Operation control method and device of robot, robot and storage medium

Abstract

The invention relates to the technical field of robots, and discloses a robot operation control method and device, a robot and a storage medium, and the method comprises the steps: scanning a point cloud picture of a scene in real time, carrying out the pairing calculation of a source point cloud in the point cloud picture and a preset point cloud, and obtaining a target point cloud; the preset point cloud comprises three-dimensional coordinate points of a plurality of position points; the target point cloud comprises position information of mapping points, in the point cloud picture, of all position points in the preset point cloud; optimizing the position information of each mapping point in the target point cloud; calculating a driving path of the robot in the scene according to the coordinate information of the current position point and the parking point of the robot; according to the coordinate information of the action point corresponding to the parking point, the action path of the robot on the parking point position is calculated; and driving according to the driving path, parking at the parking point, and finishing the grabbing work on the target parking point according to the action path on the parking point. According to the technical scheme, the operation efficiency of the robot can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of robots, and particularly to an operation control method, device, robot and computer-readable storage medium for a robot. Background Art

[0002] In recent years, with the gradual expansion of the domestic power grid system, due to more complex scenario requirements, higher operation efficiency requirements, and higher safety requirements for operators. In some complex environmental scenarios such as high-risk live working scenarios, the use of operation robots and unmanned aerial vehicles as carriers of new operation modes is increasing. However, due to the increasing types of on-site operation scenarios and large differences in the site, it is difficult to standardize the management and control. Currently, when using operation robots, it is necessary to manually select the corresponding operation tasks during the operation process to achieve the purpose of completing the operation tasks, resulting in low efficiency. Summary of the Invention

[0003] In view of the above problems, the embodiments of the present invention provide an operation control method, device, equipment and computer-readable storage medium for a robot, which are used to improve the operation efficiency of the robot.

[0004] According to one aspect of the embodiments of the present invention, an operation control method for a robot is provided. The method includes: scanning a point cloud map of a target scene in real time, performing pairing calculation on the source point cloud in the point cloud map and a preset point cloud to obtain a target point cloud;

[0005] Wherein, the preset point cloud includes three-dimensional coordinate points of a plurality of preset position points, and the three-dimensional coordinate points of each preset position point are obtained by measuring and recording the preset position points of a preset operation scene using a radar device; the preset position points include: a preset parking point and a corresponding preset action point; the target point cloud includes: the position information of the mapping points of each preset position point in the preset point cloud in the point cloud map;

[0006] Optimizing the position information of each mapping point in the target point cloud to obtain the coordinate information corresponding to each mapping point; the coordinate information corresponding to the mapping point includes: the coordinate information of the target parking point and the coordinate information of the position of the target action point corresponding to the target parking point;

[0007] Calculating the driving path of the robot in the target scene according to the current position point of the robot and the coordinate information of the target parking point; calculating the action path of the robot at the target parking point according to the coordinate information of the target action point corresponding to the target parking point;

[0008] Driving according to the driving path, wherein, parking at the target parking point and completing the grasping work at the target parking point according to the action path at the target parking point.

[0009] The operation control method of the robot provided by the present invention can store corresponding target points according to the tasks in different scenarios, realizing the standardized management of operation tasks. When the operation robot needs to perform an operation on one of the tasks in the current scenario, the robot imports the corresponding task file, and then can generate the driving path and the corresponding action path in the current scenario, realizing the automatic generation of the task path and task actions, as well as the automatic operation of the robot, improving the operation efficiency of the robot.

[0010] In an alternative manner, pairing and calculating the source point cloud in the point cloud map with a preset point cloud to obtain a target point cloud includes:

[0011] By using the nearest neighbor search algorithm, pairing and calculating the source point cloud and the preset point cloud in the point cloud map, and determining the target points closest to each of the preset position points in the source point cloud;

[0012] Using a preset space transformation algorithm to perform at least one space transformation operation on the source point cloud in the point cloud map to obtain the space-transformed source point cloud and the space-transformed target points;

[0013] Taking the space-transformed target points as the mapping points of each of the preset position points in the point cloud map to obtain the target point cloud.

