A robot operation task coding method, device, equipment and storage medium

Abstract

This invention relates to the field of coding technology, specifically to a method, apparatus, device, and storage medium for coding robot operation tasks. The invention first decomposes the robot's operation task into individual sub-actions; then, it encodes the attribute information of each sub-action to obtain attribute codes for each sub-action; finally, based on the attribute codes and execution parameters of each sub-action, it encodes the operation task. As can be seen from the above analysis, this invention encodes the attribute information of each sub-action of the operation task separately, thereby achieving more detailed encoding of the operation task attributes. Furthermore, by combining the attribute encoding with the execution parameters of the sub-actions, the operation task is further encoded, resulting in a highly accurate operation task code.

Description

Technical Field

[0001] This invention relates to the field of coding technology, specifically to a method, apparatus, device, and storage medium for coding robot operation tasks. Background Technology

[0002] Autonomous intelligent agent systems, represented by robots, have broad application prospects and significant application value in numerous fields such as industry and service. To ensure that robots can complete complex operational tasks, the tasks to be performed by the robot need to be encoded, and the robot then executes the corresponding tasks based on the encoded information. Current technologies only encode the entire operational task, without encoding the attribute information of the sub-actions that constitute the task, resulting in low accuracy in task encoding.

[0003] In summary, existing technologies have low coding accuracy for operational tasks.

[0004] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a robot operation task encoding method, apparatus, device, and storage medium, which solves the problem of low encoding accuracy for operation tasks in existing technologies.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a robot operation task encoding method, comprising:

[0008] Break down the robot's operational tasks to obtain individual sub-actions;

[0009] The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot.

[0010] The operation task is encoded based on the attribute codes of each sub-action and the execution parameters of each sub-action. The execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action.

[0011] In one implementation, the decomposed robot's operational task is divided into various sub-actions, including:

[0012] The sequence of actions constituting the operation task is determined, and the actions in the sequence are arranged in the order in which the robot performs each action.

[0013] Compare adjacent actions corresponding to adjacent times to obtain dissimilar adjacent actions;

[0014] The action sequence is segmented by separating dissimilar adjacent actions to obtain the segmented action sequence.

[0015] Based on the segmented action sequence, each sub-action is obtained.

[0016] In one implementation, encoding the attribute information of each sub-action to obtain the attribute code of each sub-action, wherein the attribute information is used to characterize the force attributes between the robot generating the sub-action and the object operated by the robot, including:

[0017] Determine the non-contact attribute and trajectory type in the attribute information, wherein the trajectory type is used to characterize the robot's movement trajectory type;

[0018] The non-contact attribute is encoded using two binary bits;

[0019] The trajectory type is encoded using four-bit binary encoding;

[0020] The attribute code of each sub-action is obtained based on the binary code of the non-contact attribute of each sub-action and the binary code of the trajectory type.

[0021] In one implementation, encoding the attribute information of each sub-action to obtain the attribute code of each sub-action, wherein the attribute information is used to characterize the force attributes between the robot generating the sub-action and the object operated by the robot, including:

[0022] The continuous contact, trajectory type, and force direction in the attribute information are determined. The trajectory type is used to characterize the type of robot movement trajectory, and the force direction is the direction of the force applied by the robot to the object.

[0023] The continuous contact is encoded using two binary bits;

[0024] The trajectory type is encoded using two binary bits;

[0025] The direction of force application is encoded using two binary digits;

[0026] The attribute codes of each sub-action are obtained based on the binary codes of the continuous contact, the trajectory type, and the force direction of each sub-action.

[0027] Alternatively, determine the continuous contact and trajectory type in the attribute information, whereby the trajectory type is used to characterize the robot's movement trajectory type;

[0028] The continuous contact is encoded using two binary bits;

[0029] The trajectory type is encoded using two binary bits;

[0030] The attribute codes of each sub-action are obtained based on the binary codes of the continuous contact of each sub-action and the binary codes of the trajectory type.

