Control method of chess robot, control method of robot object grasping

Abstract

The present disclosure relates to a control method for a chess robot, a control method for robot object grasping, and a chess robot. The current chessboard information or current object position arrangement information obtained is not only used for artificial intelligence's move decision-making or ordinary movement decision-making, but also for considering various complex scenarios in real chess movements or real operation spaces. As a result, it is possible to flexibly and autonomously adjust the angle of the robot's manipulator arm when operating a target chess piece or target object according to complex scenarios, and actively avoid touching chess pieces or objects other than the target chess piece or target object to interfere with the chess game or operation space. Based on the current chessboard information or the current object position arrangement information, it is also possible to actively fine-tune the obstructing chess pieces or objects that interfere with the operation, further realizing independent and flexible adaptability.

Description

Technical Field

[0001] The present disclosure relates to the field of robotics, and more particularly, to a control method for a chess robot, a control method for robot object grasping, and a chess machine. Background Art

[0002] In the field of chess robots, traditional robots use vacuum suction cups or electromagnets as grasping devices to grasp chess pieces.

[0003] In technical solutions that use vacuum suction cups as gripping devices, due to the uneven top surfaces of chess pieces used in traditional intellectual activities, such as Chinese chess, international chess, and Go, vacuum suction cups cannot reliably or even completely grasp the target chess piece. Furthermore, the vacuum suction cup can only reliably grasp the chess piece if its edge does not extend beyond the edge of the chess piece's top surface and is preferably aligned with the center of the chess piece's top surface. Furthermore, chess pieces used in traditional intellectual activities are often made of non-ferromagnetic materials such as wood, glass, and plastic. Therefore, in technical solutions that use electromagnets as gripping devices, the chess pieces must be specially customized, for example, using ferromagnetic materials, significantly increasing the cost of intellectual activities. Furthermore, similar to technical solutions that use vacuum suction cups as gripping devices, reliable gripping of chess pieces with uneven top surfaces, such as non-cylindrical chess pieces, is also impossible due to the limited contact area between the surface and the electromagnet. Therefore, technical solutions that use electromagnets require special customization of chess pieces, increasing costs and failing to reliably grasp the target objects in intellectual activities.

[0004] Furthermore, the gripping device in the form of a vacuum suction cup or electromagnet is too mechanical in shape, and is far from the gripping device of a real human player, that is, the shape of the hand, and is unable to truly restore the traditional intellectual sports scene and improve the human-computer experience.

[0005] Therefore, there is a need for a control method for a chess-playing robot that can robustly implement reliable manipulation of a target object, a control method for robot object grasping, and a chess-playing robot. Summary of the Invention

[0006] The present disclosure provides a control method for a chess robot that can robustly and reliably operate on a target object, a control method for robot object grasping, and a chess robot. The control method and the chess robot can precisely and reliably operate on a target object, such as a target chess piece.

[0007] According to the embodiment of the present disclosure, the chess game may be any chess game, for example, Chinese chess, international chess, or Go.

[0008] Corresponding to the corresponding chess game, the target object, such as the target chess piece, can be any corresponding chess piece, such as Chinese chess pieces, international chess pieces, and Go pieces.

[0009] Corresponding to the corresponding chess game, the operation space of the target object can be, for example, any corresponding chess board, such as a Chinese chess board, an international chess board, or a Go board.

[0010] According to an embodiment of the present disclosure, a control method for a chess robot is provided, wherein the chess robot uses a mechanical arm to operate chess pieces, and the control method includes:

[0011] Obtaining current chessboard information, the current chessboard information including the position coordinates of chess pieces on the current chessboard in a world coordinate system; obtaining logical coordinates of a first target chess piece; transforming the logical coordinates of the first target chess piece into physical coordinates in a world coordinate system based on size information of the current chessboard; determining an angle at which the robotic arm operates the first target chess piece on the physical coordinates based on the current chessboard information; and controlling the robotic arm to operate the first target chess piece on the physical coordinates according to the determined angle.

[0012] According to another preferred design solution of the chess robot control method disclosed in the present invention, determining the angle at which the robotic arm operates the first target chess piece on the physical coordinates based on the current chessboard information further includes:

[0013] Performing chess piece detection around the physical coordinates to determine the position coordinates of chess pieces around the physical coordinates; and determining a gripping angle for operating the first target chess piece based on the result of the chess piece detection.

[0014] According to another preferred design solution of the chess robot control method disclosed in the present invention, determining the angle at which the robotic arm operates the first target chess piece on the physical coordinates based on the current chessboard information further includes:

[0015] Taking the physical coordinate as the center, in each of a plurality of given directions, the position of the chess piece closest to the physical coordinate along the given direction is determined; based on the position of the chess piece closest to each of the plurality of given directions, a grasping angle for operating the first target chess piece is determined.

[0016] According to another preferred design scheme of the chess robot control method disclosed in the present invention, the logical coordinates of the target chess piece include the logical placement coordinates of the target chess piece, and the physical coordinates in the world coordinate system include the physical placement coordinates corresponding to the logical placement coordinates.

[0017] According to another preferred design scheme of the chess robot control method disclosed in the present invention, the logical coordinates of the target chess piece also include the logical piece-taking coordinates of the target chess piece, and the physical coordinates in the world coordinate system also include the physical piece-taking coordinates corresponding to the logical piece-taking coordinates.

[0018] According to another preferred design of the chess robot control method disclosed in the present invention, the control method further includes:

[0019] Determining whether there is a chess piece to be replaced on the physical coordinates; wherein controlling the robotic arm to operate the first target chess piece on the physical coordinates according to the determined angle further includes:

[0020] When it is determined that there is a chess piece to be replaced on the physical coordinates, the chess piece to be replaced is used as a second target chess piece, and the robotic arm is controlled to grab the second target chess piece and drop the first target chess piece on the physical coordinates according to the determined grabbing angle.

[0021] According to another preferred design of the chess robot control method disclosed herein, the robotic arm includes a first robotic gripper, wherein controlling the robotic arm to grab the second target chess piece and drop the first target chess piece at the physical coordinate according to the determined grab angle further includes:

[0022] Control the first mechanical gripper to grab the second target chess piece on the physical coordinate according to the determined grabbing angle and move the second target chess piece to a predetermined position; and control the first mechanical gripper to drop the first target chess piece on the physical coordinate according to the determined grabbing angle.

[0023] According to another preferred design scheme of the chess robot control method disclosed in the present invention, the robotic arm includes a first robotic gripper and a second robotic gripper, wherein the second robotic gripper is controlled to grab the second target chess piece on the physical coordinate according to the determined grabbing angle; and the first robotic gripper is controlled to drop the first target chess piece on the physical coordinate according to the determined grabbing angle.

[0024] According to another preferred design of the chess robot control method disclosed in the present invention, the control method further includes:

[0025] Based on the current chessboard information, determine whether the distance between the adjacent chess piece of the physical coordinate and the physical coordinate is less than a predetermined distance threshold; when the distance between the adjacent chess piece of the physical coordinate and the physical coordinate is less than the predetermined distance threshold, control the robotic arm to fine-tune the position of the adjacent chess piece of the physical coordinate, wherein the position fine-tuning is used to adjust the adjacent chess piece to its corresponding expected position.

[0026] According to another preferred design of the chess robot control method disclosed in the present invention, the control method further includes: when the angle of operating the first target chess piece cannot be successfully determined, outputting a prompt message for prompting that the chess piece operation has failed.

