KR20220078452A - Manipulator and method for controlling thereof - Google Patents

Abstract

A manipulator is disclosed. A manipulator according to the present disclosure includes a hand, a depth sensor, a force sensor, a memory, and a processor, wherein the processor controls the hand to grip the object, and the object based on a sensing value of the force sensor obtained while gripping the object obtains information on and stores it in the memory, controls the hand so that the ground on which the object is to be placed and the first area of the object come into contact, obtains location information about the contact area between the first area and the ground, Acquire the rotation direction to rotate the object based on the information on the object, control the hand to rotate the object in the rotation direction with the contact area as the center of rotation, and release the grip of the object when the second area of the object and the ground come into contact control the hand to

Description

Manipulator and its control method

The present disclosure relates to a manipulator and a control method thereof, and more particularly, to a manipulator for seating an object on the ground and a control method thereof.

In recent years, with the development of robot technology, various types of robots such as cleaning robots, service robots, and industrial robots are being used. As an example of the industrial robot, there is a manipulator in the form of a human hand and arm to perform various operations.

Referring to FIG. 1 , the manipulator 11 may perform a placing operation of placing the gripped object 12 on the ground 13 . At this time, the manipulator 11 must stably perform the placement so that the object does not fall over. In the conventional placing method, the posture of the object 12 is estimated based on shape information of the object 12 , and placement is performed based on the estimated posture. However, the conventional method could not accurately estimate the posture of the object 12 when the shape of the object 12 is asymmetric, thus limiting stable positioning.

Accordingly, there is a need for a technology for a more stable placing method.

One technical problem to be solved by the present invention is to provide a manipulator capable of stably placing an object.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to an exemplary embodiment of the present disclosure for solving the above-described technical problem, a manipulator includes: a hand; depth sensor; a force sensor for acquiring an external force acting on the hand; a memory storing at least one instruction; and a processor, wherein the processor controls the hand to grip the object, and obtains information about the object based on the sensed value of the force sensor obtained while gripping the object, and stores the information in the memory and controlling the hand so that the ground on which the object is to be placed and the first area of the object come into contact with each other, obtain location information on the contact area between the first area and the ground, and information on the location information and the object to obtain a rotation direction to rotate the object based on, control the hand to rotate the object in the rotation direction with the contact area as a rotation center, and according to the rotation, the second area of the object and the ground Upon this contact, a manipulator for controlling the hand to release the grip of the object may be provided.

The information on the object may include gravity acting on the object and a distance from the force sensor to the line of action of the gravity.

The processor is configured to: Position information on the contact area based on the information on the object, the sensing value of the depth sensor with respect to the ground, and the sensing value of the force sensor obtained when the ground and the first area come into contact can be obtained.

The processor may obtain a torque centered on the contact area based on the information on the object and the location information, and obtain the rotation direction based on the torque.

The processor may determine that the first area is in contact with the ground when the sensing value of the force sensor is greater than a preset first value.

The processor may determine that the second region is in contact with the ground when the amount of change in the value of the force sensor for a preset time is greater than a preset second value.

The processor may obtain shape information of the object based on a sensing value of the depth sensor, and identify a seating surface of the object including the first area and the second area based on the shape information of the object. can

The processor is configured to allow the first region to contact the ground when a difference between a first direction of a first normal vector with respect to the ground and a second direction of a second normal vector with respect to the seating surface is within a preset range. You can control the hand.

According to another exemplary embodiment of the present disclosure for solving the above-described technical problem, in a control method of a manipulator including a hand, a depth sensor, and a force sensor for acquiring an external force acting on the hand, gripping the object using the hand; acquiring and storing information on the object based on a sensing value of the force sensor acquired while gripping the object; contacting the ground on which the object is to be placed with a first area of the object; obtaining location information on a contact area between the first area and the ground; obtaining a rotation direction in which to rotate the object based on the location information and information on the object; rotating the object in the rotation direction with the contact area as a rotation center; and releasing the grip of the object when the second area of the object and the ground come into contact with the rotation according to the rotation.

