanying drawings. In each of the drawings, the same or similar structural elements are assigned the same or similar reference numerals. Furthermore, the embodiments described below do not limit the technical scope of the invention and the meaning of the terms set forth in the claims.

[0036] Fig. 3 is a functional block diagram showing the structure of a main portion in one embodiment of the robot controller according to the present embodiment. As shown in Fig. 3, the robot controller 2 according to the present embodiment controls the robot 1 having the hand 11 to take out a workpiece W stacked in the container 4, and comprises a processing unit 21 and a storage unit 24. In this case, the robot 1 and the image pickup device 3 are the same as those described with reference to Fig. 1 are essentially the same, which is why a detailed description of them will be omitted.

[0037] The processing unit (the arithmetic processing unit) 21 includes a picking position calculation unit 22 and an operation path generation unit 23, and the storage unit 24 includes a path generation program 25. The path generation program 25 includes a spatial information storage unit 26 and a shape storage unit 27.

[0038] The picking position calculation unit 22 calculates a picking position of a workpiece W picked by the robot 1 based on image information from the image pickup device 3 that captures an image including workpieces W. Specifically, the picking position calculation unit 22 detects the workpiece W from an image captured by the image pickup device 3 to determine its position, and calculates the picking position of the workpiece W that can be picked by the hand 11 of the robot 1. It should be noted that the image pickup device 3 can capture an image including the workpiece W and the hand 11.

[0039] The spatial information storage unit 26 stores a movement range within which the robot 1 can operate and a collision range (X) within which the robot collides with the surroundings within the movement range. In this case, the collision range is, for example, information regarding a spatial range such as an obstacle with which the individual parts of the robot 1 must not collide when generating the operation path of the robot 1 (the hand 11).

[0040] The shape storage unit 27 stores a shape of the robot 1 and the hand 11. In this case, the shape storage unit 27 stores both a pre-grasping hand shape before the hand grasps the object and a post-grasping hand shape after the hand grasps the object. Furthermore, the shape storage unit 27 may also store information such as shapes of a plurality of different types of workpieces W, a hand shape before and after grasping each workpiece W (a shape and a load configuration of each workpiece), and weight information associated with each workpiece W, and the like.

[0041] The path generation program 25 is executed by the processing unit 21 and is a program for generating an operation path of the hand 11 based on image information from the image pickup device 3 and outputs from the space storage unit 26 and the shape storage unit 27. It should be noted that, for example, when the capacity of the processing unit 21 of the robot controller 2 is insufficient, an external computer having excellent processing capacity may be added, and the image processing, the processing of the path generation program 25, and the like may be executed by it.

[0042] The operation path generation unit 23 generates an operation path for the hand 11 (the robot 1) based on the outputs of the picking position calculation unit 22, the spatial information storage unit 26 and the shape storage unit 27 and the image information from the image pickup device 3.

[0043] It should be noted that the operation path generation unit 23 generates a pre-gripping path from a predetermined initial position (a first position) of the hand 11 to the removal position of the workpiece W based on the hand shape before gripping (the shape of the load of the hand shape before gripping). Furthermore, the operation path generation unit 23 generates a post-gripping path from the removal position of the workpiece W to a predetermined final position (a second position) of the hand 11 based on the hand shape after gripping (the shape of the load of the hand shape after gripping).

[0044] For example, when the robot system is configured to pick up multiple types of workpieces W, the shape storage unit 27 outputs a post-grasping hand shape corresponding to the type of a specific workpiece W to the operation path generation unit 23. Then, the operation path generation unit 23 generates a post-grasping path of the hand 11 based on the post-grasping hand shape output from the shape storage unit 27.

[0045] It should be noted that when the hand 11 is attached to an arm (a movable portion) 10 that can be operated with respect to the robot 1, the operation path generation unit 23 can modify the path of the arm 11 after grasping based on an operation of the hand 11 with respect to the robot 1. Specifically, the operation path generation unit 23 can correct the hand shape before grasping and the hand shape after grasping stored in the shape storage unit 27 based on the operation of the hand 11 with respect to the robot 1 and generate the operation path of the hand 11.

[0046] For example, a 3D image pickup device using multiple cameras or a TOF-type image sensor can be used as the image pickup device 3, but depending on the specifications, a two-dimensional image pickup device can also be used as the image pickup device 3. As described above, according to the robot controller of the present embodiment, it is possible to create an efficient operation path before and after gripping the workpiece, which does not involve contact and the like by the hand.

[0047] Fig. Fig. 4 is a diagram for explaining an example of processing in an embodiment of the robot system according to the present embodiment, and is used to explain processing in a system in which the robot controller is Fig. 3 is applied. It should be noted that Fig. 4(a) is intended to describe the events before a workpiece W is grasped by the hand 11 and Fig. 4(b) is intended to describe what happens after the workpiece W is grasped by the hand 11. In this case, Fig. 4(a) and Fig. 4(b) the above-described Fig. 2(a) and Fig. 2(b), where Fig. 4(a) with the exception of the hand model before gripping the workpiece (the hand mold before gripping) essentially the same structures as Fig. 2(a).