[0027] A second aspect of the present disclosure relates to a control method for robot object grasping, wherein the robot uses a mechanical arm to manipulate the object, and the control method comprises:

[0028] Obtain current object position arrangement information, wherein the current object position arrangement information includes the position coordinates of the object in the current operating space in the world coordinate system; obtain the target position of the first target object; based on the current object position arrangement information, determine the grasping angle of the robotic arm to operate the first target object at the target position; and control the robotic arm to operate the first target object at the target position according to the determined grasping angle.

[0029] According to another preferred design of the control method for robot object grasping disclosed herein, determining the grasping angle of the robot arm operating the first target object at the target position based on the current object position arrangement information further includes:

[0030] Object detection is performed around the target position to determine the position coordinates of objects around the target position; and a gripping angle for operating the first target object is determined based on a result of the object detection.

[0031] According to another preferred design of the control method for robot object grasping disclosed herein, determining the grasping angle of the robot arm operating the first target object at the target position based on the current object position arrangement information further includes:

[0032] Taking the target position as the center, in each given direction of multiple given directions, determine the position of the closest object to the target position along the given direction; based on the position of the closest object determined in each given direction of the multiple given directions, determine the grasping angle for operating the first target object.

[0033] A third aspect of the present disclosure relates to a chess robot, wherein the chess robot has:

[0034] A chessboard information acquisition unit is used to obtain current chessboard information, wherein the current chessboard information includes the position coordinates of the chess pieces on the current chessboard in the world coordinate system; a logical coordinate determination unit is used to obtain the logical coordinates of the first target chess piece; a logical coordinate transformation unit is used to transform the logical coordinates of the first target chess piece into physical coordinates in the world coordinate system; an angle determination unit is used to determine the angle at which the robotic arm operates the first target chess piece on the physical coordinates based on the current chessboard information; and an operation control unit is used to control the robotic arm to operate the first target chess piece on the physical coordinates according to the determined grasping angle.

[0035] The fourth aspect of the present disclosure relates to a chess robot, wherein the chess robot has: a visual sensor; a robotic arm; a processor, the processor obtains the logical coordinates of a first target chess piece based on current chessboard information obtained by the visual sensor; and a robotic arm controller, the robotic arm controller transforms the logical coordinates of the first target chess piece into physical coordinates in a world coordinate system according to the size information of the current chessboard, and determines the grasping angle of the robotic arm to operate the first target chess piece on the physical coordinates based on the current chessboard information obtained by the visual sensor, and controls the robotic arm to operate the first target object on the physical coordinates according to the determined grasping angle.

[0036] Embodiments of the present disclosure provide a control method for a chess robot, a control method for robot object grasping, and a chess machine, wherein, when operating a target object, such as a target chess piece, it is possible to determine the angle at which the robotic arm operates the target object at the target position based on current object position arrangement information, such as current chessboard information, so as to achieve flexible, autonomous, accurate, and efficient operation of the target object without affecting the object position arrangement information when there is crowding around the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some exemplary embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0038] Figure 1A A schematic diagram of an application environment of a chess robot according to the present disclosure is shown;

[0039] Figure 1B An embodiment of a chess robot according to the present disclosure is shown;

[0040] Figure 2 A flow chart showing an embodiment of a control method for a chess-playing robot according to the present disclosure is shown;

[0041] Figure 3 A flow chart showing an embodiment of determining an angle for operating a first target chess piece;

[0042] Figure 4 A flow chart showing another embodiment of determining the angle for operating the first target chess piece;

[0043] Figure 5 A flow chart illustrating an embodiment of a method for controlling a robot object grasping according to the present disclosure is shown;

[0044] Figure 6 : shows a flow chart of another embodiment of the control method of the chess robot according to the present disclosure;

[0045] Figure 7 , which shows a flow chart of an implementation method for fine-tuning adjacent chess pieces around a first target chess piece;

[0046] Figure 8 A block diagram of a chess-playing robot according to the present disclosure is shown. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present disclosure more apparent, the following will describe in detail exemplary embodiments of the present disclosure with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0048] In this specification and the drawings, steps and elements having substantially the same or similar features are denoted by the same or similar reference numerals, and repeated description of these steps and elements will be omitted.

[0049] In this specification and the accompanying drawings, elements are described in singular or plural form, depending on the embodiment. However, the singular and plural forms are appropriately selected for the situations presented merely for convenience of explanation and are not intended to limit the present disclosure thereto. Therefore, the singular form may include the plural form, and the plural form may also include the singular form, unless the context clearly indicates otherwise.

[0050] In this specification and the drawings, the terms "first\second" are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0051] Artificial Intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making.

[0052] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0053] Currently, with the advancement of AI technology, research and application are being expanded across a wide range of fields, including smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, autonomous driving, drones, robotics, smart healthcare, and smart customer service. Currently, leveraging AI's perception, reasoning, and decision-making capabilities, AI is being applied to traditional intellectual activities, such as chess, to enrich entertainment and enrich educational content.

[0054] Currently, AI can be combined not only with touchscreen displays but also with robots, particularly robotic arms, to enable, for example, human-machine games. Here, AI is used to make strategic decisions in mind games, while the flexible manipulation capabilities of robots, particularly robotic arms, are leveraged to realistically simulate and replicate the actual maneuvers of a real human opponent in mind games. This approach, compared to touchscreen-based interaction, more realistically replicates traditional mind game scenarios and enhances the human-machine experience.

[0055] As mentioned above, in the technical solution of using a vacuum suction cup as a gripping device, not only does it require additional customization of chess pieces made of ferromagnetic materials, but it also reduces the chess player's chess playing experience. In addition, in actual movement situations, human chess players cannot ensure that the chess pieces are always accurately placed at the target position, such as the cross intersection of the chessboard grid. Therefore, even if the upper surface of the chess piece is flat, it cannot be guaranteed that the vacuum suction cup can always be accurately aligned with the center of the upper surface of the target chess piece. For example, there may be complex scenarios such as chess pieces being crowded together, players placing chess pieces improperly, and chess pieces blocking the way. However, current chess robots do not take such complex scenarios into consideration. Therefore, when the gripping device of current chess robots operates chess pieces, it may touch or even move chess pieces other than the desired piece, thereby causing undesirable changes to the chess surface.

[0056] Figure 1A A schematic diagram of an application environment of a chess robot according to the present disclosure is shown. According to one aspect of the present disclosure, a chess robot 10 is provided. Figure 1A 2 exemplarily shows an embodiment of a chess-like robot 10 according to the present disclosure. Here, the chess-like robot 10 is constructed as a manipulator robot, which has a manipulator gripper 11, a manipulator arm 12, a visual sensor 13, a processor 14 and a manipulator arm controller 15.

[0057] Figure 1A exemplarily shows the target object operated by the chess robot 10. According to an embodiment of the present disclosure, the target object operated is a first target chess piece 17 on the chessboard, which is, for example, a chess piece.

