Robot device and control method thereof

Abstract

A robotic device is disclosed. The robot device comprises: a main body; a robot arm capable of selectively using a plurality of gripper tips of different types; at least one sensor; memory in which at least one instruction is stored; and at least one processor operating according to the execution of the at least one instruction. When executed individually or collectively by the at least one processor, the robot device identifies characteristics of an object on the basis of a sensing value of the at least one sensor, and controls the robot arm to grip the object by using a gripper tip of a type corresponding to the identified characteristics among the plurality of gripper tips.

Description

Robot device and control method thereof

[0001] The present disclosure relates to a robot device and a method for controlling the same, and more specifically, to a robot device including a gripper tip and a method for controlling the same.

[0002] With technological advancements, robotic technology is being utilized to replace human labor in various fields. In particular, robotic devices are being developed in sectors requiring delicate and precise tasks, such as factories, construction, medical sites, and aerospace.

[0003] However, conventional robot devices use non-replaceable, single-shaped gripper tips, which made it difficult to grasp objects of specific shapes or materials. Additionally, conventional robot devices had the problem that even for the same object, it could be difficult to grasp depending on the object's orientation or position.

[0004] A robot device including a plurality of robot arms and a method for controlling the same are provided.

[0005] Additional embodiments will be presented in the detailed description below, some of which are obvious from the detailed description, and other embodiments can also be presented through learning from the presented embodiments.

[0006] A robot device according to one embodiment of the present disclosure comprises a main body, a robot arm connected to the main body and capable of selectively using a plurality of gripper tips of different types, at least one sensor, a memory storing at least one instruction, and a processor that operates according to the execution of the at least one instruction. When executed individually or collectively by the at least one processor, the robot device identifies characteristics of an object based on the sensing value of the at least one sensor and controls the robot arm to grasp the object using a gripper tip of a type corresponding to the identified characteristics among the plurality of gripper tips.

[0007] According to one embodiment of the present disclosure, the robot arm may include a rotator on which the plurality of gripper tips are mounted in different directions. When executed individually or collectively by the at least one processor, the robot device may cause the rotator to rotate so that a type of gripper tip corresponding to the identified characteristic among the plurality of gripper tips faces the object.

[0008] According to one embodiment of the present disclosure, the robot arm may include a coupling portion to which the plurality of gripper tips can be attached. When executed individually or collectively by the at least one processor, the robot device may control the robot arm to attach the plurality of gripper tips to the coupling portion so that a gripper tip of a type corresponding to the identified characteristics of the plurality of gripper tips faces the object.

[0009] According to one embodiment of the present disclosure, the plurality of gripper tips includes a first gripper tip and a second gripper tip. The contact surface of the second gripper tip may be larger than the contact surface of the first gripper tip. When executed individually or collectively by the at least one processor, the robot device may control the robot arm to grip the object using the first gripper tip when the size of the object is less than a preset size range, and to grip the object using the second gripper tip when the size of the object is greater than or equal to the size range.

[0010] According to one embodiment of the present disclosure, the plurality of gripper tips may include a first gripper tip and a second gripper tip. The contact surface of the second gripper tip may be larger than the contact surface of the first gripper tip. When executed individually or collectively by the at least one processor, the robot device may identify the spatial characteristics of the space where the object is located based on the sensing value of the at least one sensor, and select one gripper tip among the plurality of gripper tips based on the spatial characteristics and the characteristics of the object.

[0011] According to one embodiment of the present disclosure, the spatial characteristics may include information regarding at least one of the position of the object within the space, the distance between the object and the object, and the contact relationship between the object and the object. When executed individually or collectively by the at least one processor, the robot device may control the robot arm to grasp the object using the second gripper tip if the object is located at the edge of the space, grasp the object using the first gripper tip if the distance is less than a preset first distance, grasp the object using the second gripper tip if the distance is greater than or equal to the first distance, and grasp the object using the first gripper tip if the object and the at least one object are in contact.

[0012] When executed individually or collectively by the at least one processor according to one embodiment of the present disclosure, the robot device may select one of the plurality of gripper tips based on the type of operation to be performed after gripping the object.

[0013] According to one embodiment of the present disclosure, the plurality of gripper tips may include a first gripper tip and a second gripper tip. The contact surface of the second gripper tip may be larger than the contact surface of the first gripper tip. When executed individually or collectively by the at least one processor, the robot device may control the robot arm to grip the object using the second gripper tip if the operation to be performed after gripping the object is a lifting operation, grip the object using the first gripper tip if the operation is a switching operation that changes the direction in which the object is placed, and grip the object using the first gripper tip if the operation is a working operation that performs a task while moving the object within a preset range.

[0014] According to one embodiment of the present disclosure, the memory may store a database of a plurality of types of gripper tips. When executed individually or collectively by the at least one processor, the robot device may select a gripper tip corresponding to the characteristics of the object among the plurality of gripper tips based on the database.

[0015] According to one embodiment of the present disclosure, the memory may store an artificial intelligence model trained to select a gripper tip that matches the characteristics of an object among the plurality of gripper tips. When executed individually or collectively by the at least one processor, the robot device may input information regarding the characteristics of the object from the plurality of gripper tips into the artificial intelligence model and select a gripper tip based on the output value of the artificial intelligence model.

[0016] A control method for a robot device comprising a robot arm capable of selectively using a plurality of gripper tips of different types according to one embodiment of the present disclosure and at least one sensor comprises the steps of identifying a characteristic of an object based on a sensing value of the at least one sensor and controlling the robot arm to grip the object using a gripper tip of a type corresponding to the identified characteristic among the plurality of gripper tips.

[0017] According to one embodiment of the present disclosure, the robot arm may include a rotator on which the plurality of gripper tips are mounted in different directions. The step of controlling the robot arm may include the step of rotating the rotator so that a gripper tip of a type corresponding to the identified characteristic among the plurality of gripper tips faces the object.

[0018] According to one embodiment of the present disclosure, the plurality of gripper tips may include a first gripper tip and a second gripper tip. The contact surface of the second gripper tip may be larger than the contact surface of the first gripper tip. The step of controlling the robot arm may include gripping the object using the first gripper tip when the size of the object is less than a preset size range, and gripping the object using the second gripper tip when the size of the object is greater than or equal to the size range.

[0019] A control method for a robot device according to one embodiment of the present disclosure may further include the step of identifying spatial characteristics of a space where an object is located based on the sensing value of at least one sensor. The step of controlling the robot arm may include the step of selecting one gripper tip among a plurality of gripper tips based on the characteristics of the object.