[0048] If, as in Fig. 4(a), when a workpiece W is gripped by the hand 11, the hand 11 approaches the posture of the workpiece W based on, for example, image information acquired by the image pickup device 3 and the like, so as to be in a relative position taught to the hand. Since the shape of the hand 11 in this case is in the state before gripping the workpiece W, if the shape of the hand 11 is stored in advance in the storage unit, for example, the operation path of the hand 11 can be generated based on the shape of the hand 11 (the shape before gripping).

[0049] Specifically, the operation path generation unit 23 generates a pre-gripping path from the predetermined initial position (first position) of the hand 11 to the take-out position of the workpiece W based on the hand shape before gripping (the shape of the load of the hand shape before gripping). At this time, since the shape of the hand 11 does not change from the initial position to the take-out position of the workpiece W, the hand 11 does not come into contact with the wall and the like of the container 4.

[0050] On the other hand, if, as in Fig. 4(b), when the hand 11 that has gripped the workpiece W is moved, the shape of the hand 11 has changed significantly due to the gripping of the workpiece W compared to the shape of the hand 11 itself. Now, in the robot system of the present embodiment, the shape of the hand 11 that has gripped the workpiece W (the hand shape after gripping) is stored together with the hand shape before gripping in the shape storage unit 27.

[0051] Specifically, the operation path generation unit 23 generates the post-gripping path from the workpiece removal position to the end position based on the hand shape after gripping (the shape of the load of the hand shape after gripping). Therefore, for example, even if the post-gripping hand shape has changed to be larger than the pre-gripping hand shape, a post-gripping path can be generated in which the hand 11 (the workpiece W) does not come into contact with the wall of the container 4 and the like.

[0052] It should be noted that, for example, from a distance between claws 11a and 11b of the hand (the opening degree of the claws), it can be recognized whether the hand 11 has gripped the workpiece W or not, as can be seen from a comparison of Fig. 4(a) and Fig. 4(b). Furthermore, for example, in the case of a suction-type hand 11c using a negative pressure, as described later with reference to Fig. 9, whether the workpiece W has been gripped or not can be detected, for example, from a change in the pressure (negative pressure) or a change in the weight of the hand 11c. As a result, it can be determined whether the hand 11 is moved based on the path before gripping or the path after gripping.

[0053] In this case, the robot system according to the present embodiment can be applied not only when the hand shape after grasping changes to become larger than the hand shape before grasping, but also when the hand shape after grasping changes to become smaller than the hand shape before grasping. Specifically, when the hand shape after grasping changes to become smaller than the hand shape before grasping, the operation path generation unit 23 can trim an unnecessary path and generate the post-grasp path based on the reduced hand shape after grasping.

[0054] The above processing can perform a simulation by executing the path generation program 25 of the storage unit 24 through the processing unit 21 to generate a path, and operating the robot 1 based on the path. As described above, according to the robot controller of the present embodiment, it is possible to generate an efficient operation path without contact and the like occurring before and after grasping a workpiece by hand.

[0055] Fig. 5 and Fig. 6 are diagrams for explaining an example of a method for generating a collision avoidance path applied to the robot system according to the present embodiment, wherein a collision area X is present on an operation path of a hand (of the robot). Fig. 5 and Fig. 6, reference character A denotes a starting position of the operating path of the hand 11, B a final position of the operating path of the hand 11, C an avoidance point (a preliminary avoidance point), and X the collision area.

[0056] As in Fig. 5, for example, when the hand 11 moves from the initial position A to the final position B of the operating path, the hand 11 will collide with the collision area X if the hand 11 is moved directly from A to B. Therefore, the operating path of the hand 11 is changed to pass through the avoidance point C in the course of the movement from A to B, and an operating path R on which the hand 11 does not collide with the collision area X is generated.

[0057] In other words, when the hand 11 moves from the initial position A to the final position B of the operating path, a provisional avoidance point C is obtained between a position P immediately before and a position Q immediately after, at which a straight line connecting A and B crosses the collision area X. This provisional avoidance point C is preferably obtained on the bisector between the immediately before position P and the immediately after position Q or in the vicinity of the bisector.

[0058] Next, it is determined whether the collision area X exists or not on a straight line connecting the initial position A and the provisional avoidance point C, and if the collision area X does not exist, a path R1 connecting the initial position A and the provisional avoidance point C is first established.