[0058] According to an embodiment of the present disclosure, the operating mechanism for manipulating a target object is constructed as a first mechanical gripper 11. With this first mechanical gripper, anthropomorphic operations such as picking up and dropping a first target chess piece 17 can be performed. Compared to the aforementioned electromagnet and vacuum cup gripping devices, flexible and stable manipulation can also be achieved for chess pieces with non-flat top surfaces, such as chess pieces. This achieves a better human-machine experience in intelligent motion, is applicable to a wide range of chess games, and reduces the cost of customized chess pieces. In a more specific embodiment, a tactile sensor can be arranged inside the mechanical gripper to assess the grasping quality of the target chess piece. Thus, if the grasping quality is poor, a reminder can be issued through human-machine interaction, such as voice output or image output, to inform the player that the robot is currently unable to securely grasp the target chess piece. Furthermore, if the grasping quality is poor, the robot can be controlled, for example, by the mechanical arm controller 15, to repeatedly grasp the target chess piece until the tactile sensor arranged inside the mechanical gripper provides feedback that the mechanical gripper has achieved a secure grasp.

[0059] According to an embodiment of the present disclosure, a visual sensor 13 is fixed to the end of the robotic arm 12 together with the first robotic gripper 11. The visual sensor 13 is constructed as a visual sensor, a tactile sensor, a radar sensor such as a lidar sensor, etc., and is capable of visually sampling the current chessboard during a chess game to obtain current chessboard information 16, which includes the position of each chess piece on the current chessboard in the world coordinate system.

[0060] Furthermore, according to another embodiment of the present disclosure, the chess-like robot may also be constructed as a humanoid robot 10 ′. Figure 1B An embodiment of a humanoid robot 10' according to the present disclosure is shown. According to this embodiment, the visual sensor 13' can be constructed as the eyes of the humanoid robot 10', and the mechanical gripper 11' can be constructed as the hand of the humanoid robot 10'. Because the humanoid robot 10' resembles a real chess player, compared to traditional manipulator-arm or gantry-crane robots, the mechanical feel of chess robots is further reduced, further improving the player's human-machine experience.

[0061] According to an embodiment of the present disclosure, a communication cable is disposed within the robotic arm, used to signal-connect the visual sensor 13 to a processor 14 disposed within the chess robot base, thereby transmitting the current chessboard information 16 to the processor 14. The processor 14 is constructed as a hardware circuit capable of performing AI operations, including but not limited to an FPGA, a DSP, an ARM microcontroller, a CPU, and the like. The chess AI is implemented within the processor 14, and the logical coordinates of the first target chess piece 17 are obtained based on the current chessboard information obtained, for example, by the visual sensor 13. Furthermore, according to an embodiment of the present disclosure, the robotic arm controller 15 is also disposed within the chess robot base and is also constructed as a hardware circuit capable of performing logical operations, including but not limited to an FPGA, a DSP, an ARM microcontroller, a CPU, and the like. According to an embodiment of the present disclosure, the processor 14 and the robotic arm controller 15 can be implemented separately, with the robotic arm controller 15 in signal communication with the processor 14, or they can be integrated as any device capable of performing their respective functions. In the embodiment of the present disclosure, the manipulator controller 15 transforms the logical coordinates of the first target chess piece 17 into physical coordinates in the world coordinate system according to the size information of the current chessboard, and determines the gripping angle of the manipulator to operate the first target chess piece on the physical coordinates based on the current chessboard information 16 obtained by the visual sensor 13, and controls the manipulator to operate the first target chess piece 17 on the physical coordinates according to the determined gripping angle. Figure 2, the specific steps performed by the chess robot 10 in the control method of the chess robot according to the present disclosure are described in more detail.

[0062] According to another aspect of the present disclosure, a control method 200 for a chess-like robot is provided. Figure 2 Detailed description of the invention A flow chart of an embodiment of a method for controlling a chess-like robot according to the present invention is shown in FIG.

[0063] According to an embodiment of the present disclosure, first, in step S210, current chessboard information is obtained. The current chessboard information includes the position coordinates of the chess pieces on the current chessboard in the world coordinate system. For example, the current chessboard information can be obtained from a separate camera, or the chess robot can use a visual sensor to visually capture each chess piece on the current chessboard.

[0064] Then, in step S220, the logical coordinates of the first target chess piece are obtained. For example, the processor 14 may perform an AI operation to determine the first target chess piece 17 to be operated on in the next move, and correspondingly determine the logical coordinates of the first target chess piece 17.

[0065] Then, in step S230, the logical coordinates of the first target chess piece 17 are transformed into physical coordinates in the world coordinate system. For example, the processor 14 can directly transform the logical coordinates of the first target chess piece 17 into physical coordinates in the world coordinate system after obtaining them.

[0066] Then, in step S240, based on the current chessboard information, the angle at which the robotic arm 12 manipulates the first target chess piece 17 on the physical coordinates is determined. For example, the robotic arm controller 15 and / or the processor 14 may be used to determine the angle based on the current chessboard information.

[0067] Then, in step S250, the robot arm is controlled to operate the first target chess piece on the physical coordinate according to the determined angle. For example, the robot arm controller 15 can be used to operate the first target chess piece 17 based on the determined angle.

[0068] Hereinafter, the control method of the chess robot according to the embodiment of the present disclosure will be described in conjunction with chess.

[0069] According to an embodiment of the present disclosure, in step S210 of the control method of the chess robot, first, with the help of the visual sensor 13, each chess piece on the current chessboard is visually collected, and the position information of each chess piece is visually collected, thereby obtaining the current chessboard information. Usually, in the case of chess, the chessboard is divided into 1 to 8 rows and a to h columns, thereby, the position information of a chess piece can be marked as a logical coordinate (for example, e3 indicates that the position of the chess piece on the chessboard is the e-th column and the 3rd row). In addition, since the actual size of the chessboard is different, the position coordinates of the chess piece in the actual world coordinate system on the chessboard can also be collected first (for example, (0.2m, 0.3m), indicating that the actual position coordinates of the chess piece on the chessboard in the actual world coordinate system are 0.2 meters in the horizontal coordinate and 0.3 meters in the vertical coordinate), and then converted into logical coordinates to facilitate the chess AI to perform related operations. Therefore, according to an embodiment of the present disclosure, the current chessboard information includes the logical coordinates of the chess squares where each chess piece on the current chessboard is located. According to another embodiment of the present disclosure, the coordinate positions of each chess piece on the current chessboard in the world coordinate system can also be directly obtained with the help of the visual sensor 13. Thus, the current chessboard information includes the position coordinates of the chess pieces on the current chessboard in the world coordinate system.

[0070] As described above, the current chessboard information 16 is transmitted to the processor 14 via a communication cable arranged inside the robotic arm 12. In step S220, the chess AI running in the processor 14 makes a corresponding judgment on the current chess game based on the current chessboard information. For example, if the chess game has not terminated, the chess AI in the processor 14 generates a set of chess piece placement arrangements and corresponding winning rates. Here, the chess AI selects the chess piece placement arrangement with the highest winning rate in a set of chess piece placement arrangements as the placement arrangement to be executed, and determines the chess piece that needs to be operated to implement this placement arrangement as the first target chess piece 17. Thus, after determining the first target chess piece 17 to be operated, the logical coordinates of the first target chess piece (for example, e3f3) are obtained. In addition, since human players have a certain degree of arbitrariness when playing chess, chess pieces do not always fall accurately into the chess square or at the cross intersection of the chess square. Therefore, in a more specific embodiment, when obtaining the logical coordinates of the first target chess piece, the logical chess piece used in the chess AI operation is also corresponded to the chess piece that is placed or inaccurately in reality through visual positioning, so as to overcome the failure of capturing the target chess piece due to the position deviation of the chess piece in reality.

