Control device and control method

Abstract

[Problem] To make it possible for a hand unit to properly grasp a variety of objects. [Solution] A control device comprising a sensor switching unit for switching which tactile force sensor among a plurality of tactile force sensors that are provided to a hand unit and have different properties is to be used for grasping control of an object by the hand unit on the basis of the physical properties of the object.

Description

Control device and control method

[0001] The present disclosure relates to a control device and a control method.

[0002] In recent years, robotic devices capable of grasping objects, such as robot hands or manipulators, have come to be used in various industrial fields. As a result, the types and characteristics of objects that can be grasped by robotic devices have become more diverse.

[0003] On the other hand, in order to properly grasp an object with the hand unit provided on the robot device, it is important to detect the characteristics of the object, such as its size, weight, softness, or surface texture, using a force-tactile sensor, and to appropriately control the grasping force of the hand unit based on the detected characteristics.

[0004] For example, Patent Document 1 below discloses a robot that changes the sensitivity mode of a tactile sensor provided in a hand unit in accordance with tactile information of a target object acquired when the target object is grasped. The robot disclosed in Patent Document 1 can change the resolution of the tactile sensor in accordance with the load when grasping the target object.

[0005] Japanese Patent Application Laid-Open No. 2022-157130

[0006] However, depending on the physical characteristics of the object, it may be difficult to properly grasp it by simply changing the sensitivity of the force-tactile sensor. For example, in order to properly grasp objects of different sizes, it may be important to change the detection range or spatial resolution of the force-tactile sensor in addition to the sensitivity of the force-tactile sensor.

[0007] Therefore, the present disclosure proposes a new and improved control device and control method that can appropriately grip a variety of objects with a hand unit.

[0008] According to the present disclosure, a control device is provided that includes a sensor switching unit that switches between a plurality of force-tactile sensors with different characteristics provided in a hand unit, and that switches the force-tactile sensor used to control the gripping of an object by the hand unit based on the physical characteristics of the object.

[0009] Furthermore, according to the present disclosure, a control method is provided that includes switching a force-tactile sensor used to control the gripping of an object by the hand unit from among a plurality of force-tactile sensors with different characteristics provided in the hand unit based on the physical characteristics of the object.

[0010] 1 is a schematic diagram showing the configuration of a hand unit. FIG. 1 is a schematic diagram showing a detailed configuration of the vicinity of the claws of the hand unit. FIG. 2 is a schematic diagram showing the spatial resolution of a second sensor. FIG. 3 is a schematic diagram showing a detailed configuration of the vicinity of the claws of the hand unit according to a first modified example. FIG. 4 is a schematic diagram showing a detailed configuration of the vicinity of the claws of the hand unit according to a second modified example. FIG. 5 is a schematic diagram showing the claws of the hand unit according to the second modified example, viewed from the gripping surface side. FIG. 6 is a block diagram showing the functional configuration of a control device according to an embodiment of the present disclosure. FIG. 7 is a flowchart showing the flow of a method for controlling the hand unit by the control device. FIG. 8 is a schematic diagram showing the behavior of the hand unit in steps S105 to S106. FIG. 9 is a schematic diagram showing the behavior of the hand unit in steps S107 to S108. FIG. 10 is a schematic diagram showing an example of detecting the position of an object placed on a shelf using a first sensor and gripping the object using a second sensor. FIG. 11 is a schematic diagram showing an example of detecting the position of an object placed on a shelf using a second sensor and gripping the object using the first sensor. FIG. 12 is a schematic diagram showing an example of detecting the position of an object placed on a floor surface using the first sensor and the second sensor. 1 is a schematic diagram illustrating an example of recognizing the texture of a surface of an object placed on a floor surface using a first sensor and a second sensor;

[0011] Preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted.

[0012] The description will be given in the following order: 1. Hand unit 1.1. Configuration example 1.2. Modification 2. Control device 2.1. Configuration example 2.2. Control method 2.3. Modification 3. Hardware configuration example

[0013] <1. Hand Unit> (1.1. Configuration Example) A hand unit controlled by a control device according to an embodiment of the present disclosure will be described with reference to FIGS. 1 to 3. FIG. 1 is a schematic diagram showing the configuration of the hand unit 10. FIG. 2 is a schematic diagram showing a detailed configuration of the vicinity of the claws 15 of the hand unit 10. FIG. 3 is a schematic diagram showing the spatial resolution of the second sensor 12.

[0014] 1 , the hand unit 10 includes a main body 18 and a plurality of claws 15, each of which includes a link 17 and a buffer member 16. The hand unit 10 may be, for example, a two-claw gripper including two claws 15.

[0015] The main body 18 is a connection portion between the arm of the robot device or manipulator and the hand 10, and is provided at the base of the hand 10. Although not shown, the main body 18 may be provided with a mechanism and a controller for opening and closing the multiple claws 15 via the link 17, and may be connected to a cord or tube for supplying electricity or compressed air as a power source for opening and closing the multiple claws 15.