The step of obtaining the location information on the contact area includes information on the object, the sensing value of the depth sensor with respect to the ground, and the sensing value of the force sensor obtained when the ground and the first area come into contact with each other. Based on this, location information on the contact area may be acquired.

The obtaining of the rotation direction includes obtaining a torque centered on the contact area based on the information on the object and the position information, and obtaining the rotation direction based on the torque. can do.

The control method may further include, when the sensing value of the force sensor is greater than a preset first value, determining that the first area is in contact with the ground.

The control method may further include a step of determining that the second area is in contact with the ground when the amount of change of the sensed value of the force sensor for a preset time is greater than a preset second value.

The control method may include: acquiring shape information of the object based on a sensing value of the depth sensor; and identifying a seating surface of the object including the first area and the second area based on the shape information of the object.

The contacting of the ground with the first area of the object may include when a difference between a first direction of a first normal vector with respect to the ground and a second direction of a second normal vector with respect to the seating surface is within a preset range. The ground may be brought into contact with the first area of the object.

The solutions of the problems of the present disclosure are not limited to the above-described solutions, and solutions that are not mentioned will be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the present specification and the accompanying drawings. will be able

According to various embodiments of the present disclosure as described above, the manipulator may stably place an object. Accordingly, an accident in which the object falls during the placing process can be prevented.

In addition, the effects obtainable or predicted by the embodiments of the present disclosure are to be disclosed directly or implicitly in the detailed description of the embodiments of the present disclosure. For example, various effects predicted according to embodiments of the present disclosure will be disclosed in the detailed description to be described later.

1 is a diagram for explaining a placing operation of a manipulator.
2 is a block diagram illustrating a configuration of a manipulator according to an embodiment of the present disclosure.
3 is a diagram for describing information acquired by a manipulator according to an embodiment of the present disclosure.
4 is a view for explaining a method of determining a seating surface of an object according to an embodiment of the present disclosure.
5 is a view for explaining a method of obtaining a rotation direction according to an embodiment of the present disclosure.
6 is a diagram for explaining a method of placing an object according to an embodiment of the present disclosure.
7 is a flowchart illustrating a method of controlling a manipulator according to an embodiment of the present disclosure.

Terms used in this specification will be briefly described, and the present disclosure will be described in detail.

Terms used in the embodiments of the present disclosure are selected as currently widely used general terms as possible while considering the functions in the present disclosure, which may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, etc. . In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding disclosure. Therefore, the terms used in the present disclosure should be defined based on the meaning of the term and the contents of the present disclosure, rather than the simple name of the term.

Embodiments of the present disclosure may be subjected to various transformations and may have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope of the specific embodiments, and it should be understood to include all transformations, equivalents and substitutions included in the spirit and scope of the disclosure. In describing the embodiments, if it is determined that a detailed description of a related known technology may obscure the subject matter, the detailed description thereof will be omitted.

Terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as "comprises" or "consisting of" are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, but one or more other It should be understood that this does not preclude the possibility of addition or presence of features or numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art to which the present disclosure pertains can easily implement them. However, the present disclosure may be implemented in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present disclosure in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

2 is a block diagram illustrating a configuration of a manipulator according to an embodiment of the present disclosure. The manipulator 100 may include a sensor unit 110 , a driving unit 120 , a communication interface 130 , a memory 140 , and a processor 150 .

The sensor unit 110 may include a depth sensor 111 . The depth sensor 111 may sense an object or the ground around the manipulator 100 . The processor 150 may acquire an object or shape information (eg, a point cloud) of the ground on which the object is to be seated, based on the sensing value of the depth sensor 111 . The depth sensor 111 may include an RGB-D sensor, a lidar sensor, and a ToF sensor.

