Manipulator and method for controlling a manipulator

Abstract

A manipulator is disclosed. The manipulator according to the present disclosure includes a gripper, a depth sensor, a force sensor that senses an external force acting on the gripper, a memory, and a processor, wherein the processor controls the gripper to grasp an object, acquires first information about the object based on a first sensed value obtained by the force sensor while grasping the object, controls the gripper so that a first region of the object comes into contact with a surface on which the object is to be placed, acquires position information about a contact region between the first region and the surface, acquires a rotation direction for rotating the object based on the position information and the first information about the object, controls the gripper to rotate the object in the rotation direction with respect to the contact region, and controls the gripper to release the grasp of the object when a second region of the object comes into contact with the ground.

Description

Technical Field

[0001] This disclosure relates to a manipulator and a method for controlling the manipulator, and more specifically, to a manipulator for placing an object on the ground and a method for controlling the manipulator. Background Technology

[0002] In recent years, with the development of robotics technology, various types of robots are being used, such as cleaning robots, service robots, and industrial robots. As an example of industrial robots, there are manipulators in the form of human hands and arms used to perform various operations. Summary of the Invention

[0003] Technical issues

[0004] Figure 1 This is a diagram illustrating the placement operation of the manipulator. (Refer to...) Figure 1 The manipulator 11 can perform a placement operation to place the grasped object 12 onto the ground or surface 13. In this case, the manipulator 11 must place the object stably so that it does not fall. In the current placement method, the pose of the object 12 is estimated based on its shape information, and placement is performed based on the estimated pose. However, in the current method, when the shape of the object 12 is asymmetrical, the pose of the object 12 cannot be accurately estimated, thus limiting its stability in placement.

[0005] Therefore, a technique is needed for a more stable placement method.

[0006] Technical solution

[0007] A manipulator capable of stably placing objects is provided.

[0008] Other aspects will be set forth in part in the description which follows, and in part will be apparent from the description, or may be learned by practicing the embodiments presented.

[0009] According to one aspect of this disclosure, a manipulator is provided, comprising: a gripper; a depth sensor; a force sensor configured to sense an external force acting on the gripper; a memory storing instructions; and a processor configured to execute instructions to perform the following operations: controlling the gripper to grasp an object; acquiring first information about the object based on a first sensing value obtained by the force sensor while grasping the object; controlling the gripper such that a first region of the object contacts a surface on which the object will be placed; acquiring position information about a contact area between the first region and the surface; acquiring a rotation direction for rotating the object based on the position information and the first information about the object; controlling the gripper to rotate the object about the contact area in the rotation direction; and controlling the gripper to release the object based on a second region of the object contacting the surface.

[0010] The first information about the object may include information about the gravity acting on the object, and information about the distance from the force sensor to the line of action of gravity.

[0011] The processor can also be configured to execute instructions to perform the following operations: based on first information about the object, a second sensing value about the surface obtained by a depth sensor, and a third sensing value obtained by a force sensor while the first region is in contact with the surface, to obtain the position information about the contact area.

[0012] The processor can also be configured to execute instructions to perform the following operations: to obtain a torque centered on the contact area based on first information about the object and the position information, and to obtain the rotation direction based on the torque.

[0013] The processor can also be configured to execute instructions to perform the following operation: based on a first sensing value obtained by the force sensor being greater than a first value, identify that a first region is in contact with the surface.

[0014] The processor can also be configured to execute instructions to perform the following operation: based on the fact that the change in a first sense value obtained by the force sensor within a predetermined time is greater than a second value, identify that a second region is in contact with the surface.

[0015] The processor can also be configured to execute instructions to: acquire shape information about the object based on a second sensing value obtained by a depth sensor, and identify a mounting surface of the object, including a first region and a second region, based on the shape information about the object.

[0016] The processor can also be configured to execute instructions to control the gripper such that, based on the difference between a first direction of a first normal vector about the surface and a second direction of a second normal vector about the placement surface within a predetermined range, a first region contacts the surface.

