Robot working area coverage status processing method and apparatus

By determining the loop of the work area in the target map and expanding it, and setting different values ​​in the grid, the problem of not being able to count the number of times the same area is covered in the existing technology is solved, and real-time statistics of the number of times and coverage rate of the robot's work area are realized.

WO2026237326A1PCT designated stage Publication Date: 2026-11-19FIBOCOM WIRELESS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2025/138481
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-16
Filing Date
2025-11-28
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Current technology can only count the coverage rate of tasks performed by robots, but cannot count the number of times the same area is covered.

Method used

By determining the loop of the work area in the target map based on the edge ground truth, and expanding the loop in the target map based on the robot's width, different values ​​are set in the grid inside and outside the edge, and the robot's coverage data is replayed to determine the coverage.

Benefits of technology

It enables real-time statistics on the number of times and coverage rate of the robot's operating area, providing more comprehensive coverage data support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025138481_19112026_PF_FP_ABST
    Figure CN2025138481_19112026_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed are a robot working area coverage status processing method and apparatus. The method comprises: determining a loop of a working area in a target map on the basis of a boundary ground truth, and dilating the loop in the target map on the basis of a width of a robot to obtain a boundary of the working area, wherein the boundary ground truth comprises real-time dynamic data generated by the robot operating along the boundary of the target map; setting different values in grid cells located inside the boundary and outside the boundary, respectively; and replaying coverage data of the robot within the working area, and determining a coverage status of the working area on the basis of current values in the grid cells within the working area, wherein the coverage data comprises a trajectory of the robot performing a task within the working area and a value indicative of a number of times the robot passes through a current grid cell while performing the task, and the coverage status comprises a traversal count for the grid cells within the working area and a coverage rate of the working area.
Need to check novelty before this filing date? Find Prior Art

Description

Methods and devices for handling robot operation area coverage issues

[0001] Citation of relevant applications

[0002] This disclosure claims the full benefits of Chinese invention patent application No. 202510643423.3, filed on May 16, 2025 with the State Intellectual Property Office of the People's Republic of China, entitled "Method and Apparatus for Processing Coverage of Robot Operating Area", the entire contents of which are incorporated herein by reference.

[0003] field

[0004] This disclosure generally relates to the field of robotics, and more specifically to methods and apparatus for processing the coverage of robot operating areas.

[0005] background

[0006] The method for determining the coverage rate during robot task execution is as follows: after fixing the coordinates, the robot's position changes are captured by a fixed imaging device, converted into a robot trajectory, and then the robot coverage rate is calculated. It is evident that existing technologies can only determine the coverage rate of the robot's task execution, but cannot count the number of times the robot covers the same area.

[0007] Overview

[0008] Firstly, this disclosure provides a method for processing the coverage of a robot's operating area, which includes:

[0009] The loop of the work area is determined in the target map based on the edge ground truth, and the loop is expanded in the target map based on the robot's width to obtain the edge of the work area. The edge ground truth includes real-time dynamic data generated by the robot running along the edge of the target map.

[0010] Different values ​​are set for the grid cells inside and outside the edge, respectively; and

[0011] The robot's coverage data is replayed in the work area, and the coverage status of the work area is determined based on the current values ​​in the grids of the work area. The coverage data includes the trajectory of the robot performing the task in the work area and a value representing the number of times the robot passes through the current grid during the task. The coverage status includes the number of times the grids in the work area are covered and the coverage rate of the work area.

[0012] Secondly, this disclosure provides a processing device for determining the coverage of a robot's operating area, comprising:

[0013] The first processing module is configured to determine the loop of the work area in the target map based on the edge ground truth, and to expand the loop in the target map based on the robot's width to obtain the edge of the work area, wherein the edge ground truth includes real-time dynamic data generated by the robot running along the edge of the target map;

[0014] The setting module is configured to set different values ​​in the grid cells inside and outside the edge; and

[0015] The second processing module is configured to replay the robot's coverage data in the work area and determine the coverage status of the work area based on the current values ​​in the grids of the work area. The coverage data includes the trajectory of the robot performing a task in the work area and a value representing the number of times the robot passes through the current grid during the task. The coverage status includes the number of times the grids in the work area are covered and the coverage rate of the work area.

[0016] Thirdly, this disclosure provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute the processing method for determining the robot's work area coverage as described in this disclosure.