[0059] If the collision area X exists on the straight line connecting the initial position A and the provisional avoidance point C, it is determined whether or not the collision area X exists on a straight line connecting the immediately preceding position P and the provisional avoidance point C. If the collision area X does not exist on the straight line connecting the immediately preceding position P and the provisional avoidance point C, a path R (A → P → C) leading from the initial point A via the immediately preceding position P to the provisional avoidance point C is first established. On the other hand, if the collision area X exists, for example, on the straight line connecting the immediately preceding position P and the provisional avoidance point C, the path R (A → P → C) described with reference to Fig. 6 described processing is carried out.

[0060] Further, it is determined whether the collision area X exists or not on a straight line connecting the provisional avoidance point C and the end position B, and if the collision area X does not exist, a path R2 connecting the provisional avoidance point C and the end position B is established. In other words, the provisional avoidance point C is set as the avoidance point C, and the initially established paths R1 and R2 are actually established as operation paths of the hand 11.

[0061] As a result, the paths R1 and R2 connecting the initial position A, the avoidance point C, and the final position B are established, thus generating a collision avoidance path. It should be noted that when the collision area X exists on the straight line connecting the provisional avoidance point C and the final position B, the path can be determined in the same way as in the above-described case where the collision area X exists on the straight line connecting the initial position A and the provisional avoidance point C. Next, with reference to Fig. 6 a case will be described in which the collision area X exists on the straight line connecting the immediately preceding position P and the provisional avoidance point C.

[0062] Fig. 6(a) and Fig. 6(b) show the case where an obstruction exists on an operating path between an immediately preceding position P1 of the collision area X and a preliminary avoidance point C, and are used to explain a generation process for generating a collision avoidance path for this case. As shown in Fig. 6(a), when the collision area X exists on a straight line connecting the immediately preceding position P and the provisional avoidance point C, the immediately preceding position P is regarded as an initial position A1 and the provisional avoidance point C is regarded as an end position B1, and a new determination of a provisional avoidance point C1 is made.

[0063] Since, concretely, the collision area X exists, for example, on a straight line connecting the initial position A1 (P) to the final position B1 (C), as in Fig. 6(b), the provisional avoidance point C1 is determined on the bisector between the immediately preceding position P and the immediately succeeding position Q1.

[0064] In other words, it is determined whether the collision area X exists on the straight line connecting the initial position A1 and the provisional avoidance point C1, and if the collision area X does not exist, a path R10 connecting the initial position A1 and the provisional avoidance point C1 is first established. Since in the example shown in Fig. 6(a) and Fig. As shown in Figure 6(b), since the collision area X does not exist on the straight line connecting the initial position A1 and the provisional avoidance point C1, the path R10 is established. And since the collision area X does not exist on a straight line connecting the provisional avoidance point C1 and the final position B1, a path R20 is established.

[0065] As a result, for example, the path from the original starting position A to the provisional avoidance point C (B1) can be set as A → P (A1) → C1 → C (B1), that is, R10 → R20 can be set. In this case, if the collision area X exists on the straight line connecting the provisional avoidance point C1 and the final position B1, similar processing can be repeated, and an operation path (a collision avoidance path R) that does not pass through the collision area X can be generated.

[0066] It should be noted that the method for generating a collision avoidance path described with reference to Fig. 5 and Fig. 6 is merely an example, and various methods for generating a collision avoidance path can be applied to the robot system according to the present embodiment.

[0067] Fig. Fig. 7 is a functional block diagram showing the structure of a main portion in a modification example of the robot controller according to the present embodiment. As can be seen from a comparison of Fig. 7 and Fig. 3, the processing unit 21 in the controller 2 according to the present modification includes, in addition to the removal position calculation unit 22 and the operation path generation unit 23, a workpiece shape measuring unit 28 and a hand shape generation unit 29 after gripping.

[0068] The workpiece shape measuring unit (the object shape measuring unit) 28 measures a shape of the workpiece W based on image information from the image pickup device 3. In this case, the shape of the workpiece W measured by the workpiece shape measuring unit 28 may be used as the shape of the workpiece W used in the processing by the processing unit 21, but the shape of the workpiece W stored in the shape storage unit 27 may be accessed to apply it to the workpiece W.

[0069] The post-grip hand shape generation unit 29 generates a post-grip hand shape (the shape of the load after gripping) based on the workpiece shape measured by the workpiece shape measuring unit 28. In this case, the post-grip hand shape generation unit 29 can determine a specific type of workpiece among a plurality of workpieces based on, for example, the output of a weight sensor provided in the hand 11 and output a post-grip hand shape corresponding to the workpiece.

[0070] The image pickup device 3 may be implemented, for example, as a 3D image pickup device that generates no blind spot by using a plurality of high-precision cameras. In this case, the post-grasping hand shape generation unit 29 generates the post-grasping hand shape mainly based on the image information from the 3D image pickup device 3, for example, according to the operation by the robot system 100 or the workpiece W handled by the robot system 100. Note that even if the post-grasping hand shape generation unit 29 can generate the post-grasping hand shape directly from the image information, it is preferable to generate the post-grasping hand shape by referring to a plurality of post-grasping hand shapes stored in advance in the hand shape storage unit 27.