The sensor unit 110 may include a force sensor 112 . The force sensor 112 may be provided in the hand (or gripper) and the joint included in the manipulator 100 to sense an external force acting on the hand and the joint. For example, the force sensor 112 may sense gravity acting on an object gripped by the hand. That is, the force sensor 112 may sense the weight of the object gripped by the hand. The force sensor 112 may include a Force/Torque (F/T) sensor.

The sensor unit 110 may include an Inertial Measurement Unit (IMU) sensor 113 . The processor 150 may acquire acceleration information or angular velocity information of the manipulator 100 based on the sensed value of the IMU sensor 113 . Also, the sensor unit 110 may include an RGB camera. The processor 150 may identify an object included in a photographed image captured by the RGB camera. In addition, the sensor unit 110 may include an encoder for acquiring positions and speeds of joints and links included in the manipulator 100 . The encoder may sense the position and rotation speed of a motor for driving the joint.

The driving unit 120 may include an actuator that provides power to the manipulator 100 . For example, the actuator may provide torque to the hand and joint. The actuator may include various types of motors, such as linear motors, AC sub-motors, step motors, and the like.

The communication interface 130 includes at least one circuit and may communicate with various types of external devices according to various types of communication methods. For example, the communication interface 130 may obtain information about the ground on which the object is to be placed from an external device or an external server. The information about the ground may include a position, a shape, and a direction of a normal vector of the ground. On the other hand, the communication interface 130 is a Wi-Fi module, a Bluetooth module, a ZigBee module, a Beacon module, a cellular communication module, a 3G (3rd generation) mobile communication module, 4G (4th generation) mobile It may include at least one of a communication module, a 4th generation Long Term Evolution (LTE) communication module, and a 5G (5th generation) mobile communication module.

The memory 140 may store an operating system (OS) for controlling overall operations of the components of the robot 100 and commands or data related to components of the robot 100 . For example, the memory 140 may store information about the object. The information on the object may include a magnitude of gravity acting on the object and a distance (ie, a moment arm) from the force sensor 112 to an action line of gravity.

The memory 140 may store data necessary for the module for controlling the operation of the manipulator 100 to perform various operations. Modules for controlling the operation of the manipulator 100 include an object information acquisition module 151 , a seating 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 obtaining module 156 and a hand control module 157 may be included. Meanwhile, the memory 140 may be implemented as a non-volatile memory (eg, a hard disk, a solid state drive (SSD), a flash memory), a volatile memory, or the like.

The processor 150 may be electrically connected to the memory 140 to control overall functions and operations of the electronic device 100 . When a user command for operating the manipulator 100 is input, the processor 150 may load data for the modules 151 to 157 stored in the nonvolatile memory to perform various operations into the volatile memory. have. Here, the loading refers to an operation of loading and storing data stored in the non-volatile memory into the volatile memory so that the processor 150 can access it.

The object information acquisition module 151 may acquire various information about the object. For example, the object information acquisition module 151 may acquire shape information of an object based on a sensing value of the depth sensor 111 . The shape information of the object may include a point cloud corresponding to the object.

As another example, the object information acquisition module 151 may acquire the weight of the object gripped by the manipulator 100 . Specifically, the object information obtaining module 151 is configured to calculate the gravity acting on the object based on the sensed value of the force sensor 112 obtained in a state in which the manipulator 100 is stopped while holding the object (that is, the weight of the object). can be obtained.

)을 획득할 수 있다.As another example, the object information acquisition module 151 may acquire a first moment arm corresponding to the object. Here, the first moment arm may mean a distance from the force sensor 112 to the line of action of gravity acting on the object in a state in which the object and the ground do not contact. The object information acquisition module 151 may acquire the first moment arm based on the force and torque sensed by the force sensor 112 . For example, the object information acquisition module 151 is based on [Equation 1], the first moment arm corresponding to the object (

) can be obtained.

[Equation 1]

,

각각은 핸드가 오브젝트를 파지한 상태에서 힘 센서(112)에 의해 센싱되는 힘과 토크를 의미한다.here,

,

Each means a force and a torque sensed by the force sensor 112 in a state in which the hand grips the object.