[0020] According to one embodiment of the present disclosure, the step of identifying spatial characteristics of the space where the object is located based on the sensing value of the at least one sensor may include the step of identifying characteristics of a gripping point for the object based on the sensing value of the at least one sensor. The step of selecting a gripper tip of the robot arm based on the characteristics of the object may include the step of selecting a gripper tip of the robot arm based on the characteristics of the gripping point, the spatial characteristics, and the characteristics of the object.

[0021] A non-permanent computer-readable medium according to one embodiment of the present disclosure includes instructions stored in the medium, and when the instructions are executed by at least one processor, the processor executes a method of controlling a robot device. The method includes the steps of identifying characteristics of a target based on a sensing value of at least one sensor of the robot device, and controlling a robot arm of the robot device to grasp a target object with a gripper tip using one of a plurality of gripper tips of the robot arm corresponding to the identified characteristics.

[0022] A method for controlling a robot device may be performed by at least one processor when executed by the processor according to instructions stored in a non-permanent computer-readable medium according to one embodiment of the present disclosure. The method may further include the robot arm including a rotator with each gripper tip mounted in a different direction, and controlling the robot arm may further include rotating the rotator so that the gripper tip corresponding to the identified characteristic faces the object.

[0023] A method executed by one or more processors according to instructions stored in a non-persistent computer-readable medium according to one embodiment of the present disclosure may include a plurality of gripper tips, which may include a first gripper tip and a second gripper tip, and the contact area of ​​the second gripper tip may be larger than the contact area of ​​the first gripper tip. The step of controlling a robot arm may further include the step of grasping an object using the first gripper tip when the size of the object is smaller than a preset size range, and the step of grasping an object using the second gripper tip when the size of the object is greater than or equal to the preset size range.

[0024] According to one embodiment of the present disclosure, a method for controlling a robot device may be executed by at least one processor in accordance with instructions stored in a non-persistent computer-readable medium. The method may further include the step of identifying spatial characteristics of a space where a target is located based on a sensing value of at least one sensor, and the step of controlling a robot arm may further include the step of selecting a gripper tip from a plurality of gripper tips according to the characteristics of the target.

[0025] In a method in which one or more processors execute according to instructions stored in a non-persistent computer-readable medium according to one embodiment of the present disclosure, the step of identifying spatial characteristics of a space in which a target is located based on sensing values ​​of one or more sensors may include the step of identifying grip point characteristics of the target based on sensing values ​​of at least one sensor, and the step of selecting a gripper tip of a robot arm according to the characteristics of the target may include the step of selecting a gripper tip of a robot arm based on grip point characteristics, spatial characteristics, and characteristics of the target.

[0026] As described above, other aspects and features of specific embodiments of the present disclosure may be more clearly understood from the following description provided with reference to the accompanying drawings:

[0027] FIG. 1 is a drawing showing a robot device according to at least one embodiment of the present disclosure.

[0028] FIG. 2 is a drawing showing a gripper according to at least one embodiment of the present disclosure.

[0029] FIG. 3 is a drawing showing a gripper tip according to at least one embodiment of the present disclosure.

[0030] FIG. 4 is a block diagram of a robot device according to at least one embodiment of the present disclosure.

[0031] FIGS. 5A and 5B are drawings for explaining a method of selecting a gripper tip based on the characteristics of an object according to at least one embodiment of the present disclosure.

[0032] FIGS. 6a to 6c are drawings for explaining a method of selecting a gripper tip based on the characteristics of an object according to at least one embodiment of the present disclosure.

[0033] FIGS. 7 to 10 are flowcharts illustrating a control method for a robot device according to at least one embodiment of the present disclosure.

[0034] Various embodiments are described in more detail below with reference to the attached drawings. The embodiments described in this specification may be modified in various ways. Specific embodiments may be depicted in the drawings and described in detail in the detailed description. However, specific embodiments disclosed in the attached drawings are intended only to facilitate understanding of various embodiments. Accordingly, the various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutions of such embodiments.

[0035] The singular form of the noun corresponding to the item may include one or multiple items, unless the relevant context clearly indicates otherwise.

[0036] In this document, each of the phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", and "at least one of A, B, or C" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof.

[0037] The term "and / or" includes a combination of multiple related described components or any of the multiple related described components.

[0038] Terms such as "first," "second," or "first" or "second" may be used simply to distinguish a component from another component and do not limit the components in other aspects (e.g., importance or order).

[0039] Where any (e.g., 1st) component is referred to as "coupled" or "connected" to another (e.g., 2nd) component, with or without the terms "functionally" or "communicationly," it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0040] Terms such as "include" or "have" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in this document, and do not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0041] When it is said that a component is "connected," "combined," "supported," or "in contact" with another component, this includes not only cases where the components are directly connected, combined, supported, or in contact, but also cases where they are indirectly connected, combined, supported, or in contact through a third component.

[0042] In this disclosure, the expression "identical" means not only complete agreement but also includes differences to the extent that account for processing error ranges.

[0043] When it is said that a component is located "on" another component, this includes not only cases where one component is in contact with the other, but also cases where another component exists between the two components.

[0044] In the embodiment, the 'module' or multiple 'parts' may be integrated into at least one module and implemented by at least one processor, except for the 'module' or 'part' that needs to be implemented in specific hardware.

[0045] Operations performed by a module, program, or other component according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.

[0046] Meanwhile, the various elements and areas in the drawings are depicted schematically. Accordingly, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0047] With respect to any method or process described herein, identification codes may be used for convenience of description but are not intended to describe the order of each step or action. Unless otherwise specified in the context, each step or action may be implemented in a different order than the exemplified order. Unless otherwise specified in the context of this disclosure, one or more steps or actions may be omitted.

[0048] Below, a robot device (1) according to various embodiments will be described in detail with reference to the drawings.

[0049] FIG. 1 is a drawing showing a robot device (1) according to at least one embodiment of the present disclosure.

[0050] The robot device (1) may include a main body (10), a robot arm (100), and at least one sensor (200).

[0051] The main body (10) is configured to include devices for overall management of the operation of the robot device (1). The main body (10) is a device that forms the external shape of the robot device (1). In FIG. 1, the main body (10) is shown as a simple rectangular shape, but it is not necessarily limited thereto and can be formed in various forms, such as a body in the case of a humanoid robot, a core module in the case of a 3-axis core module, or a central module in the case of a quadruped robot. In addition, the main body (10) may be formed in a manner that is integral with the robot arm and gripper, or it may be formed in a manner that is separated and then assembled. The main body (10) may be referred to by various terms such as housing, cabinet, core module, body, etc.