[0071] As described above, the shape storage unit 27 may also store information such as shapes of a plurality of different types of workpieces W, hand shapes before and after gripping each workpiece W, and weights associated with each workpiece W. In this case, the hand shape generation unit 29 after gripping may determine the type of workpiece based on both the workpiece shape measured by the workpiece shape measuring unit 28 and the weight of the workpiece measured by a weight sensor.

[0072] The operation path generation unit 23 generates, based on the output of the hand shape generation unit 29 after grasping, an operation path for the hand 11 such that the robot 1 does not collide with the surroundings. In this case, the operation path generation unit 23 generates, as described with reference to Fig. 3, based on the hand shape before gripping, a pre-gripping path from the predetermined initial position of the hand 11 to the removal position of the workpiece W. In addition, the operation path generation unit 23 generates, based on the hand shape after gripping, a post-gripping path from the removal position of the workpiece W to the predetermined final position of the hand 11.

[0073] Fig. 8 is a diagram for explaining an example of processing in a modification example of the robot system according to the present embodiment. In this case, the image pickup device 3 is implemented, for example, by a plurality of high-precision cameras as a high-precision 3D image pickup device that creates no blind spot. Furthermore, bins 4 in which a plurality of workpieces W are randomly arranged are sequentially exchanged with other bins 4 when the picking process by the robot 1 (the hand 11) is completed.

[0074] For example, as described above, when exchanging multiple containers 4 for taking out workpieces W, the shapes and locations of the containers 4 may vary depending on the respective solids. In such a case, the operation path generation unit 23 may generate the operation path of the hand 11 by detecting, for example, changes in the shape and location of a container 4 based on the image information from the image pickup device 3.

[0075] It should be noted that the image pickup device 3 is not limited to a high-precision 3D image pickup device with no blind spot, but a preferred image pickup device can be selected based on the accuracy and operation content required of the robot system 100. In any case, by modifying the robot system 100 according to the present embodiment, an efficient operation path can be created in which contact and the like do not occur before and after the hand 11 grasps the workpiece W.

[0076] Fig. Fig. 9 is a diagram for explaining an example of workpieces handled by the robot system according to the present embodiment, and illustrating a case where the robot system 100 handles three types of workpieces W1, W2, and W3 having different shapes. In this case, Fig. 9(a) an overall structure of the robot system, Fig. 9(b) a hand model after gripping a workpiece and Fig. 9(c) Hand models after gripping workpieces corresponding to the three types of workpieces.

[0077] As in Fig. As shown in Figure 9(a), the robot system 100 performs an operation for removing three types of workpieces W1, W2, and W3 having different shapes. The hand 11c of the robot 1 is configured to suck and remove the workpieces W by negative pressure, rather than by grasping (removing) the workpieces W with the claws.

[0078] As in Fig. 9(b), for example, when the workpiece W1 is gripped by the hand (of suction type) 11c, the picking-up position generating unit 22 calculates a picking-up position W1a of the workpiece W based on the image information from the image pickup device 3. In this case, the picking-up position W1a is set, for example, at a center position of an upper surface of the workpiece W. Then, the robot controller 2 controls the robot 1 so that the hand 11c provided at the tip of the arm 10 is moved to the picking-up position W1a to grip (suck) the workpiece W.

[0079] As in Fig. As shown in Fig. 9(c), the picking positions W1a, W2a, and W3a of the three types of workpieces W1, W2, and W3 are set at center positions of the upper surfaces of the respective workpieces W1, W2, and W3. Furthermore, the robot controller 2 controls the robot 1 to move to the picking position W1a, W2a, or W3a where the picking is performed by the hand 11c, and to grasp the workpiece W1, W2, or W3.

[0080] In this case, in the shape storage unit 27, for example, hand shapes before and after gripping plural kinds of workpieces W1, W2 and W3 having different shapes by the hand 11c (the hand shape before gripping and the hand shape after gripping) are stored in advance.

[0081] As described above, for example, when three kinds of workpieces W1, W2, and W3 having different shapes are handled, the picking position calculation unit 22 determines the kind of workpiece W1, W2, or W3 based on the image captured by the image pickup device 3. In addition, the picking position calculation unit 22 calculates the picking position W1a, W2a, or W3a of the determined Workpiece type.

[0082] The shape storage unit 27 outputs a pre-gripping hand shape and a post-gripping hand shape corresponding to each specific type of workpiece. Further, the operation path generation unit 23 generates an operation path of the hand 11c based on the pre-gripping hand shape and the post-gripping hand shape output from the shape storage unit 27.

[0083] It should be noted that the shape storage unit 27 may store, for example, information about shapes of the plural types of workpieces W1, W2, and W3 and / or information about weights of the plural types of workpieces W1, W2, and W3. In this case, the hand shape generation unit 29 may also determine the type of workpiece W based on, for example, the workpiece shape measured by the workpiece shape measuring unit 28.

