Control system for manipulators, method for controlling manipulators, and program
The control system for manipulators predicts contact states and adjusts gripping forces to ensure appropriate contact forces, addressing the issue of object and environment damage during physical interactions.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2023-09-08
- Publication Date
- 2026-07-29
AI Technical Summary
Existing manipulator control systems fail to manage contact forces appropriately during physical interactions with gripped objects and surrounding objects, leading to potential damage to either the object or the surrounding environment.
A control system for manipulators that includes an environment recognition unit, arm control unit, and hand control unit to predict contact states and adjust gripping forces based on object types and environmental data, ensuring appropriate contact forces are applied.
The system effectively controls manipulator movements to minimize damage to both gripped objects and surrounding objects by adjusting gripping forces, reducing the risk of object dropping or damage during contact.
Smart Images
Figure 0007896579000001 
Figure 0007896579000002 
Figure 0007896579000003
Abstract
Description
Technical Field
[0001] The present invention relates to a control system for a manipulator, a control method for a manipulator, and a program.
Background Art
[0002] In Patent Document 1, a control system for a manipulator is disclosed. In this system, in the manipulator, when an impact is detected, position control and impedance control are switched, and after impact avoidance, control to return to the original position is disclosed.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] In the technology according to Patent Document 1, there is a problem that in physical contact (e.g., placing or lifting) between the gripped object held by the manipulator and the surrounding objects, the movement of the manipulator cannot be controlled to contact with an appropriate contact force. Specifically, when placing a gripped object (e.g., an egg) on a surrounding object (e.g., a tabletop) using a manipulator, if the gripped object is strongly grasped and pressed against the surrounding object, an excessive contact force from the surrounding object is transmitted to the gripped object, and the gripped object may be damaged or, conversely, the surrounding object may be damaged. On the other hand, when placing a gripped object (e.g., a book) on a surrounding object (e.g., a bookshelf) using a manipulator, if the gripped object is not strongly grasped, the contact force transmitted from the surrounding object to the gripped object may not be sufficient, and there is a possibility that the gripped object cannot be properly placed on the surrounding object.
[0005] In view of such challenges, this disclosure aims to provide a manipulator control system, a manipulator control method, and a program that can control the movement of a manipulator so that it can make physical contact with a grasped object and a surrounding object with an appropriate contact force. [Means for solving the problem]
[0006] The control system for a manipulator of the present disclosure comprises an arm and a hand attached to the arm for gripping an object to be gripped, the control system comprising: an environment recognition unit for recognizing surrounding objects in the environment surrounding the manipulator; an arm control unit for controlling the movement of the arm; and a hand control unit for predicting the contact state between the object to be gripped and the surrounding objects and adjusting the gripping force of the hand according to the prediction of the contact state.
[0007] With the configuration described above, the control system for the manipulator of this disclosure recognizes surrounding objects using an object recognition engine, predicts the contact state between the grasped object and the surrounding objects, and adjusts the gripping force of the hand according to the predicted contact state. In this way, the control system for the manipulator can control the movement of the manipulator so that the grasped object held by the manipulator and the surrounding objects make contact with an appropriate contact force.
[0008] Furthermore, in the control system for the manipulator of this disclosure, the arm control unit controls the arm to place the object to be grasped on the surrounding object, and the hand control unit determines whether the difference between the position coordinates of the surrounding object and the position coordinates of the hand that grasps the object to be grasped is less than or equal to a predetermined threshold, and if it is determined that the difference is less than or equal to the predetermined threshold, it adjusts the gripping force of the hand to be weaker than the current gripping force.