[0016] The claws 15 are highly rigid structural members that clamp an object to be grasped by the hand unit 10. A plurality of claws 15 are provided on the main body 18 via links 17. The hand unit 10 can grasp an object with the plurality of claws 15 by opening and closing the plurality of claws 15 relative to one another.

[0017] The claws 15 may be connected to the main body 18 via the links 17, or may be directly connected to the main body 18 without the links 17. However, by connecting the claws 15 to the main body 18 via the links 17, the opening width between the claws 15 can be made wider and more complex gripping operations can be performed.

[0018] The link 17 is a highly rigid structural member that connects the main body 18 and the claw 15. One end of the link 17 is rotatably connected to the main body 18, and the other end is rotatably connected to the claw 15. Specifically, one end of the link 17 is rotatably connected to each of the separated portions of the main body 18 via a joint having a rotation axis perpendicular to the plane of Fig. 1 . The other end of the link 17 is rotatably connected to each of the ends of the claw 15 via a joint having a rotation axis similarly perpendicular to the plane of Fig. 1 .

[0019] The buffer material portion 16 is made of, for example, a low-rigidity, low-resilience gel material and is provided on the surfaces (hereinafter also referred to as gripping surfaces) of the plurality of claw portions 15 that face each other. The buffer material portion 16 is provided to relieve pressure applied to an object to be gripped by the hand unit 10 from the plurality of claw portions 15 when the object is clamped between the plurality of claw portions 15. The buffer material portion 16 may be made of, for example, urethane gel, acrylic gel, or silicone gel. When the surfaces of the plurality of claw portions 15 that face each other are viewed in plan, the shape of the buffer material portion 16 may be circular or rectangular. For example, the three-dimensional shape of the buffer material portion 16 may be hemispherical.

[0020] Furthermore, in order to grip an object with an appropriate force, the claw portion 15 is equipped with a plurality of force-tactile sensors that detect the force-tactile sensation applied to the claw portion 15. Specifically, the claw portion 15 is equipped with a first sensor and a second sensor with different characteristics that detect the force applied to the claw portion 15. By switching the force-tactile sensor used when gripping an object between the first sensor and the second sensor, the hand portion 10 can detect the force-tactile sensation when gripping various objects with a force-tactile sensor having appropriate characteristics.

[0021] 2, the claw portion 15 is provided with a first sensor 11 and a second sensor 12. The first sensor 11 and the second sensor 12 may be force-tactile sensors that differ from each other in at least one of sensitivity, detection range, and spatial resolution, for example.

[0022] The first sensor 11 is a force-tactile sensor with higher sensitivity and lower spatial resolution than the second sensor 12, and is provided at a position on the link 17 side of the claw 15. The first sensor 11 may be, for example, a strain gauge, a piezoelectric element, or a load cell. The first sensor 11 can detect with high sensitivity the force or strain applied to the point where the first sensor 11 is provided. The detection range of the first sensor 11 may be 0.01 N to 1 N.

[0023] The second sensor 12 is a force-tactile sensor with lower sensitivity and higher spatial resolution than the first sensor 11, and is provided between the claw 15 and the buffer material 16. The second sensor 121 may be, for example, a capacitance-type, optical-type, or piezo-resistive pressure distribution sensor. The second sensor 12 can detect the pressure applied to the surface of the claw 15 that grips an object (i.e., the gripping surface) for each of multiple regions within the surface. The second sensor 12 can also estimate the force or slippage applied in the shear direction of the surface that grips the object from the change in pressure distribution within the surface that grips the object of the claw 15. The detection range of the second sensor 12 may be 1 N to 10 N.

[0024] 3, the second sensor 12 may detect the pressure applied to each of nine regions 12A equally divided into a 3 x 3 matrix, thereby detecting the pressure distribution applied to the gripping surface of the claw portion 15. However, it goes without saying that the second sensor 12 may also detect the pressure for each of regions divided more finely.

[0025] The hand unit 10, controlled by the control device according to this embodiment, switches the force-tactile sensor used to control the gripping of an object between the first sensor 11 and the second sensor 12 based on the physical characteristics of the object to be gripped. The physical characteristics of the object include, for example, at least one of the size, mass, surface hardness, and surface friction coefficient of the object. These physical characteristics determine whether delicate grip force control or grip force control that takes into account a wide range of pressure is required when gripping an object with the hand unit 10. Therefore, the hand unit 10 can grip the object more appropriately by switching the force-tactile sensor used to control the gripping of the object between the first sensor 11 and the second sensor 12, which have different characteristics, based on the physical characteristics of the object.

[0026] (1.2. Modifications) (First Modification) A first modification of the hand unit 10 controlled by the control device according to the present embodiment will be described with reference to Fig. 4. Fig. 4 is a schematic diagram showing a detailed configuration of the vicinity of the claws 15 of the hand unit 10 according to the first modification. The hand unit 10 according to the first modification differs from the configuration shown in Fig. 2 in the positions of the first sensor 11 and the second sensor 12.