[0084] Further, the hand shape generation unit 29 can detect the weight of the workpiece W after gripping, for example, through a weight sensor (not shown) provided in the hand 11c, and determine the gripped workpiece W based on the measured weight. In addition, the type of the gripped workpiece W can also be determined based on both the shape and the weight. And when the hand, for example, has a shape as described with reference to Fig. 4 and the opening degree of the individual claws that grip the plural types of workpieces is different, the type of workpiece can be determined from the opening degree of the individual claws.

[0085] Fig. Fig. 10 is a flowchart for explaining an example of processing in an embodiment of the robot control program according to the present embodiment. The robot control program (the path generation program 25) is stored, for example, in the storage unit 24 of the robot controller 2 shown in Fig. 3, and is executed by the processing unit (the arithmetic processing unit) 21. The robot control program is, for example, a program that simulates and generates a path before gripping from a first position to a removal position of the workpiece and a path after gripping from the removal position of the workpiece to a second position.

[0086] As in Fig. As shown in Fig. 10, at the start (START) of an example of processing in an embodiment of the robot control program according to the present embodiment, the image pickup device 3 captures an image at step ST1. Furthermore, at step ST2, a grasping position by the hand 11 of the robot 1 is calculated from the image captured by the image pickup device 3.

[0087] Further, in step ST3, it is determined whether or not the robot 1 (the hand 11) collides with a peripheral device and the like. In this case, the determination of whether or not the robot 1 collides with a peripheral device and the like is made at step ST3, for example, based on image information from the image pickup device 3, outputs from the spatial information storage unit 26 and the shape storage unit 27, and the like.

[0088] If it is determined at step ST3 that the robot 1 collides with the peripheral device and the like (YES), the process returns to step ST2, and the grasping position by the hand 11 is calculated again from the captured image. On the other hand, if it is determined at step ST3 that the robot 1 does not collide with the peripheral device and the like (NO), the process proceeds to step ST4, and the path before grasping until reaching the grasping position is calculated (generated).

[0089] In other words, at step ST4, the pre-gripping path from the predetermined first position to the removal position of the workpiece W is generated based on the hand shape (the pre-gripping hand shape) before the workpiece is gripped. Specifically, the operation path generation unit 23 generates the pre-gripping path based on the outputs of the removal position calculation unit 22 and the spatial information storage unit 26, the pre-gripping hand shape from the shape storage unit 27, and the image information from the image pickup device 3.

[0090] Next, the process proceeds to step ST5 to determine whether the robot 1 collides with a peripheral device and the like. If it is determined in step ST5 that the robot 1 collides with a peripheral device and the like (YES), the process proceeds to step ST9, and it is determined whether the number of times of determining YES is equal to or greater than a predetermined number of times M.

[0091] At step ST9, the number of times of determination of YES is counted, and if it is determined that the number of times of determination of YES is equal to or greater than the set number of times M (YES), the process returns to step ST2 and recalculates the grasping position. In other words, if the robot 1 collides with the peripheral device and the like on the path before grasping calculated at step ST4 equal to or greater than the set number of times M, the grasping position calculated at step ST2 is determined to be inappropriate and the grasping position is recalculated. It should be noted that if it is determined at step ST9 that the number of times of determination of YES is not equal to or greater than the set number of times M (NO), the process returns to step ST4 and recalculates the path before grasping.

[0092] On the other hand, if it is determined at step ST5 that the robot 1 does not collide with the peripheral device and the like (NO), the process proceeds to step ST6, and a post-gripping path is calculated based on a hand shape (a hand shape after gripping) after the workpiece W is gripped.

[0093] In other words, at step ST6, the post-gripping path from the removal position of the workpiece W to a predetermined second position is calculated based on the hand shape (the post-gripping hand shape) after the workpiece W is gripped. Specifically, the operation path generation unit 23 generates the post-gripping path based on the outputs of the removal position calculation unit 22 and the spatial information storage unit 26, the post-gripping hand shape from the shape storage unit 27, and the image information from the image pickup device 3.

[0094] Further, at step ST7, it is determined whether the robot 1 collides with a peripheral device and the like. If it is determined at step ST7 that the robot 1 collides with a peripheral device and the like (YES), the process proceeds to step ST10, and it is determined whether or not the number of times of determining YES is equal to or greater than a predetermined number of times N.

[0095] At step ST10, the number of times YES is determined at step ST7 is counted, and if it is determined that the number of times YES is equal to or greater than the set number of times N (YES), the process returns to step ST2 and recalculates the grasping position. In other words, if the robot 1 collides with the peripheral device and the like on the post-grasping path calculated at step ST6, the grasping position calculated at step ST2 is inappropriate, and the grasping position is recalculated. If it is determined at step ST10 that the number of times YES is not equal to or greater than the set number of times N (NO), the process returns to step ST6 and recalculates the post-grasping path.