[0009] For example, when using a manipulator to place an object to be grasped (e.g., an egg) onto a surrounding object (e.g., a tabletop), if the object to be grasped is gripped tightly and pressed against the surrounding object, the contact force from the surrounding object will be transmitted to the object to be grasped, potentially causing damage to the object to be grasped or, conversely, damaging the surrounding object. On the other hand, if the object to be grasped is gripped loosely, there is a risk that the gripping state by the manipulator (e.g., position and orientation within the hand) may change or the object to be grasped may fall while the object to be grasped is being manipulated. However, the control system of the manipulator of this disclosure, with the above configuration, weakens the gripping force of the hand just before the object to be grasped comes into contact with the surrounding object, and when a contact force is applied, the object to be grasped moves within the hand to absorb the contact force, thereby reducing the contact force applied to the object to be grasped and the surrounding object. Therefore, the control system can reduce the possibility of damage to the object to be grasped or, conversely, damage to the surrounding object. At the same time, the control system can reduce the risk of the gripping state by the manipulator changing or the gripped object falling while the object is being manipulated.
[0010] Furthermore, in the control system for the manipulator of this disclosure, the arm control unit determines the relationship between the type of object to be gripped and the type of surrounding object, and adjusts the gripping force of the hand based on the relationship.
[0011] For example, in physical contact between an object held by a manipulator and surrounding objects, the appropriate contact force differs depending on the type of object. The manipulator control system of this disclosure, with the above configuration, can control the movement of the manipulator so that, in physical contact between an object held by the manipulator and surrounding objects, the manipulator can make contact with an appropriate contact force depending on the type of object.
[0012] In the control system for a manipulator of this disclosure, the hand control unit uses the movement information of the manipulator to predict the contact state between the object to be gripped and surrounding objects, and adjusts the gripping force of the hand according to the predicted contact state.
[0013] For example, the movement information of the manipulator body (e.g., speed, momentum) has a very significant impact on predicting the contact state between the grasped object and the surrounding objects. With the above configuration, the control system of the manipulator of this disclosure can accurately predict the contact state.
[0014] The control method for a manipulator according to this disclosure is a method for controlling a manipulator comprising an arm and a hand attached to the arm for gripping an object to be gripped, wherein the method recognizes surrounding objects in the environment surrounding the manipulator, controls the movement of the arm, predicts the contact state between the object to be gripped and the surrounding objects, and adjusts the gripping force of the hand according to the predicted contact state.
[0015] With the above configuration, the control method for the manipulator of this disclosure recognizes surrounding objects using an object recognition engine, predicts the contact state between the grasped object and the surrounding objects, and adjusts the gripping force of the hand according to the predicted contact state. By doing so, the control method for the manipulator of this disclosure can control the movement of the manipulator so that the grasped object held by the manipulator and the surrounding objects make contact with an appropriate contact force.
[0016] The program of this disclosure is a program that causes a computer to control a manipulator comprising an arm and a hand attached to the arm for gripping an object to be gripped, and causes the computer to perform the following processes: recognize surrounding objects in the environment surrounding the manipulator, control the movement of the arm, predict the contact state between the object to be gripped and the surrounding objects, and adjust the gripping force of the hand according to the predicted contact state.
[0017] With the configuration described above, the program of this disclosure recognizes surrounding objects using an object recognition engine, predicts the contact state between the grasped object and the surrounding objects, and adjusts the gripping force of the hand according to the predicted contact state. In this way, the program of this disclosure can control the movement of the manipulator so that the grasped object held by the manipulator and the surrounding objects make contact with an appropriate contact force.
Advantages of the Invention
[0018] According to the present disclosure, it is possible to provide a control system for a manipulator, a control method for a manipulator, and a program that can control the movement of the manipulator so that, in physical contact between a gripped object gripped by the manipulator and a surrounding object, contact can be made with an appropriate contact force.
Brief Description of the Drawings
[0019] [Figure 1] It is an external perspective view showing an example of the configuration of a robot according to the first embodiment. [Figure 2] It is a block diagram showing an example of the configuration of a control device according to the first embodiment. [Figure 3] It is a flowchart showing an example of the operation of a control device according to the first embodiment. [Figure 4] It is a schematic diagram showing an example of the operation of a control device according to the first embodiment. [Figure 5] It is a flowchart showing another example of the operation of a control device according to the first embodiment.