[0031] In one implementation, encoding the attribute information of each sub-action to obtain the attribute code of each sub-action, wherein the attribute information is used to characterize the force attributes between the robot generating the sub-action and the object operated by the robot, including:

[0032] Determine the non-continuous contact and the state of the robot's gripper in the attribute information;

[0033] The non-continuous contact is encoded using two binary bits;

[0034] The state of the hand is encoded using four-bit binary code;

[0035] The attribute codes of each sub-action are obtained based on the binary codes of the non-continuous contact of each sub-action and the binary codes of the hand state.

[0036] In one implementation, the operation task is encoded based on the attribute encoding of each sub-action and the execution parameters of each sub-action. The execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action, including:

[0037] By adding the binary code of the start instruction before the attribute code and the binary code of the end instruction after the attribute code, the local code of the operation task is obtained.

[0038] Based on the execution parameters of each sub-action and the local encoding of the operation task, the operation task is encoded to obtain the global encoding of the operation task.

[0039] One implementation also includes:

[0040] Construct switching codes for each of the aforementioned sub-actions;

[0041] The switching code is inserted between the attribute codes of each of the sub-actions.

[0042] Secondly, embodiments of the present invention also provide a robot operation task encoding device, wherein the device comprises the following components:

[0043] The task decomposition module is used to break down the robot's operation tasks into individual sub-actions;

[0044] An attribute encoding module is used to encode the attribute information of each of the sub-actions to obtain the attribute code of each of the sub-actions. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot.

[0045] The task encoding module is used to encode the operation task based on the attribute encoding of each sub-action and the execution parameters of each sub-action. The execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action.

[0046] Thirdly, embodiments of the present invention also provide a terminal device, wherein the terminal device includes a memory, a processor, and a robot operation task coding program stored in the memory and executable on the processor, wherein when the processor executes the robot operation task coding program, it implements the steps of the robot operation task coding method described above.

[0047] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a robot operation task coding program, wherein when the robot operation task coding program is executed by a processor, the steps of the robot operation task coding method described above are implemented.

[0048] Beneficial Effects: This invention first decomposes the robot's operation task into individual sub-actions; then, it encodes the attribute information of each sub-action to obtain attribute codes for each sub-action; finally, based on the attribute codes and execution parameters of each sub-action, it encodes the operation task. As can be seen from the above analysis, this invention encodes the attribute information of each sub-action of the operation task separately, thereby achieving more detailed encoding of the operation task attributes. Furthermore, by combining the attribute encoding with the execution parameters of the sub-actions, the operation task is further encoded, resulting in a highly accurate operation task code. Attached Figure Description

[0049] Figure 1 This is an overall flowchart of the present invention;

[0050] Figure 2 This is a flowchart illustrating the attribute encoding process in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the encoding of operation tasks in an embodiment of the present invention;

[0052] Figure 4 This is a schematic diagram illustrating the action attribute analysis in an embodiment of the present invention;

[0053] Figure 5 This is a schematic diagram illustrating the action parameter analysis in an embodiment of the present invention;

[0054] Figure 6 This is a block diagram illustrating the internal structure of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0055] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments and accompanying drawings. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0056] Research has shown that autonomous intelligent agent systems, represented by robots, have broad application prospects and significant value in numerous fields such as industry and service. To ensure that robots can complete complex tasks, the tasks to be performed by the robot need to be encoded, and the robot then executes the corresponding tasks based on the encoded information. Current technologies only encode the entire task at a time, without encoding the attribute information of the sub-actions that constitute the task, resulting in low accuracy in task encoding.

[0057] To address the aforementioned technical problems, this invention provides a robot operation task encoding method, apparatus, device, and storage medium, which solves the problem of low encoding accuracy for operation tasks in existing technologies.