[0014] In an alternative manner, using a preset space transformation algorithm to perform at least one space transformation operation on the source point cloud in the point cloud map to obtain the space-transformed source point cloud and the space-transformed target points includes:

[0015] Using a preset space transformation algorithm to perform at least one space transformation operation on the source point cloud in the point cloud map, and iteratively adjusting the space transformation parameters in the preset space transformation algorithm so that the average distance between the space-transformed target points and the corresponding preset position points is less than a preset threshold, or the number of iterations reaches the upper limit.

[0016] In an alternative manner, optimizing the position information of each mapping point in the target point cloud to obtain the coordinate information corresponding to each mapping point includes:

[0017] Constructing a cube frame with a preset size centered on each mapping point in the point cloud map; extracting the point cloud data in each cube frame;

[0018] Process the point cloud data in the target cube frame using the least squares method to determine the wire of the target mapping point; obtain the coordinate points and corresponding vector directions of the target mapping point according to the wire of the target mapping point; wherein, the target cube frame is the cube frame corresponding to the target mapping point, and the target mapping point is any mapping point;

[0019] Use the coordinate points and corresponding vector directions of each mapping point as the coordinate information corresponding to each mapping point.

[0020] In an alternative way, use a radar device to measure and record the preset position points in the preset operation scenario, including:

[0021] Establish a corresponding three-dimensional model for the operation points in the preset operation scenario, and determine at least one preset parking point in the three-dimensional model;

[0022] Simulate the action postures of the robot to complete the grasping work at the preset parking point, and determine several preset action points corresponding to the robot at the preset parking point; the preset action points include: the left arm action point and the right arm action point; there is a sequence for each action point.

[0023] In an alternative way, the preset operation scenario at least includes: a lead wire, a main wire, and a wire clamp with a buckle, and the wire clamp is used to fix the lead wire and the main wire at the position of the wire clamp bayonet using the buckle;

[0024] The robot includes: a first robotic arm with a gripper and a second robotic arm with a gripper;

[0025] Wherein, the first robotic arm is the left arm of the robot, the second robotic arm is the right arm of the robot, or the first robotic arm is the right arm of the robot, and the second robotic arm is the left arm of the robot.

[0026] In an alternative way, simulating the action postures of the robot to complete the grasping work at the preset parking point and determining several preset action points corresponding to the robot at the preset parking point includes:

[0027] Set a first reference point for the first robotic arm and a second reference point for the second robotic arm;

[0028] Simulate the robot at the preset parking point to control the first robotic arm to move from the first reference point to the preset installation position of the lead wire, and determine the first action point of the first robotic arm; control the gripper of the first robotic arm to close to clamp the lead wire;

[0029] Control the first robotic arm to move from the first action point of the first robotic arm to the first reference point, and determine the second action point of the first robotic arm;

[0030] Control the second robotic arm to move from the second reference point to the position where the wire clamp is located, and determine the first action point of the second robotic arm; control the jaws of the second robotic arm to close to clamp the wire clamp.

[0031] Control the second robotic arm to move from the first action point of the second robotic arm to the preset installation position of the main wire, so that the main wire enters the position of the wire clamp opening of the wire clamp, and determine the second action point of the second robotic arm.

[0032] Control the first robotic arm to move from the second action point of the first robotic arm to the preset installation position of the main wire, and determine the third action point of the first robotic arm; control the first robotic arm to push the lead wire into the position of the wire clamp opening of the wire clamp.

[0033] Control the second robotic arm to release the wire clamp and close the lock of the wire clamp to fix the lead wire and the main wire in the position of the wire clamp opening; control the second robotic arm to move from the preset installation position of the main wire to the second reference point, and determine the third action point of the second robotic arm.

[0034] Control the first robotic arm to release the lead wire and move from the preset installation position of the main wire to the first reference point, and determine the fourth action point of the first robotic arm.

[0035] Determine several action points of the robot according to the sequence of the first action point, the second action point, the third action point and the fourth action point of the first robotic arm, and the first action point, the second action point and the third action point of the second robotic arm.

[0036] According to another aspect of the embodiments of the present invention, there is provided an operation control device for a robot, including: a matching module, an optimization module, a planning module and a control module.

[0037] The matching module is configured to scan the point cloud map of the target scene in real time, perform pairing calculation on the source point cloud in the point cloud map and the preset point cloud to obtain the target point cloud.