[0017] According to one aspect of this disclosure, a method for controlling a manipulator is provided, the manipulator including a gripper, a depth sensor, and a force sensor configured to acquire an external force acting on the gripper, the method comprising: gripping an object using the gripper; acquiring first information about the object based on a first sensing value acquired by the force sensor while gripping the object; bringing a surface on which the object is placed into contact with a first region of the object; acquiring positional information about a contact area between the first region and the surface; acquiring a rotational direction for rotating the object based on the positional information and the first information about the object; rotating the object about the contact area in the rotational direction; and releasing the object by the gripper based on a second region of the object contacting the surface.

[0018] The first information about the object may include information about the gravity acting on the object, and information about the distance from the force sensor to the line of action of gravity.

[0019] The step of obtaining positional information about the contact area may include: obtaining positional information about the contact area based on first information about the object, a second sensing value about the surface obtained by a depth sensor, and a third sensing value obtained by a force sensor while the first area is in contact with the surface.

[0020] The step of obtaining the rotation direction may include: obtaining a torque centered on the contact area based on first information about the object and the position information, and obtaining the rotation direction based on the torque.

[0021] The method may further include: identifying a first region in contact with the surface based on a first sensing value of a force sensor being greater than a first value.

[0022] The method may further include: identifying a second region in contact with the surface based on the fact that the change in a first sensing value obtained by the force sensor within a predetermined time is greater than a second value.

[0023] The method may further include: acquiring shape information about an object based on sensing values ​​obtained by a depth sensor; and identifying a placement surface of the object, including a first region and a second region, based on the shape information about the object.

[0024] According to one aspect of this disclosure, an apparatus is provided, comprising: a gripper; a memory storing instructions; and a processor configured to execute instructions to perform the following operations: acquiring first information about an object gripped by the gripper based on force-sensing values; acquiring position information about a first region of the object and a contact region between a surface in contact with the object; acquiring a rotation direction for rotating the object based on the position information and the first information about the object; rotating the object about the contact region in the rotation direction; and releasing the object by the gripper based on a second region of the object contacting the ground.

[0025] The processor can also be configured to execute instructions to perform the following operations: obtain torque based on first information about the object and the position information, and obtain the rotation direction based on the torque.

[0026] The processor can also be configured to execute instructions to perform the following operation: based on a force-sensing value greater than a predetermined first value, identify that a first region is in contact with the surface.

[0027] The processor can also be configured to execute instructions to identify a second region in contact with the surface based on the fact that the change in the force-sensing value within a predetermined time period is greater than a predetermined second value.

[0028] The processor can also be configured to execute instructions to perform the following operations: acquiring shape information about the object based on depth sensing values, and identifying a placement surface of the object, including a first region and a second region, based on the shape information about the object.

[0029] The solutions to the problems disclosed herein are not limited to the solutions described above, and those skilled in the art to which this disclosure pertains will clearly understand the solutions not described based on this disclosure and the accompanying drawings.

[0030] Beneficial effects

[0031] According to the various embodiments of this disclosure as described above, the manipulator can stably place an object. Therefore, accidents where the object falls during the placement process can be prevented.

[0032] Furthermore, the effects that can be obtained or predicted by the embodiments of this disclosure will be disclosed directly or implicitly in the detailed description of the embodiments of this disclosure. For example, various effects predicted according to the embodiments of this disclosure will be disclosed in the specific embodiments described below.