[0071] As described above, the processor 14 transmits the obtained logical coordinates of the first target chess piece to the robot controller 15. When the robot actually operates the first target chess piece 17, as described above, the actual physical coordinates of the first target chess piece 17 in the world coordinate system must also be known.

[0072] For the sake of clarity, Figure 1A As shown in the world coordinate system {A}, the direction of the normal vector of the chessboard plane is uniformly defined as the z-axis direction of the world coordinate system {A}, the direction parallel to the x-axis of the chessboard is defined as the x-axis direction of the world coordinate system {A}, and the direction parallel to the y-axis of the chessboard is defined as the y-axis direction of the world coordinate system {A}. Thus, in step S230, based on the size information of the current chessboard, a correspondence between the length, width, and length of the current chessboard and the virtual coordinates is established, and the logical coordinates of the first target chess piece are transformed into physical coordinates in the world coordinate system.

[0073] In a more detailed embodiment, for example, when the chess game is Go, where all chess pieces are fixedly placed at other spatial locations at the start of the game and are always taken from other fixed spatial locations during the game, such as always from a chess basket, the logical coordinates of the target chess piece only include the logical drop coordinates of the target chess piece (e.g., f3). Here, the logical drop coordinates need to be converted into physical drop coordinates (e.g., converting f3 to (0.25m, 0.5m)). Therefore, the physical coordinates in the world coordinate system include the physical drop coordinates corresponding to the logical drop coordinates.

[0074] In a more detailed embodiment, for example, when the chess game is international chess, Chinese chess, etc., and all chess pieces are placed on the chessboard at the beginning of the chess game, so there is no subsequent removal of pieces from other fixed spatial positions, such as a chess basket, the logical coordinates of the target chess piece also include the logical removal coordinates of the target chess piece (for example, e3). Here, it is necessary to transform the logical drop coordinates (for example, f3) and the logical removal coordinates (for example, e3) together into physical drop coordinates and physical removal coordinates (for example, transforming e3 into (0.2m, 0.3m) and transforming f3 into (0.25m, 0.5m)). Therefore, the physical coordinates in the world coordinate system also include the physical removal coordinates corresponding to the logical removal coordinates.

[0075] Because the robotic arm 12 is used to manipulate the first target chess piece 17, the fingertip of the robotic gripper 11 needs to be inserted between the first target chess piece and the surrounding chess pieces on the chessboard. Therefore, determining whether there are other chess pieces around the target chess piece to be manipulated, determining which of these other chess pieces is close enough to the target object for the fingertip of the robotic gripper 11 to be positioned, and then rotating the robotic gripper accordingly is essential for achieving stable and reliable manipulation of the chess pieces.

[0076] In addition, if Figure 1AAs shown in the robotic gripper coordinate system {G}, the elbow direction of the robotic gripper 11 is uniformly defined as the zg-axis direction, the direction parallel to the plane where the two clamps of the two-claw robotic gripper 11 are located and perpendicular to the zg-axis is defined as the xg-axis direction, and the direction orthogonal to the above two is defined as the yg-axis direction.

[0077] According to an embodiment of the present disclosure, the angles described below may refer to the angles the robotic gripper rotates around the zg-axis of the robotic gripper coordinate system {G} when the robotic arm is manipulating a target object or chess piece, i.e., when the zg-axis of the robotic gripper coordinate system {G} is parallel to the z-axis of the world coordinate system {A}. However, the present disclosure is not limited thereto, and other angle measurement methods may be employed depending on practical circumstances.

[0078] Accordingly, in step S240, based on the acquired current chessboard information, the actual arrangement of the chess pieces around the physical coordinates of the first target chess piece is obtained, and the angle at which the first mechanical gripper 11 should be rotated around the zg axis is determined.

[0079] According to the embodiment of the present disclosure, by considering the current chessboard information in the actual game scene and determining the angles in sequence for operation, it is possible to effectively prevent the first mechanical gripper 11 from touching or even moving chess pieces that are not intended to be operated near the physical coordinates of the first target chess piece, thereby further improving the stability and reliability of the chess robot. The specific embodiment of determining the angle will be described below in conjunction with Figure 3 and Figure 4 Elaborate in more detail.

[0080] After determining the angle for operating the first target chess piece, in step S250, the robotic arm controller 15 controls the robotic arm 12 to move the first robotic gripper 11 to directly above the first target chess piece based on the previously converted physical coordinates of the first target chess piece, that is, the zg axis of the robotic gripper coordinate system is oriented and parallel to the z axis direction of the world coordinate system, and then rotates the robotic gripper around the zg axis according to the determined angle to complete the operation of the first target chess piece.

[0081] Figure 3 An embodiment of step S240 of determining the angle of operating the first target chess piece is shown. Here, step S240 of method 200 is refined into two sub-steps S241 and S242.

[0082] According to an embodiment of the present disclosure, first, in sub-step S241, chess piece detection is performed around the physical coordinates of the first target chess piece 17 to determine the position coordinates of chess pieces that exist around the physical coordinates. For example, chess piece detection can also be performed around the physical coordinates of the first target chess piece 17 using a separately provided camera to determine whether chess pieces exist around the physical coordinates of the first target chess piece 17, or chess piece detection can also be performed using a visual sensor provided on the chess robot.

[0083] Then, in sub-step S242, based on the results of the chess piece detection, a grasping angle for manipulating the first target chess piece 17 is determined. For example, the angle determination can be performed by the robotic arm controller 15 and / or the processor 14 based on the results of the chess piece detection in sub-step S241. Here, the angle corresponding to the position where no chess piece exists can be determined as the grasping angle for manipulating the first target chess piece, ensuring that the first robotic gripper is operated in the direction corresponding to the position where no chess piece exists around the first target chess piece 17, thereby accurately and efficiently grasping the first target chess piece 17.

[0084] Below, an embodiment of the method for determining the angle for operating the first target chess piece S240 will be described with a flowchart in conjunction with chess:

[0085] In sub-step S241, the physical coordinates of the first target chess piece are first detected to determine whether there are chess pieces located around the physical coordinates. For example, the eight positions around the physical coordinates of the target chess piece may be detected: left, right, top, bottom, diagonally to the upper right, and diagonally to the upper left. This is to determine whether there are chess pieces located at the eight positions around the physical coordinates of the target chess piece.

[0086] In sub-step S242 (see the dotted-line box), based on the results of the aforementioned piece detection, a grasping angle for manipulating the first target piece is determined. Specifically, based on the results of the aforementioned piece detection, a determination is made as to the corresponding angle to which the robotic gripper should be rotated in order to stably and reliably manipulate the first target piece without contacting other surrounding pieces. In the disclosed embodiment, this angle determination is performed by the robotic arm controller 15.

[0087] For example, if there is no chess piece at the placement position on the left, the angle can be determined to be 0° accordingly; if there is no chess piece at the placement position on the upper direction, the angle can be determined to be 90° accordingly; if there is no chess piece at the placement position on the upper left, the angle can be determined to be 45° accordingly; if there is no chess piece at the placement position on the upper right, the angle can be determined to be -45° accordingly.

[0088] If there is no position for the fingertip of the mechanical gripper 11 in any of the four directions, the mechanical gripper is rotated 180° and the above test is repeated. For example, if after rotating 180°, it is detected that: if there is no chess piece at the right position, the angle can be determined to be 0°; if there is no chess piece at the lower position, the angle can be determined to be 90°; if there is no chess piece at the lower right position, the angle can be determined to be 45°; if there is no chess piece at the lower left position, the angle can be determined to be -45°.

