WO2023178920A1

WO2023178920A1 - Chess placement method and apparatus, electronic device, chess playing robot, storage medium, and program

Info

Publication number: WO2023178920A1
Application number: PCT/CN2022/114913
Authority: WO
Inventors: 吴华栋; 张展鹏; 杨帆; 贾凡; 成慧
Original assignee: 上海商汤智能科技有限公司
Priority date: 2022-03-23
Filing date: 2022-08-25
Publication date: 2023-09-28
Also published as: CN114734456A

Abstract

A chess placement method and apparatus, an electronic device, a chess playing robot, a computer storage medium, and a computer program. The chess placement method comprises: controlling an image acquisition device to acquire a first image, the first image representing an image of a chessboard and each chess piece; in response to the existence of a blocking area in a chessboard image area in the first image, determining a first area in the area other than the blocking area in the chessboard image area; in response a chess piece corresponding to at least one correct placement position is not placed in the at least one correct placement position in the first area, generating a chess placement instruction according to the at least one correct placement position and the actual position of at least one chess piece in the first image, the correct placement position representing a chess piece placement position determined according to a chess piece placement rule; and controlling an executor of a chess playing robot to execute the chess placement instruction.

Description

Chess playing method, device, electronic equipment, game robot, storage medium and program

Cross-references to related applications

This application is based on a Chinese patent application with application number 202210293846.3 and a filing date of March 23, 2022, titled "Chess placing method, device, electronic equipment, game robot and storage medium", and requires priority for this Chinese patent application The entire content of this Chinese patent application is hereby incorporated into this application as a reference.

Technical field

The present disclosure relates to, but is not limited to, the field of intelligent device control, and in particular, to a chess playing method, device, electronic device, chess-playing robot, computer storage medium, and computer program.

Background technique

In related technologies, game robots can be used to realize normal games of Go, chess, chess and other chess events; the human-computer interaction chess placement algorithm is an important part of the game robot software, and its core work is to be in the game before the game starts. The pieces on the chess board are arranged in preparation for a standard opening or endgame game.

Contents of the invention

The embodiments of the present disclosure at least provide a chess playing method, device, electronic device, chess robot, computer storage medium and computer program.

The embodiment of the present disclosure provides a method of playing chess, which may include:

Control the image acquisition device to collect a first image, the first image represents the image of the chessboard and each chess piece; in response to the occlusion area in the chessboard image area in the first image, in the chessboard image area except the occlusion area In the area, a first area is determined; in response to the at least one correct placement position in the first area not placing a chess piece corresponding to the at least one correct placement position, according to the at least one correct placement position and the first The actual position of at least one chess piece in the image is used to generate a chess placement instruction; the correct placement position represents the placement position of the chess piece determined according to the chess piece placement rules; the actuator of the chess robot is controlled to execute the chess placement instruction.

In some embodiments, determining the first area in the area of the checkerboard image area except the occlusion area includes: selecting the first area in the area of the chessboard image area except the occlusion area. A partial area is used as the first area; wherein the distance between each pixel point in the first area and the boundary of the occlusion area is greater than a first distance threshold, and each pixel point in the first area is connected to each already-occluded area. The distance of the placed chess pieces is greater than the second distance threshold.

It can be understood that in the embodiment of the present disclosure, a partial area can be selected as the third chessboard image area in the area other than the occlusion area based on the distance to the boundary of the occlusion area and the distance to each placed chess piece. One area; and, the chess placement process is determined based on the correct placement of the first area. Therefore, the impact of the occlusion area and each placed chess piece in the chessboard image area on the chess placement process can be effectively reduced. The chess placement process can be In the process, it effectively copes with the obstruction of the chessboard and chess pieces by various objects such as human arms and robotic arms.

In some embodiments, after controlling the actuator and executing the chess placement instruction, the method further includes: re-executing the control of the image acquisition device to collect the first image, determining the first area, and generating the chess placement. instructions, and the step of executing the chess placement instruction until each correct placement position in the first area has a chess piece corresponding to each correct placement position. It can be seen that in the embodiment of the present disclosure, by re-executing the steps of controlling the image acquisition device to collect the first image, determining the first area, generating the chess placement instruction, and executing the chess placement instruction, the chessboard image area can be In the area except the occlusion area, placing the chess pieces corresponding to each correct placement position in the first area is beneficial to the area in the chessboard image area except the occlusion area. Play chess efficiently.

In some embodiments, the method further includes: in response to the presence of an occlusion area in the chessboard image area, and each of the correct placement positions in the first area is placed with a corresponding to each correct placement position. The chess piece controls the actuator to move to the initial position of the actuator; the initial position is located in an area outside the chessboard; re-execute the control image acquisition device to collect the first image, determine the first area, and generate the The steps of placing the chess instruction, executing the chess instruction, and controlling the actuator to move to the initial position until there is no occlusion area in the chessboard image area and each correct placement position in the chessboard image area A chess piece is placed corresponding to each correctly placed position.

It can be seen that in the human-computer interaction chess playing scene or the chess playing scene using a chess robot alone, the actuator can be moved outside the chessboard, and then the first image is re-acquired, and the chess playing is realized based on the re-collected first image. Therefore, when the actuator of the chess-playing robot does not block the chessboard, high-reliability chess placement can be achieved through the actuator.

In some embodiments, generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image includes: responding to the first correct placement position not placing all chess pieces. In the case of chess pieces, determine the first chess piece category corresponding to the first correct placement position; the first correct placement position is the correct placement position among the at least one correct placement position; determine all chess pieces in each of the chess pieces. The first chess piece to be placed of the first chess piece category; according to the actual position of the first chess piece to be placed and the first correct placement position, generate the chess placement instruction for the first chess piece to be placed .

It can be seen that when the chess piece is not placed in the first correct placement position, the first chess piece to be placed can be accurately placed in the first correct placement position according to the actual position of the first chess piece to be placed and the first correct placement position. Meet actual chess placement needs.

In some embodiments, determining the first chess piece to be placed of the first chess piece category among the chess pieces includes: determining each chess piece of the first chess piece category among the chess pieces; Among the chess pieces of the first chess piece category, the chess piece closest to the first correct placement position is determined as the first chess piece to be placed. It can be seen that among the chess pieces of the first chess piece category, the chess piece closest to the first correct placement position can be determined as the first chess piece to be placed, and the movement path of the first chess piece to be placed is from the first The actual position of the chess piece to be placed is the first correct position. Therefore, the efficiency of placing the chess piece for the first chess piece to be placed can be improved.

In some embodiments, generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image includes: in response to the first correct placement position being changed by the first The first chess piece to be placed corresponding to the correct placement position is occupied, and the distance between the center point of the first correct placement position and the center point of the first chess piece to be placed is greater than the third distance threshold, according to the first chess piece to be placed. The actual position of the chess piece and the first correct placement position are used to generate the chess placement instruction for the first chess piece to be placed; the first correct placement position is the correct one of the at least one correct placement position. Place the location.

It can be seen that in response to the first correctly placed position being occupied by the first chess piece to be placed corresponding to the first correctly placed position, and the distance between the center point of the first correctly placed position and the center point of the first chess piece to be placed is greater than the Three distance thresholds, it can be considered that the placement of the first chess piece to be placed is not accurate enough. In this case, according to the actual position of the first chess piece to be placed and the first correct placement position, the second correct chess piece can be accurately placed at the first correct placement position. Once the chess pieces are placed. In the scenario of human-machine interactive chess playing, the chess pieces placed by humans may not be as accurate as the mechanical arms, and there will be a certain degree of offset. By implementing the technical solutions of the embodiments of the present disclosure, chess pieces placed by humans that are not accurate enough can be solved without The position is fine-tuned without affecting the user experience, so as to meet the actual chess placement needs.

In some embodiments, the method further includes: traversing the correct placement positions in the first area in order of distance from the actuator to determining the first correct placement position. Understandably, since the first correct position is obtained by traversing the correct placement positions in the first area in order of distance from the actuator from near to far, it is conducive to efficient implementation during the chess placement process. Movement of the actuator.