[0052] A robot arm (100) can be connected to one side of the main body (10). The robot arm (100) is configured to move the gripper (1000) to a specific position by moving each joint of a plurality of joints (101, 102, 103). The robot arm (100) may be formed in a manner that is integral with the main body (10), or it may exist as a module independent of the main body (10) and be formed in a manner that is assembled to the main body (10).

[0053] The robot arm (100) may include a plurality of joints (101, 102, 103). The plurality of joints (101, 102, 103) can move in various ways around each axis. Although the plurality of joints (101, 102, 103) are all shown as I-shaped modules in FIG. 1, they are not necessarily limited thereto and can be formed into various types of modules, such as L-shaped modules.

[0054] A robot arm (100) may include a gripper (1000) and a plurality of gripper tips (1100). The gripper (1000) may be in a form corresponding to being attached to the ends of a plurality of joints (101, 102, 103). When the plurality of joints (101, 102, 103) move the gripper (1000) to a specific position for performing a task, the gripper (1000) can perform the task at the specific position. For example, the gripper (1000) may move to a specific position after gripping an object. Additionally, the gripper (1000) can perform various tasks such as cleaning, screwing, and welding after gripping an object.

[0055] The robot arm (100) may include a plurality of gripper tips (1100). The plurality of gripper tips (1100) may be formed in different types of shapes. The gripper (1000) may be formed in different types of shapes and may grip an object using a type of gripper tip corresponding to the characteristics of the object. Since this will be explained in detail starting from FIG. 2, this explanation is omitted.

[0056] At least one sensor (200) may be placed at a location separated from the main body (10), the robot arm (100), and the robot device (1) (e.g., a location selected to provide a third-person view). The robot device (1) may acquire object or surrounding shape information based on the sensing value of at least one sensor (200). The robot device (1) may identify the characteristics of the object based on the sensing value of at least one sensor (200). The robot device (1) may identify the spatial characteristics of the space where the object is located based on the sensing value of at least one sensor (200). Here, spatial characteristics refer to information regarding at least one of the position of the object within the space, the distance between the object and at least one object located around the object, and the contact relationship between the object and the object. Additionally, the robot device (1) may identify the characteristics of the gripping point of the robot arm (100) based on the sensing value of at least one sensor (200). Here, the characteristics of the gripping point may vary depending on the operation of the robot device (1). For example, when the robot device (1) attempts to lift an object, the characteristics of the gripping point may be a point where the torque of the object is minimized or near the center of gravity of the object. When the robot device (1) attempts to rotate an object, the characteristics of the gripping point may be the point furthest from the center of rotation of the object. However, it is not necessarily limited to this, and the characteristics of the gripping point may be various points within the object depending on the user's actions. The robot device (1) can identify various information based on the sensing values ​​of at least one sensor (200). At least one sensor (200) may include a vision sensor, an infrared sensor, an ultrasonic sensor, etc. However, it is not necessarily limited to this, and may include various sensors capable of detecting sensing values ​​regarding the characteristics of the object, spatial information of the object, surrounding shape information, information on the gripping point of the object, etc.

[0057] FIG. 2 is a drawing showing a gripper (1000) according to at least one embodiment of the present disclosure.

[0058] In FIG. 2, the gripper (1000) may include a first coupling part (1010), a plurality of fingers (1020, 1030), a second connecting part (1110), a first gripper tip (1120), a second gripper tip (1130), and a rotator (2000).

[0059] The first coupling part (1010) is configured to be coupled to one side of the robot arm (100). The gripper (1000) can be coupled to a plurality of joints (101, 102, 103) of the robot arm (100) through the first coupling part (1010). The first coupling part (1010) can be coupled to the plurality of joints (101, 102, 103) through various joint couplings, such as a revolute joint coupling, a spherical joint coupling, or a screw joint coupling.

[0060] A plurality of fingers (1020, 1030) may be arranged facing each other with respect to the center of the gripper (1000). The first finger (1020) may include a plurality of first finger joints (1021, 1022). The second finger (1030) may include a plurality of second finger joints (1031, 1032).

[0061] Multiple fingers (1020, 1030) can grasp an object using each of the multiple finger joints. Multiple fingers (1020, 1030) can perform precise operations using each of the multiple finger joints.

[0062] A plurality of gripper tips (1100) can be coupled with a plurality of fingers (1020, 1030) through a second connecting part (1110). A first gripper tip (1120) and a second gripper tip (1130) can be positioned opposite each other with respect to the second connecting part (1110). However, this is not necessarily limited thereto, and a plurality of gripper tips (1100) can be positioned at various locations centered on the second connecting part (1110).

[0063] The first gripper tip (1120) is a gripper tip used when gripping an object with a small contact surface. For example, the first gripper tip (1120) may be selected when gripping an object such as a thread, string, and earphone.

[0064] The second gripper tip (1130) is a gripper tip used when gripping an object with a larger contact surface compared to the object gripped by the first gripper tip. For example, it can be selected when gripping an object such as a shoe, an apple, or a thermos bottle.

[0065] However, the plurality of gripper tips (1100) are not necessarily limited to the first gripper tip (1120) and the second gripper tip (1130), and may include gripper tips of various shapes, forms, and materials depending on the characteristics of the object, the characteristics of the gripping point, user settings, user preferences, etc.

[0066] The robot arm (100) may include a rotator (2000). The rotator (2000) may be in a form in which a plurality of gripper tips (1100) are mounted in different directions through a second connecting part (1110). The rotator (2000) may be formed in a manner that is integral with the plurality of gripper tips (1100), or it may be formed in a manner that is independent. The robot arm (100) may rotate the rotator (2000) so that a type of gripper tip corresponding to the characteristics of the object identified based on the sensing value of at least one sensor (200) among the plurality of gripper tips (1100) faces the object. However, it is not necessarily limited thereto, and if the rotation module (2000) includes a motor, the rotator (2000) may rotate the second connecting part (1110) through the motor so that one of the plurality of gripper tips faces the object.

[0067] The embodiment illustrated in FIG. 2 shows two gripper tips (1120 and 1130) attached to each connector (1110), but the present disclosure is not limited thereto, and additional gripper tips may be attached at other points around the circumference of the connector (1110).

[0068] FIG. 3 is a drawing showing a plurality of gripper tips (1100) according to at least one embodiment of the present disclosure.