[0038] Wherein, the preset point cloud includes three-dimensional coordinate points of several preset position points, and the three-dimensional coordinate points of each preset position point are measured and recorded by using a radar device for the preset position points of the preset operation scene; the preset position points include: a preset parking point and a corresponding preset action point; the target point cloud includes: the position information of the mapping points of each preset position point in the preset point cloud in the point cloud map.

[0039] An optimization module, configured to optimize the position information of each of the mapping points in the target point cloud to obtain the coordinate information corresponding to each of the mapping points; the coordinate information corresponding to the mapping points includes: the coordinate information of the target parking point and the coordinate information of the position of the target action point corresponding to the target parking point;

[0040] A planning module, configured to calculate the driving path of the robot in the target scene according to the current position point of the robot and the coordinate information of the target parking point; calculate the action path of the robot at the position of the target parking point according to the coordinate information of the target action point corresponding to the target parking point;

[0041] A control module, configured to drive according to the driving path, wherein, stop at the target parking point and complete the grasping work at the target parking point according to the action path at the target parking point.

[0042] According to another aspect of the embodiments of the present invention, there is provided an operation control device for a robot, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations of the operation control method for the robot as described in any one of the above.

[0043] According to still another aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, in which at least one executable instruction is stored, and the executable instruction causes an operation control device / device for a robot to execute the operations of the operation control method for the robot as described in any one of the above.

[0044] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to be able to understand the technical means of the embodiments of the present invention more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features, and advantages of the embodiments of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically described below. Description of the Drawings

[0045] The drawings are only used to illustrate the embodiments and are not considered as a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0046] Figure 1 It shows a schematic flowchart of an embodiment of the operation control method for a robot provided by the present invention;

[0047] Figure 2 It shows a schematic diagram of the scene before the robot operation of an embodiment of the operation control method for a robot provided by the present invention;

[0048] Figure 3 It shows a schematic diagram of the scene after the operation of the robot in an embodiment of the operation control method of the robot provided by the present invention;

[0049] Figure 4 It shows a schematic structural diagram of an embodiment of the operation control device of the robot provided by the present invention;

[0050] Figure 5 It shows a schematic structural diagram of an embodiment of the operation control device of the robot provided by the present invention. Detailed implementation manners

[0051] Hereinafter, exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein.

[0052] Embodiment 1, Figure 1 It shows a flowchart of an embodiment of the operation control method of the robot provided by the present invention, and this method is executed by the robot. As Figure 1 shown, this method includes the following steps:

[0053] Step 110: Continuously scan the point cloud map of the target scene, perform paired calculation on the source point cloud in the point cloud map and a preset point cloud to obtain a target point cloud;

[0054] Wherein, the preset point cloud includes three-dimensional coordinate points of several preset position points, and the three-dimensional coordinate points of each preset position point are obtained by measuring and recording the preset position points of the preset operation scene using a radar device; the preset position points include: a preset parking point and a corresponding preset action point; the target point cloud includes: the position information of the mapping points of each preset position point in the preset point cloud in the point cloud map.

[0055] In some embodiments of the present invention, performing paired calculation on the source point cloud in the point cloud map and a preset point cloud to obtain a target point cloud includes:

[0056] Performing paired calculation on the source point cloud and the preset point cloud in the point cloud map through a nearest neighbor search algorithm, and determining the target points closest to each preset position point in the source point cloud;

[0057] Performing at least one spatial transformation operation on the source point cloud in the point cloud map using a preset spatial transformation algorithm to obtain a spatially transformed source point cloud and a spatially transformed target point;

[0058] Taking the spatially transformed target points as the mapping points of each preset position point in the point cloud map to obtain a target point cloud.

[0059] In some embodiments of the present invention, at least one spatial transformation operation is performed on the source point cloud in the point cloud map by using a preset spatial transformation algorithm to obtain the spatially transformed source point cloud and the spatially transformed target points, including:

[0060] Using a preset spatial transformation algorithm, at least one spatial transformation operation is performed on the source point cloud in the point cloud map, and the spatial transformation parameters in the preset spatial transformation algorithm are iteratively adjusted so that the average distance between the spatially transformed target points and the corresponding preset position points is less than a preset threshold, or the number of iterations reaches the upper limit.