In some embodiments, the number of the at least one correct placement position is greater than or equal to two; the chess placement instruction is generated based on the at least one correct placement position and the actual position of at least one chess piece in the first image, Including: in response to the situation that at least two correct placement positions are mutually occupied by at least two chess pieces to be placed, based on the actual positions of at least some of the chess pieces in the at least two chess pieces to be placed and a predefined area outside the chessboard , generating the chess placement instructions for at least some of the chess pieces.

It can be understood that when at least two correct placement positions are occupied by at least two chess pieces to be placed, due to the influence of the placed chess pieces on the placement process of the chess pieces to be placed, the at least two chess pieces to be placed cannot be directly placed. Any one of the chess pieces to be placed is moved to the correct position. By moving at least part of the at least two chess pieces to be placed to a predefined area outside the chessboard, it is beneficial to realize at least two chess pieces to be placed in the next chess placement process. Correct placement of chess pieces.

In some embodiments, the method further includes: traversing the correct placement locations in the first area in order of distance from the actuator to determining the at least two correct placement locations. Location. Understandably, since at least two correct positions are obtained by traversing the correct placement positions in the first area in order of distance from the actuator from near to far, it is beneficial to reduce execution during the chess placement process. The moving distance of the actuator can be effectively realized.

In some embodiments, the method further includes: in response to the fact that there is no occlusion area in the chessboard image area and the number of chess pieces in the first image is less than the first number, determining that the chess placement state is a missing piece state; The first quantity is the total number of chess pieces determined according to the chess piece placement rules. Understandably, there is no occlusion area in the chessboard image area, and the number of chess pieces in the first image is less than the first number. It can be considered that the chess pieces in the first image are not enough to achieve a complete chess placement process. Therefore, by accurately determining The status of the chess piece is a lack of pieces, which is conducive to subsequent targeted processing based on the lack of pieces.

In some embodiments, the method further includes: generating prompt information indicating a missing substate when a missing substate is generated at least twice in a row. It can be seen that since the prompt information indicating a missing son is generated when the missing son state is generated at least twice in a row, the occurrence of a missing son can be determined more reliably to a certain extent.

The embodiment of the present disclosure also provides a chess playing device, which may include: a control part and a processing part, wherein,

The control part is configured to control the image acquisition device to acquire a first image, where the first image represents an image of the chessboard and each chess piece;

A processing part configured to determine a first area in a region other than the occlusion area in the chessboard image area in response to the presence of an occlusion area in the chessboard image area; in response to the first area The chess piece corresponding to the at least one correct placement position is not placed in at least one correct placement position, and a chess placement instruction is generated based on the at least one correct placement position and the actual position of at least one chess piece in the first image; so The above-mentioned correct placement position means the placement position of the chess pieces determined according to the chess piece placement rules;

The control part is also configured to control the actuator of the chess-playing robot to execute the chess-playing instructions.

Embodiments of the present disclosure also provide an electronic device, which includes an image acquisition device, a processor, and a memory for storing a computer program that can be run on the processor; wherein the processor is used to run the computer program. To perform any of the above chess placement methods.

An embodiment of the present disclosure also provides a chess-playing robot. The chess-playing robot includes an actuator for grabbing objects, and also includes any of the above-mentioned chess-playing devices or any of the above-mentioned electronic devices.

In some embodiments, the actuator is a robotic arm.

Embodiments of the present disclosure also provide a computer storage medium on which a computer program is stored. When the computer program is executed by a processor, any one of the above chess playing methods can be implemented.

An embodiment of the present disclosure also provides a computer program, which includes computer readable code. When the computer readable code is run in an electronic device, the processor in the electronic device executes for implementing any of the above chess playing. method.

It can be seen that, using the technical solutions of the embodiments of the present disclosure, when there is an occlusion area on the chessboard, chess placing instructions can be generated based on the correct placement of chess pieces outside the occlusion area on the chessboard and the actual position of the chess pieces. , Therefore, the impact of the occlusion area on the chess placement process can be effectively reduced, that is, when the chessboard or chess pieces are occluded, the unoccluded image information can be used to reliably achieve chess placement.

It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit the technical solution of the present disclosure.

Description of the drawings

The accompanying drawings herein are incorporated into and constitute a part of this specification. They illustrate embodiments consistent with the disclosure and, together with the description, serve to explain the technical solutions of the disclosure.

Figure 1 is a flow chart of a chess placement method according to an embodiment of the present disclosure;

Figure 2 is a flow chart of another chess placement method according to an embodiment of the present disclosure;

Figure 3 is a schematic flowchart of generating chess placement instructions in an embodiment of the present disclosure;

Figure 4 is a schematic diagram of a scene for generating chess placement instructions in an embodiment of the present disclosure;

Figure 5 is a flow chart for determining the first chess piece to be placed in an embodiment of the present disclosure;

Figure 6 is a schematic diagram of another scenario for generating chess placement instructions in an embodiment of the present disclosure;

Figure 7 is a schematic diagram of another scene for generating chess placement instructions in an embodiment of the present disclosure;

Figure 8 is a flow chart of yet another chess placing method according to an embodiment of the present disclosure;

Figure 9 is a schematic flow chart of calling the chess placement algorithm function to execute the chess placement algorithm in an embodiment of the present disclosure;

Figure 10 is a schematic structural diagram of a chess placing device according to an embodiment of the present disclosure;

FIG. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure are further elaborated below in conjunction with the accompanying drawings and examples. The described embodiments should not be regarded as limiting the present disclosure. Those of ordinary skill in the art will All other embodiments obtained without creative efforts belong to the scope of protection of this disclosure.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or a different subset of all possible embodiments, and Can be combined with each other without conflict.

The terms "first/second/third" involved are only used to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first/second/third" can be used interchangeably if permitted. The specific order or sequence may be changed so that the embodiments of the disclosure described herein can be implemented in an order other than that illustrated or described herein.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The terminology used herein is for the purpose of describing the disclosure only and is not intended to be limiting of the disclosure.

The term "and/or" in this article is just an association relationship that describes related objects, indicating that three relationships can exist. For example, A and/or B can mean: A exists alone, A and B exist simultaneously, and they exist alone. B these three situations. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, and C, which can mean including from A, Any one or more elements selected from the set composed of B and C.

In order to better understand the chess placement method provided by the embodiments of the present disclosure, the chess placement method used in related technologies will be described below.

In related technologies, the chess placement method implemented based on the chess robot needs to assume that there is no obstruction between the chess board and the chess pieces (for example, people cannot block any chess pieces), and that there is no interference during the chess placement process (for example, people cannot move any chess pieces). ), which makes the chess-playing robot less efficient and less interactive with users, which reduces the user experience to a certain extent.

In some scenarios, the process in which humans and robots play chess at the same time can be called human-computer interactive chess playing. To achieve efficient human-computer interactive chess playing, the following issues need to be considered: First, different objects may appear on the chessboard, including But it is not limited to the human arm and the mechanical arm of the chess robot, which causes the chessboard and chess pieces to be blocked to varying degrees; secondly, people may move unplaced chess pieces or move already placed chess pieces, interfering with the chess placement process; thirdly, The chess pieces placed by humans may not be as accurate as those of a robotic arm, and there will be a certain degree of offset. The robotic arm needs to be fine-tuned without affecting the user experience. Fourth, it is necessary to accurately distinguish between the failure to complete the chess piece due to occlusion and the lack of pieces. It is impossible to complete the chess placement, and prompts are given to ask people to cooperate to complete the chess placement; fifth, the most efficient way must be selected to complete the chess placement to better meet the actual needs of users.

The embodiment of the present disclosure proposes a chess-playing method, which can be applied to a chess-playing robot. The chess-playing robot may include a processor and an actuator for grabbing objects; for example, the processor is used to control the working state of the actuator, and execute The device may be a robotic arm or other device, and the end of the robotic arm may be provided with a suction cup or clamp. The above-mentioned processor can be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), or a Programmable Logic device. At least one of Device (PLD), Field-Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller, and microprocessor.