[0033] Other aspects, advantages, and key features of this disclosure will become apparent to those skilled in the art from the following detailed description of various embodiments of the disclosure taken in conjunction with the accompanying drawings. Attached Figure Description

[0034] The above and other aspects, features, and advantages of specific embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings, in which:

[0035] Figure 1 This is a diagram illustrating the placement operation of the manipulator;

[0036] Figure 2 This is a diagram illustrating the configuration of the manipulator according to an embodiment;

[0037] Figure 3 This is a diagram illustrating information acquired by the manipulator according to an embodiment;

[0038] Figure 4 This is a diagram illustrating a method for determining the placement surface of an object according to an embodiment;

[0039] Figure 5 This is a diagram illustrating a method for obtaining the rotation direction according to an embodiment;

[0040] Figure 6 This is a diagram illustrating a method of placing an object according to an embodiment; and

[0041] Figure 7 This is a flowchart of a method for controlling a manipulator according to an embodiment. Detailed Implementation

[0042] The terminology used in the example embodiments will be briefly explained, and the example embodiments will be described in more detail with reference to the accompanying drawings.

[0043] Considering the configuration and functionality of this disclosure, the terminology used herein has been selected as currently widely used and common terms, but may vary depending on the intent of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in specific cases, terms may be arbitrarily chosen. In such cases, the meaning of the terms will be described in the description of the corresponding embodiments. Therefore, the terms used in this specification should not necessarily be interpreted as simple names of the terms, but rather defined based on the meaning of the terms and the overall content of this disclosure.

[0044] Exemplary embodiments may vary and may be provided in different exemplary embodiments. Various example embodiments will be described with reference to the accompanying drawings. However, this is not necessarily intended to limit the scope of the exemplary embodiments to the particular embodiment form. Rather, modifications, equivalents, and substitutions may be employed that are included within the concepts and technical scope disclosed herein. Although exemplary embodiments have been described, such specific descriptions are omitted if it is determined that they obscure the gist of this disclosure.

[0045] Terms such as "first" and "second" may be used to describe various elements, but the elements should not be limited by these terms. The terminology used herein is intended only to explain specific exemplary embodiments and not to limit the scope of this disclosure.

[0046] Unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In this application, the term "comprising" means the presence of a feature, number, step, operation, component, element, or combination thereof written in the specification, but does not preclude the possibility of the presence of one or more other features, numbers, steps, operations, components, elements, or combinations thereof, or the addition of one or more other features, numbers, steps, operations, components, elements, or combinations thereof.

[0047] Exemplary embodiments of this disclosure will now be described in more detail in a manner that will be understood by those skilled in the art. However, exemplary embodiments may be implemented in various different configurations and are not limited to the description provided herein. Furthermore, well-known functions or structures are not described in detail as they would obscure the invention with unnecessary detail.

[0048] Figure 2 This is a diagram illustrating the configuration of a manipulator according to an embodiment of the present disclosure. The manipulator 100 may include a sensor 110, a driver 120, a communication interface 130, a memory 140, and a processor 150.

[0049] Sensor 110 may include depth sensor 111. Depth sensor 111 may sense objects or ground or surface around manipulator 100. Processor 150 may acquire shape information (e.g., point cloud) of the object or the ground on which the object will be placed, based on the sensed values ​​of depth sensor 111. Depth sensor 111 may include RGB-D sensor, light detection and ranging (LiDAR) sensor, and time-of-flight (ToF) sensor.

[0050] Sensor 110 may include force sensor 112. Force sensor 112 may be disposed in a hand or gripper and joint included in manipulator 100 to sense external forces acting on the hand and joint. For example, force sensor 112 may sense the weight acting on an object grasped by the hand. That is, force sensor 112 may sense the weight of the object grasped by the hand. Force sensor 112 may include a force / torque (F / T) sensor.

[0051] Sensor 110 may include an inertial measurement unit (IMU) sensor 113. Processor 150 may acquire acceleration or angular velocity information of manipulator 100 based on the sensed values ​​of IMU sensor 113. Additionally, sensor 110 may include an RGB camera. Processor 150 may identify objects included in images captured by the RGB camera. Furthermore, sensor 110 may include encoders for acquiring the position and velocity of joints and links included in manipulator 100. The encoders may sense the position and rotational speed of motors used to drive the joints.