[0069] A plurality of gripper tips (1100) may include a second connecting part (1110), a first gripper tip (1120), and a second gripper tip (1130). The second connecting part (1110) may be arranged in a manner corresponding to a shape protruding perpendicular to the longitudinal direction of the plurality of gripper tips (1100) from the center of the plurality of gripper tips (1100). The second connecting part (1110) may be coupled to a plurality of fingers (1020, 1030) of the gripper (1000). Additionally, the second connecting part (1110) may be coupled to a rotation module (2000) disposed on one side of the gripper (1000). The plurality of gripper tips (1100) may be rotated around the second connecting part (1110). Specifically, a plurality of gripper tips (1100) can be rotated around the second connecting part (1110) so that a type of gripper tip corresponding to the identified characteristic is directed toward the object. For example, if a thin object with a narrow area is identified based on the sensing value of at least one sensor (200), the first gripper tip (1120) can be rotated around the second connecting part (1110) so that it is directed toward the object. Conversely, if an object with a larger area than the object that the first gripper tip (1120) can grip is identified based on the sensing value of at least one sensor (200), the second gripper tip (1130) can be rotated around the second connecting part (1110) so that it is directed toward the object.

[0070] The first gripper tip (1120) may include a first gripping portion (1121). The first gripping portion (1121) may be formed in a shape corresponding to a pointed end. The first gripping portion (1121) may be formed in a shape corresponding to a shape bent at a certain angle in the longitudinal direction of the plurality of gripper tips (1100). Specifically, the first gripping portion (1121) may be formed in a shape corresponding to a shape bent at a certain angle in the longitudinal direction of the plurality of gripper tips (1100) so that the first gripping portions (1121) come together. Through this, the first gripper tip (1120) can grip an object with a small and thin contact surface.

[0071] The second gripper tip (1130) may include a second gripping portion (1131). The second gripping portion (1131) may have a broad end shape. The second gripping portion (1131) may include an uneven surface member on one side. Specifically, the uneven surface member of the second gripping portion (1131) may be an elastic body. For example, the uneven surface member may be made of various materials such as rubber, silicone, polyurethane, EPDM, etc. Through this, the second gripper tip (1130) can grip an object with a larger contact surface than the object that the first gripper tip (1120) can grip.

[0072] FIG. 4 is a block diagram of a robot device (1) according to at least one embodiment of the present disclosure.

[0073] The robot device (1) may include a robot arm (100), a memory (3010), and a processor (3020).

[0074] The memory (3010) is configured to contain various programs, instructions, and data required for the operation of the robot device (1). At least one instruction can be stored in the memory (3010). Although the memory (3010) is depicted as being separate from the processor (3020) in FIG. 4, it is not necessarily limited thereto, and the memory (3010) may be implemented as an internal memory such as ROM (e.g., EEPROM (electrically erasable programmable read-only memory)) or RAM included in the processor (3020).

[0075] Alternatively, the memory (3010) may be implemented in the form of a memory embedded in the robot device (1) or in the form of a memory that can be attached to and detached from the robot device (1), depending on the purpose of data storage. Specifically, the memory (3010) may be implemented in various forms such as volatile memory, SRAM (static RAM), or SDRAM (synchronous dynamic RAM), etc., non-volatile memory (e.g., OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, flash memory, hard drive, or solid state drive (SSD), CF (compact flash), SD (secure digital), MicroSD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital), MMC (multi-media card), etc.

[0076] In the present disclosure, the term memory (3010) may be used to include a storage unit, a ROM (not shown), a RAM (not shown) within a processor (3020), or a memory card (not shown) mounted on an electronic device (e.g., a micro SD card, a memory stick). Although the memory (3010) is depicted as one in FIG. 4, the memory (3010) may be implemented in various numbers.

[0077] The memory (3010) is configured to store at least one instruction, O / S (Operating System), program, and data, etc., regarding the robot device (1).

[0078] The memory (3010) is accessed by the processor (3020). In the memory (3010), data reading, writing, modification, deletion, updating, etc. by the processor (3020) can be performed.

[0079] Specifically, the memory (3010) may store various information such as assembly status information of each joint of the robot arm (100), information of the gripper (1000) of the robot arm (100), information about a plurality of gripper tips (1100), information about each tip of the plurality of gripper tips (1100), information about a rotating module (2000) capable of changing the plurality of gripper tips (1100), and characteristic information of the object, pre-set size range information of the object, current placement information of the gripper tips (1120, 1130), pre-set first distance range, pre-set range for performing work, etc., as well as programs and commands for controlling the operation of the robot device (1) and other devices.

[0080] The memory (3010) can store multiple previously trained artificial intelligence models. For example, the artificial intelligence models can be implemented as CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory), DNN (Deep Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), etc., but are not limited to such examples. These artificial intelligence models are computing systems implemented based on the neural networks of human or animal brains, and may be referred to as learning models, machine learning models, neural network models, deep learning models, etc. The memory (3010) may store a database of types of gripper tips corresponding to each object characteristic. Additionally, the memory (3010) may store an artificial intelligence model trained to select a gripper tip that matches the characteristics of the object.

[0081] The processor (3020) controls the overall operation of the robot device (1). For example, the processor (3020) is connected to a configuration of the robot device including a memory (3010) and can control the overall operation of the electronic device by executing at least one instruction stored in the memory (3010) as described above. In particular, the processor (3020) can be implemented as a single processor as well as as a plurality of processors.

[0082] The processor (3020) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing operations. The processor (3020) may include at least one electrical circuit and may process instructions (or programs, data, etc.) stored in memory individually or collectively in a distributed manner.

[0083] The processor (3020) may include a processor assembly comprising one or more processing circuits. The processor (3020) may include any processing circuit that is operative to control the performance and operations of one or more components of the robot device (e.g., memory and / or drive unit (sensor)). For example, the processor (3020) (e.g., AP) may be implemented as a system on chip (SoC) (e.g., a single chip or a chipset). For example, the processor (3020) may be implemented as multiple cores (or at least one core circuit), multiple chips, or multiple chipsets.

[0084] For example, the processor (3020) may include one or more processing circuits. The processor (3020) may include one or more processing circuits configured to perform various functions of the present disclosure individually and / or collectively. As an example without limitation, at least a portion of the processor (3020) may be included in a first chip of the robot device (1), and at least another portion of the processor (3020) may be included in a second chip of a robot device different from the first chip of the robot device (1).

[0085] For example, the processor (3020) may include a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), an image signal processor (ISP), a display controller, a memory controller, a storage controller, a communication processor (CP), and / or a sensor interface. These components of the processor (3020) are merely exemplary. The processor (3020) may include additional components other than those described above. Additionally, some components of the processor (3020) may be omitted. Furthermore, some components of the processor (3020) may be included as separate components of the robot device (1) outside of the processor (3020). For example, some components of the processor (3020) (e.g., a memory controller) may be included within other components (e.g., at least a portion of memory, an interface (e.g., available for connection to at least one component of the robot device (1)), a display).