The information about the object obtained in this way may be stored in the memory 140 .

The seating surface determination module 152 may determine the seating surface of the object to be in contact with the ground on which the object is to be placed. The seating surface determination module 152 may generate a plurality of convex hulls for an object based on a point cloud corresponding to the object. A convex hull may mean a polygonal two-dimensional virtual plane including a partial area of an object. The seating surface determination module 152 may identify one convex hull including a seating surface among a plurality of convex hulls. For example, the seating surface determination module 152 may identify a convex hull in which a minimum distance from a point corresponding to a center of gravity of an object to an edge of the convex hull is maximum among a plurality of convex hulls. A more detailed description of the method of identifying the seating surface will be described later with reference to FIG. 4 .

The ground information acquisition module 153 may acquire information about the ground. In particular, the ground information obtaining module 153 may obtain a normal vector corresponding to the ground. The ground information obtaining module 153 may obtain a point cloud corresponding to the ground based on the sensing value of the depth sensor 111 . In addition, the ground information obtaining module 153 may obtain an average normal vector corresponding to the ground based on the point cloud.

Meanwhile, in the present disclosure, the ground refers to an arbitrary surface on which an object is placed, and may include a surface of a workbench or table on which an object can be placed as well as the ground in the dictionary meaning. In addition, the ground may have a flat shape, but is not limited thereto and may have a curved shape.

The contact detection module 154 may detect a contact between the object and the ground. For example, the contact detection module 154 may determine whether the object and the ground are in contact based on the value sensed by the force sensor 112 . Specifically, 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 preset first value, the contact detection module 154 detects that the object and the ground are in contact. It can be judged that Alternatively, the contact detection module 154 may determine that the object and the ground are in contact by comparing the magnitude of the force sensed by the force sensor 112 with a preset value.

Also, the contact detection module 154 may determine whether the object and the ground are in contact based on the amount of change in the value sensed by the force sensor 112 . For example, if the amount of change in the sensed value of the force sensor 112 sensed for a preset time is greater than the preset second value, the contact detection module 154 may determine that the object and the ground are in contact.

Meanwhile, the touch sensing method of the touch sensing module 154 may vary depending on the contact state between the object and the ground. For example, when the object and the ground are not in contact with the first state, the contact detection module 154 subtracts the weight of the object stored in the memory 140 from the magnitude of the force sensed by the force sensor 112 and By comparing the set first value, it may be determined whether the object and the ground are in contact. On the other hand, when the first area of the object is in a second state in contact with the ground, the touch detection module 154 compares the change amount of the sensed value of the force sensor 112 with a preset second value to the second area of the object It can be determined whether or not there is contact with the ground.

Meanwhile, in the above, a method for detecting a touch using the force sensor 112 has been described, but this is only an exemplary embodiment, and the touch detection module 154 determines whether the object and the ground are in contact based on the sensing value of the IMU sensor 113 . can be judged For example, when the magnitude of the signal sensed by the IMU sensor 113 is greater than a preset value, the contact detection module 154 may determine that the object has made contact with the ground.

)을 획득할 수 있다. 예를 들어, 접촉 정보 획득 모듈(155)은 오브젝트와 지면이 접촉할 때 센싱되는 힘 센서(112)의 센싱값에 기초하여 제2 모멘트 팔(

)을 획득할 수 있다. 구체적으로, 접촉 정보 획득 모듈(155)은 [수학식 2]에 기초하여 제2 모멘트 팔(

)을 산출할 수 있다.The contact information obtaining module 155 may obtain location information about the contact area between the object and the ground. The contact information acquisition module 155 is a second moment arm (

) can be obtained. For example, the contact information obtaining module 155 may be configured to use the second moment arm (

) can be obtained. Specifically, the contact information acquisition module 155 is based on [Equation 2] the second moment arm (

) can be calculated.