[0052] The driver 120 may include an actuator that powers the manipulator 100. For example, the actuator may provide torque to the hand and joints. The actuator may include various types of motors, such as linear motors, AC sub-motors, stepper motors, etc.

[0053] The communication interface 130 may include at least one circuit and can communicate with various types of external devices according to various communication methods. For example, the communication interface 130 may obtain information about the ground or surface on which an object is placed from an external device or external server. The information about the ground may include the location and shape of the ground and the direction of the normal vector. The communication interface 130 may include at least one of a Wi-Fi module, a Bluetooth module, a ZigBee module, a beacon module, a cellular communication module, a third-generation (3G) mobile communication module, a fourth-generation (4G) mobile communication module, a 4G Long Term Evolution (LTE) communication module, and a fifth-generation (5G) mobile communication module.

[0054] The memory 140 may store the operating system (OS) for all operations of the components of the manipulator 100, as well as commands or data related to the components of the manipulator 100. For example, the memory 140 may store information about an object. Information about the object may include the magnitude of the gravity acting on the object, and the distance from the force sensor 112 to the line of action of gravity (i.e., the torque arm).

[0055] The memory 140 can store data required by modules for controlling the operation of the manipulator 100 to perform various operations. Modules for controlling the operation of the manipulator 100 may include an object information acquisition module 151, a placement surface determination module 152, a ground information acquisition module 153, a contact detection module 154 and a contact information acquisition module 155, a rotation direction acquisition module 156, and a hand control module 157. The memory 140 can be implemented as non-volatile memory (e.g., hard disk, solid-state drive (SSD), flash memory), volatile memory, etc.

[0056] Processor 150 is electrically connected to memory 140 to control all functions and operations of manipulator 100. When user commands for operating manipulator 100 are input, processor 150 can load data stored in non-volatile memory for modules 151 to 157 into volatile memory to perform various operations. Loading refers to the operation of loading data stored in non-volatile memory and storing it in volatile memory so that it can be accessed by processor 150.

[0057] The object information acquisition module 151 can acquire various information about the object. For example, the object information acquisition module 151 can acquire the shape information of the object based on the sensing values ​​of the depth sensor 111. The shape information of the object may include a point cloud corresponding to the object.

[0058] As another example, the object information acquisition module 151 can acquire the weight of the object grasped by the manipulator 100. The object information acquisition module 151 can acquire the gravity acting on the object (i.e., the weight of the object) based on the sensing value of the force sensor 112 acquired when the manipulator 100 is stopped while grasping the object.

[0059] As another example, the object information acquisition module 151 can acquire a first torque arm corresponding to the object. The first torque arm can refer to the distance from the force sensor 112 to the line of action of gravity acting on the object when the object and the ground are not in contact with each other. The object information acquisition module 151 can acquire the first torque arm based on the force and torque sensed by the force sensor 112. For example, the object information acquisition module 151 can acquire the first torque arm corresponding to the object based on equation (1).

[0060]

[0061] in, and Each of these refers to the force and torque sensed by the force sensor 112 when the hand is grasping the object.

[0062] Information about the acquired object can be stored in memory 140.

[0063] The placement surface determination module 152 can determine the placement surface of an object, which contacts the ground on which the object is placed. The placement surface determination module 152 can generate multiple convex hulls for the object based on a point cloud corresponding to the object. A convex hull can refer to a virtual two-dimensional plane in the form of a polygon that includes a portion of the object. The placement surface determination module 152 can identify one of the multiple convex hulls that includes the placement surface. For example, the placement surface determination module 152 can identify the convex hull with the largest minimum distance from a point corresponding to the object's center of gravity to the edge of the convex hull. The following will refer to... Figure 4A more detailed description of the method for identifying the placement surface.