[0061] Specifically, the spatial transformation operations include but are not limited to rotation and translation. The robot performs a spatial transformation on the source point cloud in the point cloud map by using the spatial transformation parameters in the preset spatial transformation algorithm. The spatial transformation parameters include rotation parameters and translation parameters.

[0062] Specifically, the robot adjusts the spatial transformation parameters so that the average distance between the corresponding point pairs of the spatially transformed source point cloud and the target point cloud reaches the minimum; if the average distance between the spatially transformed source point cloud and the target point cloud is less than a preset threshold, or the number of iterations has reached the upper limit, the iterative process is terminated. If the condition that the average distance is less than the preset threshold is not satisfied, the spatially transformed source point cloud is used as the new source point cloud and the iteration continues until the requirements of the objective function are met.

[0063] Step 120: Optimize the position information of each mapping point in the target point cloud to obtain the coordinate information corresponding to each mapping point; the coordinate information corresponding to the mapping point includes: the coordinate information of the target parking point and the coordinate information of the position of the target action point corresponding to the target parking point.

[0064] In some embodiments of the present invention, optimizing the position information of each mapping point in the target point cloud to obtain the coordinate information corresponding to each mapping point includes:

[0065] Construct a cube frame with a preset size centered on each mapping point in the point cloud map; extract the point cloud data in each cube frame;

[0066] Use the least squares method to process the point cloud data in the target cube frame to determine the wire of the target mapping point; according to the wire of the target mapping point, obtain the coordinate point and the corresponding vector direction of the target mapping point; where the target cube frame is the cube frame corresponding to the target mapping point, and the target mapping point is any one mapping point;

[0067] Take the coordinate point and the corresponding vector direction of each mapping point as the coordinate information corresponding to each mapping point.

[0068] Preferably, the robot constructs a cube frame with a side length of 100 mm centered on each of the mapping points, frames all the real-time point clouds near the mapping points, and uses the least squares method to confirm the exact coordinate points and corresponding vector directions of the wires at the mapping points, thereby confirming the coordinate positions of the mapping points; and further confirms the action postures of the robot at each mapping point according to the task content.

[0069] Step 130: Calculate the driving path of the robot in the target scenario according to the current position point of the robot and the coordinate information of the target parking point; calculate the action path of the robot at the target parking point according to the coordinate information of the target action point corresponding to the target parking point.

[0070] Specifically, the robot records the tasks of the operation process, the corresponding target points (i.e., mapping points), and the action postures in the form of json to generate a task file. When the robot needs to perform an operation on a target task in the current scenario, it imports the corresponding task file, and then the driving path and the corresponding action path in the current scenario can be generated.

[0071] Step 140: Drive along the driving path. Specifically, stop at the target parking point and complete the grasping work at the target parking point according to the action path at the target parking point.

[0072] In some embodiments of the present invention, a radar device is used to measure and record preset position points in a preset operation scenario, including:

[0073] Establish a corresponding three-dimensional model for the operation points in the preset operation scenario, and determine at least one preset parking point in the three-dimensional model;

[0074] Simulate the action postures of the robot to complete the grasping work at the preset parking point, and determine a number of preset action points corresponding to the robot at the preset parking point; the preset action points include: a left-arm action point and a right-arm action point; each of the action points is provided with a sequence.

[0075] In some embodiments of the present invention, the preset operation scenario at least includes: a lead wire, a main wire, and a wire clamp with a buckle, and the wire clamp is used to fix the lead wire and the main wire at the position of the wire clamp bayonet by using the buckle;

[0076] The robot includes: a first robotic arm with a gripper and a second robotic arm with a gripper;

[0077] Wherein, the first robotic arm is the left arm of the robot, the second robotic arm is the right arm of the robot, or the first robotic arm is the right arm of the robot, and the second robotic arm is the left arm of the robot.

[0078] Preferably, as an example, the operation task of the robot is to fix the lead wire and the main wire with a wire clamp. Specifically, the robot places the lead wire and the main wire into the position of the wire clamp bayonet, and closes the lock to fix the lead wire and the main wire in the position of the wire clamp bayonet of the wire clamp. It should be noted that this example is only one example of the method of the present invention, and the operation task of the robot can also be other grasping operations.