Modes for Carrying Out the Invention
[0020] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and redundant descriptions are omitted as necessary for clarity of explanation.
[0021] (First Embodiment) First, the configuration of the robot 1 according to the first embodiment will be described using FIG. 1. FIG. 1 is an external perspective view showing an example of the configuration of a robot 1 according to the first embodiment. As shown in FIG. 1, the robot 1 includes a control device 10, a manipulator 20, an environmental sensor 30, and a tactile sensor 40.
[0022] The control device 10 is a computer. The control device 10 controls the manipulator 20, the environmental sensor 30, and the tactile sensor 40. The control device 10 is mounted on the main body of the robot 1. Alternatively, the control device 10 may be installed outside the main body of the robot 1 and control it by communicating with the robot 1. Furthermore, the control device 10 may not be a single computer, but a control system 10 implemented by multiple computers.
[0023] The manipulator 20 is rotatably mounted on the body of the robot 1. The manipulator 20 is a mobile manipulator that can move freely within the environment, mounted on the body of the robot 1 which is equipped with a travel mechanism. The manipulator 20 may also be a stationary arm robot in a factory or similar location. The manipulator 20 comprises an arm 21 and a hand 22. The arm 21 is a robotic arm. The arm 21 comprises one or more links and joints that rotatably connect each link. One end of the link is connected to the body of the robot 1 via a joint. The other end of the link is connected to the hand 22 via a joint. The hand 22 is a robotic hand for grasping objects. For example, the hand 22 is a multi-fingered hand having multiple fingers.
[0024] The environmental sensor 30 is installed on the head of the robot 1. The environmental sensor 30 is a sensor that measures environmental information, which is information about the environment around the manipulator 20. Specifically, the environmental sensor 30 is a 3D depth sensor that measures images including surrounding objects and the distance between surrounding objects as environmental information.
[0025] The tactile sensor 40 is installed in the gripping area of the hand 22. The tactile sensor 40 is a sensor that measures the current gripping force of the object being gripped by the hand 22. For example, the tactile sensor 40 is a film-type tactile sensor that measures the gripping force of the hand 22 by measuring the frictional force and pressure applied to the measurement area. Alternatively, the tactile sensor 40 may be a multi-array type tactile sensor that simultaneously measures the frictional force and pressure applied to the measurement area at multiple points. By using the gripping force information obtained from the tactile sensor 40, it is possible to estimate the contact force acting between the gripped object and the surrounding object when the gripped object comes into contact with the surrounding object. By collecting and analyzing contact force data, it is possible to predict whether the contact force is appropriate before contact occurs.
[0026] Next, the configuration of the control device 10 according to the first embodiment will be described using Figure 2. Figure 2 is a block diagram showing an example of the configuration of the control device 10 according to the first embodiment. As shown in Figure 2, the control device 10 includes an environment recognition unit 11, an arm control unit 12, and a hand control unit 13.
[0027] The environmental recognition unit 11 recognizes the environment surrounding the manipulator 20. Specifically, the environmental recognition unit 11 acquires environmental information from the environmental sensor 30. From the environmental information, the environmental recognition unit 11 uses an object recognition engine, such as a deep learning model, to recognize the object to be grasped by the manipulator 20 and surrounding objects. At this time, the environmental recognition unit 11 recognizes the type of object to be grasped and the type of surrounding objects. In addition, the environmental recognition unit 11 recognizes the position coordinates of surrounding objects relative to the robot coordinate system from the environmental information.