[0017] Fourthly, this disclosure provides a computer storage medium storing computer-executable instructions for executing the robot operation area coverage processing method described in this disclosure.

[0018] In some implementation schemes, after simulating the robot's work area and trajectory, the coverage data can be replayed to determine the coverage rate of the work area and the number of times the grid is covered after one or more operations based on the values ​​within the grid. This provides more comprehensive coverage data support and solves the technical problem in related technologies that can only count the coverage rate during the robot's task execution process, but cannot count the number of times the same area is covered.

[0019] Brief description of the attached figures

[0020] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0021] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0022] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0023] Figure 1 is a flowchart of a method for processing robot operation area coverage according to an embodiment of this disclosure;

[0024] Figure 2 is an optional flowchart of a method for processing the coverage of a robot's working area according to an embodiment of this disclosure;

[0025] Figure 3 is a flowchart of a coverage task robot coverage rate statistics method provided in an embodiment of this disclosure;

[0026] Figure 4 is a schematic diagram of coverage statistics simulation of a coverage task robot provided in an embodiment of this disclosure;

[0027] Figure 5 is a schematic diagram of the structure of a processing device for robot operation area coverage provided in an embodiment of this disclosure; and

[0028] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure.

[0029] Detailed Explanation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0031] The following disclosure provides numerous different embodiments or examples for implementing various structures of this disclosure. To simplify this disclosure, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the scope of this disclosure. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0032] To address the technical problem in related technologies that can only calculate the coverage rate during robot task execution but cannot calculate the number of times the same area is covered, this disclosure provides a method for processing the coverage of the robot's work area, as shown in Figure 1. The steps of this method include:

[0033] Step 101: Determine the loop of the work area in the target map based on the edge ground truth, and expand the loop in the target map based on the robot's width to obtain the edge of the work area. The edge ground truth includes real-time dynamic data generated by the robot running along the edge of the target map.

[0034] Step 102: Set different values ​​for the grid cells inside and outside the edges; and

[0035] Step 103: Replay the robot's coverage data in the work area and determine the coverage of the work area based on the current values ​​in the grids in the work area. The coverage data includes the robot's trajectory in the work area and the value used to characterize the number of times the robot passes through the current grid during the task execution. The coverage includes the number of times the grids in the work area are covered and the coverage rate of the work area.

[0036] In some implementations, the target map is a simulated map corresponding to the area where the robot actually needs to work, while the edge ground truth is the real-time dynamic data generated by the robot running along the edges of the actual work area. Therefore, determining the loop of the work area in the target map based on the edge ground truth means simulating the real-time dynamic data onto the target map to determine the loop that runs along the edge of the target map. The area enclosed by this loop is the robot's work area in the target map. Since the robot itself has a certain width, in order to determine a work area in the target map that more closely matches the actual work area, the loop in the target map needs to be expanded. The expanded edge then matches the edge of the actual work area.

[0037] In some implementations, since the target map is divided into multiple grids, after the edges are simulated, corresponding values ​​can be set within the grids to distinguish whether the grid is inside or outside the edge; that is, different values ​​can be used to distinguish between robot working areas and non-working areas.

[0038] In some implementations, taking a robot performing a lawnmowing task as an example, the value of each grid cell in the work area is 0 before the robot begins mowing. Each time the robot passes a grid cell, the value increases by 0.01. For example, if the robot passes the same grid cell 10 times during the mowing task, the value of that grid cell changes from 0 to 0.1, meaning the number of times the robot has covered that grid cell can be directly determined from the grid cell value. Similarly, for non-zero values ​​in a grid cell, it indicates that the robot has already passed through that grid cell and performed the mowing task, meaning that the grid cell has been covered. Therefore, by counting the number of grid cells with non-zero values ​​and the number of grid cells with zero values ​​in the original work area, the ratio of the two can be used to determine the coverage rate of the robot during the mowing task.

[0039] Through steps 101 to 103 above, the loop of the work area is determined in the target map based on the edge ground truth, and the loop is expanded in the target map based on the robot's width to obtain the edge of the work area. Then, different values ​​are set in the grid cells inside and outside the edge. Finally, the robot's coverage data is replayed in the work area, and the coverage of the work area is determined based on the current values ​​in the grid cells within the work area. It can be seen that, in this embodiment of the disclosure, after simulating the robot's work area and trajectory, by replaying the coverage data, the coverage rate of the work area and the number of times the grid cells are covered after one or more operations can be determined based on the values ​​in the grid cells. This provides more comprehensive data support for coverage, solving the technical problem in the prior art that can only count the coverage rate during the robot's task execution process, but cannot count the number of times the same area is covered.