[0027] 4, the claw portion 15 is provided with a first sensor 11 and a second sensor 12. The first sensor 11 and the second sensor 12 are force-tactile sensors that differ from each other in at least one of sensitivity, detection range, and spatial resolution, for example.

[0028] The first sensor 11 is provided stacked with the second sensor 12 between the claw portion 15 and the buffer portion 16. The first sensor 11 is provided closer to the claw portion 15 than the second sensor 12, and connects the buffer portion 16 and the second sensor 12 to the claw portion 15. This allows the first sensor 11 to detect with high sensitivity the force or strain applied to the point connecting the buffer portion 16 and the second sensor 12 to the claw portion 15.

[0029] The second sensor 12 is provided between the claw portion 15 and the buffer portion 16, stacked on the first sensor 11. The second sensor 12 is provided closer to the buffer portion 16 than the first sensor 11, and is provided on the surface of the buffer portion 16 opposite to the surface that clamps the object. This allows the second sensor 12 to detect the distribution of pressure applied to the buffer portion 16 when the object is clamped.

[0030] The hand unit 10 according to the first modified example can be made smaller by stacking the first sensor 11 and the second sensor 12 between the claw unit 15 and the buffer unit 16.

[0031] (Second Modification) A second modification of the hand unit 10 controlled by the control device according to the present embodiment will be described with reference to Figures 5 and 6. Figure 5 is a schematic diagram showing a detailed configuration of the vicinity of the claws 15 of the hand unit 10 according to the second modification. Figure 6 is a schematic diagram showing the claws 15 of the hand unit 10 according to the second modification, viewed from the gripping surface side. The hand unit 10 according to the second modification differs from the configuration shown in Figure 2 in the positions of the first sensor 11 and the second sensor 12.

[0032] 5 and 6, the claw portion 15 is provided with a first sensor 11 and a second sensor 12. The first sensor 11 and the second sensor 12 are force-tactile sensors that differ from each other in at least one of sensitivity, detection range, and spatial resolution, for example.

[0033] The first sensor 11 is provided on the gripping surface side of the claw portion 15 in a region different from the second sensor 12. For example, the first sensor 11 is stacked with the contact portion 11A that comes into contact with the object, and is provided in a region outside the region where the second sensor 12 is provided. This allows the first sensor 11 to detect with high sensitivity the force or strain applied to the contact portion 11A when the object is clamped.

[0034] The second sensor 12 is provided on the gripping surface side of the claw portion 15 in an area different from that of the first sensor 11. The second sensor 12 is stacked with the buffer portion 16 and provided in an area more inward than the area where the first sensor 11 is provided. This allows the second sensor 12 to detect the distribution of pressure applied to the buffer portion 16 when an object is clamped.

[0035] The hand unit 10 according to the second modified example can be made even smaller by providing the first sensor 11 and the second sensor 12 in parallel on the gripping surface of the claw unit 15 .

[0036] 2. Control Device> (2.1. Configuration Example) Next, a control device according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a block diagram showing the functional configuration of the control device 100 according to this embodiment.

[0037] 7, the control device 100 includes a sensor switching unit 101, a detection control unit 102, and a grip control unit 103. The control device 100 controls the gripping operation of the object by the hand unit 10 described above.

[0038] When attempting to reliably grasp an object with the hand unit 10, it is important to accurately detect the position of the object. However, when detecting the position of the object using an image of the object captured by a camera, the accuracy of recognizing the object in the captured image may be low, making it difficult to accurately detect the position of the object. In particular, when grasping a variety of objects with the hand unit 10, it is difficult to recognize all of the various objects with high accuracy from the captured image. Therefore, the control device 100 controls the hand unit 10 to bring the hand unit 10 into contact with the object in order to detect the position of the object.

[0039] Specifically, the control device 100 first switches the force-tactile sensor to either the first sensor 11 or the second sensor 12 based on the physical characteristics of the object to be grasped, thereby causing the hand unit 10 to detect the position of the object. Next, the control device 100 switches the force-tactile sensor to either the first sensor 11 or the second sensor 12 based on the physical characteristics of the object to be grasped, thereby causing the hand unit 10 to grasp the object.

[0040] The sensor switching unit 101 switches the force-tactile sensor used for the object detection operation by the hand unit 10 or the object gripping operation by the hand unit 10 between the first sensor 11 and the second sensor 12 based on the physical characteristics of the object. The physical characteristics of the object used for switching the force-tactile sensor by the sensor switching unit 101 are, for example, at least one of the size, mass, surface hardness, and surface friction coefficient of the object.

[0041] As an example, the size of an object can be estimated by object recognition of the object from an image captured by a camera or the like. The size of an object can be estimated by detecting whether or not there is contact between the object and the hand unit 10 when the hand unit 10 is moved to trace the object. Note that the size of an object may be the length of the object in the longest direction, the length of the object in the shortest direction, or the diameter when the object is approximated as a sphere.