[0086] The processor (3020) can cause other components of the robot device (1) to perform various operations by executing instructions stored in memory (3010). The processor (3020) processes setting values, function commands, etc. according to a stored control program or control data, and can output control signals related to functions that the robot device (1) can perform or communication signals for communicating with an external robot device. The processor (3020) may also perform at least one of the various operations described above based on an artificial intelligence model. The processor (3020) for executing the artificial intelligence model may be implemented through a combination of software and a general-purpose processor such as a CPU, AP, DSP (Digital Signal Processor), a graphics-dedicated processor such as a GPU, VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU.

[0087] If the processor (3020) is implemented as a processor dedicated to artificial intelligence, it may be designed as a hardware chip such as an ASIC or FPGA specialized in processing a specific artificial intelligence model.

[0088] When the processor (3020) is implemented as a dedicated processor, it may be implemented to include a memory (3010) for implementing an embodiment of the present disclosure, or may be implemented to include a memory processing function for using external memory. The processor (3020) may be implemented as one or multiple processors. Additionally, the processor (3020) may perform various operations based on programs, instructions, data, etc. stored in the memory (3010).

[0089] The processor (3020) can identify the characteristics of an object based on the sensing value of at least one sensor (200). Here, the object refers to an object that the robot device (1) can grasp to perform a specific task. The processor (3020) can control the robot arm (100) to grasp the object using a type of gripper tip corresponding to the characteristics of the identified object among a plurality of gripper tips (1100). Additionally, the processor (3020) can control a plurality of joints (101, 102, 103), a gripper (1000), a plurality of fingers (1020, 1030), and a rotation module (2000), etc., of the robot arm (100) to grasp the object using a type of gripper tip corresponding to the characteristics of the identified object among a plurality of gripper tips (1100).

[0090] Additionally, the processor (3020) can control the robot arm (100) to attach and detach a plurality of gripper tips (1100) to the connecting part (1110) so that a gripper tip of a type corresponding to the identified characteristic among the plurality of gripper tips (1100) faces the object.

[0091] For example, if you want to change from the first gripper tip (1120) to the second gripper tip (1130), the processor (3020) can control the robot arm (100) to detach the first gripper tip (1120) from the connection part (1110) and attach the second gripper tip (1130) to the second connection part (1110).

[0092] However, the method of controlling the robot arm (100) to attach and detach multiple gripper tips (1100) to the connecting part (1110) so that a gripper tip of a type corresponding to the identified characteristic among the multiple gripper tips (1100) faces the object may include various methods.

[0093] In the following description, the multiple joints (101, 102, 103), gripper (1000), multiple fingers (1020, 1030), and rotation module (2000) of the robot arm (100) can each be controlled, but this is treated as the same expression as controlling the robot arm (100).

[0094] The processor (3020) can rotate the rotator (2000) so that a type of gripper tip corresponding to the characteristics of the identified object among the plurality of gripper tips (1100) faces the object. For example, if the first gripper tip (1120) is suitable for the characteristics of the identified object among the plurality of gripper tips (1100), the processor (3020) can use the rotator (2000) to rotate the first gripper tip (1120) to a position where the object can be grasped. However, if the first gripper tip (1120) was already positioned in a graspable position before the robot device (1) detected it through at least one sensor (200), the processor (3020) may not perform separate control. Likewise, if the second gripper tip (1130) is suitable for the characteristics of the identified object among the multiple gripper tips (1100), the processor (3020) can rotate the second gripper tip (1130) to a position where the object can be grasped using a rotator (2000). However, if the second gripper tip (1130) was already positioned in a graspable position before the robot device (1) detected it through at least one sensor (200), the processor (3020) may not perform separate control.

[0095] The processor (3020) can control the robot arm (100) to grip the object using the first gripper tip (1120) if the size of the object is less than the preset size range, and to grip the object using the second gripper tip (1130) if the size of the object is greater than or equal to the preset size range. Here, the preset size range may be set based on the maximum size range of the object to which the first gripper tip can be selected. However, it is not necessarily limited to this, and the preset size range may be set to various size ranges, such as the minimum size range of the object to which the second gripper tip can be selected. Here, the preset size range may be stored in memory in advance.

[0096] The processor (3020) can identify spatial characteristics of the space where an object is located based on the sensing value of at least one sensor (200). Specifically, the processor (3020) can identify spatial characteristics of the space where an object is located based on the sensing value of at least one sensor (200) if at least one object is located around the object in the space where the object is located. The processor (3020) can select the gripper tip (1120, 1130) of the robot arm (100) based on the spatial characteristics of the space where the object is located and the characteristics of the object. Here, the spatial characteristics of the space where the object is located may include various information such as coordinate information where the object is located and coordinate information of objects surrounding the object. In addition, the spatial characteristics of the space where the object is located may include information regarding at least one of the position of the object within the space, the distance between the object and at least one object located around the object, and the contact relationship between the object and the object. The characteristics of the object may include various information such as the size, material, and shape of the object. In addition, the characteristics of the gripping point may be included in the characteristics of the object.

[0097] The processor (3020) can identify characteristics of a gripping point on an object based on the sensing value of at least one sensor (200). The processor (3020) can select a gripper tip (1120, 1130) of a robot arm (100) based on characteristics of the gripping point of the object, characteristics of the space where the object is located, and characteristics of the object. Here, the characteristics of the gripping point of the object may include various information such as location information where the torque value is smallest and center of gravity location information, based on the size, material, and shape of the object.

[0098] The processor (3020) can grasp an object using the second gripper tip (1130) if the object is located at the edge of the space where the object is located. Here, the edge may be an area that can be detached, such as the edge of a table. The processor (3020) can grasp the object using the first gripper tip (1120) if the distance between the object and surrounding objects is less than a preset first distance. The processor (3020) can grasp the object using the second gripper tip (1130) if the distance between the object and surrounding objects is greater than or equal to a preset first distance. Here, the preset first distance may correspond to a distance narrower than the gripping range of the second gripper tip (1130). In addition, the preset first distance may be the same as the object size range that the first gripper tip (1120) can grip. However, it is not necessarily limited to this, and the preset first distance may vary depending on the user's settings.

[0099] The processor (3020) can grasp the object using the first gripper tip (1120) when the object and surrounding objects are in contact.

[0100] The processor (3020) can select a gripper tip (1120, 1130) corresponding to the characteristics of the object based on a database of types of gripper tips (1120, 1130) corresponding to the characteristics of the object.