In the embodiment of the present disclosure, the above-mentioned chess-playing method can also be applied to electronic devices. The electronic device can be a part of the chess-playing robot, or it can be another device that forms a communication connection with the chess-playing robot. In the case where the electronic device forms a communication connection with the chess-playing robot, In the case of other connected devices, the electronic device may include at least one of the host computer and cloud device corresponding to the robot; the electronic device may include a processor; in the case of other devices that form a communication connection with the chess robot, The electronic device can send chess placement instructions to the chess robot.

An image acquisition device can be installed in the game robot or electronic device, and the processor of the game robot can control the image acquisition device of the game robot to collect images; in the case where the electronic device is another device that forms a communication connection with the game robot, the electronic device can control the image The acquisition device acquires images.

Figure 1 is a flow chart of a chess placement method according to an embodiment of the present disclosure. As shown in Figure 1, the process may include:

Step 101: Control the image acquisition device to acquire a first image, where the first image represents the image of the chessboard and each chess piece.

In the embodiment of the present disclosure, the image acquisition device may be disposed toward the chessboard for capturing at least an image of the chessboard. For example, the shooting area of the image acquisition device may also include the surrounding area of the chessboard.

In some embodiments, the chessboard may be a chess board, a chess board, a Go board, etc., and correspondingly, the chess pieces are chess pieces, chess pieces, Go pieces, etc.

Step 102: In response to the presence of an occlusion area in the chessboard image area in the first image, determine a first area in the chessboard image area except the occlusion area.

In some embodiments, the first image can be analyzed to obtain the analysis result of the first image; the analysis result of the first image at least includes the chessboard image area and the position of each chess piece in the image; according to the analysis result of the first image, Determine whether there is an occlusion area in the checkerboard image area. In practical applications, after acquiring the first image, the first image can be segmented into regions to determine the chessboard image area and the image area outside the chessboard; by detecting and identifying the chess pieces on the first image, the chess pieces can be determined The position in the first image; for example, the chess piece can be detected and recognized in the first image according to a pre-trained target detection model.

In some embodiments, the chessboard image in the first image can be input into a pre-trained occlusion recognition model, and the occlusion recognition model is used to identify the occlusion areas in the chessboard image area; for example, the occlusion recognition model refers to pre-training based on a large number of The classifier obtained by training image data for classification training. It can be understood that the training image data for pre-training includes a first type of sample image in which the chessboard or chess pieces are occluded, and a second type of sample image in which the chessboard and chess pieces are not occluded. The first type of sample image and the second type of sample image are classified through a classification algorithm. Class sample images are used for training, and the trained occlusion recognition model can be obtained. The first type of sample image may be an image in which at least one of the chessboard and the chess pieces is blocked by other objects. For example, the other objects may be the actuators of a chess robot or human hands.

In some embodiments, the entire area in the checkerboard image area except the occlusion area may be used as the first area, or a part of the checkerboard image area except the occlusion area may be used as the first area.

Step 103: In response to the fact that the chess piece corresponding to the at least one correct placement position is not placed in the at least one correct placement position in the first area, generate a chess placing instruction based on the at least one correct placement position and the actual position of the at least one chess piece in the first image. ; The correct placement position means the placement position of the chess pieces determined according to the chess piece placement rules.

In the embodiment of the present disclosure, the chess piece placement rules may represent rules that meet the opening standards of the chess game, or may be rules determined based on the preset endgame chess record. It is understandable that the chess piece placement rules are known rules, for example, chess The rules for placing chess pieces at the beginning of the game, the rules for placing chess pieces at the beginning of chess, and the rules for placing chess pieces corresponding to the end game of chess are all known rules.

In the embodiment of the present disclosure, the chess pieces corresponding to each correctly placed position on the chess board are determined according to the chess piece placement rules; for example, for a chess board or a Go chess board, the correct placement position of the chess pieces is part of the horizontal line on the chess board. At the intersection point with the vertical line, the correct placement position of the chess piece can be expressed by the coordinates of the corresponding intersection point; for the chess board, the correct placement position of the chess piece is part of the grid on the chessboard, and the correct placement position of the chess piece can be expressed by the corresponding grid The coordinates of the center point of .

It can be understood that for the same chessboard, the chess pieces corresponding to each correctly placed position are the same type of chess pieces, and each correctly placed chess piece can be used to place a chess piece in a type of chess piece. For example, in a chess board, a certain correctly placed chess piece The position is used to place the chess pieces with the category "Pawn". There are 5 chess pieces with the category "Pawn". The correct placement position can place one of the 5 chess pieces with the category "Pawn". Different chess pieces of the same category can be placed in different correct placement positions. For example, in the scene of the chess opening game, different chess pieces of the category "bishop" are placed at different chessboard intersections.

In some embodiments, at least one chess piece to be placed and the target position of at least one chess piece to be placed can be determined based on at least one correct placement position and the actual position of at least one chess piece in the first image; according to at least one chess piece to be placed The current actual position and target position of the chess pieces can determine the chess placement instructions for moving the chess pieces to be placed.

In practical applications, the position of the chess piece (actual position and target position) can be represented by the coordinates of the center point of the chess piece.

Step 104: Control the actuator of the chess-playing robot to execute the chess-playing instructions.

In some embodiments, when the actuator includes a robotic arm, the processor of the chess-playing robot can control the working state of the robotic arm so that the robotic arm executes chess placement instructions to realize the placement of each chess piece on the chessboard. Alternatively, the electronic device can send a chess placement instruction to the chess robot to control the actuator of the chess robot to execute the chess placement instructions.

It can be seen that when there is an occlusion area on the chessboard, chess placement instructions can be generated based on the correct placement of chess pieces outside the occlusion area on the chessboard and the actual position of the chess pieces. Therefore, the interference with the occlusion area can be effectively reduced. The impact of the chess placement process, that is, when the chessboard or chess pieces are occluded, the unoccluded image information can be used to reliably achieve chess placement.

In some embodiments, a part of the area in the checkerboard image area other than the occlusion area can be selected as the first area; wherein the distance between each pixel in the first area and the boundary of the occlusion area is greater than the first area. distance threshold, and the distance between each pixel in the first area and each placed chess piece is greater than the second distance threshold.

In the embodiment of the present disclosure, in order to reduce the impact of the occlusion area on the chess placement process, the position that is within a first distance threshold from the boundary of the occlusion area can be determined as a position where chess pieces cannot be placed; for example, the first distance threshold It can be the radius of a chess piece, the diameter of a chess piece, 1.1 times the diameter of a chess piece, etc.; similarly, in order to reduce the impact of each placed chess piece on the chess placement process, the distance to the chess piece can be set to the second distance The position within the threshold is determined as a position where chess pieces cannot be placed; for example, the second distance threshold is the diameter of a chess piece, 1.2 times the diameter of a chess piece, etc. The first distance threshold and the second distance threshold may be the same or different. For example, the first distance threshold and the second distance threshold may both be the diameter of a chess piece.

In some embodiments, after the control actuator executes the chess placement instruction, steps 101 to 104 can be re-executed until each correct placement position in the first area has a chess piece corresponding to each correct placement position.

It can be understood that when step 101 is re-executed, due to the change in the position of the chess pieces caused by the latest chess placement, the first image collected by the image acquisition device will change, that is, the first image collected by the image acquisition device will be the updated The first image, that is, it is necessary to perform steps 102 to 104 based on the updated first image until each correct placement position in the first area has a chess piece corresponding to each correct placement position.

In practical applications, after each time the image acquisition device is controlled to collect the first image, the first area can be determined based on the first image, and it can be determined whether each correct placement position in the first area is placed corresponding to each correct placement position. chess piece.

In response to the chess piece corresponding to the at least one correctly placed position not being placed at at least one correctly placed position in the first area, the actuator may be continued to be controlled to place the chess piece by performing steps 103 to 104 .