[0042] As one example, the mass of the object can be obtained from a mass sensor installed in the environment where the object is present. As another example, the mass of the object can be obtained by object recognition of the object from an image captured by a camera or the like, and searching for the mass of the recognized object from a database or the like that stores general masses of various objects. As another example, the mass of the object can be estimated from the gripping force when the object was previously gripped by the hand unit 10, or the sensing results obtained by the second sensor 12 at that time. As yet another example, the mass of the object can be estimated by detecting, with the first sensor 11, the reaction force generated when the object is pushed horizontally by the hand unit 10 a predetermined distance. Note that, to estimate the mass from the reaction force, a calibration result previously performed using an object of known mass may be used.

[0043] As an example, the hardness of the surface of the object can be estimated by detecting the reaction force generated when the surface of the object is pressed from above by the hand unit 10 a predetermined distance using the first sensor 11 or the second sensor 12. Note that the estimation of hardness from the reaction force may use the results of a calibration performed in advance using an object of known hardness.

[0044] As an example, the coefficient of friction of the surface of the object can be estimated by detecting the fluctuation in pressure distribution when the object is traced with the hand unit 10 using the second sensor 12. Specifically, if the amount of fluctuation in the center of pressure distribution when the surface of the object is traced with the hand unit 10 is extremely small, it can be determined that the coefficient of friction of the surface of the object is low (i.e., slippery).

[0045] The detection control unit 102 controls the operation of the hand unit 10 to detect the position of an object. Specifically, the detection control unit 102 controls the operation of the hand unit 10 to detect the position of an object based on the sensing results of the force-tactile sensor (the first sensor 11 or the second sensor 12) switched based on the physical characteristics of the object.

[0046] The grip control unit 103 controls the operation of the hand unit 10 to grip an object. Specifically, the grip control unit 103 controls the operation of the hand unit 10 to grip an object based on the sensing results of the force-tactile sensor (the first sensor 11 or the second sensor 12) that is switched based on the physical characteristics of the object.

[0047] Based on the size of the object, the sensor switching unit 101 may switch the force-tactile sensor used to detect the position of the object and the force-tactile sensor used to grasp the object between the first sensor 11 and the second sensor 12. The threshold for switching the force-tactile sensor between the first sensor 11 and the second sensor 12 may be, for example, the thickness of the claw portion 15 in the normal direction of the surface that grips the object.

[0048] According to this, the detection control unit 102 can detect the position of a large object by detecting contact between the tip of the claw 15 with the first sensor 11. Thereafter, the grip control unit 103 can grip the large object with the gripping surface of the claw 15 based on the sensing result of the second sensor 12, which has higher spatial resolution. The detection control unit 102 can also detect the position of a small object by detecting contact between the gripping surface of the claw 15 with the second sensor 12. Thereafter, the grip control unit 103 can grip the small object with the tip of the claw 15 based on the sensing result of the first sensor 11, which has higher sensitivity. Therefore, the control device 100 can cause the hand unit 10 to grip both small and large objects.

[0049] The sensor switching unit 101 may switch the force-tactile sensor used when grasping an object between the first sensor 11 and the second sensor 12 based on the mass of the object.

[0050] According to this, the detection control unit 102 can detect the position of the object by detecting contact between the object and the tip of the claw unit 15 with the first sensor 11. The grip control unit 103 can then grip an object whose mass is lighter than a first threshold or heavier than a second threshold with the tip of the claw unit 15 based on the sensing result of the first sensor 11 (provided the first threshold is less than the second threshold). The grip control unit 103 can also grip an object whose mass is equal to or greater than the first threshold and less than the second threshold with the gripping surface of the claw unit 15 based on the sensing result of the second sensor 12 (provided the first threshold is less than the second threshold). Therefore, the control device 100 can grip a light object with the hand unit 10 with high sensitivity and can grip a heavy object with the hand unit 10 without damaging the buffer unit 16.

[0051] The sensor switching unit 101 may switch the force-tactile sensor used to detect the position of the object and the force-tactile sensor used to grasp the object between the first sensor 11 and the second sensor 12 based on the hardness of the surface of the object. The threshold for switching the force-tactile sensor between the first sensor 11 and the second sensor 12 may be, for example, the hardness of the surface of the second sensor 12 or the cushioning material unit 16.

[0052] According to this, the detection control unit 102 can detect the position of the object by using the first sensor 11 to detect contact between the tip of the claw portion 15 and an object softer than the second sensor 12 or the surface of the buffer portion 16. Thereafter, the grip control unit 103 can grip the object softer than the second sensor 12 or the surface of the buffer portion 16 with the gripping surface of the claw portion 15 based on the sensing result of the second sensor 12, which has higher spatial resolution. Furthermore, the detection control unit 102 can detect the position of the object by using the second sensor 12 to detect contact between the gripping surface of the claw portion 15 and an object harder than the second sensor 12 or the surface of the buffer portion 16. Thereafter, the grip control unit 103 can grip the object harder than the second sensor 12 or the surface of the buffer portion 16 with the tip of the claw portion 15 based on the sensing result of the first sensor 11, which has higher sensitivity. Therefore, the control device 100 can use the first sensor 11 to detect contact with an object whose surface is low in hardness and therefore difficult to detect with the second sensor 12 .