[0028] The arm control unit 12 controls the movement of the arm 21 of the manipulator 20. Specifically, the arm control unit 12 determines which peripheral object from among the recognized peripheral objects will be used to place the object to be grasped on. The arm control unit 12 calculates a trajectory plan for the arm 21 so that the object to be grasped is placed on the peripheral object. Then, the arm control unit 12 controls the movement of the arm 21 so that it moves along the trajectory plan. The arm control unit 12 also determines which peripheral object from among the recognized peripheral objects will be used to lift the object to be grasped. The arm control unit 12 calculates a trajectory plan for the arm 21 so that it lifts the object to be grasped. Then, the arm control unit 12 controls the movement of the arm 21 so that it moves along the trajectory plan. During the movement of the arm 21, the arm control unit 12 calculates the position coordinates of the end-effector of the hand 22 relative to the robot seat system from the joint angles and link lengths of the arm 21.
[0029] The hand control unit 13 controls the operation of the hand 22 of the manipulator 20. Specifically, the hand control unit 13 predicts the contact state between the object to be grasped and surrounding objects. Predicting the contact state includes predicting the possibility of contact between the object to be grasped and surrounding objects, and predicting whether or not contact is imminent. It also includes predicting the types of the object to be grasped and the surrounding objects, and whether the contact force transmitted to each object when they come into contact is appropriate. The hand control unit 13 then controls the gripping force of the hand 22 according to the predicted contact state. Specifically, the hand control unit 13 obtains the current gripping force of the hand 22 from the tactile sensor 40. The hand control unit 13 adjusts the current gripping force of the hand 22 to weaken it to a predetermined value according to the predicted contact state. The hand control unit 13 also adjusts the current gripping force of the hand 22 to strengthen it to a predetermined value according to the predicted contact state. Here, the predetermined value is the gripping force value calculated from the pressure and frictional force applied to the measurement area of the tactile sensor 40. Alternatively, in the case of simultaneous multi-point measurement, the predetermined value may be the gripping force value calculated from the number of measurement points measured in the measurement area of the tactile sensor 40.
[0030] For example, when the arm control unit 12 controls the movement of the arm 21 to place the object to be grasped onto a surrounding object, the hand control unit 13 performs the following processing: During the movement of the arm 21, the hand control unit 13 determines whether the difference between the position coordinates of the surrounding object relative to the robot coordinate system and the position coordinates of the end-effector of the hand 22 falls below a predetermined threshold. In other words, the hand control unit 13 predicts the possibility of contact between the object to be grasped and the surrounding object, and whether contact between the object to be grasped and the surrounding object is imminent. If the hand control unit 13 determines that the difference between the position coordinates of the object to be contacted and the position coordinates of the end-effector of the hand 22 is below a predetermined threshold, it adjusts the current gripping force of the hand 22, that is, the gripping force during the operation of the arm 21, to a predetermined value. By doing so, the hand control unit 13 can reduce the possibility of damage to each object by reducing the contact force, even if the contact force transmitted to each object when they come into contact is excessive. At the same time, the hand control unit 13 can reduce the risk of the gripping state by the manipulator changing or the gripped object falling while the object is being manipulated by weakening the gripping force immediately beforehand. However, the configuration is not limited to the above; the hand control unit 13 may also adjust the current gripping force of the hand 22 to a predetermined value if it determines that the difference between the position coordinates of the object being contacted and the position coordinates of the hand end of the hand 22 is below a predetermined threshold.
[0031] Furthermore, when the arm control unit 12 controls the movement of the arm 21 to place the object to be grasped onto a surrounding object, the hand control unit 13 performs the following processing: The hand control unit 13 determines the relationship between the type of object to be grasped and the type of surrounding object. In other words, the hand control unit 13 predicts what the type of object to be grasped and the type of surrounding object are, and whether the contact force transmitted to each object when they come into contact is appropriate. Based on the relationship between the type of object to be grasped and the type of surrounding object, the hand control unit 13 adjusts the gripping force of the hand 22. For example, if the object to be grasped is an egg and the surrounding object is a table, it is predicted that the contact force transmitted to each object will be excessive and there will be a possibility of damage to each object, so the hand control unit 13 weakens the current gripping force of the hand 22, that is, the gripping force of the arm 21 during operation, to a predetermined value. On the other hand, if the object to be grasped is a book and the surrounding object is a bookshelf, it is predicted that the contact force transmitted to the object will not be sufficient and it will not be able to be placed properly, so the hand control unit 13 strengthens the current gripping force of the hand 22 to a predetermined value.