[0058] For example, the robot's control system needs to pre-code the operation tasks. For instance, operation task A needs to be pre-coded: the robot moves from one point to another and presses an object located at the other point. Operation task A includes two sub-actions that the robot needs to perform: movement a1 and pressing object a2. The attribute information of the movement a1 sub-action is encoded as 001000 (the first two 0s represent non-contact between the robot and the object, 1000 represents movement along the horizontal x-axis, and the last zero represents that the robot does not rotate during the movement). The attribute information of the pressing object a2 sub-action is encoded as 010101 (the first two 0s represent continuous contact between the robot and the object, the middle two 0s represent the robot applying a force perpendicular to the contact surface to the object, and the last two 0s represent that the force is pressure). Simultaneously, the execution parameters of the movement a1 sub-action (e.g., movement distance of three meters, encoded as 11) and the execution parameters of the pressing object a2 sub-action (e.g., pressing force of 2N, encoded as 10) are encoded. The final operation task A is coded as 0010000101011110. When 0010000101011110 is input into the robot, the robot will perform the operation task of moving from one point to another and pressing the object located at the other point.

[0059] Exemplary methods

[0060] The robot operation task encoding method of this embodiment can be applied to a terminal device, which can be a terminal product with encoding function, such as a robot control system. In this embodiment, for example... Figure 1 As shown, the robot operation task encoding method specifically includes the following steps:

[0061] S100 breaks down the robot's operational tasks into individual sub-actions.

[0062] S200, the attribute information of each of the sub-actions is encoded to obtain the attribute code of each of the sub-actions. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot.

[0063] S300, based on the attribute codes of each sub-action and the execution parameters of each sub-action, the operation task is encoded, wherein the execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action.

[0064] In one embodiment, step S100 includes the following steps S101 to S104:

[0065] S101, determine the action sequence that constitutes the operation task, and arrange the actions in the action sequence in the order in which the robot performs each action.

[0066] S102, compare adjacent actions corresponding to adjacent times to obtain dissimilar adjacent actions.

[0067] S103, segment the dissimilar adjacent actions in the action sequence to obtain the segmented action sequence.

[0068] S104. Based on the segmented action sequence, each sub-action is obtained.

[0069] For example, the action sequence corresponding to an operation task includes action 1, action 2, action 3, ..., action N, each action corresponding to a unit of time. If action 1 and action 2 are different, a split marker is added between them, resulting in two sub-actions: action 1 and action 2. Similarly, if action 2 and action 3 are the same, no split marker is added between them, and action 2 and action 3 are merged into one sub-action. This embodiment can accurately divide the operation task into various sub-actions by comparing the similarities and differences of actions at adjacent times.

[0070] In one embodiment, step S200 includes the following steps S201a to S204a:

[0071] S201a, determine the non-contact attribute and trajectory type in the attribute information, wherein the trajectory type is used to characterize the robot's movement trajectory type.

[0072] S202a uses two binary bits to encode the non-contact attribute.

[0073] S203a uses a four-bit binary code to encode the trajectory type.

[0074] S204a, based on the binary encoding of the non-contact attribute of each sub-action and the binary encoding of the trajectory type, the attribute encoding of each sub-action is obtained.

[0075] for example Figure 2 In the text, the sub-action of yaw movement (as long as the robot does not move upwards, it is considered yaw movement, such as the robot moving along the X-axis or Y-axis in the XOY horizontal plane) is non-contact (the robot does not contact the object). The attribute-based code for this sub-action is 001000 (the first two digits 00 represent non-contact, and 1 represent movement along the X-axis).

[0076] like Figure 2 As shown, the code for the robot's vertical movement sub-action is 000010 (the last 0 indicates that the robot did not rotate during the vertical movement; if rotation occurred, the last bit would be 1).

[0077] In another embodiment, step S200 includes the following steps S201b to S205b:

[0078] S201b, determine the continuous contact, trajectory type, and force direction in the attribute information, wherein the trajectory type is used to characterize the robot's movement trajectory type, and the force direction is the direction of the force applied by the robot to the object.

[0079] S202b uses two binary bits to encode the continuous contact.

[0080] S203b uses two binary bits to encode the trajectory type.

[0081] S204b uses two binary bits to encode the direction of the applied force.

[0082] S205b, based on the binary code of the continuous contact of each sub-action, the binary code of the trajectory type, and the binary code of the force direction, the attribute code of each sub-action is obtained.

[0083] For sub-actions involving continuous contact, the first two bits are 0 and 1, and the last four bits are encoded according to the three contact directions of oblique cutting, perpendicular, and rotation, as well as the direction of force applied to the contact surface. The direction of force applied outward is 1, and the direction applied inward is 0. The contact directions include oblique cutting, perpendicular, and rotation.