[Equation 2]

,

는 오브젝트와 지면이 접촉할 때 센싱되는 힘 센서(112)의 센싱값(즉, 힘/토크)을 의미하고,

,

는 오브젝트와 지면의 접촉이 발생하기 전에 획득된 센서(112)의 센싱값을 의미한다. 즉,

,

는 메모리(140)에 저장된 오브젝트에 대한 정보를 의미한다.here,

,

is the sensed value (ie, force / torque) of the force sensor 112 sensed when the object and the ground contact,

,

denotes a sensed value of the sensor 112 obtained before the contact between the object and the ground occurs. in other words,

,

denotes information about an object stored in the memory 140 .

,

)에서 오브젝트와 지면의 접촉이 발생하기 전의 센싱값(

,

)을 차감하여 오브젝트와 지면의 접촉에 의한 외력(

,

)을 획득할 수 있다. 그리고, 접촉 정보 획득 모듈(155)은 접촉에 의한 외력(

,

)에 기초하여 제2 모멘트 팔(

)을 획득할 수 있다.The contact information acquisition module 155 provides a sensing value (

,

), the sensing value (

,

) by subtracting the external force (

,

) can be obtained. And, the contact information acquisition module 155 is an external force (

,

) based on the second moment arm (

) can be obtained.

,

), 오브젝트에 대한 정보(

,

) 및 지면에 대한 뎁스 센서(111)의 센싱값에 기초하여 접촉 영역의 위치(

)를 획득할 수 있다. 구체적으로, 접촉 정보 획득 모듈(155)은 [수학식 3]에 기초하여 접촉 영역의 위치(

)를 획득할 수 있다.On the other hand, the contact information acquisition module 155 is an external force (

,

), information about the object (

,

) and the position of the contact area (

) can be obtained. Specifically, the contact information obtaining module 155 determines the position of the contact area (

) can be obtained.

[Equation 3]

)은 지면에 대응되는 평면 방정식을 의미한다. 접촉 정보 획득 모듈(155)은 뎁스 센서(111)의 센싱값에 기초하여 지면에 대응되는 포인트 클라우드를 획득할 수 있다. 그리고, 접촉 정보 획득 모듈(155)은 포인트 클라우드 및 평면 추출(plane extraction) 알고리즘에 기초하여 평면 방정식(즉,

)을 획득할 수 있다.Here, the formula (

) means a plane equation corresponding to the ground. The contact information obtaining module 155 may obtain a point cloud corresponding to the ground based on the sensing value of the depth sensor 111 . And, the contact information obtaining module 155 is based on the point cloud and plane extraction algorithm based on the plane equation (that is,

) can be obtained.

,

) 및 접촉 영역의 위치(

)에 기초하여 회전 방향을 획득할 수 있다. 구체적으로, 회전 방향 획득 모듈(156) [수학식 4]에 기초하여 회전 방향(

)을 획득할 수 있다.The rotation direction obtaining module 156 may obtain a rotation direction in which to rotate the object based on the contact area as a rotation center. For example, the rotation direction acquisition module 156 provides information about the object (

,

) and the location of the contact area (

) based on the rotation direction can be obtained. Specifically, based on the rotation direction acquisition module 156 [Equation 4], the rotation direction (

) can be obtained.

[Equation 4]

)와 오브젝트에 작용하는 중력(

)에 기초하여 접촉 영역을 회전 중심으로 한 토크(

)를 획득할 수 있다. 그리고, 회전 방향 획득 모듈(156)은 획득된 토크(

)에 기초하여 회전 방향(

)을 획득할 수 있다.The rotation direction acquisition module 156 provides a vector (

) and the gravity acting on the object (

) based on the torque (

) can be obtained. And, the rotation direction acquisition module 156 is the acquired torque (

) based on the direction of rotation (

) can be obtained.