[0089] Thus, by rotating the first mechanical gripper 11 in the direction of the unplaced chess piece placement positions around the first target chess piece, it is possible to ensure that the fingertips of the first mechanical gripper 11 are placed in the direction of the unplaced chess piece placement positions around the first target chess piece. Since no chess pieces are placed in this direction, there is sufficient space for the fingertips of the first mechanical gripper 11 to be placed, thus effectively preventing the fingertips of the first mechanical gripper 11 from touching or even moving surrounding chess pieces, further improving the stability and reliability of the chess robot.

[0090] In a more detailed embodiment, if no placement position exists in all directions, i.e., if the move cannot be made in all directions, step S240 of determining the angle at which the first target chess piece is to be manipulated may further include an optional sub-step S243 (see the sub-steps indicated by the dashed box). In sub-step S243, the chess piece is placed in mid-air, and a prompt indicating the failure of the chess piece manipulation is output through corresponding human-computer interaction, such as voice output or image output, to remind the player to adjust the chess piece. Furthermore, the manipulated target chess piece may be placed in mid-air, waiting for the player to adjust it. This further prevents undesired movement of chess pieces near the physical coordinates, improving the precision of the manipulation.

[0091] Figure 4 Another embodiment of step S240 of determining the angle for manipulating the first target chess piece is shown. Here, step S240 of method 200 is refined into two sub-steps S241 ′ and S242 ′.

[0092] According to an embodiment of the present disclosure, first, in sub-step S241', with the physical coordinates as the center, the position of the chess piece closest to the physical coordinates along each of a plurality of given directions is determined. For example, the position of the chess piece closest to the physical coordinates along the given direction can also be determined using a separately provided camera, thereby separately recording the position of each chess piece closest to the physical coordinates in each given direction.

[0093] Then, in sub-step S242', based on the position of the closest chess piece determined in each of the multiple given directions, a grasping angle for manipulating the first target chess piece 17 is determined. For example, the angle corresponding to the position of the chess piece closest to the physical coordinates and farthest from the physical coordinates can be determined as the grasping angle for manipulating the first target chess piece 17. In this way, due to the farthest distance, sufficient operating space is ensured for the first mechanical gripper.

[0094] Next, another embodiment of the method for determining the angle for operating the first target chess piece S240 will be described with a flowchart in conjunction with chess:

[0095] In sub-step S241', first, with the physical coordinates as the center, the position of the chess piece closest to the physical coordinates along each of a plurality of given directions is determined. In a more detailed embodiment, for example, a specific judgment area can be defined with the physical coordinates as the center and a predetermined radius, and the positions of each chess piece closest to the physical coordinates within the judgment area are determined.

[0096] In sub-step S242', based on the position of the closest chess piece determined in each of the multiple given directions, a grasping angle for operating the first target chess piece is determined. For example, the corresponding angle in the given direction where the position of the farthest closest chess piece is located can be determined as the grasping angle for operating the first target chess piece. For another example, the closest chess piece in each given direction whose position is greater than a predetermined distance from the position of the first target chess piece can be determined, and the corresponding angle in the given direction where one of the determined closest chess pieces is located is determined as the grasping angle for operating the first target chess piece. In an embodiment of the present disclosure, the above-mentioned determination of the grasping angle is performed by the robotic arm controller 15.

[0097] In the above-mentioned more detailed embodiment, for example, the chess piece that is farthest from the physical coordinates among the chess pieces closest to the physical coordinates can be determined, and the corresponding angle of the position of the determined chess piece can be determined as the gripping angle for operating the first target chess piece. Thus, by rotating the mechanical gripper 11 to the direction of the position of the farthest closest chess piece, it can be ensured that the fingertip of the mechanical gripper 11 is always placed between the physical coordinates and the farthest closest chess piece. Due to the farthest distance, it is ensured that there is enough space between the first target chess piece and the chess pieces near it to place the mechanical gripper 11, so it can also effectively prevent the fingertips of the mechanical gripper 11 from touching or even moving the surrounding chess pieces, further improving the stability and reliability of the chess robot.

[0098] like Figure 3In the embodiment shown in , if there is no placement position in all directions, that is, no placement is possible in all directions, then Figure 4 Another embodiment of step S240 of determining the angle of the first target chess piece to be manipulated can also include an optional sub-step S243 (see the sub-step indicated by the dashed box). In sub-step S243, the chess piece is placed in mid-air, and a prompt indicating a failed chess piece manipulation is output through corresponding human-computer interaction, such as voice output or image output, to remind the player to adjust the chess piece. In addition, the manipulated target chess piece can be placed in mid-air to wait for the player to adjust it. This further avoids undesirable movement of chess pieces near the physical coordinates, improving the precision of the operation.

[0099] Although the embodiments of the present disclosure use chess and other chess games as the operation objects, the inventive concept of the control method of determining the optimal grasping angle of the mechanical gripper according to the direction leaving enough space according to the embodiments of the present disclosure is also applicable to fields other than chess games, such as logistics, automated assembly lines, etc., which need to consider the actual arrangement of objects and grasp the target object from dense objects without touching other objects as much as possible.

[0100] Therefore, according to another aspect of the present disclosure, a control method 500 for robot object grasping is provided. Figure 5 Detailed description of the invention A flow chart of an embodiment of a method for controlling a robot object grasping according to the present invention is shown in FIG.

[0101] According to the illustrated embodiment, first, in step S510, the current object position arrangement information is acquired using a sensor. Here, the current object position arrangement information includes the position coordinates of the objects in the current operating space in the world coordinate system. The sensor transmits the current object position arrangement information to a coordinate determination unit. In step S520, the coordinate determination unit determines the target object to be operated on and its target position. Similarly, it is then necessary to determine in which direction sufficient space is left for lowering the robotic gripper.

[0102] Therefore, in step S530, based on the acquired current object position arrangement information, the actual arrangement of the adjacent objects around the target position of the first target object is obtained, and the angle at which the mechanical gripper should be rotated around the Z-axis is determined. According to the embodiments of the present disclosure, the mechanical gripper 11 can be effectively prevented from contacting or even moving undesirable objects near the target position of the first target object, further improving the stability and reliability of the robot's object grasping.

[0103] After determining the grasping angle for operating the first target object, in step S540, the robotic arm controller controls the robotic arm to move the robotic gripper to directly above the first target object based on the target position of the first target object previously converted, and then rotates the robotic gripper around the Z axis according to the determined angle to complete the grasping operation of the first target object.

[0104] Here, just Figure 3 and Figure 4 The chess pieces in the embodiment shown are objects in a broad sense, and can also be represented by Figure 3 and Figure 4 The specific implementation shown in FIG5 is used to implement the determination of the gripping angle of the first target object in step S530. Therefore, for the sake of brevity, the more specific implementation of step S530 will not be further described. The more specific implementation of step S530 can be found in FIG5. Figure 3 as well as Figure 4 Corresponding description of the embodiment shown in .