[0053] The sensor switching unit 101 may switch the force-tactile sensor used when grasping an object between the first sensor 11 and the second sensor 12 based on the coefficient of friction of the surface of the object. The threshold for switching the force-tactile sensor between the first sensor 11 and the second sensor 12 may be, for example, the coefficient of friction of the surface of the second sensor 12 or the cushioning material unit 16.

[0054] According to this, the detection control unit 102 can detect the position of the object by detecting contact between the object and the tip of the claw 15 with the first sensor 11. Thereafter, the grip control unit 103 can grip an object with a friction coefficient lower than a threshold value with the tip of the claw 15 based on the sensing result of the first sensor 11, which has higher sensitivity. Furthermore, the grip control unit 103 can grip an object with a friction coefficient higher than a threshold value with the gripping surface of the claw 15 based on the sensing result of the second sensor 12, which has higher spatial resolution. Therefore, the control device 100 can control the gripping of an object with a low surface friction coefficient, which is difficult to control with the second sensor 12, with the first sensor 11.

[0055] As described above, the switching between the first sensor 11 and the second sensor 12 based on the physical characteristics of the object may be determined based on a threshold value set for one of the physical characteristics of the object. Alternatively, the switching between the first sensor 11 and the second sensor 12 based on the physical characteristics of the object may be determined by comprehensively considering, for example, multiple physical characteristics of the object.

[0056] For example, switching between the first sensor 11 and the second sensor 12 may be determined by classifying the object using a multi-class classification method with a learning model such as a support vector machine. Specifically, the sensor switching unit 101 can determine whether to use the first sensor 11 or the second sensor 12 for the object detection operation or the object grasping operation by classifying the object using the learning model that uses multiple physical properties of the object as input.

[0057] Furthermore, switching between the first sensor 11 and the second sensor 12 may be determined by accumulating evaluation results of the position detection and gripping operation for each object and learning the correspondence between the accumulated evaluation results and multiple physical properties of the object. By using a learning model that has learned the correspondence between the evaluation results and multiple physical properties of the object, the sensor switching unit 101 can determine whether the first sensor 11 or the second sensor 12 should be the force-tactile sensor used for the object detection operation or gripping operation.

[0058] According to the control device 100 of this embodiment having the above configuration, the hand unit 10 can automatically switch between multiple force-tactile sensors with different characteristics to detect the position of an object and perform a grasping operation.

[0059] (2.2. Control Method) Next, a control method for the hand unit 10 by the control device 100 according to this embodiment will be described with reference to Figs. 8 to 10. Fig. 8 is a flowchart showing the flow of a control method for the hand unit 10 by the control device 100. The flowchart shown in Fig. 8 shows an example in which the force-tactile sensor is switched using the size of the object as the physical property of the object. Fig. 9 is a schematic diagram showing the behavior of the hand unit 10 in steps S105 and S106, and Fig. 10 is a schematic diagram showing the behavior of the hand unit 10 in steps S107 and S108.

[0060] 8 , an image of an object is captured by a camera to acquire the size of the object as a physical characteristic of the object (S101). Next, the captured image is subjected to object recognition to acquire the size of the object as a physical characteristic of the object (S102). Next, the control device 100 controls the trajectory of the hand unit 10 to bring the hand unit 10 closer to the object for position detection and grasping (S103).

[0061] Furthermore, the sensor switching unit 101 determines whether the size, which is a physical property of the object, is equal to or larger than a threshold value (S104). Here, the threshold value may be the thickness of the claws 15 in the normal direction of the surface that grips the object.

[0062] If the size of the object is equal to or larger than the threshold value (S104 / YES), the detection control unit 102 detects the position of the object by detecting contact between the object and the hand unit 10 using the first sensor 11 (S105). Thereafter, the grip control unit 103 controls gripping of the object using the second sensor 12 (S106).

[0063] Specifically, as shown in FIG. 9 , the hand unit 10 brings the tips of the claws 15 as probes close to the object Ob and moves them vertically or horizontally to bring the tips of the claws 15 into contact with the object Ob. This allows the first sensor 11 to detect contact between the tips of the claws 15 and the object Ob as a force or strain applied to the claws 15. Therefore, the detection control unit 102 can determine the outer edge of the object Ob based on the contact between the object Ob and the tips of the claws 15, thereby detecting the position of the object Ob. The grip control unit 103 then controls the gripping force using the second sensor 12 to clamp the object Ob between the gripping surfaces of the claws 15, thereby gripping the object Ob.

[0064] If the size of the object is less than the threshold value (S104 / NO), the detection control unit 102 detects the position of the object by detecting contact between the object and the hand unit 10 using the second sensor 12 (S107). Thereafter, the grip control unit 103 controls gripping of the object using the first sensor 11 (S108).