)으로 오브젝트를 회전시킬 수 있다. 이에 따라, 오브젝트의 제2 영역은 지면과 접촉할 수 있다. 오브젝트의 제2 영역이 지면과 접촉한 것으로 판단되면, 핸드 제어 모듈(157)은 오브젝트의 파지를 해제하도록 핸드를 제어할 수 있다.The hand control module 157 may generate a control command for controlling the hand included in the manipulator 100 and may control the operation of the hand based on the control command. For example, the hand control module 157 may control the hand to grip the object. Also, the hand control module 157 may control the hand to move or rotate while holding the object. At this time, when the difference between the first direction of the first normal vector with respect to the seating surface of the object and the second direction of the second normal vector with respect to the ground is within a preset range, the hand control module 157 contacts the object with the ground. You can control the hand to do it. Accordingly, the first area of the object may contact the ground. Then, the hand control module 157 rotates the first area of the object and the contact area of the ground in the rotational direction (

) to rotate the object. Accordingly, the second region of the object may contact the ground. If it is determined that the second area of the object is in contact with the ground, the hand control module 157 may control the hand to release the grip of the object.

)과 토크(

)를 획득할 수 있다. 그리고, 매니퓰레이터(100)는 상술한 [수학식 1]에 기초하여 오브젝트에 대응되는 제1 모멘트 팔(

)을 획득할 수 있다. 여기서, 제1 모멘트 팔(

)은 힘 센서(112)로부터 중력의 작용선(L)까지의 거리를 의미한다. 중력의 작용선(L)은 오브젝트(31)의 무게 중심(C)을 통과할 수 있다.3 is a diagram for describing information acquired by a manipulator according to an embodiment of the present disclosure. Referring to FIG. 3 , the manipulator 100 may acquire a point cloud corresponding to the object 31 based on a sensing value of the depth sensor 111 . In addition, the manipulator 100 generates a force (

) and torque (

) can be obtained. And, the manipulator 100 is based on the above-mentioned [Equation 1], the first moment arm corresponding to the object (

) can be obtained. Here, the first moment arm (

) is the distance from the force sensor 112 to the line of action L of gravity. The line of action L of gravity may pass through the center of gravity C of the object 31 .

), 교점(P)으로부터 꼭짓점까지의 거리(

)를 산출할 수 있다. 매니퓰레이터(100)는 복수의 컨벡스 헐 중 교점(P)으로부터 컨벡스 헐의 변/꼭짓점까지의 거리가 최소값(

)이 최대가되는 컨벡스 헐을 안착면(

)으로 결정할 수 있다.4 is a view for explaining a method of determining a seating surface of an object according to an embodiment of the present disclosure. The manipulator 100 may determine a seating surface 42 to be in contact with the ground among a plurality of surfaces of the object 41 . The manipulator 100 may generate a plurality of convex hulls for the object 41 based on the point cloud corresponding to the object 41 . The manipulator 100 determines, for each of the plurality of convex hulls, the distance (

), the distance from the intersection (P) to the vertex (

) can be calculated. The manipulator 100 determines that the distance from the intersection (P) of the plurality of convex hulls to the side/vertex of the convex hull is the minimum value (

) is the maximum convex hull seating surface (

) can be determined.

The manipulator 100 may move the object 41 so that the determined seating surface 42 comes into contact with the ground. At this time, the manipulator 100 moves the object 41 so 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 seating surface 42 is within a preset range. can do it Accordingly, as shown in FIG. 5 , the first area A1 of the object 51 may contact the ground 52 .

)와 오브젝트(51)에 작용하는 중력(

)에 기초하여 접촉 영역(A1)을 회전 중심으로 한 토크(

)를 획득할 수 있다. 구체적으로, 매니퓰레이터(100)는 전술한 [수학식 4]에 기초하여 토크(

)를 획득할 수 있다. 그리고, 매니퓰레이터(100)는 획득된 토크(

)에 기초하여 회전 방향(

)을 획득할 수 있다.5 is a view for explaining a method of obtaining a rotation direction according to an embodiment of the present disclosure. The manipulator 100 may rotate the object 51 around the first area A1 that is a contact area between the object 51 and the ground 52 . Meanwhile, the manipulator 100 may obtain a rotation direction to rotate the object 51 . For example, the manipulator 100 uses a vector (

) and the gravity acting on the object 51 (

) based on the torque (

) can be obtained. Specifically, the manipulator 100 generates torque (

) can be obtained. And, the manipulator 100 is the obtained torque (

) based on the direction of rotation (

) can be obtained.