[0101] The processor (3020) can select the gripper tip (1120, 1130) of the robot arm (100) based on the type of action to be performed after grasping the object.

[0102] If the action to be performed after grasping the object is a lifting action, the processor (3020) can grasp the object using the second gripper tip (1130). If the action to be performed after grasping the object is a switching action to switch the direction in which the object is placed, the processor (3020) can grasp the object using the first gripper tip (1120). If the action to be performed after grasping the object is a work action to perform a task while moving the object within a preset range, the processor (3020) can control the robot arm (100) to grasp the object using the first gripper tip (1120). Here, the preset range may be a range capable of performing precise work. However, it is not necessarily limited to this, and the preset range may be various ranges depending on the user's settings.

[0103] The processor (3020) can input information about the characteristics of an object into an artificial intelligence model and select a gripper tip (1120, 1130) of a robot arm (100) based on the output value of the artificial intelligence model. Here, the artificial intelligence model may be a model trained to select a gripper tip (1120, 1130) that matches the characteristics of the object.

[0104] FIGS. 5A and 5B are drawings for explaining a method of selecting a gripper tip (1120, 1130) based on the characteristics of an object according to at least one embodiment of the present disclosure. FIGS. 5A and 5B are drawings for explaining a method of selecting a type of gripper tip (1120, 1130) corresponding to the characteristics identified among several objects.

[0105] FIG. 5a is a drawing for explaining a method of selecting a first gripper tip (1120) among a plurality of gripper tips (1100), and FIG. 5b is a drawing for explaining a method of selecting a second gripper tip (1130) among a plurality of gripper tips (1100).

[0106] In FIGS. 5A and 5B, objects such as shoes, a mobile phone, earphones, an apple, and a thermos are placed on a table. A robot device (1) can detect object and surrounding shape information, etc. based on the sensing value of at least one sensor (200). In FIG. 5A, the robot device (1) can detect location information of a thermos, location information of an apple, location information of a shoe, location information of a shoelace, location information of a mobile phone, and location information of an earphone, etc. based on the sensing value of at least one sensor (200). Additionally, the robot device (1) can detect information regarding the shape, material, size, etc. of the thermos, apple, shoe, shoelace, mobile phone, and earphone, etc. based on the sensing value of at least one sensor (200).

[0107] In FIG. 5a, when the robot device (1) detects that the size of an object is less than a preset size range based on the sensing value of at least one sensor (200), the robot device (1) can select a first gripper tip (1120) based on the characteristics of the object. For example, when the robot device (1) detects a grippable object as a shoelace (4010), an earphone fastener (4020), and an earphone cord (4030) based on the sensing value of at least one sensor (200), since the size of the object is less than a preset size range, the robot device (1) can select a first gripper tip (1120) based on the characteristics of the object.

[0108] If the first gripper tip (1120) is suitable for the characteristics of the identified object among the multiple gripper tips (1100), the first gripper tip (1120) can be rotated to a position where the object can be grasped using the robot device (1) rotator (2000). However, if the first gripper tip (1120) was already positioned to a graspable position before the robot device (1) detected it through at least one sensor (200), the robot device (1) may not perform separate control.

[0109] In FIG. 5b, if the robot device (1) detects that the size of an object is greater than or equal to a preset size range based on the sensing value of at least one sensor (200), the robot device (1) can select a second gripper tip (1130) based on the characteristics of the object. For example, if the robot device (1) detects a grippable object as a shoe (5010), a thermos (5020), and an apple (5030) based on the sensing value of at least one sensor (200), since the size of the object is greater than or equal to a preset size range, the robot device (1) can select a second gripper tip (1120) based on the characteristics of the object.

[0110] Here, the robot device (1) can change from the first gripper tip (1120) to the second gripper tip (1130) or from the second gripper tip (1130) to the first gripper tip (1120) using a rotator (2000).

[0111] In FIG. 5b, if the second gripper tip (1130) is suitable for the characteristics of the object identified among the plurality of gripper tips (1100), the robot device (1) can rotate the second gripper tip (1130) to a position where the object can be grasped using a rotator (2000). However, if the second gripper tip (1130) was already positioned in a graspable position before the robot device (1) detected it through at least one sensor (200), the robot device (1) may not perform separate control.

[0112] Subsequently, in FIGS. 5a and 5b, the robot device (1) identifies the position of the gripping point of an object based on the sensing value of at least one sensor (200), and the robot device (1) can grip the object using the gripper tip (1120, 1130).

[0113] FIGS. 6a to 6c are drawings for explaining a method of selecting a gripper tip (1120, 1130) based on the characteristics of an object according to at least one embodiment of the present disclosure.

[0114] FIG. 6a is a drawing for explaining a method of selecting a second gripper tip (1130) based on the characteristics of a first object (6010) which is the entire shoe, FIG. 6b is a drawing for explaining a method of selecting a first gripper tip (1120) based on the characteristics of a second object (6020) which is a shoelace, and FIG. 6c is a drawing for explaining a method of selecting a first gripper tip (1120) based on the characteristics of a third object (6030) which is the heel of the shoe.

[0115] In FIGS. 6a to 6c, the robot device (1) is determined to identify the characteristics of objects placed in FIGS. 5a and FIG. 5b based on the sensing value of at least one sensor (200) and to grasp each member of the shoe.

[0116] In FIGS. 6a to 6c, the robot device (1) can identify a first object (6010), which is the entire shoe, a second object (6020), which is the shoelace, and a third object (6030), which is the heel of the shoe, based on the sensing value of at least one sensor (200). Here, the robot device (1) may use different types of gripper tips (1120, 1130) among a plurality of gripper tips (1100) corresponding to the characteristics of the identified object, depending on a specific task set by the user.

[0117] In FIG. 6a, when a user sets a task to grasp and move a first object (6010), the robot device (1) can select a second gripper tip (1130), which is a type of gripper tip (1120, 1130) corresponding to the first object (6010), based on the sensing value of at least one sensor (200).

[0118] In FIG. 6b, when a user sets a task of tying shoelaces, the robot device (1) can select a first gripper tip (1120), which is a type of gripper tip (1120, 1130) corresponding to a second object (6020), based on the sensing value of at least one sensor (200).

[0119] In FIG. 6c, when a task is set to assist when a user puts on shoes, the robot device (1) can select a first gripper tip (1120), which is a type of gripper tip (1120, 1130) corresponding to a third object (6030), based on the sensing value of at least one sensor (200).

[0120] However, it is not necessarily limited to this, and the robot device (1) may have different types of gripper tips (1120, 1130) corresponding to the object depending on the task set by the user.