[0040] In some implementations, to distinguish between the robot's work area and non-work area, corresponding numbers can be set in the grid cells of the target map to differentiate them. For example, the grid cells for the work area can be set to 0, and the grid cells for the non-work area can be set to 0.5; other numbers can also be used, as long as they can distinguish between the work area and the non-work area. Based on this, the method of setting different values ​​in the grid cells inside and outside the edge involved in step 102 above can further include:

[0041] Step 11: Set a first number in the grid of the work area of ​​the target map, and set a second number in the grid of the non-work area of ​​the target map, wherein the first number and the second number are different.

[0042] In some implementation schemes, by setting different numbers, the working area and the non-working area can be distinguished relatively easily, so that the coverage rate and the number of times the robot performs tasks can be easily and quickly calculated.

[0043] In some implementations, the method of replaying the robot's coverage data in the work area involved in step 103 above may further include: simulating the robot's work trajectory in the work area based on time sequence, and incrementing the value in the current grid by one unit each time the same grid is passed, so that the value of the current grid is a third number.

[0044] In some implementations, the initial value of a grid cell in the current work area is 0 (the first number). When the robot performs a task and passes through the grid, the value of the grid increases by one unit, such as 0.01, so the value of the grid at this time is 0.01 (the third number). If the robot passes through the grid four more times during subsequent task execution, the value of the grid at this time is 0.05 (the third number). Therefore, it is clear that the number of times a grid has been covered can be conveniently and quickly determined directly from its value.

[0045] In some implementations, to more directly determine the coverage rate and number of times the robot covers the area during operation, corresponding values ​​can be set in the grid cells of the simulated work area. When the robot is not working, the value in the grid cell is 0. After the robot starts working, the value of the grid cell it passes through increases by one unit. This one unit can be set according to actual needs, such as 0.01 or 0.1. Based on this, the method of determining the coverage of the work area based on the current value in the grid cells of the work area mentioned in step 103 above can further include:

[0046] Step 21: Obtain the current value of each grid cell in the current work area, and determine the number of times the grid cell is covered based on the current value. Each time the robot passes through a grid cell during the task execution, the value within that grid cell increases by one unit.

[0047] Step 22: Obtain the number of target grid cells whose values ​​have changed in the work area, and determine the coverage rate as the ratio of the number of target grid cells to the total number of grid cells in the work area.

[0048] In some implementations, taking robotic lawn mowing as an example, the number in a grid increases by 0.01 each time it passes through it. For instance, if the value in a grid changes from 0 to 0.1, it means the robot has passed through that grid 10 times during the mowing process. Therefore, the coverage count of the current grid can be directly determined from the value in the grid. Furthermore, when calculating coverage, the number of grids with a value of 0 before the task begins can be counted first. Then, during the mowing task, the number of non-zero grids in the work area can be counted at any time. The ratio of the number of non-zero grids to the number of grids with a value of 0 at the initial moment is determined as the coverage rate. Therefore, in this embodiment, the current coverage rate and coverage count can be calculated in real time.

[0049] In some implementations, the robot parameters during the simulation process can be optimized to improve the coverage of tasks performed by the robot. Based on this, as shown in Figure 2, the method further includes:

[0050] Step 201: Determine the parameters to be optimized associated with the robot, and construct the solution vector in the solution space based on the parameters to be optimized;

[0051] Step 202: Simulation optimization of the solution vectors in the solution space is performed based on the particle swarm optimization algorithm to obtain the optimized parameters; and

[0052] Step 203: Optimize the robot's parameters based on the optimized parameters.

[0053] In some implementations, step 201 may further include: determining the parameters to be optimized as target parameters, wherein the target parameters are the range of backward distance when the robot encounters an obstacle during the execution of the task, and the range of rotation angle adjustment when encountering an obstacle; constructing a corresponding two-dimensional vector based on the backward distance range and the rotation angle adjustment range to obtain the solution vector.