[0065] Specifically, as shown in FIG. 10 , the hand unit 10 brings the cushioning material 16 of the claws 15 into contact with the object Ob by moving the claws 15 downward with the surfaces thereof (i.e., the gripping surfaces) facing downward. In this manner, the second sensor 12 can detect the contact between the cushioning material 16 and the object Ob as a change in pressure distribution on the gripping surfaces of the claws 15. Therefore, the detection control unit 102 can detect the position of the object Ob from the pressure distribution within the gripping surfaces of the claws 15. Thereafter, the gripping control unit 103 can grip the object Ob by clamping the object Ob at the tips of the claws 15 while controlling the gripping force with the first sensor 11.

[0066] According to the above operation, the control device 100 switches the force-tactile sensor based on the physical properties of the object, thereby enabling the hand unit 10 to detect the position of the object and to properly grasp the object.

[0067] (2.3. Modifications) (First Modification) A first modification of the control of the hand unit 10 by the control device 100 will be described with reference to Figs. 11 and 12. The first modification of the control of the hand unit 10 is a modification in which, when the object is not observed by a camera or the like, the hand unit 10 searches for the object and grasps the searched object with the hand unit 10. Fig. 11 is a schematic diagram showing an example in which the first sensor 11 is used to detect the position of an object Ob placed on a shelf Sh, and the second sensor 12 is used to grasp the object Ob. Fig. 12 is a schematic diagram showing an example in which the second sensor 12 is used to detect the position of an object Ob placed on a shelf Sh, and the first sensor 11 is used to grasp the object Ob.

[0068] 11 , for example, an object Ob on a shelf Sh may be hidden in a blind spot and not be observed depending on the camera's orientation and angle of view. In such a case, the control device 100 causes the hand unit 10 to search for the object Ob using the first sensor 11.

[0069] For example, the hand unit 10 moves the tip of the claw 15 as a probe toward the back of the shelf Sh. As a result, the tip of the claw 15 comes into contact with the object Ob, and the first sensor 11 can detect the contact between the tip of the claw 15 and the object Ob as a force or strain applied to the claw 15. Therefore, the detection control unit 102 can detect the position of the object Ob based on the contact with the tip of the claw 15. Thereafter, the grip control unit 103 controls the gripping force with the second sensor 12 while clamping the object Ob between the gripping surfaces of the claw 15, thereby gripping the object Ob.

[0070] On the other hand, if the size of the object Ob is small, the object Ob may not be found when the hand unit 10 searches using the first sensor 11. In such a case, as shown in Fig. 12, the control device 100 causes the hand unit 10 to search for the object Ob using the second sensor 12.

[0071] For example, the hand unit 10 moves the claws 15 downward toward the back of the shelf Sh with the surfaces (i.e., the gripping surfaces) of the claws 15 on which the buffer portions 16 are provided facing downward. As a result, the buffer portions 16 provided on the claws 15 come into contact with the object Ob, and the second sensor 12 can detect the contact between the buffer portions 16 and the object Ob as a change in pressure distribution on the gripping surfaces of the claws 15. Therefore, the detection control unit 102 can detect the position of the object Ob from the pressure distribution on the gripping surfaces of the claws 15. Thereafter, the grip control unit 103 controls the gripping force with the first sensor 11 to clamp the object Ob with the tips of the claws 15, thereby gripping the object Ob.

[0072] According to the first variant of the control of the hand unit 10, even if the object Ob is not observed by a camera or the like, the control device 100 can search for the object Ob with the hand unit 10 and grasp the object Ob.

[0073] (Second Modification) A second modification of the control of the hand unit 10 by the control device 100 will be described with reference to Figs. 13 and 14. The second modification of the control of the hand unit 10 is a modification that more reliably detects an object Ob placed on a floor surface Fr by simultaneously using the first sensor 11 and the second sensor 12. Fig. 13 is a schematic diagram showing an example of detecting the position of an object Ob placed on a floor surface Fr using the first sensor 11 and the second sensor 12. Fig. 14 is a schematic diagram showing an example of recognizing a texture Tx on the surface of an object Ob placed on a floor surface Fr using the first sensor 11 and the second sensor 12.

[0074] As shown in FIG. 13 , for example, assume that a thin object Ob is placed on a floor surface Fr. In this case, the hand unit 10 moves the claws 15 toward the object Ob while detecting with the first sensor 11 that the tips of the claws 15 are in contact with the floor surface Fr. As a result, the buffer material 16 provided on the claws 15 contacts the object Ob, and the second sensor 12 can detect the contact between the buffer material 16 and the object Ob as a change in pressure distribution on the gripping surface of the claws 15. Therefore, the detection control unit 102 can detect the position of the object Ob from the pressure distribution on the gripping surface of the claws 15. Based on the sensing result of the first sensor 11, the control device 100 can move the hand unit 10 toward the object Ob while maintaining the height of the hand unit 10 near the floor surface Fr. Therefore, the control device 100 can reliably detect the position of the object Ob with the second sensor 12.