[0032] Furthermore, when the arm control unit 12 controls the movement of the arm 21 to lift another surrounding object placed on the surrounding object as the object to be gripped, the hand control unit 13 performs the following processing: The hand control unit 13 determines the relationship between the type of object to be gripped and the type of surrounding object. Based on the relationship between the type of object to be gripped and the type of surrounding object, the hand control unit 13 adjusts the gripping force of the hand 22. If the object to be gripped or the surrounding object on which it is placed is a viscous object, it is predicted that the contact force transmitted to the object (e.g., tension) will be excessive and the object to be gripped will not be able to be lifted properly, so the hand control unit 13 increases the current gripping force of the hand 22 to a predetermined value.
[0033] Furthermore, especially in the case of a mobile manipulator 20 that can move freely within the environment, the movement information of the mobile manipulator 20 (e.g., speed, momentum) has a very significant impact on the hand control unit 13's prediction of the contact state. Therefore, the hand control unit 13 uses the movement information of the manipulator 20 to predict the contact state between the object to be grasped and surrounding objects. For example, the hand control unit 13 obtains the movement information of the manipulator 20 from the arm control unit 12. Alternatively, if a speed sensor (not shown) is attached to the manipulator 20, the hand control unit 13 may obtain the movement information of the manipulator 20 from the speed sensor. The hand control unit 13 adjusts the gripping force of the hand 22 according to the predicted contact state. Thus, the control device 10 can accurately predict the contact state between the object to be grasped and surrounding objects.
[0034] Furthermore, regarding the timing of adjusting the gripping force of the hand 22, the hand control unit 13 notes that if the adjustment timing is too early, there is a possibility that the gripping force of the object to be gripped will be excessive (or insufficient) before contact. Therefore, it is desirable that the timing of adjusting the gripping force of the hand 22 be after predicting the contact state between the object to be gripped and the surrounding objects, and at the latest at the time when the object to be gripped is actually gripped. Accordingly, the hand control unit 13 adjusts the gripping force of the hand 22 after a predetermined period has elapsed from the timing of predicting the contact state. For example, if the hand control unit 13 determines that the possibility of collision between the object to be gripped and the surrounding objects has increased after a predetermined period has elapsed from the timing of predicting the contact state, it adjusts the gripping force of the hand 22. Also, if the hand control unit 13 determines that the relative distance between the object to be gripped and the surrounding objects has become closer after a predetermined period has elapsed from the timing of predicting the contact state, it adjusts the gripping force of the hand 22. Therefore, with respect to the timing of adjusting the gripping force of the hand 22, the control device 10 can reduce the possibility that the gripping force of the object to be gripped will be excessive (or insufficient) before contact if the adjustment timing is too early.
[0035] Next, an example of the operation of the control device 10 according to the first embodiment will be described using Figures 3 and 4. Figure 3 is a flowchart illustrating an example of the operation of the control device 10 according to the first embodiment. Figure 4 is a schematic diagram showing an example of the operation of the control device 10 according to the first embodiment.
[0036] As a prerequisite for the following operations, the arm control unit 12 of the control device 10 calculates a trajectory plan for the arm 21 so that the object to be grasped comes into contact with the surrounding object, which is the table, and starts controlling the movement of the arm 21 to move the arm 21 along the trajectory plan.
[0037] As shown in Figures 3 and 4, first, in step S101, the environmental recognition unit 11 of the control device 10 calculates the position coordinates of the table top relative to the robot seating system from the environmental information acquired from the environmental sensor 30. Next, in step S102, the arm control unit 12 calculates the position coordinates of the end-effector of the hand 22 relative to the robot seat system from the joint angles and link lengths of the arm 21.