It can be seen that in the embodiment of the present disclosure, by re-executing the steps of controlling the image acquisition device to collect the first image, determining the first area, generating the chess placement instruction, and executing the chess placement instruction, the chessboard image area can be In the area except the occlusion area, placing the chess pieces corresponding to each correct placement position in the first area is beneficial to the area in the chessboard image area except the occlusion area. Play chess efficiently.

In some embodiments, referring to Figure 2, the chess placement method according to the embodiment of the present disclosure may further include the following steps:

Step 201: In response to the presence of an occlusion area in the chessboard image area, and each correct placement position in the first area has a chess piece corresponding to each correct placement position, control the actuator to move to the initial position of the actuator; the initial position is located on the chessboard outside the area.

Here, the initial position can be the default position of the actuator, and the default position of the actuator can be the position set by the user; in some embodiments, the distance between the initial position and the chessboard can be less than the set value, which is beneficial to improving the actuator The efficiency and speed of playing chess.

Step 202: Re-execute the steps of controlling the image acquisition device to collect the first image, determining the first area, generating chess placement instructions, executing chess placement instructions, and controlling the actuator to move to the initial position until there is no occlusion area in the chessboard image area. , and each correctly placed position in the chessboard image area has a chess piece corresponding to each correctly placed position.

In the embodiment of the present disclosure, in response to the fact that there is no occlusion area in the chessboard image area, and each correctly placed position in the chessboard image area has a chess piece corresponding to each correctly placed position, it can be determined that the chess placement state is the chess placement completion state; in some cases In the embodiment, when it is determined that the chess placement state is the chess placement completion state, a prompt message indicating the completion of the chess placement may be issued and the process ends; the prompt information indicating the completion of the chess placement may be text prompt information, sound prompt information, etc., for example , the prompt message for completing the chess placement can be the following text prompt message: "The robot is ready, please move first."

In some embodiments, referring to Figure 3, the process of generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image may include:

Step 301: In response to the fact that no chess piece is placed at the first correct placement position, determine the first chess piece category corresponding to the first correct placement position; the first correct placement position is the correct placement position among at least one correct placement position.

Here, the first correct placement can be one correct placement position, or it can be at least two correct placement positions; based on the contents recorded in the foregoing embodiments, in response to the situation that the chess piece is not placed at the first correct placement position, the chess piece placement rules can be , determine the first chess piece category corresponding to the first correct placement position; for example, referring to Figure 4, when the first correct placement position is point E, according to the chess piece placement rules at the beginning of chess, the first correct placement position can be determined The corresponding first chess piece category is "rook". When the first correct placement position is point F, according to the chess piece placement rules at the beginning of chess, it can be determined that the first chess piece category corresponding to the first correct placement position is "horse".

Step 302: Determine the first chess piece to be placed of the first chess piece category among each chess piece.

In some embodiments, based on the contents recorded in the foregoing embodiments, when there are at least two chess pieces in the first chess category, one chess piece can be selected as the first chess piece to be placed among the chess pieces in the first chess category. Chess pieces; for example, if the first chess piece category is "Pawn", and there are 5 chess pieces in the first chess piece category, you can select one chess piece as the first chess piece to be placed among the 5 chess pieces of the "Pawn" category. piece.

When the chess piece of the first chess piece category is one chess piece, the chess piece of the first chess piece category can be directly used as the first chess piece to be placed.

Step 303: Generate a chess placement instruction for the first chess piece to be placed based on the actual position of the first chess piece to be placed and the first correct placement position.

In practical applications, the first correct placement position can be used as the target position of the first chess piece to be placed, and the placement instruction for the first chess piece to be placed can be to move the first placed chess piece from the actual position to the target position. Instruction, it can be understood that after the instruction to move the first placed chess piece from the actual position to the target position, the actual position of the first chess piece to be placed has changed.

Referring to Figure 4, when the first correct placement position is point E, the first chess piece to be placed corresponding to point E is the first chess piece 401, and the target position of the first chess piece 401 is determined as point E, thereby generating a target for The placement instruction of the first chess piece 401.

It can be seen that when the chess piece is not placed at the first correct placement position, the first chess piece to be placed can be accurately placed at the first correct placement position according to the actual position of the first chess piece to be placed and the first correct placement position. Meet actual chess placement needs.

In some embodiments, referring to Figure 5, step 302 may specifically include the following steps:

Step 3021: Determine each chess piece of the first chess piece category among each chess piece in the first image.

Step 3022: Among the chess pieces of the first chess piece category, determine the chess piece closest to the first correct placement position as the first chess piece to be placed.

In the embodiments of the present disclosure, based on the contents recorded in the foregoing embodiments, it can be known that the chess pieces of the first chess piece category may include at least two chess pieces. It can be seen that among the chess pieces of the first chess piece category, the chess piece closest to the first correct placement position can be determined as the first chess piece to be placed, and the movement path of the first chess piece to be placed is from the first The actual position of the chess piece to be placed is the first correct position. Therefore, the efficiency of placing the chess piece for the first chess piece to be placed can be improved; the placed or unplaced chess pieces that humans move intentionally or unintentionally can be placed in the shortest path. to the correct location.

In some embodiments, the process of generating a chess placement instruction based on at least one correct placement position and the actual position of at least one chess piece in the first image may include:

In response to the first correctly placed position being occupied by the first chess piece to be placed corresponding to the first correctly placed position, and the distance between the center point of the first correctly placed position and the center point of the first chess piece to be placed is greater than the third distance threshold, The chess placing instruction for the first chess piece to be placed is generated according to the actual position of the first chess piece to be placed and the first correct placement position; the first correct placement position is the correct one of the at least one correct placement position. Place the location.

In the embodiment of the present disclosure, when the correct placement position of the chess piece is an intersection point, the center point of the first correct placement position is the first correct placement position itself; for example, for chess, the center point of the first correct placement position is Intersection point; when the correct placement position of the chess piece is a grid, the center point of the first correct placement position is the center point of the corresponding grid; for example, for chess, the center point of the first correct placement position is the center point of the grid point.

In some embodiments, the distance between the center point of the first correctly placed position and the center point of the first chess piece to be placed can be recorded as D, and the third distance threshold is smaller than the second distance threshold. For example, the third distance threshold is the difference between the side length of the grid on the chessboard minus the diameter of the chess piece.

In the case where the distance D is greater than the second distance threshold, based on the foregoing description, it can be considered that no chess piece is placed at the first correct placement position, that is, the first correct placement position is not occupied by a chess piece.

When the distance D is less than or equal to the third distance threshold, based on the aforementioned content, it can be considered that the first correct placement position is occupied by the first chess piece to be placed, and the placement accuracy of the chess piece at the first correct placement position is relatively high. In this case, it is not necessary to re-place the chess piece for the first chess piece to be placed.

When the distance D is greater than the third distance threshold and the distance D is less than or equal to the second distance threshold, it can be considered that the placement of the first chess piece to be placed is not accurate enough. In this case, it is necessary to place the first chess piece to be placed. Fine-tuning the position of the chess piece, that is, it is necessary to generate a chess placement instruction for the first chess piece to be placed, in order to improve the placement accuracy of the chess pieces placed in the first zone.

Referring to Figure 6, when the first correct placement position is point E, according to the chess piece placement rules at the beginning of chess, it can be determined that the first chess piece category corresponding to the first correct placement position is "rook"; in Figure 6, In the case where the first correct placement position is point E, the first chess piece to be placed corresponding to point E is the second chess piece 601. The distance between the center point of the second chess piece 601 and point E is recorded as distance D. At distance D When the distance D is greater than the third distance threshold and the distance D is less than or equal to the second distance threshold, a placement instruction for the second chess piece 601 is generated to achieve fine-tuning of the position of the second chess piece 601 .

In some embodiments, the correct placement positions in the first area can also be traversed in order of distance from the actuator from closest to far to determine the first correct placement position.