[0105] Figure 6 , a flowchart of another embodiment of the control method of a chess robot according to the present disclosure is shown. Here, the control method of the chess robot further includes a step S230' of determining whether there is a chess piece to be replaced at the physical coordinate. In the embodiment of the present disclosure, the manipulator controller 15 controls the manipulator to operate the first target chess piece at the physical coordinate according to the determined angle, further including: when it is determined that there is a chess piece to be replaced at the physical coordinate, in step S250, the chess piece to be replaced is used as the second target chess piece, and the manipulator is controlled to grab the second target chess piece and drop the first target chess piece at the physical coordinate according to the determined grab angle.

[0106] Next, combine Figure 6 The flowchart shown in further describes the control method of the chess robot according to an embodiment of the present disclosure.

[0107] After step S230 of transforming the logical coordinates of the first target chess piece into physical coordinates in the world coordinate system, the control method for the chess robot may further, preferably in an additional step S230', determine whether a chess piece to be replaced exists at the physical coordinates. For example, the current chessboard information acquired in step S210 may be used to determine whether a chess piece to be replaced exists at the physical coordinates, particularly at the physical drop coordinates. This allows for determining the type of operation to be performed.

[0108] According to an embodiment of the present disclosure, when there is no chess piece to be replaced at the physical chess coordinate, it is determined that the type of operation to be performed in step S250 is to move the first target chess piece to the physical chess coordinate.

[0109] For example, in Chinese chess or international chess, this means that the robot arm 12 only needs to be controlled to perform the so-called "take" operation at the physical take coordinates and the so-called "place" operation at the physical place coordinates, without having to perform the "capture" operation. In other words, the operation type can be a "move" operation.

[0110] Correspondingly, in step S250, when the result of the sub-step S251 of determining the operation type is "move", for example, the robotic arm controller 15 controls the robotic arm 12 to operate the first target chess piece according to the previously determined angle, which further includes performing the following sub-movements in the corresponding sub-step S252 of step S250:

[0111] - According to the physical sub-coordinate, move the first mechanical gripper 11 to the physical sub-coordinate;

[0112] - Open the first mechanical gripper 11;

[0113] - Rotate the mechanical gripper according to the determined physical grabbing angle at the chessboard coordinates and lower the mechanical gripper to the height of the chessboard;

[0114] - closing the mechanical gripper to grab the first target chess piece;

[0115] - Raising the first mechanical gripper 11 and moving it to the physical chessboard coordinates according to the physical chessboard coordinates, rotating the first mechanical gripper according to the determined gripping angle at the physical chessboard coordinates, and lowering the first mechanical gripper 11 again to the height of the chessboard;

[0116] - opening the first mechanical gripper 11 to release the first target chess piece;

[0117] - Raise the first robotic gripper 11 and move the first robotic gripper 11 back to its initial position.

[0118] According to an embodiment of the present disclosure, when there is a chess piece to be replaced on the physical coordinates, it means that the robot not only needs to operate the first target chess piece, but also needs to move the second target chess piece on the physical coordinates out of the chessboard to achieve the "eating" operation in Chinese chess and international chess. Therefore, correspondingly, in the step S250, when it is determined that there is a chess piece to be replaced on the physical coordinates, the chess piece to be replaced is used as the second target chess piece, and the manipulator is controlled to grab the second target chess piece and drop the first target chess piece on the physical coordinates according to the determined grasping angle. For example, the manipulator controller 15 controls the manipulator 12 to operate the first target chess piece according to the previously determined angle, which further includes executing the following sub-movements in the corresponding sub-step S253:

[0119] - According to the physical drop coordinates, move the first mechanical gripper 11 to the physical drop coordinates;

[0120] - Open the first mechanical gripper 11;

[0121] - rotating the mechanical gripper according to the determined gripping angle when taking the piece, and lowering the first mechanical gripper to the height of the chessboard;

[0122] - closing the first mechanical gripper to grab the second target chess piece;

[0123] - Raise the first mechanical gripper 11 and place it at a fixed position outside the chessboard, such as a special position for placing captured pieces, and open the first mechanical gripper 11 to remove the captured pieces;

[0124] - According to the physical sub-coordinate, move the first mechanical gripper 11 to the physical sub-coordinate;

[0125] - Open the first mechanical gripper 11;

[0126] - rotating the first mechanical gripper according to the determined grasping angle at the physical chessboard coordinate, and lowering the first mechanical gripper to the height of the chessboard;

[0127] - closing the first mechanical gripper to grab the first target chess piece;

[0128] - Raising the first mechanical gripper 11 and moving it to the physical chessboard coordinates according to the physical chessboard coordinates, rotating the first mechanical gripper according to the determined gripping angle at the physical chessboard coordinates, and lowering the first mechanical gripper 11 again to the height of the chessboard;

[0129] - opening the first mechanical gripper 11 to release the first target chess piece;

[0130] - Raise the first robotic gripper 11 and move the first robotic gripper 11 back to its initial position.

[0131] Thus, according to the embodiment of the present disclosure, whether performing the so-called "movement" or "capture" operation on the first target chess piece, that is, in the so-called "taking piece" and "dropping piece" processes in sub-steps S252 and S253, the current chessboard information is taken into account and the first target chess piece or the second target chess piece is grasped and placed at the corresponding angle. As a result, in each possible contact process with the target chess piece, it is ensured that there is enough space to place the mechanical gripper 11, that is, in each movement, the fingertips of the first mechanical gripper 11 are effectively prevented from touching or even moving the surrounding chess pieces, further improving the stability and reliability of the chess robot.

[0132] Furthermore, according to a more specific embodiment of the present disclosure, a pair of mechanical grippers can be simultaneously constructed at the execution end of the chess robot, that is, the mechanical arm can include a first mechanical gripper and a second mechanical gripper. When executing sub-step S252 corresponding to moving the first target chess piece to the physical drop coordinate, only one of the two mechanical grippers needs to be used to perform the previously described sub-movement. However, when executing sub-step S253 corresponding to the so-called "capture piece", the first mechanical gripper and the second mechanical gripper can be controlled to perform the following sub-movements:

[0133] - according to the physical sub-coordinates, moving the first mechanical gripper and the second mechanical gripper to the physical sub-coordinates;

[0134] - Open the first mechanical gripper;

[0135] - rotating the first mechanical gripper according to the determined grasping angle at the physical chessboard coordinate, and lowering the first mechanical gripper to the height of the chessboard;

[0136] - closing the first mechanical gripper to grab the first target chess piece;

[0137] - Raise the first mechanical gripper, and according to the physical drop coordinates, move the first mechanical gripper and the second mechanical gripper to the physical drop coordinates;

[0138] - Open the second gripper;

[0139] - Rotating the second mechanical gripper according to the determined grasping angle at the physical coordinate of the chess piece, and lowering the second mechanical gripper to the height of the chessboard;

[0140] - closing the second mechanical gripper to grab the captured second target chess piece;

[0141] - rotating the first mechanical gripper according to the determined grasping angle at the physical coordinate of the chess piece, and lowering the first mechanical gripper to the height of the chessboard;

[0142] - opening the first mechanical gripper to release the first target chess piece;

[0143] - Raise the first and second mechanical grippers and move them back to their initial positions.

[0144] It can be seen that according to the embodiment of the present disclosure, not only is the angle at which the first and second mechanical grippers are rotated to complete the operation considered in each so-called "taking the piece" and "dropping the piece" process in sub-steps S252 and S253, but it can also truly simulate the human hand to achieve a single-handed single piece exchange, further improving the efficiency of the robot's chess playing and improving the human-computer experience.