[0038] Next, in step S103, the hand control unit 13 determines whether the difference between the position coordinates of the tabletop relative to the robot seat system and the position coordinates of the end-effector of the hand 22 relative to the robot seat system is less than or equal to a predetermined threshold. If it is determined that the difference between the position coordinates of the tabletop and the position coordinates of the end-effector of the hand 22 is less than or equal to the predetermined threshold (YES in step S103), the process proceeds to step S104. On the other hand, if it is determined that the difference between the position coordinates of the tabletop and the position coordinates of the end-effector of the hand 22 is not less than or equal to the predetermined threshold (NO in step S103), the process returns to step S101.
[0039] In step S104, the hand control unit 13 reduces the current gripping force of the hand 22, that is, the gripping force of the arm 21 during operation, to a predetermined value. This predetermined value represents a gripping force sufficient to prevent the object to be gripped from slipping off the hand 22.
[0040] Next, another example of the operation of the control device 10 according to the first embodiment will be described using Figure 5. Figure 5 is a flowchart of another example of the operation of the control device 10 according to the first embodiment.
[0041] As a prerequisite for the following operations, the arm control unit 12 of the control device 10 calculates a trajectory plan for the arm 21 so that the object to be grasped comes into contact with a surrounding object, and starts controlling the movement of the arm 21 to move the arm 21 along the trajectory plan. Similar to the operations shown in Figures 3 and 4, the control device 10 performs the processes described in steps S101 to S103 above.
[0042] In step S201, after the YES processing in step S103, the hand control unit 13 calculates the relationship between the type of object to be grasped and the type of surrounding object. In step S202, the hand control unit 13 adjusts the gripping force of the hand 22 based on the relationship between the type of object to be gripped and the type of surrounding object. For example, if the object to be gripped is an egg and the surrounding object is a table, the hand control unit 13 weakens the current gripping force of the hand 22, i.e., the gripping force of the arm 21 during operation, to a predetermined value, as it is predicted that the contact force transmitted to each object will be excessive and that each object may be damaged. On the other hand, if the object to be gripped is a book and the surrounding object is a bookshelf, the hand control unit 13 strengthens the current gripping force of the hand 22 to a predetermined value, as it is predicted that the contact force transmitted to the object will not be sufficient and that it will not be able to be placed properly.
[0043] As described above, the control device 10 according to the first embodiment adjusts the gripping force of the hand according to the prediction of the contact state between the object to be gripped and the surrounding object. By doing so, the control device 10 can control the movement of the manipulator so that the object to be gripped by the manipulator 20 and the surrounding object make contact with an appropriate contact force in physical contact.
[0044] Furthermore, the control device 10 according to the first embodiment reduces the current gripping force of the hand 22 to a predetermined value just before the gripped object comes into contact with a surrounding object. By doing so, the control device 10 can absorb the contact force by allowing the gripped object to move within the hand 22 when a contact force is generated, thereby reducing the contact force applied to the gripped object and the surrounding object. Therefore, the control device 10 can reduce the possibility of the gripped object being damaged or, conversely, damaging the surrounding object. At the same time, the control device 10 can reduce the risk of the gripping state by the manipulator changing or the gripped object falling while the gripped object is being manipulated.
[0045] Furthermore, the control device 10 adjusts the gripping force of the hand 22 based on the relationship between the type of object being gripped and the type of surrounding objects. By doing so, the control device 10 can control the movement of the manipulator so that, in physical contact between the object being gripped and the surrounding objects, appropriate contact force can be applied depending on the type of object.
[0046] Furthermore, in the comparative example, when placing the object to be gripped onto a surrounding object using a manipulator, the contact force can be reduced by placing it at a low speed, but this has the disadvantage of increasing the working time. However, since the control device 10 does not place the object at a low speed, it does not have the disadvantage of increased working time.