[0096] On the other hand, if it is determined at step ST7 that the robot 1 does not collide with the peripheral device and the like (NO), the process proceeds to step ST8, and the removal of the workpiece W by the robot 1 (the hand 11) is performed. In other words, the simulation of the removal of the workpiece W by the robot 1 (the operation path) is completed, and the robot controller 2 actually controls the robot 1 to remove the workpiece W.

[0097] In this case, the set number of times M at step ST9 and the set number of times N at step ST10 are generally preferably set to M < N. This is because the determination of YES at step ST7 (the robot 1 collides with the peripheral device and the like) is based on the determination of NO at step ST5 (the robot 1 does not collide with a peripheral device and the like). Further, for a determination of NO at step ST5, it is necessary that the number of determinations of YES at least in step ST5 be less than M.

[0098] Specifically, it is considered that even if the number of times (N) of processing at step ST10 is greater than the number of times (M) of processing at step ST7, time can be used more efficiently than returning to step ST2 and performing the processing again. For example, since returning a process that has progressed to step ST7 to step ST2 and performing the processing again involves considerable time waste, setting M < N is considered favorable. It should be noted that the values of M and N can be set to values optimal for the robot system to which the robot control program of the present embodiment is actually applied.

[0099] As described above, according to the robot control program of the present embodiment, it is possible to generate an efficient operation path in which contact and the like do not occur before and after the workpiece W is grasped by the hand 11. The robot control program (the program for simulating the operation path) described above can be executed, for example, by an externally added computer when the computational processing capacity of the robot controller 2 is insufficient.

[0100] The robot control program according to the present embodiment described above may be recorded on a computer-readable non-temporary recording medium or in a non-volatile semiconductor memory device, or provided via wired or wireless communication. In this case, as the computer-readable non-temporary recording medium, for example, an optical disk such as a CD-ROM (Compact Disc Read Only Memory) or a DVD-ROM, or a hard disk device, and the like can be envisaged. Further, a PROM (Programmable Read Only Memory), a Flash Memory (registered trademark), and the like can be conceived as non-volatile semiconductor memory devices. Furthermore, distribution from a server device may be provided via a wired or wireless LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

[0101] As described above in detail, by the robot controller, the robot system, and the robot control program according to the present embodiment, it is possible to create an efficient operation path in which contact and the like by the hand do not occur before and after grasping an object with a hand.

[0102] Although embodiments of the present disclosure have been described in detail, the present disclosure is not limited to the individual embodiments described above. In these embodiments, various additions and substitutions, modifications, partial omissions, and the like are possible without departing from the gist of the invention or without departing from the idea and spirit of the invention derived from the content described in the claims and its equivalents. For example, in the embodiments described above, the order of each operation and the order of each process are shown by way of example, but are not limited thereto. The same applies when numerical values or equations are used in the description of the embodiments described above.

[0103] With regard to the embodiments described above, the following is further disclosed: Appendix 1

[0104] A robot controller (2) for controlling a robot (1) to remove an object (W) in bulk by the robot (1) having a hand (11), has a removal position calculation unit (22) configured to calculate a removal position of the object (W) based on image information from an image pickup device (3) that captures an image including an object (W) to be detected by the robot (1); a spatial information storage unit (26) configured to store a movement range in which the robot (1) can be operated and a collision range in which the robot collides with the environment in the movement range (1); a shape storage unit (27) arranged to store a shape of the robot (1) and the hand (11); and an operation path generation unit (23) configured to generate an operation path of the hand (11) based on outputs of the removal position calculation unit (22), the spatial information storage unit (26) and the shape storage unit (27) so that the robot (1) does not collide with the environment, on, where the shape storage unit (27) is arranged to store a pre-grasping hand shape before the hand (11) grasps the object (W) and a post-grasping hand shape after the hand (11) has grasped the object (W). Appendix 2

[0105] When controlling the robot according to Annex 1 the image recording device (3) is arranged to record an image containing the object (W) and the hand (11). Appendix 3

[0106] When controlling the robot according to Annex 1 or 2 the image recording device (3) is arranged to record a three-dimensional image containing the object (W) and the hand (11), the operation path generation unit (23) is configured to generate the operation path of the hand (11) on the basis of an output of the withdrawal position calculation unit (22), information of the three-dimensional image captured by the image pickup device (3), and the hand shape before grasping and the hand shape after grasping stored in the shape storage unit (27). Appendix 4

[0107] In the robot controller according to one of the appendices 1 to 3, the operating path generating unit (23) is arranged such that it based on the hand shape before grasping, a path before grasping is generated from a predetermined first position to the removal position of the object (W), and based on the hand shape after grasping, a path after grasping is generated from the removal position of the object (W) to a predetermined second position of the hand. Appendix 5