[0064] The ground information acquisition module 153 can acquire information about the ground. Specifically, the ground information acquisition module 153 can acquire the normal vector corresponding to the ground. The ground information acquisition module 153 can acquire a point cloud corresponding to the ground based on the sensing values ​​of the depth sensor 111. In addition, the ground information acquisition module 153 can acquire the average normal vector corresponding to the ground based on the point cloud.

[0065] In this document, "ground" can refer to any surface on which an object is placed, and can include the surface of a workbench or table on which an object is placed, as well as the ground as defined in the dictionary. Furthermore, the ground can have a flat shape, but is not limited to this, and can also have a curved shape.

[0066] The contact detection module 154 can detect contact between an object and the ground. For example, the contact detection module 154 can identify whether an object is in contact with the ground based on the value sensed by the force sensor 112. The contact detection module 154 can identify that the object is in contact with the ground when the value obtained by subtracting the weight of the object stored in the memory 140 from the magnitude of the force sensed by the force sensor 112 is greater than a predetermined first value. Alternatively, the contact detection module 154 can identify that the object is in contact with the ground by comparing the magnitude of the force sensed by the force sensor 112 with a predetermined value.

[0067] Additionally, the contact detection module 154 can identify whether an object is in contact with the ground based on the amount of change in the value sensed by the force sensor 112. For example, if the amount of change in the value sensed by the force sensor 112 within a predetermined time is greater than a predetermined second value, the contact detection module 154 can identify that the object is in contact with the ground.

[0068] The contact detection method of the contact detection module 154 can vary depending on the contact state between the object and the ground. For example, when the object and the ground are not in contact (i.e., the first state), the contact detection module 154 can identify whether the object is in contact with the ground by comparing a value obtained by subtracting the weight of the object stored in the memory 140 from the magnitude of the force sensed by the force sensor 112 with a predetermined first value. When a first area of ​​the object is in contact with the ground (i.e., the second state), the contact detection module 154 can identify whether a second area of ​​the object is in contact with the ground by comparing the change in the sensed value of the force sensor 112 with a predetermined second value.

[0069] The contact detection method using force sensor 112 has been described above, but this is only an example, and the contact detection module 154 can identify whether an object is in contact with the ground based on the value sensed by IMU sensor 113. For example, when the magnitude of the signal sensed by IMU sensor 113 is greater than a predetermined value, the contact detection module 154 can identify that the object is in contact with the ground.

[0070] The contact information acquisition module 155 can acquire positional information about the contact area between the object and the ground. The contact information acquisition module 155 can also acquire the second torque arm. Second torque arm This is achieved by contacting the distance from force sensor 112 to the line of action of the external force. For example, contact information acquisition module 155 can acquire the second torque arm based on the value sensed by force sensor 112 when the object contacts the ground. The contact information acquisition module 155 can calculate the second moment arm based on equations (2) and (3).

[0071]

[0072]

[0073] f s (t) and τ s (t) refers to the sensed value (i.e., force / torque) detected by force sensor 112 when the object is in contact with the ground, and and This refers to the sensor values ​​acquired before an object makes contact with the ground. In other words, and This refers to the information about the object stored in memory 140.

[0074] The contact information acquisition module 155 can obtain information from the sensing value (f) when an object comes into contact with the ground. s (t),τ s Subtract the sensed value before the object comes into contact with the ground from (t) To obtain the external force caused by the contact between the object and the ground. Furthermore, the contact information acquisition module 155 can be based on the external force through contact. Obtain the second moment arm

[0075] The contact information acquisition module 155 can be based on the external force through contact. Information about objects The position of the contact area is obtained by using the sensing values ​​of the depth sensor 111. The contact information acquisition module 155 can obtain the location of the contact area based on equations (4) and (5).

[0076]

[0077]

[0078] Equation This represents the plane equation corresponding to the ground. The contact information acquisition module 155 can acquire a point cloud corresponding to the ground based on the sensing values ​​of the depth sensor 111. Additionally, the contact information acquisition module 155 can acquire the plane equation (i.e., ...) based on the point cloud and a plane extraction algorithm. ).