[0079] In some embodiments of the present invention, simulating the action posture of the robot to complete the grasping operation at the preset parking point, and determining a plurality of preset action points corresponding to the robot at the preset parking point, including:

[0080] Setting a first reference point of the first robotic arm and a second reference point of the second robotic arm;

[0081] Simulating the robot at the preset parking point to control the first robotic arm to move from the first reference point to the preset installation position of the lead wire, and determining the first action point of the first robotic arm; controlling the gripper of the first robotic arm to close to clamp the lead wire;

[0082] Controlling the first robotic arm to move from the first action point of the first robotic arm to the first reference point, and determining the second action point of the first robotic arm;

[0083] Controlling the second robotic arm to move from the second reference point to the position where the wire clamp is located, and determining the first action point of the second robotic arm; controlling the gripper of the second robotic arm to close to clamp the wire clamp;

[0084] Controlling the second robotic arm to move from the first action point of the second robotic arm to the preset installation position of the main wire, so that the main wire enters the position of the wire clamp bayonet of the wire clamp, and determining the second action point of the second robotic arm;

[0085] Controlling the first robotic arm to move from the second action point of the first robotic arm to the preset installation position of the main wire, and determining the third action point of the first robotic arm; controlling the first robotic arm to push the lead wire into the position of the wire clamp bayonet of the wire clamp;

[0086] Controlling the second robotic arm to release the wire clamp and close the lock of the wire clamp to fix the lead wire and the main wire in the position of the wire clamp bayonet; controlling the second robotic arm to move from the preset installation position of the main wire to the second reference point, and determining the third action point of the second robotic arm;

[0087] Controlling the first robotic arm to release the lead wire and move from the preset installation position of the main wire to the first reference point, and determining the fourth action point of the first robotic arm;

[0088] According to the sequence of the first action point, the second action point, the third action point and the fourth action point of the first robot arm and the first action point, the second action point and the third action point of the second robot arm, several action points of the robot are determined.

[0089] Specifically, when the robot arrives at the preset parking point, the end of the first robotic arm of the robot is controlled to move to / remain at the first reference point, and the end of the second robotic arm is controlled to move to / remain at the second reference point. After determining that the end of the first robotic arm is at the first reference point and the end of the second robotic arm is at the second reference point, the robot begins to simulate the movement posture of completing the grasping work at the preset parking point.

[0090] As one example, Figure 2 The scene before the robot operation is shown. The main line and the lead are in different positions, and the main line and the lead are set with their own installation points. The simulated robot controls the first mechanical arm to move from the first reference point to the installation point of the lead at the preset parking point, determines the first action point A1 of the first mechanical arm; controls the first mechanical arm to close the clamp at the A1 position to clamp the lead;

[0091] The robot controls the first mechanical arm to move from a first action point A1 of the first mechanical arm to a first reference point, and determines a second action point A2 of the first mechanical arm;

[0092] The robot controls the second mechanical arm to move from the second reference point to the position of the wire clamp, determines the first action point B1 of the second mechanical arm; controls the second mechanical arm to close the clamp at the B1 position to clamp the wire clamp;

[0093] The robot controls the second mechanical arm to move from the first action point B1 of the second mechanical arm to the preset installation position of the main line, so that the main line enters the position of the wire clamp bayonet of the wire clamp, and determines the second action point B2 of the second mechanical arm;

[0094] The robot controls the first mechanical arm to move from the second action point A2 of the first mechanical arm to the preset installation position of the main line, determines the third action point A3 of the first mechanical arm; controls the first mechanical arm to push the lead wire into the position of the wire clamp bayonet of the wire clamp;

[0095] The robot controls the second mechanical arm to release the wire clamp at position B2 and close the lock of the wire clamp to fix the lead wire and the main wire in the position of the wire clamp bayonet; controls the second mechanical arm to move from the preset installation position of the main wire to the second reference point, and determines the third action point B3 of the second mechanical arm;

[0096] The robot controls the first robotic arm to release the lead wire and move from the preset installation position of the main wire to the first reference point, determines the fourth action point A4 of the first robotic arm, and completes the grasping operation of the robot.