Understandably, since the first correct position is obtained by traversing the correct placement positions in the first area in order of distance from the actuator from near to far, it is conducive to efficient implementation during the chess placement process. Movement of the actuator.

In some embodiments, when the number of the above-mentioned at least one correct placement position is greater than or equal to two, the process of generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image , which can include:

In response to the situation that at least two correct placement positions are mutually occupied by at least two chess pieces to be placed, generating a target for at least some of the chess pieces based on the actual positions of at least some of the chess pieces in the at least two chess pieces to be placed and a predefined area outside the chessboard. The chess placement instructions.

Here, the predefined area is the position outside the chessboard where chess pieces are placed. The size of the predefined area can be determined according to the size and number of chess pieces. When the total number of chess pieces determined according to the chess piece placement rules is large, a larger predefined area can be set. Define the area; when the total number of chess pieces determined according to the chess piece placement rules is small, a smaller predefined area can be set. If the chess pieces are larger, a larger predefined area can be set; if the chess pieces are smaller, a smaller predefined area can be set.

In some embodiments, at least part of the at least two chess pieces to be placed may be part of the at least two chess pieces to be placed, or may be all of the at least two chess pieces to be placed.

Referring to Figure 7, outside the occlusion area 700, the third chess piece 701 with the chess piece category "Pawn" is in the correct placement position, and the fourth chess piece 702 with the chess piece category "Rook" occupies the correct position of the chess piece with the chess piece category "Horse" Placement position, the fifth chess piece 703 with the chess piece category "horse" occupies the correct placement position of the chess piece with the chess piece category "rook"; that is, the fourth chess piece 702 and the fifth chess piece 703 occupy each other's correct positions. , by moving at least one of the fourth chess piece 702 and the fifth chess piece 703 to a predefined area, it is beneficial to achieve the correct placement of the fourth chess piece 702 and the fifth chess piece 703 in the next chess placement process.

In some embodiments, the correct placement positions in the first area can also be traversed in order of distance from the actuator from nearest to far, and at least two correct placement positions are determined.

Understandably, since at least two correct positions are obtained by traversing the correct placement positions in the first area in order of distance from the actuator from near to far, it is beneficial to reduce execution during the chess placement process. The moving distance of the actuator can be effectively realized.

In some embodiments, in response to the fact that there is no occlusion area in the chessboard image area and the number of chess pieces in the first image is less than the first number, it is determined that the chess placement state is a lack of pieces state; the first number is determined according to the chess piece placement rules. The total number of chess pieces.

Understandably, there is no occlusion area in the chessboard image area, and the number of chess pieces in the first image is less than the first number. It can be considered that the chess pieces in the first image are not enough to achieve a complete chess placement process. Therefore, by accurately determining The status of the chess piece is a lack of pieces, which is conducive to subsequent targeted processing based on the lack of pieces.

In some embodiments, when a missing substate is generated at least twice in a row, prompt information indicating a missing substate may be generated. For example, when a missing substate is generated three times in a row, prompt information indicating a missing substate may be generated.

In practical applications, the prompt information indicating missing pieces may be text prompt information, sound prompt information, etc. For example, the prompt information indicating the completion of chess placement may be the following text prompt information: "There is a missing piece, please add chess pieces." After generating a prompt message indicating a missing child, the process can be ended.

It can be seen that since the prompt information indicating a missing son is generated when the missing son state is generated at least twice in a row, the occurrence of a missing son can be determined more reliably to a certain extent.

The following describes the application of the chess placement method provided by the embodiments of the present disclosure in actual scenarios, taking chess or chess as an example to illustrate the chess placement method.

Referring to Figure 8, another method of placing chess provided by an embodiment of the present disclosure may include the following steps:

Step 801: Complete the initial placement of each chess piece and the chessboard.

Here, the initial placement of each chess piece and chess board can be completed by the user. For example, the user can place each chess piece and chess board in an area that can be photographed by the image acquisition device; for example, the user can place at least some of the chess pieces flatly on the on the chessboard to achieve the initial placement of chess pieces and chessboard.

Step 802: Control the camera to collect the first image.

Here, the camera is the above-mentioned image acquisition device. In practical applications, the camera can be controlled by the processor of the game robot to acquire the first image.

Step 803: Perform image tagging.

In some embodiments, based on the foregoing description, the first image can be analyzed, and image labeling can be performed based on the analysis results of the first image.

In some embodiments, the implementation of image marking may include: marking the occlusion area, the position of each chess piece, and the category identification of each chess piece in the first image. Here, the position of each chess piece may be identified by the center point of each chess piece. coordinate representation.

Understandably, based on the information marked in the first image, the impact of the occlusion area on the correct placement of the chessboard and the chess pieces can be judged, which helps to determine which positions on the chessboard cannot be placed and which chess pieces cannot be placed at the current moment. to the correct placement position; for example, the correct placement position in the occlusion area cannot place the chess piece; in response to the correct placement position of a specific chess piece being in the occlusion area or occupied by other chess pieces, the specific chess piece cannot be placed in the corresponding correct position at the current moment. Place the location.

In some embodiments, the grayscale value of the occlusion area can be set to 255 or other non-zero value, and the grayscale value of the background of the non-occlusion area can be set to 0; the position with the category identifier of the chess piece in the chessboard image area is The correct placement position of the corresponding chess piece; within a chess piece radius of the boundary pixel point of the occlusion area, the category identifier of the chess piece cannot be identified, that is, the correct placement position is not within a chess piece radius range of the boundary pixel point of the occlusion area; two The category identifiers of chess pieces should be spaced at least twice the chess piece radius (i.e. the diameter of a chess piece).

In some embodiments, in the scene of playing chess, for the 10x9 intersection points (intersection points of horizontal lines and vertical lines) existing on the chessboard, the distance between the intersection point and the boundary of the occlusion area is less than or equal to The diameter of a chess piece determines that the intersection point is not the correct placement position; similarly, in response to the distance between the intersection point and any placed chess piece being less than or equal to the diameter of a chess piece, it is determined that the intersection point is not the correct placement position.

In the scene of chess placement, for each grid on the chess board, in response to the fact that the distance between the grid and the boundary of the occlusion area is less than or equal to the diameter of one chess piece, it is determined that the corresponding grid is not in the correct position; in response to If the distance between the grid and any placed chess piece is less than or equal to the diameter of a chess piece, it is determined that the corresponding grid is not placed in the correct position.

In practical applications, step 803 may be executed by the processor of the game robot.

Step 804: Call the chess placement algorithm function to execute the chess placement algorithm.

In the embodiment of the present disclosure, the chess-playing algorithm function can be called by the processor of the chess-playing robot to execute the chess-playing algorithm. Here, according to the input information of the chess-playing algorithm, the output result can be obtained by calling the chess-playing algorithm function to execute the chess-playing algorithm.

In some embodiments, the input information of the chess placement algorithm may include the location of the occlusion area, the location of the non-occlusion area, the location of the chessboard, the location of each chess piece, and the category identifier of each chess piece. The position and category identification of each chess piece can be represented by the array (x, y, p), where x and y represent the abscissa and ordinate coordinates of the center point of the chess piece, and p represents the category identification of the chess piece, for example, the category identification of the chess piece It can be "gun", "general", etc.

In some embodiments, the output result at least includes a status code indicating the state of the chess placement. For example, when the status code is status code 0, the status code indicates that the chess is being placed; when the status code is status code 1, the status code indicates that the chess is being placed; when the status code is status code 2 In this case, the status code indicates the state of moving the robotic arm to the initial position; in the case where the status code is status code 3, the status code indicates the missing child state.

In some embodiments, when the status code is status code 1, the output result may also include the current actual position of the chess piece to be placed, the target position, and the chess piece category identifier. For example, the chess piece category identifier may be the name or identity of the chess piece category. Identity Document (ID) and other identification information, the output result can also include an array (x1, y1, x2, y2, p1), where x1 represents the abscissa of the actual position of the center point of the chess piece to be placed, and y1 represents The ordinate of the actual position of the center point of the chess piece to be placed, x2 represents the abscissa of the target position of the chess piece to be placed, y2 represents the ordinate of the target position of the chess piece to be placed, and p1 represents the chess piece category identifier of the chess piece to be placed. .