[0079] The rotation direction acquisition module 156 can acquire the rotation direction for rotating the object based on the contact area that serves as the rotation center. For example, the rotation direction acquisition module 156 can acquire the rotation direction based on information about the object. and the location of the contact area The rotation direction is obtained. The rotation direction acquisition module 156 can obtain the rotation direction based on equations (6) and (7).

[0080]

[0081]

[0082] The rotation direction acquisition module 156 can be based on the vector from the contact area between the object and the ground to the line of action of gravity. and gravity acting on an object To obtain the torque around the contact area that serves as the center of rotation Furthermore, the rotation direction acquisition module 156 can acquire the rotation direction based on the acquired torque. Get rotation direction

[0083] The hand control module 157 can generate control commands for controlling the hand included in the manipulator 100, and can control the operation of the hand based on the control commands. For example, the hand control module 157 can control the hand to grasp an object. Furthermore, the hand control module 157 can control the hand to move or rotate while grasping the object. In this case, when the difference between the first direction of the first normal vector about the object's placement surface and the second direction of the second normal vector about the ground is within a predetermined range, the hand control module 157 can control the hand to make the object contact the ground. Therefore, a first area of ​​the object can contact the ground. Additionally, the hand control module 157 can rotate in a direction with the contact area between the first area of ​​the object and the ground as the center of rotation. The object rotates upwards. Therefore, a second region of the object can come into contact with the ground. If the contact between the second region of the object and the ground is detected, the hand control module 157 can control the hand to release its grip on the object.

[0084] Figure 3 This is a diagram illustrating information acquired by a manipulator according to an embodiment of the present disclosure. (Refer to...) Figure 3 The manipulator 100 can acquire a point cloud corresponding to the object 31 based on the sensing values ​​of the depth sensor 111. Furthermore, the manipulator 100 can acquire the force acting on the object 31 based on the sensing values ​​of the force sensor 112. and torque Furthermore, the manipulator 100 can obtain a first torque arm corresponding to the object based on the above equation (1). First torque arm This refers to the distance from the force sensor 112 to the line of action of gravity L. The line of action of gravity L can pass through the center of gravity C of the object 31.

[0085] Figure 4 This is a diagram illustrating a method for determining the placement surface of an object according to an embodiment of the present disclosure. Manipulator 100 can determine the placement surface 42 that will contact the ground among a plurality of surfaces of object 41. Manipulator 100 can generate a plurality of convex hulls about object 41 based on a point cloud corresponding to object 41. For each of the plurality of convex hulls, manipulator 100 can calculate the gravity vector v passing through the center of the point cloud and the distance (d) from the intersection point P of the convex hull to one side of the convex hull. ei ) and the distance from the intersection point P to the vertex (d vi Manipulator 100 can determine the minimum distance (d) from the intersection point P to the edge / vertice of the convex hull among multiple convex hulls. min，A The largest convex hull is used as the placement value A. * .

[0086] The manipulator 100 moves the object 41 such that the defined mounting surface 42 contacts the ground. In this case, the manipulator 100 moves the object 41 such that the difference between the first direction of the first normal vector with respect to the ground and the second direction of the second normal vector with respect to the mounting surface 42 is within a predetermined range. Therefore, as... Figure 5 As shown, the first region A1 of object 51 can contact the ground 52.