[0047] In the comparative example, there is also a method in which the arm is softened by feedback control after the object to be gripped receives a contact force from a surrounding object, but this requires the feedback control to be run at least once, and there is a possibility that the contact force cannot be sufficiently reduced. However, the control device 10 can adjust the contact force by predicting the contact state between the object to be gripped and the surrounding object and appropriately adjusting the gripping force of the hand 22 of the manipulator 20 according to the predicted contact state.
[0048] The control device 10 in the above-described embodiment is composed of hardware, software, or both, and may consist of one piece of hardware or software, or multiple pieces of hardware or software.
[0049] Specifically, the control device 10 in the above-described embodiment is comprised of a computer comprising a processor and memory. The processor may be, for example, a microprocessor, an MPU (Micro Processing Unit), or a CPU (Central Processing Unit). The processor may include multiple processors. The memory is comprised of a combination of volatile memory and non-volatile memory. The memory may include storage located separately from the processor. In this case, the processor may access the memory via an I / O interface not shown. The processor executes one or more programs containing a set of instructions for causing the computer to perform the algorithm described with reference to the drawings.
[0050] The program, when loaded into a computer, includes a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable medium or a communication medium that includes electrically, optically, acoustically or otherwise propagating signals.
[0051] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.
[0052] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.
[0053] It should be noted that the present invention is not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of the invention. [Explanation of Symbols]
[0054] 1 Robot 10 Control device (control system) 11 Environmental recognition department 12 Arm control unit 13 Hand control unit 20 Manipulators 21 Arms 22 Hand 30 Environmental Sensors 40 Tactile sensors
Claims
1. A control system for a manipulator comprising an arm and a hand attached to the arm for gripping an object to be gripped, An environment recognition unit that recognizes surrounding objects in the environment surrounding the manipulator, An arm control unit that controls the movement of the arm, The hand includes a hand control unit that predicts the contact state between the object to be gripped and the surrounding object, and adjusts the gripping force of the hand according to the predicted contact state, The hand control unit determines whether the contact force between the object to be gripped and the surrounding object is appropriate, based on the prediction derived from the combination of the type of object to be gripped and the type of surrounding object, and adjusts the gripping force of the hand based on the determination. A control system for a manipulator.
2. The arm control unit is The arm is controlled to place the object to be grasped onto the surrounding object. The aforementioned hand control unit, The system determines whether the difference between the position coordinates of the surrounding object and the position coordinates of the hand gripping the object to be gripped falls below a predetermined threshold. If it is determined that the difference falls below the predetermined threshold, the system adjusts the gripping force of the hand to be weaker than the current gripping force. A control system for a manipulator according to claim 1.
3. The manipulator is a mobile manipulator having a body that can travel within the environment, The aforementioned hand control unit, Using the movement speed information or acceleration information of the manipulator's main body, the contact state between the object to be gripped and the surrounding object is predicted, and the gripping force of the hand is adjusted according to the predicted contact state. A control system for a manipulator according to claim 1 or 2.
4. A control method for a manipulator comprising an arm and a hand attached to the arm for gripping an object to be gripped, The manipulator recognizes surrounding objects in the environment surrounding it. Controlling the movement of the arm, When predicting the contact state between the object to be gripped and the surrounding objects, and adjusting the gripping force of the hand in accordance with the predicted contact state, it is determined whether the contact force between the object to be gripped and the surrounding objects is appropriate based on the prediction which is derived from the combination of the type of object to be gripped and the type of surrounding objects, and the gripping force of the hand is adjusted based on the determination. A method for controlling a manipulator.
5. A program that causes a computer to control a manipulator comprising an arm and a hand attached to the arm for gripping an object to be gripped, The manipulator recognizes surrounding objects in the environment surrounding it. Controlling the movement of the arm, The computer is instructed to predict the contact state between the object to be gripped and the surrounding objects, and to adjust the gripping force of the hand in accordance with the predicted contact state. This process involves determining whether the contact force between the object to be gripped and the surrounding objects is appropriate based on the prediction derived from the combination of the type of object to be gripped and the type of surrounding objects, and then adjusting the gripping force of the hand based on this determination. program.