[0084] For example, Figure 2 The code for the sub-action "pressure" is 010101. The first two 01s represent that there is a continuous contact between the robot and the object to which the robot applies pressure, the middle two 01s represent that the applied pressure is perpendicular to the contact surface, and the last two 01s represent that the pressure is directed towards the outside of the object.

[0085] In another embodiment, step S200 includes the following steps S201c to S204c:

[0086] S201c, determine the continuous contact and trajectory type in the attribute information, wherein the trajectory type is used to characterize the robot's movement trajectory type.

[0087] S202c uses two binary bits to encode the continuous contact.

[0088] S203c uses two-bit binary encoding to describe the trajectory type.

[0089] S204c, based on the binary code of the continuous contact of each sub-action and the binary code of the trajectory type, the attribute code of each sub-action is obtained.

[0090] For example, Figure 2 The sub-action code for end effector orientation adjustment (end effect orientation adjustment refers to the operating posture of the end effector, such as the gripping posture of the robot gripper or the suction state of the suction cup) is 011100. The first two digits 01 represent that the robot and the object are in continuous contact, and the last four digits 1100 represent oblique cutting.

[0091] In another embodiment, step S200 includes the following steps S201d to S204d:

[0092] S201d, determine the non-continuous contact and the state of the robot's gripper in the attribute information.

[0093] S202d uses two binary bits to encode the non-continuous contact.

[0094] S203d uses a four-bit binary code to encode the state of the hand.

[0095] S204d, based on the binary code of the non-continuous contact of each sub-action and the binary code of the hand state, the attribute code of each sub-action is obtained.

[0096] For non-continuous contact sub-actions, the first two bits are 10, and the last four bits are mainly used to encode the end effector. The encoding is based on the four end effector characteristics of opening, closing, suction, and releasing. For example, opening the claw is 1000, closing the claw is 0100, and suction cup suction is 0010. For example, when opening the claw, the actual execution is based on 101000 + parameters.

[0097] For example, Figure 2 In the code, the sub-action of opening the claw is coded as 101000. The first two digits 10 represent that the robot's claw and the object being grasped are in non-continuous contact, and the last four digits 1000 represent that the robotic claw is opened.

[0098] In another embodiment, step S200 further includes: constructing a switching code for switching each of the sub-actions; and inserting the switching code between the attribute codes of each of the sub-actions.

[0099] For example, 001000 001 000100 001 011100 001 010101 001 100000, where 001000, 000100, 011100, 010101, and 100000 represent four sub-actions executed sequentially. Setting 001 between two adjacent sub-actions indicates switching from the previous sub-action to the next.

[0100] In one embodiment, step S300 includes the following steps S301 and S302:

[0101] S301, add the binary code of the start instruction before the attribute code and the binary code of the end instruction after the attribute code to obtain the local code of the operation task.

[0102] S302, based on the execution parameters of each sub-action and the local encoding of the operation task, the operation task is encoded to obtain the global encoding of the operation task.

[0103] For example, such as Figure 3 As shown, 000 represents the start, 001 represents the next step, and 111 represents the end. Combining the five actions of "diagonal movement," "vertical movement," "end-effector posture adjustment," "press," and "open claw," the execution code (local code) of the task formed by the serialization of these five actions is as follows: 000 001000 000100 011100 010101 100000 111

[0105] Then, the displacement of the oblique movement (2 meters), the displacement of the vertical movement (3 meters), the amplitude of the end attitude adjustment (2 radians), the pressure magnitude (2 N), and the opening angle of the claw (3 radians) are encoded to obtain the execution parameter code: 10 11 10 10 11.

[0106] Combining the local encoding of attributes and the encoding of execution parameters of sub-actions, the global encoding of the operation task is obtained as follows: 000 001000 000100 011100 010101 100000 111 10 11 10 1011.