[0097] Among them, there are multiple cases for the sequence of action points A1 - A4 and action points B1 - B3. The sequence of each action point can be adjusted, and action points can be added or deleted, so that the robot can place the lead wire and the main wire into the position of the clip bayonet, and close the lock to fix the lead wire and the main wire in the position of the clip bayonet of the clip.

[0098] Exemplarily, the robot can change the sequence of action points from: A1 - A2 - A3 - B1 - B2 - B3 - A4; to: B1 - A1 - A2 - A3 - B2 - B3 - A4.

[0099] Among them, the actions of the first robotic arm and the second robotic arm can also be performed simultaneously. For example, the robot can simultaneously execute the actions corresponding to action points A1 - A2 - A3 and action point B1. That is, the robot can control the first robotic arm to move from the first reference point to A1. The action corresponding to A1 is to close the gripper to clamp the lead wire, move from A1 to A2, move from A2 to A3. The action corresponding to A3 is to push the lead wire into the position of the clip bayonet of the clip. At the same time, the robot controls the second robotic arm to move from the second reference point to B1. The action corresponding to B1 is to close the gripper to clamp the clip. The robot can also simultaneously execute the actions corresponding to action points B3 and A4, that is, simultaneously control the first robotic arm and the second robotic arm to move from the preset installation position of the main wire to their respective reference points. That is, the robot can execute corresponding actions according to the action path generated by action points A1 - A2 - A3, and at the same time can execute corresponding actions according to the action path generated by action point B1.

[0100] Exemplarily, the robot can also delete action points. For example, delete the inoperative action point A2. After deletion, the robot controls the first robotic arm to move from the first reference point to A1. The action corresponding to A1 is to close the gripper to clamp the lead wire, move from A1 to A3. The action corresponding to A3 is to push the lead wire into the position of the clip bayonet of the clip.

[0101] Figure 3 It shows the scene after the robot's operation, using the clip to fix the installation points of the main wire and the lead wire together.

[0102] The operation control method of the robot provided by the present invention can store corresponding target points according to the tasks in different scenarios, realizing the standardized management of operation tasks. When the operation robot needs to perform an operation on one of the tasks in the current scenario, the robot imports the corresponding task file, and then can generate the driving path and the corresponding action path in the current scenario, realizing the automatic generation of the task path and task actions, as well as the automatic operation of the robot, improving the operation efficiency of the robot.

[0103] Embodiment 2 Figure 4 shows a schematic structural diagram of an embodiment of the operation control device of the robot provided by the present invention; as Figure 4 shown, the device 400 includes: a matching module 410, an optimization module 420, a planning module 430, and a control module 440.

[0104] The matching module 410 is used to scan the point cloud map of the target scenario in real time, perform pairing calculation on the source point cloud in the point cloud map and the preset point cloud to obtain the target point cloud;

[0105] Among them, the preset point cloud includes the three-dimensional coordinate points of several preset position points, and the three-dimensional coordinate points of each preset position point are obtained by measuring and recording the preset position points of the preset operation scenario using radar equipment; the preset position points include: preset parking points and corresponding preset action points; the target point cloud includes: the position information of the mapping points of each preset position point in the preset point cloud in the point cloud map;

[0106] The optimization module 420 is used to optimize the position information of each mapping point in the target point cloud to obtain the coordinate information corresponding to each mapping point; the coordinate information corresponding to the mapping point includes: the coordinate information of the target parking point and the coordinate information of the position of the target action point corresponding to the target parking point;

[0107] The planning module 430 is used to calculate the driving path of the robot in the target scenario according to the current position point of the robot and the coordinate information of the target parking point; calculate the action path of the robot at the position of the target parking point according to the coordinate information of the target action point corresponding to the target parking point;

[0108] The control module 440 is used to drive according to the driving path, and stop at the target parking point and complete the grasping work at the target parking point according to the action path at the target parking point.

[0109] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, refer to the partial description of the method embodiment.

[0110] Embodiment 3 Figure 5The figure shows a schematic structural diagram of an embodiment of an operation control device of a robot provided by the present invention. The specific embodiments of the present invention do not limit the specific implementation of the operation control device of the robot.