[0087] Figure 5 This is a diagram illustrating a method for obtaining a rotation direction according to an embodiment of the present disclosure. A manipulator 100 can rotate an object 51 about a first region A1, which is the contact area between the object 51 and the ground 52. The manipulator 100 can obtain the rotation direction for rotating the object 51. For example, the manipulator 100 can obtain the rotation direction based on the vector from the contact area A1 of the object 51 and the ground 52 to the line of action of gravity L. and gravity acting on object 51 To obtain the torque at the contact area A1, which is the center of rotation. The manipulator 100 can obtain torque based on the above equations (6) and (7). Additionally, the manipulator 100 can be based on the acquired torque. Get rotation direction

[0088] Figure 6 This is a diagram illustrating a method of placing an object according to an embodiment. Figure 6 As shown, the manipulator 100 can be based on the rotation direction The object 61 is rotated. Therefore, the second region A2 of the object 61 can come into contact with the ground 62. When the change in the sensing value of the force sensor 112 within a predetermined time exceeds a predetermined second value, the manipulator 100 can detect that the second region A2 is in contact with the ground 62. Furthermore, the manipulator 100 can release the grip on the object 61. Therefore, the object 61 can be stably placed on the ground 62.

[0089] Figure 7 This is a flowchart of a method for controlling a manipulator according to an embodiment of the present disclosure. In operation S710, the manipulator 100 can grasp an object using its hand. In operation S720, the manipulator 100 can acquire and store information about the object based on the sensing values ​​of a force sensor acquired while grasping the object. In this case, the manipulator 100 can acquire positional information about the contact area based on the stored object information, the sensing values ​​of a depth sensor about the ground, and the sensing values ​​of the force sensor acquired when the ground contacts a first area.

[0090] In operation S730, the manipulator 100 can bring a first region of the object into contact with the ground. In this case, the manipulator 100 can bring the first region of the object into contact with the ground such that the difference between the first direction of a first normal vector about the ground and the second direction of a second normal vector about the mounting surface is within a predetermined range. The mounting surface of the object can be obtained based on the object's shape information, which is obtained based on the sensing value of a depth sensor. When the sensing value of a force sensor is greater than a first predetermined value, the manipulator 100 can identify that the first region is in contact with the ground.

[0091] During operation S740, the manipulator 100 can acquire positional information about the contact area between the first region and the ground. The manipulator 100 can acquire positional information about the contact area based on object information, the depth sensor's sensing value about the ground, and the force sensor's sensing value acquired when the ground contacts the first region.

[0092] In operation S750, the manipulator 100 can obtain the rotation direction for rotating the object based on position information and information about the object. In operation S760, the manipulator 100 can rotate the object in the obtained rotation direction. In this case, the manipulator 100 can cause the object to rotate around the contact area, which serves as the center of rotation.

[0093] During operation S770, when the second region of the object comes into contact with the ground due to the object's rotation, the manipulator 100 can release the grip on the object. When the change in the sensing value of the force sensor within a predetermined time is greater than a predetermined second value, the manipulator 100 can detect that the second region is in contact with the ground.

[0094] The various exemplary embodiments described above can be implemented in a recording medium that can be read by a computer or a computer-like device using software, hardware, or a combination thereof. In some cases, the embodiments described herein can be implemented by the processor itself. In a software configuration, the various embodiments described in the specification (such as processes and functions) can be implemented as separate software modules. Each software module can perform one or more functions and operations described in this specification.

[0095] Methods for controlling a display device according to various exemplary embodiments may be stored on a non-transitory computer-readable medium. When computer instructions stored in such a non-transitory computer-readable medium are executed by a processor, a particular device may perform processing operations according to the various embodiments described above.

[0096] Non-transitory computer-readable recording media are media that store data and can be read by a device. For example, non-transitory computer-readable media can be optical discs (CDs), digital versatile optical discs (DVDs), hard disks, Blu-ray discs, universal serial bus (USB), memory cards, read-only memory (ROM), etc.

[0097] The foregoing exemplary embodiments and advantages are merely illustrative and should not be construed as limiting this disclosure. This teaching can be readily applied to other types of devices. Furthermore, the description of the exemplary embodiments is intended to be illustrative and not to limit the scope of the claims, and many alternatives, modifications, and variations will be apparent to those skilled in the art.