[0075] 14 , for example, assume that a thin object Ob having a texture Tx such as an uneven surface is placed on a floor Fr. In this case, the hand unit 10 moves the claws 15 toward the object Ob while detecting with the first sensor 11 that the tips of the claws 15 are in contact with the floor Fr. As a result, the buffer material 16 provided on the claws 15 comes into contact with the texture Tx on the surface of the object Ob, and the second sensor 12 can detect the contact between the buffer material 16 and the texture Tx as a change in the pressure distribution on the gripping surface of the claws 15. Therefore, the detection control unit 102 can detect the uneven shape of the texture Tx formed on the surface of the object Ob from the pressure distribution on the gripping surface of the claws 15. That is, the control device 100 can detect the shape of the texture Tx on the surface of the object Ob using the second sensor 12 by keeping the hand unit 10 near the floor surface Fr based on the sensing results of the first sensor 11 and bringing the hand unit 10 close to the object Ob.

[0076] 3. Hardware Configuration Example The hardware configuration of the control device 100 according to this embodiment will be described further with reference to Fig. 15. Fig. 15 is a block diagram showing an example of the hardware configuration of the control device 100 according to this embodiment.

[0077] The functions of the control device 100 according to this embodiment can be realized by cooperation between software and the hardware described below. The functions of the sensor switching unit 101, the detection control unit 102, and the grip control unit 103 can be executed by, for example, the CPU 901.

[0078] As shown in FIG. 15 , the control device 100 includes a CPU (Central Processing Unit) 901 , a ROM (Read Only Memory) 902 , and a RAM (Random Access Memory) 903 .

[0079] The control device 100 may further include a host bus 904a, a bridge 904, an external bus 904b, an interface 905, an input device 906, an output device 907, a storage device 908, a drive 909, a connection port 910, or a communication device 911. The control device 100 may include a processing circuit such as a DSP (Digital Signal Processor) or an ASIC (Application Specific Integrated Circuit) instead of or together with the CPU 901.

[0080] The CPU 901 functions as an arithmetic processing unit or a control unit, and controls the operation within the control unit 100 in accordance with various programs recorded in the ROM 902, the RAM 903, the storage unit 908, or a removable recording medium attached to the drive 909. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, and parameters used during the execution of the programs.

[0081] The CPU 901, ROM 902, and RAM 903 are interconnected by a host bus 904a capable of high-speed data transmission. The host bus 904a is connected to an external bus 904b, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 904. The external bus 904b is connected to various components via an interface 905.

[0082] The input device 906 is a device that accepts input from a user, such as a mouse, keyboard, touch panel, button, switch, or lever. The input device 906 may also be a microphone that detects the user's voice. The input device 906 may also be, for example, a remote control device that uses infrared rays or other radio waves, or may be an externally connected device that supports operation of the control device 100.

[0083] The input device 906 further includes an input control circuit that outputs an input signal generated based on information input by the user to the CPU 901. By operating the input device 906, the user can input various data to the control device 100 or instruct the control device 100 to perform processing operations.

[0084] The output device 907 is a device that can visually or audibly present information acquired or generated by the control device 100 to the user. The output device 907 may be, for example, a display device such as an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), an OLED (Organic Light Emitting Diode) display, a hologram, or a projector, or may be a sound output device such as a speaker or headphones, or a printing device such as a printer. The output device 907 can output information acquired by processing by the control device 100 as video such as text or an image, or sound such as voice or audio.

[0085] The storage device 908 is a data storage device configured as an example of a storage unit of the control device 100. The storage device 908 may be configured, for example, by a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, or a magneto-optical storage device. The storage device 908 can store programs executed by the CPU 901, various data, various data acquired from the outside, and the like.

[0086] The drive 909 is a device for reading or writing data from or to a removable recording medium such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and is built into or externally attached to the control device 100. For example, the drive 909 can read information recorded on an attached removable recording medium and output the information to the RAM 903. The drive 909 can also write data to an attached removable recording medium.

[0087] The connection port 910 is a port for directly connecting an external device to the control device 100. The connection port 910 may be, for example, a Universal Serial Bus (USB) port, an IEEE 1394 port, or a Small Computer System Interface (SCSI) port. The connection port 910 may also be an RS-232C port, an optical audio terminal, or a High-Definition Multimedia Interface (HDMI) (registered trademark) port. By connecting the connection port 910 to an external device, various types of data can be transmitted and received between the control device 100 and the external device.

[0088] The communication device 911 is, for example, a communication interface configured with a communication device for connecting to the communication network 920. The communication device 911 may be, for example, a communication card for a wired or wireless LAN (Local Area Network), Wi-Fi (registered trademark), Bluetooth (registered trademark), or WUSB (Wireless USB). The communication device 911 may also be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various types of communication.

[0089] The communication device 911 can transmit and receive signals, for example, via the Internet or other communication devices using a predetermined protocol such as TCP / IP. The communication network 920 connected to the communication device 911 is a wired or wireless network, and may be, for example, an Internet communication network, a home LAN, an infrared communication network, a radio wave communication network, or a satellite communication network.

[0090] It is also possible to create a program for causing hardware such as the CPU 901, ROM 902, and RAM 903 built into a computer to perform functions equivalent to those of the control device 100. It is also possible to provide a computer-readable recording medium on which the program is recorded.