[0121] Subsequently, in FIGS. 6a, 6b and 6c, the robot device (1) identifies the position of the gripping point of an object based on the sensing value of at least one sensor (200), and the robot device (1) can grip the object (6010, 6020, 6030) using the gripper tip (1120, 1130).

[0122] FIG. 7 is a flowchart illustrating a control method of a robot device (1) according to at least one embodiment of the present disclosure.

[0123] In FIG. 7, the robot device (1) can identify the characteristics of an object based on the sensing value of at least one sensor (S1010). The robot device (1) can control the robot arm (100) to grasp the object using a type of gripper tip (1120, 1130) corresponding to the characteristics of the identified object among a plurality of gripper tips (1100) (S1020).

[0124] The robot device (1) can rotate the rotator (2000) so that a type of gripper tip (1120, 1130) corresponding to the characteristics of the identified object among a plurality of gripper tips (1100) faces the object.

[0125] If the size of the object is less than a preset size range, the robot device (1) can grasp the object using the first gripper tip (1120). If the size of the object is greater than or equal to a preset size range, the robot device (1) can grasp the object using the second gripper tip (1130).

[0126] Here, detailed descriptions of the characteristics of the object, the robot arm (100), the plurality of gripper tips (1100), the first gripper tip (1120), and the second gripper tip (1130), etc., have been described above, so such descriptions are omitted.

[0127] FIG. 8 is a flowchart illustrating a control method of a robot device (1) according to at least one embodiment of the present disclosure.

[0128] In FIG. 8, the robot device (1) can identify spatial characteristics of the space where an object is located based on the sensing value of at least one sensor (200) (S1110). Subsequently, the robot device (1) can select gripper tips (1120, 1130) of the robot arm (100) based on the characteristics of the object (S1120).

[0129] The robot device (1) can identify the characteristics of a gripping point on an object based on the sensing value of at least one sensor (200). Additionally, the robot device (1) can select a gripper tip (1100) of a robot arm (100) based on the characteristics of the gripping point, the characteristics of the space where the object is located, and the characteristics of the object.

[0130] Here, since detailed explanations regarding the spatial characteristics of the space where the object is located, the characteristics of the object, and the characteristics of the gripping point have been described above, such explanations are omitted.

[0131] FIG. 9 is a flowchart illustrating a control method of a robot device (1) according to at least one embodiment of the present disclosure.

[0132] The robot device (1) can identify the spatial characteristics of the space where the object is located and the characteristics of the gripping point on the object based on the sensing value of at least one sensor (200) (S1210). The robot device (1) can select a gripper tip of the robot arm (100) based on the characteristics of the gripping point, the spatial characteristics of the space where the object is located, and the characteristics of the object (S1220). The robot device (1) can control the robot arm (100) to grip the object using a type of gripper tip (1120, 1130) corresponding to the characteristics of the identified object among a plurality of gripper tips (1100) (S1230).

[0133] The robot device (1) can select a second gripper tip (1130) if the object is located at the edge of the space where the object is located. Here, the edge of the space where the object is located may be an area where there is a risk of falling out of the space, such as the edge of a table, the edge of a desk, or the edge of a wall. The robot device (1) can select a first gripper tip (1120) if the distance between the object and surrounding objects is less than a preset first distance, and select a second gripper tip (1130) if the distance is greater than or equal to the first distance. Since the description of the preset first distance has been described above, a description thereof is omitted.

[0134] The robot device (1) can select the first gripper tip (1120) when the object and surrounding objects are in contact.

[0135] If the action to be performed after the robot device (1) grasps an object is a lifting action, the robot device (1) can grasp the object using the second gripper tip (1130). If the action to be performed after the robot device (1) grasps an object is a switching action that changes the direction in which the object is placed, the robot device (1) can grasp the object using the first gripper tip (1120). If the action to be performed after the robot device (1) grasps an object is a working action that performs a task while moving the object within a preset range, the robot device (1) can grasp the object using the first gripper tip (1120).

[0136] FIG. 10 is a flowchart illustrating a control method of a robot device (1) according to at least one embodiment of the present disclosure.

[0137] The robot device (1) can acquire object and surrounding shape information based on the sensing value of at least one sensor (200) (S1310). Subsequently, the robot device (1) can generate a group of candidate gripping points for performing a task (S1320). Here, the group of candidate gripping points may vary depending on the case where the user sets a task. The group of candidate gripping points may vary depending on the characteristics of the object, etc. Subsequently, the robot device (1) can determine the suitability of the gripper tip (1120, 1130) in its current state (S1330). Here, if it is determined that the suitability of the gripper tip (1120, 1130) in its current state is suitable, the robot device (1) can grip the object and perform a task using the gripper tip (1120, 1130) in its current state (S1350). Conversely, if it is determined that the suitability of the current gripper tips (1120, 1130) is not suitable, the robot device (1) can change the gripper tips (1120, 1130) by controlling the rotator (2000) (S1340). Afterwards, the robot device (1) can grip an object and perform work using the gripper tips (1120, 1130) changed via the rotator (2000) (S1350). Afterwards, the robot device (1) can determine whether the work is completed (S1360). If the robot device (1) determines that the work is completed, the robot device (1) can terminate the work. Conversely, if the robot device (1) determines that the work is not completed, the robot device (1) can perform the work again starting from the step of generating a candidate group of gripping points for the object to be worked on.

[0138] Each of the components described in this document may consist of one or more components, and the names of such components may vary depending on the type of electronic device.

[0139] Although various embodiments of the present disclosure have been described individually above, each embodiment is not required to be implemented alone, and the configuration and operation of each embodiment may be implemented in combination with at least one other embodiment.

[0140] According to the various embodiments described above, by using an artificial intelligence model trained to select a gripper tip that matches the characteristics of an object, the accuracy of selecting the gripper tip can be increased, thereby providing users with a high level of satisfaction with the artificial intelligence function.

[0141] Various embodiments of the present disclosure may be implemented as software stored on a machine-readable storage media that can be mounted on or connected to a robot device.

[0142] Specifically, a non-transient readable storage medium may be provided that stores software for sequentially performing the steps of: identifying spatial characteristics of a space where an object is located and characteristics of a gripping point for an object based on a sensing value of at least one sensor; selecting a gripper tip of a robot arm based on the characteristics of the gripping point of an object, spatial characteristics of the space where an object is located and characteristics of an object; and controlling a robot arm to grip an object using a gripper tip of a type corresponding to the characteristics of the identified object among a plurality of gripper tips.

[0143] A device equipped with such a non-transient readable medium can perform various operations, such as identifying spatial characteristics of the space where the object described in the various embodiments above is located, characteristics of the gripping point, characteristics of the object, robot arm control, and gripper tip selection.