[0145] Furthermore, as mentioned above, due to the arbitrariness of human chess players when placing chess pieces, each piece they place may have a positional deviation from its target position. Consequently, the positional deviation of the pieces around the physical coordinates may block the robot from operating the target piece. Therefore, in another more detailed embodiment of the present disclosure, the control method for a chess robot further includes fine-tuning the chess pieces. Specifically, in sub-step S251 of step S250 for determining the operation type, the placement of adjacent pieces around the physical coordinates of the first target piece may be considered to determine whether fine-tuning of the adjacent pieces with positional deviations is necessary: based on the current chessboard information, determining whether the distance between the adjacent pieces at the physical coordinates and the physical coordinates is less than a predetermined distance threshold; if the distance between the adjacent pieces at the physical coordinates and the physical coordinates is less than the predetermined distance threshold, controlling the robotic arm to fine-tune the position of the adjacent pieces at the physical coordinates, wherein the fine-tuning is used to adjust the adjacent pieces to their corresponding intended positions. Correspondingly, if fine-tuning is determined to be necessary, a corresponding sub-step S254 is executed to fine-tune the obstructing adjacent pieces to their intended positions.

[0146] Next, combine Figure 7 An implementation of the control method of the chess robot according to the embodiment of the present disclosure is further described:

[0147] Figure 7 A flowchart of one embodiment of sub-step S251 is shown in detail in FIG. For completeness, all sub-steps S251 to S254 of step S250 are shown here. The discussion of the "capture" and "move" operation types has been discussed above and will not be repeated here. Here, we will focus on sub-steps S2531 and S2532 of sub-step S251 related to "fine-tuning," as well as sub-step S254.

[0148] In a more detailed embodiment, in sub-step S2531 of sub-step S251, a predetermined distance threshold between the adjacent chess pieces and the physical coordinate can be pre-determined. For example, the visual sensor 13 can obtain the distance between the adjacent chess pieces around the physical coordinate and the physical coordinate based on the current chessboard information. In sub-step S2532, for example, the robotic arm controller 15 can be used to determine whether the distance between the adjacent chess pieces at the physical coordinate and the physical coordinate is less than the predetermined distance threshold. If the distance between one or more of the adjacent chess pieces at the physical coordinate and the physical coordinate is less than the predetermined distance threshold, for example, if the minimum distance between the edge of the adjacent chess piece and the physical coordinate is less than the radius of the target chess piece, this indicates that the adjacent chess piece is likely to block the operation on the target chess piece. Therefore, it is determined that fine-tuning is required for one or more of the adjacent chess pieces at the physical coordinate whose distance is less than the predetermined distance threshold. Accordingly, in sub-step S254, the robotic arm controller 15 can be used to control the robotic arm 12 to fine-tune the position of the adjacent chess piece at the physical coordinate and adjust it to its corresponding desired position. In the embodiment of the present disclosure, the position of the nearest square to the adjacent piece requiring fine-tuning, on which no piece exists, is determined as the corresponding expected position. Furthermore, when performing fine-tuning, the gripping angle at the adjacent piece requiring fine-tuning and the gripping angle at the expected position are also considered to interfere with the chess game. In a more specific embodiment, in sub-step S254, the first mechanical gripper may be controlled to perform the following sub-movements:

[0149] - according to the physical coordinates, moving the first mechanical gripper to an adjacent chess piece of the physical coordinates that need to be fine-tuned;

[0150] - Open the first mechanical gripper;

[0151] -Determine the grab angles at adjacent pieces that need fine-tuning;

[0152] - Rotate the first mechanical gripper according to the gripping angle of the adjacent chess piece and lower the first mechanical gripper to the height of the chessboard;

[0153] - closing the first mechanical gripper to grasp the adjacent chess piece;

[0154] - raising the first mechanical gripper and moving the first mechanical gripper to the expected position closest to the adjacent chess piece, for example, the closest chess square;

[0155] - Determine the grip angle at the closest expected position;

[0156] - rotating the first mechanical gripper according to the determined gripping angle at the closest expected position, and lowering the first mechanical gripper again to the height of the chessboard;

[0157] - opening the first mechanical gripper to release the adjacent chess piece;

[0158] - Raise the first robotic gripper and move the first robotic gripper back to its initial position.

[0159] According to the embodiment of the present disclosure, Figure 3 and Figure 4 The specific implementation method of determining the grabbing angle at the physical coordinate shown in , realizes the determination of the grabbing angle at the adjacent chess piece that needs fine-tuning and the closest expected position in sub-step S254.

[0160] Therefore, by actively fine-tuning the adjacent chess pieces that cause obstructions around the target chess piece, the chess robot can fine-tune the adjacent objects to their corresponding expected positions, actively correct the influence of improper placement, and eliminate the obstacles when arranging the object positions. This allows the chess robot to not only consider various complex scenes in chess games, but also independently and autonomously correct adverse factors in complex scenes, such as improper placement of chess pieces, further improving the stability and reliability of the chess robot and further realizing fine and accurate operation of the target object.

[0161] Figure 8 The control device of the chess robot according to the present disclosure is shown again in a block diagram. Figure 8 In the illustrated embodiment, the control device of the chess robot includes a chessboard information acquisition unit 810. In the embodiments of the present disclosure, the chessboard information acquisition unit 810 can be implemented as a communication module or an information reading module, which obtains current chessboard information from an external visual sensor, such as a camera, or reads the current chessboard information from a memory.

[0162] The control device of the chess robot also includes a logical coordinate determination unit 820. This unit generates a set of chess piece placement arrangements and corresponding win rates based on the current chess board information provided by the chess board information acquisition unit 810 and with the help of the chess AI. The chess AI then selects the chess piece placement arrangement with the highest win rate from the set of chess piece placement arrangements as the placement arrangement to be executed, identifies the chess piece required to implement this placement arrangement as the first target piece, and obtains the logical coordinates of the first target piece.

[0163] The control device of the chess robot also has a logical coordinate transformation unit 830, which transforms the logical coordinates of the first target chess piece into physical coordinates in the world coordinate system based on the actual size of the chessboard in the world coordinate system, so as to facilitate corresponding operations on the first target chess piece in the world coordinate system.

[0164] The control device of the chess robot further comprises an angle determination unit 840, which determines the angle at which the manipulator operates the first target chess piece on the physical coordinates based on the current chessboard information. Figure 3 and Figure 4 The embodiment shown in FIG. 1 determines the angle of operating the first target chess piece. The method used to determine the angle is shown in FIG. Figure 3 and Figure 4 , I will not go into details here.

[0165] In addition, the control device of the chess robot further includes an operation control unit 850, which is configured to control the robotic arm to operate the first target chess piece on the physical coordinates according to the determined angle. Here, the operation control unit divides the desired movement into sub-movements of the various moving parts of the chess robot, such as the robotic arm and the robotic gripper, and performs the corresponding movement through each moving part to complete the desired operation. Here, the operation control unit 850 can also control each moving part to complete Figure 6 and Figure 7 For details on the "fine-tuning" operation described in Figure 6 and Figure 7 The corresponding description is not repeated here.