[0108] In the robot controller according to any one of Annexes 1 to 4, the shape storage unit (27) is arranged to store a hand shape before grasping and a hand shape after grasping corresponding to a type of objects (W) having a same shape. Appendix 6

[0109] In the robot controller according to any one of Annexes 1 to 4, the shape storage unit (27) is arranged to store shapes of a plurality of types of objects (W1, W2, W3) having different shapes and a plurality of hand shapes before grasping and a plurality of hand shapes after grasping corresponding to the plurality of types of objects (W1, W2, W3). Appendix 7

[0110] In the robot controller according to Annex 6, the picking position calculation unit (22) is arranged to calculate the type of the object (W) on the basis of the image taken by the image pickup device (3) from the plurality of objects (W1, W2, W3) stored in the shape storage unit (27). determined, and arranged to calculate the removal position (W1a, W2a, W3a) of the determined type of object (W), the shape storage unit (27) is arranged to output a hand shape before grasping and a hand shape after grasping corresponding to the specific type of object (W), and the operation path generation unit (23) is configured to generate an operation path of the hand (11) based on the output hand shape before grasping and the output hand shape after grasping. Appendix 8

[0111] When controlling the robot according to one of Annexes 1 to 7 the hand (11) is attached to a movable portion operable relative to the robot (1), the operation path generating unit (23) is configured to correct the hand shape before grasping and the hand shape after grasping stored in the shape storing unit (27) on the basis of an operation of the hand (11) by the movable portion with respect to the robot (1), and configured to generate an operation path of the hand (11). Appendix 9

[0112] The robot control system according to one of Annexes 1 to 8 further comprises an object shape measuring unit (28) configured to measure an object shape of the object (W) based on the image information from the image pickup device (3); and a hand shape generation unit (29) configured to generate the hand shape after grasping on the basis of the object shape measured by the object shape measuring unit, on, where the operation path generation unit (23) is arranged to generate an operation path of the hand (11) based on an output of the hand shape generation unit (29) after grasping, so that the robot (1) does not collide with the environment. Appendix 10

[0113] When controlling the robot according to one of Annexes 1 to 9 the object (W) is several objects (W) that are randomly placed in a receptacle, the hand (11) takes individual objects (W) in the receiving container one after the other, and the receiving container is replaced in turn by other receiving containers. Appendix 11

[0114] In the robot controller according to Annex 10, the operation path generating unit (23) is configured to detect changes in the shape and arrangement position of the receiving container on the basis of the image information from the image pickup device (3), and is configured to generate an operation path of the hand (11). Appendix 12

[0115] A robot system (100) comprises a robot (1) with a hand (11) configured to remove an object (W) in bulk, an image pickup device (3) configured to capture an image containing the object (W), and a robot controller (2) configured to control the robot (1) such that the object (W) is removed by the hand (11), wherein the robot controller (2) is a robot controller according to one of Annexes 1 to 11. Appendix 13

[0116] A robot control program for a robot system (100) comprising a robot (1) with a hand (11) configured to take out an object (W) in bulk, an image pickup device (3) configured to take out an image containing the object (W), and a robot controller (2) configured to control the robot (1) so that the object (W) is taken out by the hand (11), causes a calculation processing unit (21) to a process for calculating a removal position of an object (W) to be detected by the robot (1) based on the image information from the image pickup device (3); and a process for generating an operation path of the hand (11) so that the robot (1) does not collide with the environment, based on the image information from the image pickup device (3), an output from a spatial information storage unit (26) configured to store a collision area in which the robot (1) collides with the environment in a movement area, and an output from a shape storage unit (27) configured to store a shape of the robot (1) and the hand (11), to carry out, whereby the shape storage unit (27) is arranged to store a pre-grasping hand shape before the hand (11) grasps the object (W) and a post-grasping hand shape after the hand (11) has grasped the object (W). Appendix 14

[0117] In the robot control program according to Annex 13 includes the process of generating the operating path of the hand (11) a pre-grasp path generation process configured to generate, based on the pre-grasp hand shape, a pre-grasp operation path from a predetermined first position to a removal position of the object (W); and a post-grip path generating process configured to generate, based on the post-grip hand shape, a post-grip operation path from the object (W) removal position to a predetermined second position. LIST OF REFERENCE SYMBOLS 1 robot 2 Robot control 3 Image recording device 4 containers (receiving containers) 10 arms 11 hands 11a, 11b Hand claw 11c Hand (suction type) 21 Processing unit (computer processing unit) 22 Pick position calculation unit 23 Operating path generation unit 24 storage units 25 Path generation program 26 Spatial information storage unit 27 Shape storage unit 28 Workpiece shape measuring unit (object shape measuring unit) 29 Unit for generating the hand shape after grasping 100 robot system W Workpiece (object) 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] JP 2022-017739

[0008] JP 2022-017738

[0008]