[0144] In non-transitory readable storage media, 'non-transitory' simply means that the storage medium does not contain a signal and is tangible; it does not distinguish whether data is stored semi-permanently or temporarily on the storage medium.

[0145] Alternatively, a program for performing the methods according to the various embodiments described above may be distributed online through an application store. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a storage medium such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0146] Each component (e.g., module or program) according to various embodiments may consist of a singular or multiple entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be further included in various embodiments. Generally or additionally, some components (e.g., module or program) may be integrated into a single entity to perform the same or similar functions as those performed by each of the respective components prior to integration. The operations performed by the module, program, or other components according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations added.

[0147] Although preferred embodiments have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure.

Claims

1. In a robot device, entity; A robot arm connected to the above main body and capable of selectively using multiple gripper tips of different types; At least one sensor; Memory in which at least one instruction is stored; and A processor that operates according to the execution of at least one of the above instructions; comprising, When executed individually or collectively by at least one processor, the robot device, Identifying the characteristics of an object based on the sensing value of at least one sensor, and A robot device that controls the robot arm to grasp the object using a gripper tip of a type corresponding to the identified characteristic among the plurality of gripper tips.

2. In Paragraph 1, The above robot arm is, A rotator comprising a plurality of gripper tips mounted in different directions; When executed individually or collectively by at least one processor, the robot device, A robot device that rotates the rotator so that a type of gripper tip corresponding to the identified characteristic among the plurality of gripper tips is directed toward the object.

3. In Paragraph 1, The above robot arm is, The above plurality of gripper tips include a detachable coupling part; and When executed individually or collectively by at least one processor, the robot device, A robot device that controls the robot arm to attach and detach the plurality of gripper tips to the connection part so that the plurality of gripper tips, of a type corresponding to the identified characteristics, are directed toward the object.

4. In Paragraph 1, The above plurality of gripper tips are, It includes a first gripper tip and a second gripper tip, The contact surface of the second gripper tip is larger than the contact surface of the first gripper tip, and When executed individually or collectively by at least one processor, the robot device, A robot device that controls the robot arm to grip the object using the first gripper tip when the size of the object is less than a preset size range, and to grip the object using the second gripper tip when the size of the object is greater than or equal to the size range.

5. In Paragraph 1, The above plurality of gripper tips are, It includes a first gripper tip and a second gripper tip, The contact surface of the second gripper tip is larger than the contact surface of the first gripper tip, and When executed individually or collectively by at least one processor, the robot device, A robot device that, when at least one object is located around the object in the space where the object is located, identifies the spatial characteristics of the space where the object is located based on the sensing value of the at least one sensor, and selects one gripper tip among the plurality of gripper tips based on the spatial characteristics and the characteristics of the object.

6. In Paragraph 5, The above spatial characteristics include information on at least one of the position of the object within the space, the distance between the object and the object, and the contact relationship between the object and the object. When executed individually or collectively by at least one processor, the robot device, If the object is located at the edge of the space, the object is grasped using the second gripper tip, and If the distance is less than a preset first distance, the object is grasped using the first gripper tip, and if the distance is greater than or equal to the first distance, the object is grasped using the second gripper tip. A robot device that controls the robot arm to grasp the object using the first gripper tip when the object and at least one object are in contact.

7. In Paragraph 1, When executed individually or collectively by at least one processor, the robot device, A robot device that selects one gripper tip from a plurality of gripper tips based on the type of operation to be performed after gripping the object.

8. In Paragraph 1, The above plurality of gripper tips are, It includes a first gripper tip and a second gripper tip, The contact surface of the second gripper tip is larger than the contact surface of the first gripper tip, and When executed individually or collectively by at least one processor, the robot device, If the action to be performed after gripping the object is a lifting action, the object is gripped using the second gripper tip, and If the above operation is a switching operation that changes the direction in which the object is placed, the object is grasped using the first gripper tip, and A robot device that controls the robot arm to grasp the object using the first gripper tip, wherein the above operation is a work operation in which the object is moved within a preset range and a work is performed.

9. In Paragraph 1, The above memory is, A database for multiple types of the above-mentioned gripper tips is stored, and When executed individually or collectively by at least one processor, the robot device, A robot device that selects a gripper tip corresponding to the characteristics of the object from among the plurality of gripper tips based on the above database.

10. In Paragraph 1, The above memory is, An artificial intelligence model trained to select a gripper tip that matches the characteristics of the object among the aforementioned plurality of gripper tips is stored, and When executed individually or collectively by at least one processor, the robot device, A robot device that inputs information regarding the characteristics of the object from the plurality of gripper tips into the artificial intelligence model and selects a gripper tip based on the output value of the artificial intelligence model.

11. A method for controlling a robot device comprising a robot arm capable of selectively using a plurality of gripper tips of different types and at least one sensor, wherein A step of identifying the characteristics of an object based on the sensing value of at least one sensor; and A method for controlling a robot device, comprising the step of controlling the robot arm to grasp the object using a gripper tip of a type corresponding to the identified characteristic among the plurality of gripper tips.

12. In Paragraph 11, The robot arm comprises a rotation module in which a plurality of gripper tips are mounted in different directions. The step of controlling the robot arm is, A method for controlling a robot device, comprising the step of rotating the rotator so that a type of gripper tip corresponding to the identified characteristic among the plurality of gripper tips faces the object.

13. In Paragraph 11, The above plurality of gripper tips includes a first gripper tip and a second gripper tip, and The contact surface of the second gripper tip is larger than the contact surface of the first gripper tip, and The step of controlling the robot arm is, A control method for a robot device comprising the step of: gripping the object using the first gripper tip when the size of the object is less than a preset size range, and gripping the object using the second gripper tip when the size of the object is greater than or equal to the size range.

14. In Paragraph 13, The method further includes the step of identifying spatial characteristics of the space where the object is located based on the sensing value of at least one sensor. The step of controlling the robot arm is, A method for controlling a robot device, comprising the step of selecting one gripper tip from a plurality of gripper tips based on the characteristics of the object.

15. In Paragraph 14, The step of identifying spatial characteristics of the space where the object is located based on the sensing value of at least one sensor is: The method includes the step of identifying the characteristics of a gripping point on the object based on the sensing value of at least one sensor. The step of selecting a gripper tip of the robot arm based on the characteristics of the object above is, A method for controlling a robot device, comprising the step of selecting a gripper tip of the robot arm based on the characteristics of the gripping point, the spatial characteristics, and the characteristics of the object.

Images