[0107] In one embodiment, such as Figure 4 As shown, the coding system includes: module B101, module B102, module B104, and module B105. Module B101 is a contact type module, including non-contact, rigid contact, flexible contact, and other contact types; module B102 is a contact time module, including continuous contact and non-continuous contact; module B103 is a force direction module, including inward and outward; module B104 is a trajectory type module, including one-dimensional motion, two-dimensional motion, three-dimensional motion, and rotation; and module B105 is a periodic module, including periodic repetitive motion and non-periodic repetitive motion.

[0108] Figure 4 In the diagram, solid black circles represent confirmed items, while hollow circles represent optional items, meaning that an action may or may not have this attribute.

[0109] In one embodiment, execution parameters are set, such as... Figure 5 As shown, module C101 is the movement module, which includes two attributes: target position and target attitude. The target position parameter is represented by [x, y, z], and the target attitude parameter is represented by [pitch, yaw, roll]. Module C102 is the force module, which includes two attributes: force magnitude and force direction. The force magnitude parameter is represented by a float value, and the force direction parameter is represented by [pitch, yaw, roll]. Module C103 is the claw module, which includes a claw shape attribute. The claw shape parameter is represented by a string value. Module C10n represents the remaining parameter modules not listed.

[0110] In summary, this invention first decomposes the robot's operation task into individual sub-actions; then, it encodes the attribute information of each sub-action to obtain attribute codes for each sub-action; finally, based on the attribute codes and execution parameters of each sub-action, it encodes the operation task. As the above analysis shows, this invention encodes the attribute information of each sub-action of the operation task separately, thereby achieving more detailed encoding of the operation task attributes. Furthermore, by combining the attribute encoding with the execution parameters of the sub-actions, the operation task is further encoded, resulting in a highly accurate operation task code.

[0111] In addition, this invention can be applied to complex skill application scenarios of robots. By parsing and encoding action primitives (sub-actions), the efficiency of robots in completing task objectives can be improved.

[0112] Exemplary device

[0113] This embodiment also provides a robot operation task encoding device, which includes the following components:

[0114] The task decomposition module is used to break down the robot's operation tasks into individual sub-actions;

[0115] An attribute encoding module is used to encode the attribute information of each of the sub-actions to obtain the attribute code of each of the sub-actions. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot.

[0116] The task encoding module is used to encode the operation task based on the attribute encoding of each sub-action and the execution parameters of each sub-action. The execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action.

[0117] Based on the above embodiments, the present invention also provides a terminal device, the principle block diagram of which can be as follows: Figure 6 As shown, the terminal device includes a processor, memory, network interface, display screen, and temperature sensor connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a robot operation task encoding method. The display screen can be an LCD screen or an e-ink screen. The temperature sensor is pre-installed inside the terminal device to detect the operating temperature of the internal components.

[0118] Those skilled in the art will understand that Figure 6 The block diagram shown is merely a partial structural diagram related to the present invention and does not constitute a limitation on the terminal device to which the present invention is applied. The specific terminal device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0119] In one embodiment, a terminal device is provided, comprising a memory, a processor, and a robot operation task coding program stored in the memory and executable on the processor. When the processor executes the robot operation task coding program, it implements the following operation instructions:

[0120] Break down the robot's operational tasks to obtain individual sub-actions;

[0121] The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot.

[0122] The operation task is encoded based on the attribute codes of each sub-action and the execution parameters of each sub-action. The execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action.

[0123] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for encoding robot operation tasks, characterized in that, include: Break down the robot's operational tasks to obtain individual sub-actions; The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot. The operation task is encoded based on the attribute codes of each sub-action and the execution parameters of each sub-action, wherein the execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action; The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attributes between the robot that generates the sub-action and the object operated by the robot, including: The continuous contact, trajectory type, and force direction in the attribute information are determined. The trajectory type is used to characterize the robot's movement trajectory type, and the force direction is the direction of the force applied by the robot to the object. The continuous contact is encoded using two binary bits; The trajectory type is encoded using two binary bits; The direction of force application is encoded using two binary digits; The attribute codes of each sub-action are obtained based on the binary codes of the continuous contact, the trajectory type, and the force direction of each sub-action. Alternatively, determine the continuous contact and trajectory type in the attribute information, whereby the trajectory type is used to characterize the robot's movement trajectory type; The continuous contact is encoded using two binary bits; The trajectory type is encoded using two binary bits; The attribute codes of each sub-action are obtained based on the binary codes of the continuous contact of each sub-action and the binary codes of the trajectory type.