Step 805: Perform corresponding operations according to the status code.

In practical applications, step 805 may be performed by the processing of the game robot.

Referring to Figure 8, when the status code is status code 1, step 805 may include step 8051; when the status code is status code 2, step 805 may include step 8052; when the status code is status code 3 , step 805 may include step 8053; when the status code is status code 0, step 805 may include step 8054.

Step 8051: Control the robotic arm to execute the chess placement instruction, and then return to step 802.

Here, according to the current actual position and target position of the chess piece to be placed, the robotic arm can be controlled to complete the grabbing and placing of the chess piece to be placed, that is, the chess placement operation for the chess piece to be placed is realized.

Step 8052: Control the robotic arm to move to the initial position, and then return to step 802.

Here, by controlling the robot arm to move to the initial position, it is helpful to reduce the occlusion caused by the robot arm to the chessboard and improve the efficiency of subsequent chess placement.

Step 8053: Generate voice prompt information, and then end the process.

Here, when the status code received three consecutive times is status code 3, voice prompt information indicating a missing son can be generated.

It can be seen that the embodiment of the present disclosure can accurately distinguish whether the chess placement cannot be completed due to occlusion or the chess placement cannot be completed due to a lack of pieces, and when a missing piece occurs, a prompt is given to require the person to cooperate to complete the chess placement.

Step 8054: Generate a prompt message indicating the completion of chess placement, and end the process.

In some embodiments, referring to Figure 9, the process of calling the chess placement algorithm function to execute the chess placement algorithm may include:

Step 901: Determine whether the chess placement status is the chess placement completion state. If yes, execute step 902. If not, execute step 903.

Step 902: Output status code 0.

Step 903: Determine whether there is a first correct placement position for unplaced chess pieces. If yes, execute step 906. If not, execute step 904.

In this step, the first correct placement position is the correct placement position in the first area. The distance between each pixel point in the first area and the boundary of the occlusion area is greater than the diameter of a chess piece, and each pixel point in the first area is The distance between each placed chess piece is greater than the diameter of one chess piece.

By executing this step, it can be determined whether there is a position where the chess should be placed and the position is not blocked or occupied. If yes, step 906 is executed. If not, step 904 is executed.

In some embodiments, in the scene of playing chess, for the 10x9 horizontal and vertical line intersections on the chessboard, traverse starting from the left side of the proximal end of the robotic arm to find the first correct placement position and determine the first correct placement position. Whether the piece can be placed at a correctly placed position? If it can be placed, according to the type of chess piece in the target chess record at that position, search for the piece of this category in the first image, and select the correct category closest to the first correctly placed position. The first chess piece to be placed is to obtain the actual position and target position of the first chess piece to be placed; the target position of the first chess piece to be placed is the first correct placement position. In the embodiment of the present disclosure, the target chess record is a chess record that represents the rules for placing chess pieces. The target chess record may be a standard opening chess record or a predetermined endgame chess record.

In some embodiments, in the scenario of playing chess, for each square on the chess board, traverse from the left side of the proximal end of the robotic arm to find the first correct placement position and determine the first correct placement Whether the position can be placed. If it can be placed, according to the category of the target chess piece at the position, search for the chess piece of this category in the first image, and select the first correct category that is closest to the first correct placement position. Place the chess pieces and obtain the actual position and target position of the first chess piece to be placed; the target position of the first chess piece to be placed is the first correct placement position. In the embodiment of the present disclosure, the target chess record is a chess record that represents the rules for placing chess pieces. The target chess record may be a standard opening chess record or a predetermined endgame chess record.

Step 904: Determine whether there is a first correct placement position that meets the set conditions; if yes, execute step 906; if not, execute step 905.

Here, the distance between the center point of the first correctly placed position and the center point of the first chess piece to be placed is recorded as D. The setting condition may be: the distance D is greater than the third distance threshold, and the distance D is less than or equal to the second Distance threshold; in this step, the third distance threshold is the difference between the side length of the grid on the chessboard minus the diameter of the chess piece, and the second distance threshold is the diameter of a chess piece.

In some embodiments, in the scene of playing chess, for the 10x9 horizontal and vertical line intersections on the chessboard, traverse starting from the left side of the proximal end of the robotic arm to find the first correct placement position and determine the first correct placement position. Whether the chess piece can be placed at the correct placement position. If the chess piece cannot be placed, based on the type of chess piece in the target chess record at that position, it is judged whether it is because the first chess piece to be placed is in the first correct placement position but the placement is not accurate enough (that is, the distance D is greater than The third distance threshold, and the distance D is less than or equal to the second distance threshold), resulting in the first correct placement position being unable to be placed. If yes, the actual position and target position of the first chess piece to be placed are obtained; the target position of the first chess piece to be placed is the first correct placement position.

In some embodiments, in the scenario of playing chess, for each square on the chess board, traverse from the left side of the proximal end of the robotic arm to find the first correct placement position and determine the first correct placement Whether the position can be placed, if not, based on the type of chess pieces in the target chess record at that position, determine whether the first chess piece to be placed is in the first correct position but the placement is not accurate enough (that is, the distance D is greater than the third distance threshold, and the distance D is less than or equal to the second distance threshold), resulting in the first correct placement position being unable to be placed. If so, obtain the actual position and target position of the first chess piece to be placed.

Step 905: Determine whether there are at least two correct placement positions occupied by at least two chess pieces to be placed. If yes, step 906 is executed. If not, step 907 is executed.

In this step, in response to the fact that there are at least two correct placement positions occupied by at least two chess pieces to be placed, some of the chess pieces of the at least two chess pieces to be placed can be moved to the free predefined positions on the left and right sides of the chessboard. area.

In some embodiments, in the scenario of playing chess, for the 10x9 horizontal and vertical line intersections on the chessboard, traverse starting from the left side of the proximal end of the robotic arm to find whether there are at least two correct placement positions. When at least two chess pieces to be placed occupy each other, if so, then at least one of the two chess pieces to be placed needs to be moved to a predefined area, and the actual position and target position of the chess piece that needs to be moved can be determined. Here, The target position of the chess piece that needs to be moved is a predefined area.

In some embodiments, in the scenario of playing chess, for each square on the chess board, traverse starting from the left side of the proximal end of the robotic arm to find whether there are at least two correct placement positions that are occupied by at least two The chess pieces to be placed occupy each other. If so, at least one of the two chess pieces to be placed needs to be moved to a predefined area. The actual position and target position of the chess piece that needs to be moved can be determined. Here, the chess piece that needs to be moved The target position of the chess piece is a predefined area.

Step 906: Output status code 1 and related information of the chess piece to be placed.

Here, the relevant information of the chess piece to be placed may include the actual position and the target position of the chess piece to be placed; the chess piece to be placed in this step may be the first chess piece to be placed or one of the at least two chess pieces to be placed. A chess piece.

Step 907: Determine whether the chess placement state is a missing piece state. If yes, step 908 is executed. If not, step 909 is executed.

Step 908: Output status code 3.

Step 909: Output status code 2.

In summary, it can be seen that the chess placement method according to the embodiment of the present disclosure can effectively deal with the obstruction of the chessboard and chess pieces by various objects. When the chessboard and chess pieces are partially obscured, the relevant unoccluded image information can be used to achieve efficient chess placement. For placed or unplaced chess pieces that humans move intentionally or unintentionally, they can be placed in the correct position through the shortest path. Accurately feedback the completion status or lack of pieces status of the chess piece in the case of possible occlusion.