)에 기초하여 오브젝트(61)를 회전시킬 수 있다. 이에 따라, 오브젝트(61)의 제2 영역(A2)은 지면(62)과 접촉할 수 있다. 매니퓰레이터(100)는 기설정된 시간 동안의 힘 센서(112)의 센싱값의 변화량이 기설정된 제2 값보다 크면, 제2 영역(A2)이 지면(62)과 접촉한 것으로 판단할 수 있다. 그리고, 매니퓰레이터(100)는 오브젝트(61)의 파지를 해제할 수 있다. 이에 따라, 오브젝트(61)는 지면(62)에 안정적으로 놓여질 수 있다.As shown in FIG. 6 , the manipulator 100 rotates in the direction of rotation (

) based on the object 61 can be rotated. Accordingly, the second area A2 of the object 61 may contact the ground 62 . The manipulator 100 may determine that the second area A2 is in contact with the ground 62 when the amount of change in the sensed value of the force sensor 112 for a preset time is greater than the second preset value. In addition, the manipulator 100 may release the grip of the object 61 . Accordingly, the object 61 may be stably placed on the ground 62 .

7 is a flowchart illustrating a method of controlling a manipulator according to an embodiment of the present disclosure. The manipulator 100 may grip the object using a hand (S710). The manipulator 100 may obtain and store information about the object based on the sensed value of the force sensor obtained while gripping the object ( S720 ). At this time, the manipulator 100 obtains location information on the contact area based on the stored object information, the sensing value of the depth sensor with respect to the ground, and the sensing value of the force sensor obtained when the ground and the first area come into contact with each other. can do.

The manipulator 100 may bring the first area of the object into contact with the ground on which the object is to be placed (S730). At this time, the manipulator 100 contacts the ground with the first area of the object so that the difference between the first direction of the first normal vector to the ground and the second direction of the second normal vector to the seating surface is within a preset range. can do it The seating surface of the object may be obtained based on shape information of the object obtained based on a sensing value of the depth sensor. When the sensed value of the force sensor is greater than the first preset value, the manipulator 100 may determine that the first area is in contact with the ground.

The manipulator 100 may acquire location information on the contact area between the first area and the ground ( S740 ). The manipulator 100 may obtain position information on the contact area based on the object information, the sensing value of the depth sensor with respect to the ground, and the sensing value of the force sensor obtained when the ground and the first area come into contact.

The manipulator 100 may obtain a rotation direction in which to rotate the object based on the location information and the information on the object ( S750 ). Then, the manipulator 100 may rotate the object in a rotation direction (S760). In this case, the manipulator 100 may rotate the object based on the contact area as a rotation center.

When the second area of the object and the ground come into contact with the rotation of the object, the manipulator 100 may release the grip of the object ( S770 ). If the amount of change in the sensed value of the force sensor for a preset time is greater than the preset second value, the manipulator 100 may determine that the second region is in contact with the ground.

Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof. In some cases, the embodiments described herein may be implemented by the processor itself. According to the software implementation, embodiments such as procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

Meanwhile, computer instructions for performing the processing operation according to various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When the computer instructions stored in the non-transitory computer-readable medium are executed by the processor, the processing operation according to the above-described various embodiments may be performed by a specific device.