Claims

[1] Robot controller for controlling a robot to remove an object in bulk by the robot having a hand, comprising a picking position calculation unit configured to calculate a picking position of the object based on image information from an image pickup device that captures an image including an object to be detected by the robot; a spatial information storage unit configured to store a movement range in which the robot can be operated and a collision range in which the robot collides with the environment in the movement range; a shape storage unit configured to store a shape of the robot and the hand; and an operation path generation unit configured to generate an operation path of the hand so that the robot does not collide with the surroundings based on outputs of the picking position calculation unit, the spatial information storage unit, and the shape storage unit, wherein the shape storage unit is configured to store a pre-grasping hand shape before the hand grasps the object and a post-grasping hand shape after the hand has grasped the object. [2] The robot controller according to claim 1, wherein the image pickup device is configured to pick up an image including the object and the hand. [3] Robot controller according to claim 1 or 2, wherein the image recording device is arranged to record a three-dimensional image containing the object and the hand, the operation path generation unit is configured to generate the operation path of the hand based on an output of the withdrawal position calculation unit, information of the three-dimensional image captured by the image pickup device, and the hand shape before grasping and the hand shape after grasping stored in the shape storage unit. [4] Robot controller according to one of claims 1 to 3, wherein the operation path generation unit is arranged to based on the pre-grasping hand shape, generates a pre-grasping path from a predetermined first position to the removal position of the object, and based on the hand shape after grasping, a post-grasp path is generated from the removal position of the object to a predetermined second position of the hand. [5] The robot controller according to any one of claims 1 to 4, wherein the shape storage unit is arranged to store a hand shape before grasping and a hand shape after grasping corresponding to a kind of objects having a same shape. [6] The robot controller according to any one of claims 1 to 4, wherein the shape storage unit is configured to store shapes of a plurality of types of objects having different shapes and a plurality of hand shapes before grasping and a plurality of hand shapes after grasping corresponding to the plurality of types of objects. [7] Robot controller according to claim 6, wherein the removal position calculation unit is configured to determine the type of object from the plurality of objects stored in the shape storage unit on the basis of the image captured by the image capturing device, and to calculate the removal position of the determined type of object, the shape storage unit is arranged to output a hand shape before grasping and a hand shape after grasping corresponding to the specific type of object, and the operation path generation unit is configured to generate an operation path of the hand based on the output hand shape before grasping and the output hand shape after grasping. [8] Robot controller according to one of claims 1 to 7, wherein the hand is attached to a movable section that can be operated in relation to the robot, the operation path generating unit is configured to correct the hand shape before grasping and the hand shape after grasping stored in the shape storing unit based on an operation of the hand by the movable portion with respect to the robot, and configured to generate an operation path of the hand. [9] Robot controller according to one of claims 1 to 8, further comprising an object shape measuring unit configured to measure an object shape of the object based on the image information from the image pickup device; and a hand shape generation unit configured to generate the hand shape after grasping on the basis of the object shape measured by the object shape measuring unit, wherein the operation path generation unit is configured to generate an operation path of the hand based on an output of the hand shape generation unit after grasping so that the robot does not collide with the environment. [10] Robot controller according to one of claims 1 to 9, wherein the object consists of several objects that are randomly placed in a receptacle, the hand removes individual objects in the receptacle one after the other, and the receptacle is replaced one after the other by other receptacles. [11] The robot controller according to claim 10, wherein the operation path generating unit is configured to detect changes in the shape and arrangement position of the receiving container based on the image information from the image pickup device, and is configured to generate an operation path of the hand. [12] A robot system comprising a robot having a hand configured to take an object in bulk, an image capturing device configured to capture an image including the object, and a robot controller configured to control the robot to take the object by the hand, wherein the robot controller is a robot controller according to any one of claims 1 to 11. [13] A robot control program for a robot system comprising a robot having a hand configured to take an object in bulk, an image pickup device configured to take an image containing the object, and a robot controller configured to control the robot to take the object by the hand, the robot control program causing a computation processing unit to: a process for calculating a picking position of an object to be detected by the robot based on the image information from the image pickup device; and a process for generating an operation path of the hand so that the robot does not collide with the environment, based on the image information from the image pickup device, an output from a spatial information storage unit configured to store a collision area in which the robot collides with the environment in a movement area, and an output from a shape storage unit configured to store a shape of the robot and the hand, to carry out, whereby the shape storage unit is configured to store a pre-grasping hand shape before the hand grasps the object and a post-grasping hand shape after the hand has grasped the object. [14] The robot control program according to claim 13, wherein the process of generating the operation path of the hand a pre-grasp path generation process configured to generate, based on the pre-grasp hand shape, a pre-grasp operation path from a predetermined first position to a removal position of the object; and a post-grasp path generating process configured to generate a post-grasp operation path from the object removal position to a predetermined second position based on the post-grasp hand shape.

Images