[0111] As Figure 5 shown, the operation control device of the robot may include: a processor 502, a communication interface 504, a memory 506, and a communication bus 508.

[0112] Among them: The processor 502, the communication interface 504, and the memory 506 complete mutual communication through the communication bus 508. The communication interface 504 is used to communicate with network elements of other devices such as clients or other servers. The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned embodiment of the operation control method for the robot.

[0113] Specifically, the program 510 may include program code, and the program code includes computer-executable instructions.

[0114] The processor 502 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the operation control device of the robot may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0115] The memory 506 is used to store the program 510. The memory 506 may include a high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0116] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. In addition, the embodiments of the present invention are not directed to any particular programming language.

[0117] In the description provided herein, numerous specific details are set forth. It will be understood, however, that embodiments of the invention may be practiced without these specific details. Similarly, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together in a single embodiment, figure, or description thereof. Among them, the claims following the specific implementation manners are hereby expressly incorporated into the specific implementation manners, where each claim itself serves as a separate embodiment of the present invention.

[0118] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive.

[0119] It should be noted that the above embodiments illustrate the present invention rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A robot operation control method, characterized in that: The method comprises: Scanning a point cloud image of a target scene in real time, performing pairing calculation on a source point cloud in the point cloud image and a preset point cloud to obtain a target point cloud; Wherein, the preset point cloud includes three-dimensional coordinate points of a plurality of preset position points; the preset position points include: preset parking points and corresponding preset action points; the target point cloud includes: position information of mapping points of each of the preset position points in the preset point cloud in the point cloud map; Optimizing the position information of each of the mapping points in the target point cloud to obtain coordinate information corresponding to each of the mapping points; the coordinate information corresponding to the mapping points includes: coordinate information of the target parking point and coordinate information of the target action point position corresponding to the target parking point; Calculate the driving path of the robot in the target scene according to the coordinate information of the current position of the robot and the target parking point; calculate the action path of the robot at the target parking point according to the coordinate information of the target action point corresponding to the target parking point; The vehicle travels along the driving path, wherein the vehicle stops at the target parking point and a grasping operation at the target parking point is completed according to an action path at the target parking point.

2. The robot operation control method according to claim 1, characterized in that: Pairing and calculating the source point cloud in the point cloud image with the preset point cloud to obtain the target point cloud includes: By using a nearest neighbor search algorithm, the source point cloud and the preset point cloud in the point cloud image are paired and calculated, and the target point closest to each of the preset position points is determined in the source point cloud; Using a preset spatial transformation algorithm, at least one spatial transformation operation is performed on the source point cloud in the point cloud image to obtain a spatially transformed source point cloud and a spatially transformed target point; The target points after spatial transformation are used as mapping points of the preset position points in the point cloud image to obtain a target point cloud.

3. The robot operation control method according to claim 2, characterized in that: Using a preset spatial transformation algorithm, at least one spatial transformation operation is performed on the source point cloud in the point cloud image to obtain a spatially transformed source point cloud and a spatially transformed target point, including: Using a preset spatial transformation algorithm, at least one spatial transformation operation is performed on the source point cloud in the point cloud map, and the spatial transformation parameters in the preset spatial transformation algorithm are iteratively adjusted so that the average distance between the target point after spatial transformation and the corresponding preset position points is less than a preset threshold, or the number of iterations reaches an upper limit.

4. The robot operation control method according to claim 1, characterized in that: Optimizing the position information of each of the mapping points in the target point cloud to obtain coordinate information corresponding to each of the mapping points includes: Constructing a cubic frame of a preset size centered on each of the mapping points in the point cloud image; extracting point cloud data in each of the cubic frames; The point cloud data in the target cube frame is processed by the least square method to determine the wire of the target mapping point; the coordinate point and the corresponding vector direction of the target mapping point are obtained according to the wire of the target mapping point; wherein the target cube frame is a cube frame corresponding to the target mapping point, and the target mapping point is any mapping point; The coordinate point and the corresponding vector direction of each mapping point are used as the coordinate information corresponding to each mapping point.