The non-transitory computer-readable medium refers to a medium that stores data semi-permanently, not a medium that stores data for a short moment, such as a register, cache, memory, etc., and can be read by a device. Specific examples of the non-transitory computer-readable medium may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

In the above, preferred embodiments of the present disclosure have been illustrated and described, but the present disclosure is not limited to the specific embodiments described above, and it is common in the technical field pertaining to the present disclosure without departing from the gist of the present disclosure as claimed in the claims. Various modifications can be made by those having the knowledge of

100: manipulator 110: sensor unit
120: driving unit 130: communication interface
140: memory 150: processor

Claims (16)

In the manipulator (manipulator),
hand;
depth sensor;
a force sensor for acquiring an external force acting on the hand;
a memory storing at least one instruction; and
processor; including;
The processor is
controlling the hand to grip the object,
Acquire information about the object based on the sensed value of the force sensor obtained while gripping the object and store the information in the memory,
controlling the hand so that the first area of the object is in contact with the ground on which the object is to be placed,
Obtaining location information on a contact area between the first area and the ground,
Obtaining a rotation direction to rotate the object based on the location information and information on the object,
controlling the hand to rotate the object in the rotation direction around the contact area as a rotation center;
When the second area of the object and the ground come into contact with the rotation, controlling the hand to release the grip of the object
manipulator. According to claim 1,
Information about the object is
Gravity acting on the object and the distance from the force sensor to the line of action of gravity
manipulator. According to claim 1,
The processor is
Obtaining position information about the contact area based on the information on the object, the sensing value of the depth sensor with respect to the ground, and the sensing value of the force sensor obtained when the ground and the first area come into contact
manipulator. According to claim 1,
The processor is
Obtaining a torque centered on the contact area based on the information on the object and the position information,
to obtain the rotation direction based on the torque
manipulator. According to claim 1,
The processor is
When the sensed value of the force sensor is greater than a preset first value, it is determined that the first area is in contact with the ground.
manipulator. According to claim 1,
The processor is
When the amount of change in the sensed value of the force sensor for a preset time is greater than a preset second value, it is determined that the second region is in contact with the ground
manipulator. According to claim 1,
The processor is
Obtaining shape information of the object based on the sensing value of the depth sensor,
identifying a seating surface of the object including the first area and the second area based on the shape information of the object
manipulator. 8. The method of claim 7,
The processor is
When 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 seating surface is within a preset range, controlling the hand so that the first area comes into contact with the ground
manipulator. In the control method of a manipulator comprising a hand, a depth sensor, and a force sensor for acquiring an external force acting on the hand,
gripping the object using the hand;
acquiring and storing information on the object based on a sensing value of the force sensor acquired while gripping the object;
contacting the ground on which the object is to be placed with a first area of the object;
obtaining location information on a contact area between the first area and the ground;
obtaining a rotation direction in which to rotate the object based on the location information and information on the object;
rotating the object in the rotation direction with the contact area as a rotation center; and
When the second area of the object and the ground come into contact with the rotation, releasing the grip of the object; including
control method. 10. The method of claim 9,
Information about the object is
Gravity acting on the object and the distance from the force sensor to the line of action of gravity
control method. 10. The method of claim 9,
The step of obtaining location information for the contact area includes:
Obtaining position information about the contact area based on the information on the object, the sensing value of the depth sensor with respect to the ground, and the sensing value of the force sensor obtained when the ground and the first area come into contact
control method. 10. The method of claim 9,
The step of obtaining the rotation direction includes:
acquiring a torque centered on the contact area based on the information on the object and the location information, and
acquiring the rotation direction based on the torque
control method. 10. The method of claim 9,
When the sensing value of the force sensor is greater than a preset first value, determining that the first area is in contact with the ground; further comprising
control method. 10. The method of claim 9,
When the amount of change in the sensed value of the force sensor for a preset time is greater than a preset second value, determining that the second region has come into contact with the ground; further comprising
control method. 10. The method of claim 9,
obtaining shape information of the object based on a sensing value of the depth sensor; and
Recognizing a seating surface of the object including the first area and the second area based on the shape information of the object; further comprising
control method. 16. The method of claim 15,
The step of contacting the ground with the first area of the object comprises:
When a difference between a first direction of a first normal vector with respect to the ground and a second direction of a second normal vector with respect to the seating surface is within a preset range, the first area of the object is brought into contact with the ground.
control method.

Images