In the human-computer interactive chess playing scene, when the human body blocks the chessboard and chess pieces, the relevant unobstructed image information can be used to realize the efficient chess playing of the robotic arm, which is beneficial to the realization of the interaction between the robotic arm and the human on the chess robot. The interactive chess playing is more efficient than playing chess with only mechanical arms. Since there is good interaction between humans and robots during the chess playing process, it can better meet the actual needs of users and is more interactive. The chess placement method of the embodiment of the present disclosure can effectively deal with various situations of occlusion of the chess board and chess pieces. When a person places the chess pieces crookedly or incorrectly, a mechanical arm can be used to correct the position. Therefore, the chess placement process is improved in the smoothness of the chess placement process. Great sex.

Embodiments of the present disclosure can be applied to game scenarios of various chess sports. For example, when the user restarts a new game of chess or a new game of international chess, the chess placement method of the embodiment of the present disclosure is used. , which can achieve efficient and accurate chess placement. Here, a new chess game can be a standard opening game or an endgame game; correspondingly, a new chess game can be a standard opening game or an endgame game.

Based on the foregoing embodiments, embodiments of the present disclosure provide a chess-playing device, which includes various parts and can be implemented by a processor in an electronic device; of course, it can also be implemented by a specific logic circuit; in implementation In the process, the processor may be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor.

Figure 10 is a schematic structural diagram of a chess playing device according to an embodiment of the present disclosure. As shown in Figure 10, the device includes a control part 1001 and a processing part 1002, wherein,

The control part 1001 is configured to control the image collection device to collect a first image, where the first image represents the image of the chessboard and each chess piece;

The processing part 1002 is configured to, in response to the presence of an occlusion area in the checkerboard image area in the first image, determine a first area in the checkerboard image area other than the occlusion area; in response to the first The chess piece corresponding to the at least one correct placement position is not placed in at least one correct placement position in the area, and a chess placement instruction is generated based on the at least one correct placement position and the actual position of at least one chess piece in the first image; The correct placement position represents the placement position of the chess pieces determined according to the chess piece placement rules;

The control part 1001 is also configured to control the actuator of the chess-playing robot to execute the chess-playing instruction.

In some embodiments, the processing part 1002 is configured to determine the first area in the area of the checkerboard image area except the occlusion area, including:

In the area in the checkerboard image area except the occlusion area, select a partial area as the first area; wherein the distance between each pixel point in the first area and the boundary of the occlusion area is greater than the third area. A distance threshold, and the distance between each pixel in the first area and each placed chess piece is greater than the second distance threshold.

In some embodiments, the control part 1001 is also configured to, after controlling the actuator and executing the chess placement instruction, re-execute the control of the image acquisition device to collect the first image, determine the first area, and generate the The chess placement instruction and the step of executing the chess placement instruction are provided until each correct placement position in the first area has a chess piece corresponding to each correct placement position.

In some embodiments, the control part 1001 is also configured to:

In response to the existence of an occlusion area in the chessboard image area, and each of the correct placement positions in the first area is placed with a chess piece corresponding to each of the correct placement positions, the actuator is controlled to move to the execution The initial position of the chessboard; the initial position is located in an area outside the chessboard;

Re-execute the steps of controlling the image acquisition device to collect the first image, determining the first area, generating the chess placement instruction, executing the chess placement instruction, and controlling the actuator to move to the initial position until the There is no occlusion area in the chessboard image area, and chess pieces corresponding to each correct placement position are placed at each correct placement position in the chessboard image area.

In some embodiments, the processing part 1002 is configured to generate a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image, including:

In response to the situation that the chess piece is not placed in the first correct placement position, the first chess piece category corresponding to the first correct placement position is determined; the first correct placement position is the at least one correct placement position. Correct placement;

Determine the first chess piece to be placed of the first chess piece category among each of the chess pieces;

According to the actual position of the first chess piece to be placed and the first correct placement position, the chess placement instruction for the first chess piece to be placed is generated.

In some embodiments, the processing part 1002 is configured to determine the first chess piece to be placed of the first chess piece category among the chess pieces, including:

Determine each chess piece of the first chess piece category among the chess pieces;

Among the chess pieces of the first chess piece category, the chess piece closest to the first correct placement position is determined as the first chess piece to be placed.

It can be seen that among the chess pieces of the first chess piece category, the chess piece closest to the first correct placement position can be determined as the first chess piece to be placed, and the movement path of the first chess piece to be placed is from the first The actual position of the chess piece to be placed is to the first correct position. Therefore, the efficiency of placing the chess piece for the first chess piece to be placed can be improved.

In response to the first correctly placed position being occupied by the first chess piece to be placed corresponding to the first correctly placed position, and the distance between the center point of the first correctly placed position and the center point of the first chess piece to be placed Greater than the third distance threshold, the chess placement instruction for the first chess piece to be placed is generated based on the actual position of the first chess piece to be placed and the first correct placement position; the first correct placement The position is a correct placement position among the at least one correct placement position.

In some embodiments, the processing part 1002 is further configured to traverse the correct placement positions in the first area in order of distance from the actuator to determine the first correct placement position. .

In some embodiments, the number of the at least one correctly placed position is greater than or equal to two; the processing part 1002 is configured to determine the actual position of the at least one chess piece in the first image according to the at least one correctly placed position. , generate chess placement instructions, including:

In response to the situation that at least two correctly placed positions are mutually occupied by at least two chess pieces to be placed, generating a The chess placement instructions for at least some of the chess pieces.

In some embodiments, the processing part 1002 is further configured to traverse the correct placement positions in the first area in order of distance from the actuator to determine the at least two correct placement.

In some embodiments, the processing part 1002 is further configured to determine that the chess placement status is a missing piece in response to the fact that there is no occlusion area in the chessboard image area and the number of chess pieces in the first image is less than the first number. State; the first number is the total number of chess pieces determined according to the chess piece placement rules.

In some embodiments, the processing part 1002 is further configured to generate prompt information indicating a missing substate when a missing substate is generated at least twice in a row.

The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or parts of the device provided by the embodiments of the present disclosure can be used to perform the methods described in the above method embodiments. For technical details not disclosed in the embodiments of the device of the present disclosure, please refer to the methods of the present disclosure. be understood from the description of the embodiments.

It should be noted that in the embodiments of the present disclosure, if the above-mentioned chess placement method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present disclosure can be embodied in the form of software products that are essentially or contribute to related technologies. The software product is stored in a storage medium and includes a number of instructions to enable a A computer device (which may be a personal computer, a server, a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read Only Memory, ROM), magnetic disk or optical disk and other media that can store program code. In this way, the embodiments of the present disclosure are not limited to any specific hardware, software, or firmware, or any combination of hardware, software, and firmware.

Embodiments of the present disclosure provide a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, some or all of the steps in any of the above-mentioned chess-playing methods are implemented. The computer-readable storage medium may be transient or non-transitory.

Computer-readable storage media may be volatile storage media or non-volatile storage media. The computer-readable storage medium may be, for example, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), ROM, electrical programmable read-only memory (Electrical Programmable Read) Only Memory, EPROM), flash memory, Static Random-Access Memory (Static Random-Access Memory, SRAM), Portable Compact Disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), Digital Multi-Function Disk (Digital Video Disc) , DVD), memory sticks, floppy disks, mechanical encoding devices, such as punched cards or raised-in-groove structures with instructions stored thereon, and any suitable combination of the above. As used herein, computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or transmitted through wires electrical signal.

Embodiments of the present disclosure provide a computer program, including computer readable code. When the computer readable code is run in a computer device, the processor in the computer device executes for implementing any of the above chess playing. Some or all of the steps in a method.

Embodiments of the present disclosure provide a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, some of the above methods are implemented or All steps. The computer program product can be implemented specifically through hardware, software or a combination thereof. In some embodiments, the computer program product is embodied as a computer storage medium. In other embodiments, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) and so on.

It should be noted here that the above description of various embodiments tends to emphasize the differences between the various embodiments, and the similarities or similarities may be referred to each other. The description of the above embodiments of equipment, storage media, computer programs and computer program products is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of equipment, storage media, computer programs and computer program products, please refer to the description of the method embodiments of the present disclosure for understanding.