[0166] The control device of the chess robot provided based on the embodiment of the present disclosure is capable of obtaining current chessboard information. Here, the current chessboard information obtained is not only used for chess AI's decision-making on chess moves, but also for considering various complex scenarios in real chess games. Thus, it is possible to flexibly and autonomously adjust the angle of the chess robot's mechanical arm when operating the target chess piece according to various complex scenarios, and actively avoid touching chess pieces other than the target chess piece to interfere with the chess game. And based on the current chessboard information, it is also possible to actively correct the obstructing chess pieces that interfere with the operation, further realizing independent and flexible adaptability. And preferably, a pair of mechanical grippers are used to realize the operation of the target chess piece, which has good anthropomorphism and can realize a single-handed single-time change of pieces, and does not require customization of the chessboard or chess pieces, while improving the human-computer experience and flexible operation, reducing the cost of customization.

[0167] In addition, an embodiment of the present disclosure further provides a computer software product, which includes program code, and when the program code is executed, it can execute the control method according to the embodiment of the present disclosure.

[0168] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will appreciate that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A control method for a chess robot, wherein: The chess robot uses a mechanical arm to operate chess pieces, and the control method includes: Obtaining current chessboard information, wherein the current chessboard information includes the position coordinates of the chess pieces on the current chessboard in the world coordinate system; Get the logical coordinates of the first target chess piece; According to the size information of the current chessboard, the logical coordinates of the first target chess piece are transformed into physical coordinates in the world coordinate system; Based on the current chessboard information, determining an angle at which the robotic arm operates the first target chess piece on the physical coordinates; and controlling the robotic arm to manipulate the first target chess piece on the physical coordinates according to the determined angle, Wherein, based on the current chessboard information, determining the angle at which the robotic arm operates the first target chess piece on the physical coordinate further includes: Performing chess piece detection around the physical coordinates to determine the position coordinates of chess pieces around the physical coordinates; and Based on the result of the chess piece detection, a grasping angle for operating the first target chess piece is determined.

2. The method according to claim 1, wherein Determining, based on the current chessboard information, an angle at which the robotic arm operates the first target chess piece on the physical coordinates, further includes: Taking the physical coordinate as the center, in each of a plurality of given directions, determine the position of the chess piece closest to the physical coordinate along the given direction; Based on the position of the closest chess piece determined in each of the multiple given directions, a grasping angle for operating the first target chess piece is determined.

3. The control method according to claim 1, wherein: The logical coordinates of the target chess piece include the logical placement coordinates of the target chess piece, and the physical coordinates in the world coordinate system include the physical placement coordinates corresponding to the logical placement coordinates.

4. The control method according to claim 1, wherein: The logical coordinates of the target chess piece also include the logical piece-taking coordinates of the target chess piece, and the physical coordinates in the world coordinate system also include the physical piece-taking coordinates corresponding to the logical piece-taking coordinates.

5. The control method according to any one of claims 1 to 3, further comprising: Determining whether there is a chess piece to be replaced at the physical coordinates; Wherein, controlling the robotic arm to manipulate the first target chess piece on the physical coordinate according to the determined angle further comprises: When it is determined that there is a chess piece to be replaced on the physical coordinates, the chess piece to be replaced is used as a second target chess piece, and the robotic arm is controlled to grab the second target chess piece and drop the first target chess piece on the physical coordinates according to the determined grabbing angle.

6. The control method according to claim 5, wherein: The robotic arm comprises a first robotic gripper, Wherein, controlling the robotic arm to grab the second target chess piece and drop the first target chess piece on the physical coordinate according to the determined grab angle further includes: controlling the first mechanical gripper to grasp the second target chess piece at the physical coordinate according to the determined grasping angle, and moving the second target chess piece to a predetermined position; and The first mechanical gripper is controlled to drop the first target chess piece on the physical coordinate according to the determined gripping angle.

7. The control method according to claim 5, wherein: The robotic arm includes a first robotic gripper and a second robotic gripper, The second mechanical gripper is controlled to pick up the second target chess piece at the physical coordinate according to the determined gripping angle; and the first mechanical gripper is controlled to drop the first target chess piece at the physical coordinate according to the determined gripping angle.

8. The control method according to claim 5, further comprising: Based on the current chessboard information, determining whether a distance between an adjacent chess piece at the physical coordinate and the physical coordinate is less than a predetermined distance threshold; When the distance between the adjacent chess piece of the physical coordinate and the physical coordinate is less than the predetermined distance threshold, the robotic arm is controlled to fine-tune the position of the adjacent chess piece of the physical coordinate, wherein the position fine-tuning is used to adjust the adjacent chess piece to its corresponding expected position.

9. The control method according to any one of claims 1 to 2, further comprising: In the case that the angle for operating the first target chess piece cannot be successfully determined, a prompt message for prompting that the chess piece operation has failed is output.

10. A control method for robot object grasping, wherein: The robot uses a mechanical arm to operate an object, and the control method includes: Acquire current object position arrangement information, where the current object position arrangement information includes position coordinates of objects in the current operation space in a world coordinate system; Obtaining a target position of a first target object; determining, based on the current object position arrangement information, a gripping angle of the robotic arm operating the first target object at the target position; and controlling the robotic arm to manipulate the first target object at the target position according to the determined grasping angle, Wherein, based on the current object position arrangement information, determining the grasping angle of the robotic arm operating the first target object at the target position further includes: Performing object detection around the target location to determine the position coordinates of objects around the target location; and Based on a result of the object detection, a grasping angle for operating the first target object is determined.

11. The method according to claim 10, wherein: Determining a grasping angle of the robotic arm operating the first target object at the target position based on the current object position arrangement information further includes: Taking the target position as the center, in each of a plurality of given directions, determine a position of an object closest to the target position along the given direction; A grasping angle for operating the first target object is determined based on a position of a closest object determined in each of the plurality of given directions.

12. A control device for a chess robot, comprising: A chessboard information acquisition unit, configured to acquire current chessboard information, wherein the current chessboard information includes the position coordinates of chess pieces on the current chessboard in a world coordinate system; A logical coordinate determination unit, configured to obtain the logical coordinates of the first target chess piece; A logical coordinate transformation unit, configured to transform the logical coordinates of the first target chess piece into physical coordinates in a world coordinate system; an angle determining unit, configured to determine an angle at which the robotic arm operates the first target chess piece on the physical coordinates based on the current chessboard information; as well as an operation control unit, configured to control the robotic arm to operate the first target chess piece on the physical coordinate according to the determined angle, Wherein, based on the current chessboard information, determining the angle at which the robotic arm operates the first target chess piece on the physical coordinate further includes: Performing chess piece detection around the physical coordinates to determine the position coordinates of chess pieces around the physical coordinates; and Based on the result of the chess piece detection, a grasping angle for operating the first target chess piece is determined.

13. A chess robot, wherein: The chess robot has: Vision sensors; robotic arm; a processor, wherein the processor obtains the logical coordinates of the first target chess piece based on the current chessboard information obtained by the visual sensor; as well as a robotic arm controller, the robotic arm controller transforming the logical coordinates of the first target chess piece into physical coordinates in a world coordinate system based on the size information of the current chessboard, and determining a gripping angle at which the robotic arm operates the first target chess piece on the physical coordinates based on the current chessboard information acquired by the visual sensor, and controlling the robotic arm to operate the first target chess piece on the physical coordinates according to the determined gripping angle. Wherein, based on the current chessboard information obtained by the visual sensor, determining the angle at which the robotic arm operates the first target chess piece on the physical coordinates further includes: Performing chess piece detection around the physical coordinates to determine the position coordinates of chess pieces around the physical coordinates; and Based on the result of the chess piece detection, a grasping angle for operating the first target chess piece is determined.

Images