2. The robot operation task encoding method as described in claim 1, characterized in that, The operation task of the decomposition robot is divided into various sub-actions, including: The sequence of actions constituting the operation task is determined, and the actions in the sequence are arranged in the order in which the robot performs each action. Compare adjacent actions corresponding to adjacent times to obtain dissimilar adjacent actions; The action sequence is segmented by separating dissimilar adjacent actions to obtain the segmented action sequence. Based on the segmented action sequence, each sub-action is obtained.

3. The robot operation task encoding method as described in claim 1, characterized in that, The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attributes between the robot that generates the sub-action and the object operated by the robot, including: Determine the non-contact attribute and trajectory type in the attribute information, wherein the trajectory type is used to characterize the robot's movement trajectory type; The non-contact attribute is encoded using two binary bits; The trajectory type is encoded using four-bit binary encoding; The attribute code of each sub-action is obtained based on the binary code of the non-contact attribute of each sub-action and the binary code of the trajectory type.

4. The robot operation task encoding method as described in claim 1, characterized in that, The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attributes between the robot that generates the sub-action and the object operated by the robot, including: Determine the non-continuous contact and the state of the robot's gripper in the attribute information; The non-continuous contact is encoded using two binary bits; The state of the hand is encoded using four-bit binary code; The attribute codes of each sub-action are obtained based on the binary codes of the non-continuous contact of each sub-action and the binary codes of the hand state.

5. The robot operation task encoding method as described in claim 1, characterized in that, The operation task is encoded based on the attribute codes of each sub-action and the execution parameters of each sub-action. The execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action, including: By adding the binary code of the start instruction before the attribute code and the binary code of the end instruction after the attribute code, the local code of the operation task is obtained. Based on the execution parameters of each sub-action and the local encoding of the operation task, the operation task is encoded to obtain the global encoding of the operation task.

6. The robot operation task encoding method as described in claim 1, characterized in that, Also includes: Construct switching codes for each of the aforementioned sub-actions; The switching code is inserted between the attribute codes of each of the sub-actions.

7. A robot operation task encoding device, characterized in that, The device comprises the following components: The task decomposition module is used to break down the robot's operation tasks into individual sub-actions; An attribute encoding module is used to encode the attribute information of each of the sub-actions to obtain the attribute code of each of the sub-actions. The attribute information is used to characterize the force attribute between the robot that generates the sub-action and the object operated by the robot. The task encoding module is used to encode the operation task based on the attribute encoding of each sub-action and the execution parameters of each sub-action, wherein the execution parameters are used to characterize the parameter information that the robot needs to configure to execute the sub-action; The attribute information of each sub-action is encoded to obtain the attribute code of each sub-action. The attribute information is used to characterize the force attributes between the robot that generates the sub-action and the object operated by the robot, including: The continuous contact, trajectory type, and force direction in the attribute information are determined. The trajectory type is used to characterize the robot's movement trajectory type, and the force direction is the direction of the force applied by the robot to the object. The continuous contact is encoded using two binary bits; The trajectory type is encoded using two binary bits; The direction of force application is encoded using two binary digits; The attribute codes of each sub-action are obtained based on the binary codes of the continuous contact, the trajectory type, and the force direction of each sub-action. Alternatively, determine the continuous contact and trajectory type in the attribute information, whereby the trajectory type is used to characterize the robot's movement trajectory type; The continuous contact is encoded using two binary bits; The trajectory type is encoded using two binary bits; The attribute codes of each sub-action are obtained based on the binary codes of the continuous contact of each sub-action and the binary codes of the trajectory type.

8. A terminal device, characterized in that, The terminal device includes a memory, a processor, and a robot operation task coding program stored in the memory and executable on the processor. When the processor executes the robot operation task coding program, it implements the steps of the robot operation task coding method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a robot operation task coding program, which, when executed by a processor, implements the steps of the robot operation task coding method as described in any one of claims 1-6.

Images