It should be noted that FIG. 11 is a schematic diagram of a hardware entity of an electronic device in an embodiment of the present disclosure. As shown in FIG. 11 , the electronic device 1100 may include: a memory 1101, a processor 1102, an image acquisition device 1103, and images stored in the memory 1101. A computer program executable on processor 1102; wherein,

The processor 1102 is used to run the computer program to execute any of the above-mentioned chess placing methods.

In practical applications, the above-mentioned memory 1101 can be volatile memory (volatile memory), such as RAM; or non-volatile memory (non-volatile memory), such as ROM, flash memory (flash memory), hard disk (Hard Disk) Drive, HDD) or solid-state drive (Solid-State Drive, SSD); or a combination of the above types of memories, and provides instructions and data to the processor 1102.

In some embodiments, the actuator is a robotic arm.

It will be understood that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that in various embodiments of the present disclosure, the size of the serial numbers of the above steps/processes does not mean the order of execution. The execution order of each step/process should be determined by its functions and internal logic, and should not be The implementation process of the embodiments of the present disclosure constitutes no limitations. The above serial numbers of the embodiments of the present disclosure are only for description and do not represent the advantages and disadvantages of the embodiments.

It should be noted that, in this document, the terms "comprising", "comprising" or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, method, article or apparatus. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article, or device that includes that element.

In the several embodiments provided in this disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components may be combined, or can be integrated into another system, or some features can be ignored, or not implemented. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be electrical, mechanical, or other forms. of.

The units described above as separate components may or may not be physically separated; the components shown as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present disclosure can be all integrated into one processing unit, or each unit can be separately used as a unit, or two or more units can be integrated into one unit; the above-mentioned integration The unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed through hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the execution includes: The steps of the above method embodiment; and the aforementioned storage media include: mobile storage devices, read-only memory (Read Only Memory, ROM), magnetic disks or optical disks and other various media that can store program codes.

Alternatively, if the above-mentioned integrated units of the present disclosure are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product in essence or that contributes to related technologies. The computer software product is stored in a storage medium and includes a number of instructions to enable a computer. A computer device (which may be a personal computer, a server, a network device, etc.) executes all or part of the methods described in various embodiments of the present disclosure. The aforementioned storage media include: mobile storage devices, ROMs, magnetic disks or optical disks and other media that can store program codes.

The above are only embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, and should are covered by the protection scope of this disclosure.

Claims

A method of playing chess, the method is executed by an electronic device, the method includes:

Control the image acquisition device to acquire a first image, where the first image represents an image of the chessboard and each chess piece;

In response to the presence of an occlusion area in the checkerboard image area in the first image, determining a first area in the area in the checkerboard image area other than the occlusion area;

In response to the at least one correct placement position in the first area not placing the chess piece corresponding to the at least one correct placement position, according to the at least one correct placement position and the actual position of the at least one chess piece in the first image , generate a chess placement instruction; the correct placement position represents the placement position of the chess pieces determined according to the chess piece placement rules;

Control the actuator of the chess-playing robot to execute the chess-playing instructions.
The method according to claim 1, wherein determining the first area in the area of the checkerboard image area except the occlusion area includes:

In the area in the checkerboard image area except the occlusion area, select a partial area as the first area; wherein the distance between each pixel point in the first area and the boundary of the occlusion area is greater than the third area. A distance threshold, and the distance between each pixel in the first area and each placed chess piece is greater than the second distance threshold.
The method according to claim 1 or 2, wherein, after controlling the actuator and executing the chess placement instruction, the method further includes:

Re-execute the steps of controlling the image acquisition device to collect the first image, determine the first area, generate the chess placement instruction, and execute the chess placement instruction until each correct placement position in the first area is A piece is placed corresponding to each of the correct placements described.
The method of claim 3, further comprising:

In response to the existence of an occlusion area in the chessboard image area, and each of the correct placement positions in the first area is placed with a chess piece corresponding to each of the correct placement positions, the actuator is controlled to move to the execution The initial position of the chessboard; the initial position is located in an area outside the chessboard;

Re-execute the steps of controlling the image acquisition device to collect the first image, determining the first area, generating the chess placement instruction, executing the chess placement instruction, and controlling the actuator to move to the initial position until the There is no occlusion area in the chessboard image area, and chess pieces corresponding to each correct placement position are placed at each correct placement position in the chessboard image area.
The method according to any one of claims 1 to 4, wherein generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image includes:

In response to the situation that the chess piece is not placed in the first correct placement position, the first chess piece category corresponding to the first correct placement position is determined; the first correct placement position is the at least one correct placement position. Correct placement;

Determine the first chess piece to be placed of the first chess piece category among each of the chess pieces;

The chess placement instruction for the first chess piece to be placed is generated based on the actual position of the first chess piece to be placed and the first correct placement position.
The method according to claim 5, wherein determining the first chess piece to be placed of the first chess piece category among the chess pieces includes:

Determine each chess piece of the first chess piece category among the chess pieces;

Among the chess pieces of the first chess piece category, the chess piece closest to the first correct placement position is determined as the first chess piece to be placed.
The method according to any one of claims 1 to 6, wherein generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image includes:

In response to the first correctly placed position being occupied by the first chess piece to be placed corresponding to the first correctly placed position, and the distance between the center point of the first correctly placed position and the center point of the first chess piece to be placed Greater than the third distance threshold, the chess placement instruction for the first chess piece to be placed is generated based on the actual position of the first chess piece to be placed and the first correct placement position; the first correct placement The position is a correct placement position among the at least one correct placement position.
The method according to any one of claims 5 to 7, wherein the method further includes:

In order of distance from the actuator from closest to farthest, the correct placement positions in the first area are traversed to determine the first correct placement position.
The method according to any one of claims 1 to 8, wherein the number of the at least one correct placement position is greater than or equal to two;

Generating a chess placement instruction based on the at least one correct placement position and the actual position of at least one chess piece in the first image includes:

In response to the situation that at least two correctly placed positions are mutually occupied by at least two chess pieces to be placed, generating a The chess placement instructions for at least some of the chess pieces.
The method of claim 9, further comprising:

In order of distance from the actuator from closest to farthest, the correct placement positions in the first area are traversed to determine the at least two correct placement positions.
The method according to any one of claims 1 to 10, wherein the method further includes:

In response to the fact that there is no occlusion area in the chessboard image area and the number of chess pieces in the first image is less than a first number, it is determined that the chess placement state is a missing piece state; the first number is determined according to the chess piece placement rules The total number of chess pieces determined.
The method of claim 11, wherein the method further includes:

When a missing substate is generated at least twice in a row, a prompt message indicating a missing substate is generated.
A chess playing device, the device includes: a control part and a processing part,

The control part is used to control the image acquisition device to collect the first image, where the first image represents the image of the chessboard and each chess piece;

A processing part configured to, in response to the presence of an occlusion area in the chessboard image area in the first image, determine a first area in the chessboard image area other than the occlusion area; in response to the first area The chess piece corresponding to the at least one correct placement position is not placed in at least one correct placement position, and a chess placement instruction is generated based on the at least one correct placement position and the actual position of at least one chess piece in the first image; so The above-mentioned correct placement position means the placement position of the chess pieces determined according to the chess piece placement rules;

The control part is also used to control the actuator of the chess-playing robot to execute the chess-playing instructions.
An electronic device, including an image acquisition device, a processor and a memory for storing a computer program capable of running on the processor; wherein the processor is used to run the computer program to perform any one of claims 1 to 12 The described chess-playing method.
A chess-playing robot includes an actuator for grabbing objects, and also includes a chess-playing device according to claim 13 or an electronic device according to claim 14.
The game robot according to claim 15, wherein the actuator is a mechanical arm.
A computer storage medium on which a computer program is stored. When the computer program is executed by a processor, the chess playing method according to any one of claims 1 to 12 is implemented.
A computer program, including computer readable code. When the computer readable code is run in an electronic device, the processor in the electronic device executes the chess playing method according to any one of claims 1 to 12. .