Claims

1. A manipulator, comprising: Clamping device; Depth sensor; A force sensor is configured to sense external forces acting on the gripper; Memory, storing instructions; as well as The processor is configured to execute instructions to perform the following operations: Control the gripper to grasp the object. First information about the object is obtained based on a first sensing value obtained via a force sensor while the object is being grasped. The gripper is controlled so that a first region of the object contacts the surface on which the object will be placed. Obtain location information about the contact area between the first region and the surface. Based on the position information and the first information about the object, the rotation direction for rotating the object is obtained. Control the gripper to rotate the object about the contact area in the rotational direction, and Based on the contact between the second region of the object and the surface, the gripper is controlled to release the object. The processor is also configured to execute instructions to perform the following operations: Shape information about the object is obtained based on a second sensing value acquired by a depth sensor, and The placement surface of the object, including a first region and a second region, is identified based on shape information about the object.

2. The manipulator as claimed in claim 1, wherein, The first information about the object includes information about the gravity acting on the object, and information about the distance from the force sensor to the line of action of gravity.

3. The manipulator as claimed in claim 1, wherein, The processor is also configured to execute instructions to perform the following operations: based on first information about the object, a second sensing value about the surface obtained by a depth sensor, and a third sensing value obtained by a force sensor while the first region is in contact with the surface, to obtain the position information about the contact area.

4. The manipulator as claimed in claim 1, wherein, The processor is also configured to execute instructions to perform the following operations: The torque centered on the contact area is obtained based on the first information about the object and the position information. The rotation direction is obtained based on the torque.

5. The manipulator as claimed in claim 1, wherein, The processor is also configured to execute instructions to identify a first region in contact with the surface based on a first sense value obtained via a force sensor being greater than a first value.

6. The manipulator as claimed in claim 1, wherein, The processor is also configured to execute instructions to perform the following operations: based on the fact that the change in a first sense value obtained via a force sensor within a predetermined time is greater than a second value, identify that a second region is in contact with the surface.

7. The manipulator as claimed in claim 1, wherein, The processor is also configured to execute instructions to control the gripper such that, based on the difference between a first direction of a first normal vector about the surface and a second direction of a second normal vector about the placement surface within a predetermined range, a first region contacts the surface.

8. A method for controlling a manipulator, the manipulator including a gripper, a depth sensor, and a force sensor, the force sensor being configured to acquire an external force acting on the gripper, the method comprising: Use a gripper to grasp an object; First information about the object is obtained based on a first sensing value obtained via a force sensor while the object is being grasped; Make the surface on which the object will be placed contact the first region of the object; Obtain location information about the contact area between the first region and the surface; The rotation direction for rotating the object is obtained based on the position information and the first information about the object; The object is rotated about the contact area in the rotational direction; as well as The object is released by the gripper based on the contact between the second region of the object and the surface. The method further includes: Shape information about the object is obtained based on a second sensing value acquired by a depth sensor; and The placement surface of the object, including a first region and a second region, is identified based on shape information about the object.

9. The method of claim 8, wherein, The first information about the object includes information about the gravity acting on the object, and information about the distance from the force sensor to the line of action of gravity.

10. The method of claim 8, wherein, The step of obtaining the position information about the contact area includes: obtaining the position information about the contact area based on first information about the object, a second sensing value about the surface obtained by a depth sensor, and a third sensing value obtained by a force sensor while the first area is in contact with the surface.

11. The method of claim 8, wherein, The steps for obtaining the rotation direction include: The torque centered on the contact area is obtained based on the first information about the object and the position information. The rotation direction is obtained based on the torque.

12. The method of claim 8, further comprising: Based on the first sensing value of the force sensor being greater than a first value, it is identified that the first region is in contact with the surface.

13. The method of claim 8, further comprising: Based on the fact that the change in the first sensing value obtained by the force sensor within a predetermined time is greater than the second value, the second region is identified as being in contact with the surface.

Images