[0054] In some implementations, the parameters to be optimized can be the robot's backward distance (x meters) and rotation angle (y degrees) each time it encounters an obstacle. Specifically, the backward distance (x) has a preset range of 0.2 to 1.5 meters. It should be noted that if the backward distance is too small, secondary collisions are likely, while if it is too large, the path is wasted. The rotation angle (y) has a preset range of 30° to 150°. It should be noted that if the rotation angle is too small, the steering will be insufficient, while if it is too large, the path will be circuitous.

[0055] Based on this, the parameters are combined into a vector XX = [x, y], where each particle represents a set of possible parameter configurations. For example, XX = [0.5m, 90°] means that the robot moves back 0.5 meters after encountering an obstacle and then rotates 90°.

[0056] In some implementations, for tasks whose coverage and number of executions are determined through simulation, the robot's parameters can be further optimized using a particle swarm optimization algorithm to improve the robot's task coverage. For example, if the parameter to be optimized is the random sampling angle range for each execution, such as the original angle range of [10°, 140°], a more suitable angle range can be found within this range to improve the robot's working efficiency.

[0057] In some implementations, the method of simulating and optimizing the solution vectors in the solution space based on the particle swarm optimization algorithm to obtain optimized parameters, as mentioned in step 202 above, may further include:

[0058] Step 31: Initialize the solution vectors in the solution space with particles to obtain a particle swarm;

[0059] Step 32: Input the particles in the particle swarm into the simulation system in sequence to obtain the output result of each particle;

[0060] Step 33: Determine the fitness of the output result based on the preset evaluation function, and update the particles in the particle swarm based on the fitness; and

[0061] Step 34: Input the updated particle swarm back into the simulation system until the optimal result is output. Determine the optimized parameters based on the optimal result. The optimal result represents the highest coverage of the robot's task execution based on the updated particles.

[0062] In some implementations, the parameters to be optimized are the backtracking distance and the rotation angle, with the backtracking distance having a preset range of 0.2 to 1.5 meters and the rotation angle (y) having a preset range of 30° to 150°. Based on this, the resulting solution vector can be any combination of the backtracking distance and the rotation angle, such as [0.5m, 90°], [0.3m, 80°], [0.6m, 100°], etc. Multiple particles are randomly generated based on the solution vector in the solution space, such as 100 particles, for example, particle 1: 0.3, 60°, particle 2: 0.8, 120°, etc.

[0063] In some implementations, the simulation system can use the ISAAC, SIM simulation platform. Specifically, the following steps can be taken: first, import the vehicle model parameters (USD / USDA), import the environment parameters (YSD / USDA), and import the robot code (ROS2 motion control code). Then, start the simulation, record the ROS2bag data packet (truth data packet), and finally provide the ROS2bag data packet to the simulation system. The simulation system then outputs the coverage rate and the number of coverage iterations.

[0064] In some implementations, the evaluation function refers to a function that determines fitness based on evaluation metrics. Specifically, the evaluation metric can be obstacle avoidance success rate, i.e., the number of times obstacles are successfully avoided divided by the total number of tests. The evaluation metric can also be task execution efficiency, i.e., the time or path length to complete the task. In some implementations, particle 1 has 2 collisions, takes 45 seconds, and has a path tortuosity of 1.8, so its fitness is 0.194. Particle 2 has 0 collisions, takes 52 seconds, and has a path tortuosity of 1.5, so its fitness is 0.213. It is evident that particle 2 has a higher fitness than particle 1, meaning that the robot performs better in task execution based on the output results after particle 2 is input into the simulation system compared to the output results after particle 1 is input.

[0065] In some implementations, the final optimal output can be the result obtained after a preset number of iterations has been met, selecting the best result from all iterations. For example, if the preset number of iterations is 1000, the optimal result is selected after 1000 iterations. Alternatively, the simulation system may not limit the number of iterations; after a certain number of iterations, the simulation system converges to the optimal result, meaning that further iterations will not yield a better result than previous ones.