5. The robot operation control method according to claim 1, characterized in that: Use radar equipment to measure and record the preset location points of the preset operation scene, including: Establishing a corresponding three-dimensional model for a work point in a preset work scene, and determining at least one preset parking point in the three-dimensional model; The action posture of the robot completing the grasping work at the preset parking point is simulated, and several preset action points corresponding to the robot at the preset parking point are determined; the preset action points include: a left arm action point and a right arm action point; each of the action points is set in a sequence.

6. The robot operation control method according to claim 5, characterized in that: The preset operation scene at least includes: a lead wire, a main wire and a wire clamp with a lock, wherein the wire clamp is used to fix the lead wire and the main wire in the position of the wire clamp bayonet by using the lock; The robot comprises: a first mechanical arm with a gripper and a second mechanical arm with a gripper; The first mechanical arm is the left arm of the robot, and the second mechanical arm is the right arm of the robot, or the first mechanical arm is the right arm of the robot, and the second mechanical arm is the left arm of the robot.

7. The robot operation control method according to claim 5 or 6, characterized in that: Simulating the action posture of the robot completing the grasping work at the preset parking point, and determining a number of preset action points corresponding to the robot at the preset parking point, including: Setting a first reference point of the first robotic arm and a second reference point of the second robotic arm; Simulating the robot controlling the first mechanical arm to move from the first reference point to the preset installation position of the lead at the preset parking point, determining the first action point of the first mechanical arm; controlling the clamping claw of the first mechanical arm to close to clamp the lead; Controlling the first mechanical arm to move from a first action point of the first mechanical arm to a first reference point, and determining a second action point of the first mechanical arm; Control the second mechanical arm to move from the second reference point to the position of the wire clamp, and determine the first action point of the second mechanical arm; control the clamping claw of the second mechanical arm to close to clamp the wire clamp; Control the second mechanical arm to move from the first action point of the second mechanical arm to the preset installation position of the main line, so that the main line enters the position of the wire clamp bayonet of the wire clamp, and determine the second action point of the second mechanical arm; Control the first mechanical arm to move from the second action point of the first mechanical arm to the preset installation position of the main line, and determine the third action point of the first mechanical arm; control the first mechanical arm to push the lead wire into the position of the wire clamp bayonet of the wire clamp; Control the second mechanical arm to release the wire clamp and close the lock of the wire clamp to fix the lead wire and the main wire in the position of the wire clamp bayonet; control the second mechanical arm to move from the preset installation position of the main wire to the second reference point, and determine the third action point of the second mechanical arm; Controlling the first mechanical arm to release the lead wire and move from a preset installation position of the main wire to a first reference point, and determining a fourth action point of the first mechanical arm; According to the sequence of the first action point, the second action point, the third action point and the fourth action point of the first robot arm and the first action point, the second action point and the third action point of the second robot arm, several action points of the robot are determined.

8. A robot operation control device, characterized in that: The device is used to perform the operation of the robot operation control method according to any one of claims 1 to 6, wherein the device comprises: a matching module, an optimization module, a planning module and a control module; A matching module is used to scan a point cloud image of a target scene in real time, and perform pairing calculations on a source point cloud in the point cloud image and a preset point cloud to obtain a target point cloud; Wherein, the preset point cloud includes three-dimensional coordinate points of a plurality of preset position points; the preset position points include: preset parking points and corresponding preset action points; the target point cloud includes: position information of mapping points of each of the preset position points in the preset point cloud in the point cloud map; An optimization module, used to optimize the position information of each mapping point in the target point cloud to obtain coordinate information corresponding to each mapping point; the coordinate information corresponding to the mapping point includes: coordinate information of the target parking point and coordinate information of the target action point position corresponding to the target parking point; A planning module, for calculating the driving path of the robot in the target scene according to the current position of the robot and the coordinate information of the target parking point; and calculating the action path of the robot at the target parking point according to the coordinate information of the target action point corresponding to the target parking point; A control module is used for driving according to the driving path, wherein the vehicle stops at the target parking point and completes the grabbing work at the target parking point according to the action path at the target parking point.

9. A robot, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of the robot operation control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction, and when the executable instruction is executed on the robot's operation control device / robot, the robot's operation control device / robot performs the operation of the robot's operation control method as described in any one of claims 1-7.

Images