[0091] Although the preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person skilled in the art of the present disclosure can conceive of various modified or altered examples within the scope of the technical idea described in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

[0092] Furthermore, the effects described herein are merely descriptive or exemplary and are not limiting. In other words, the technology according to the present disclosure may achieve other effects that will be apparent to those skilled in the art from the description of this specification, in addition to or in place of the above-described effects.

[0093] Note that the following configurations also fall within the technical scope of the present disclosure. (1) A control device comprising: a sensor switching unit that switches, from a plurality of force-tactile sensors provided in a hand unit and having different characteristics, a force-tactile sensor used to control the gripping of an object by the hand unit based on the physical characteristics of the object. (2) The control device described in (1), in which the plurality of force-tactile sensors differ from one another in at least one of sensitivity, detection range, and spatial resolution. (3) The control device described in (2), in which the plurality of force-tactile sensors include a first sensor that detects a force or strain applied to a point and a second sensor that detects a pressure distribution applied to a surface. (4) The control device described in (3), in which the sensitivity of the first sensor is higher than the sensitivity of the second sensor. (5) The control device described in any one of (1) to (4), in which the physical characteristics are at least one or more of size, mass, surface hardness, and surface friction coefficient. (6) The control device according to any one of (1) to (5), wherein the physical property is estimated based on detection results of the plurality of force-tactile sensors. (7) The control device according to any one of (1) to (5), wherein the physical property is estimated based on a recognition result of the object from an image of the object. (8) The control device according to any one of (1) to (7), wherein the sensor switching unit switches the force-tactile sensor used for grip control of the object based on a threshold value set for the physical property. (9) The control device according to any one of (1) to (7), wherein the sensor switching unit switches the force-tactile sensor used for grip control of the object based on a machine learning model using the plurality of physical properties. (10) The control device according to any one of (1) to (9), wherein the sensor switching unit further switches the force-tactile sensor used for position detection of the object from the plurality of force-tactile sensors based on the physical property of the object. (11) The control device according to (10), wherein the force-tactile sensor used to detect the position of the object detects the position of the object by detecting contact between the hand unit and the object. (12) The control device according to any one of (1) to (11), wherein the hand unit is a gripper having two or more and four or less claws.(13) The control device according to any one of (1) to (12), further comprising a grip control unit that controls gripping of the object by the hand unit based on the detection result of a force-tactile sensor used for gripping control of the object. (14) A control method including: switching, based on the physical properties of the object, a force-tactile sensor used for gripping control of the object by the hand unit from among a plurality of force-tactile sensors provided in the hand unit and having different characteristics.

[0094] REFERENCE SIGNS LIST 10 Hand unit 11 First sensor 12 Second sensor 15 Claw unit 16 Cushioning material unit 17 Link 18 Main unit 100 Control device 101 Sensor switching unit 102 Detection control unit 103 Grasping control unit Ob Object

Claims

1. A control device comprising a sensor switching unit that switches the force-tactile sensor used to control the gripping of an object by the hand unit from among multiple force-tactile sensors with different characteristics provided in the hand unit based on the physical characteristics of the object.

2. The control device according to claim 1, wherein the plurality of force-tactile sensors differ from one another in at least one of sensitivity, detection range, and spatial resolution.

3. The control device according to claim 2, wherein the plurality of force-tactile sensors include a first sensor that detects a force or strain applied to a point and a second sensor that detects a pressure distribution applied to a surface.

4. The control device according to claim 3, wherein the sensitivity of the first sensor is higher than the sensitivity of the second sensor.

5. The control device of claim 1, wherein the physical characteristic is at least one of size, mass, surface hardness, or surface coefficient of friction.

6. The control device according to claim 1, wherein the physical property is estimated based on the detection results of the plurality of force-tactile sensors.

7. The control device according to claim 1, wherein the physical characteristics are estimated based on a recognition result of the object from an image of the object.

8. The control device according to claim 1, wherein the sensor switching unit switches the force-tactile sensor used for grip control of the object based on a threshold value set for the physical property.

9. The control device according to claim 1, wherein the sensor switching unit switches the force-tactile sensor used for grip control of the object based on a machine learning model that uses a plurality of the physical characteristics.

10. The control device according to claim 1, wherein the sensor switching unit further switches the force-tactile sensor used to detect the position of the object from among the plurality of force-tactile sensors based on the physical properties of the object.

11. The control device according to claim 10, wherein the force-tactile sensor used to detect the position of the object detects the position of the object by detecting contact between the hand unit and the object.

12. The control device according to claim 1, wherein the hand unit is a gripper having two to four jaws.

13. The control device according to claim 1, further comprising a gripping control section that controls gripping of the object by the hand section based on the detection results of a force-tactile sensor used to control gripping of the object.

14. A control method including switching the force-tactile sensor used to control the gripping of an object by the hand unit from among a plurality of force-tactile sensors with different characteristics provided in the hand unit based on the physical characteristics of the object.

Images