[0066] The present disclosure will now be explained in detail with reference to a specific embodiment of this invention. This specific embodiment provides a method for statistical analysis and simulation optimization of coverage rate of a coverage task robot. In this method, a real-time dynamic module is bound to the robot as a true value for statistical analysis (a positioning true value system is connected above the cutter head). The coverage rate of a lawnmower without global positioning is statistically analyzed. As shown in Figure 3, the specific steps include:

[0067] Step 301: The robot runs along the edge (close to the edge of the map) once to obtain real-time kinematic (RTK) data along the edge;

[0068] Step 302: The robot performs several coverage operations to acquire coverage RTK data;

[0069] Step 303: Target map generation, specifically, the target map is represented as a raster map;

[0070] All data points obtained from the robot's edge movement are used to form a loop to generate a map (points inside the edge are filled with 0 as inner grid points, and grid points outside the edge are filled with 0.5 as outer grid points), and the map is expanded by 0.25 meters to generate the map's true edge;

[0071] Step 304: After generating the overlay map, obtain the robot's edge trajectory, and increment the original value by 0.01 for all grid cells (greater than or equal to 0 and less than 0.4) below the trajectory point in the range [0.2, 0.2] (depending on the cutter head width); and

[0072] Step 305: Count the total number of grid cells with a value greater than 0 and less than 0.4, multiply the area represented by each grid cell to obtain the robot's edge coverage rate.

[0073] The specific simulation is shown in Figure 4. The upper part shows the simulation results of the map and the results of simulating the coverage data onto the map. The lower part shows the coverage data after the robot has run for 250 seconds and the coverage data after the robot has run for 5000 seconds.

[0074] As described in steps 301 to 305 above, the pose truth packet can be played back or recorded in real time through a truth system to obtain the required edge data and coverage data. Then, the robot width and position width are imported into the system, the edge data is used to generate a target map loop, and the map loop is expanded (robot half-width) to form map edge data. Finally, the coverage data is replayed in the map, and the coverage results are statistically analyzed, i.e., the coverage rate and number of coverages are confirmed using the value of each grid cell in the map. It is evident that this embodiment supports real-time statistics or statistics via replay, offering flexibility and low system resource consumption. Furthermore, it can replay the entire robot movement process, facilitating troubleshooting and analysis. In addition, it can statistically analyze one or more coverage instances, providing more comprehensive data support.

[0075] In some implementations, simulation can also be used to optimize machine parameters. First, map data and vehicle data are generated using a random map generation system, and then imported into a coverage system and a physical simulation system. Next, all parameters to be optimized are fed into the particle swarm optimization (PSO) algorithm, given a data range, and then the PSO algorithm iterative optimization process is initiated. Finally, the optimization status and coverage results during the iterations are obtained. Specifically, taking the optimization objective as a randomly sampled angle interval for each iteration as an example, for instance, the original input is [10°, 140°]. First, a simulation map is generated, then the inverted map is imported into the simulation system. Finally, the PSO algorithm is run, giving the robot sampling interval [x, y] to the robot system. The simulation is run, allowing the robot to operate in the simulation environment, obtaining the machine's 12-hour coverage. This data is used as an evaluation function to feed back to the PSO algorithm to evaluate the current parameters, generate new parameters, and continue running. This process is repeated X times until the system converges. After X iterations and when the coverage stabilizes, the robot inputs the final optimal parameters.

[0076] Corresponding to Figure 1 above, this disclosure also provides a processing device for the coverage of the robot's working area, as shown in Figure 5. This device includes:

[0077] The first processing module 502 is configured to determine the loop of the work area in the target map based on the edge ground truth, and to expand the loop in the target map based on the robot's width to obtain the edge of the work area. The edge ground truth includes real-time dynamic data generated by the robot running along the edge of the target map.

[0078] Module 504 is configured to set different values ​​for grid cells inside and outside the edges; and

[0079] The second processing module 506 is configured to replay the robot's coverage data in the work area and determine the coverage of the work area based on the current value in the grid in the work area. The coverage data includes the robot's trajectory in the work area and the value used to characterize the number of times the robot passes through the current grid during the task execution. The coverage includes the number of times the grid in the work area is covered and the coverage rate of the work area.

[0080] In some implementations, a loop of the work area is determined in the target map based on edge ground truth, and the loop is expanded in the target map based on the robot's width to obtain the edge of the work area. Different values ​​are then set in the grid cells inside and outside the edge. Finally, the robot's coverage data is replayed in the work area, and the coverage of the work area is determined based on the current values ​​in the grid cells within the work area. Therefore, in this embodiment, after simulating the robot's work area and trajectory, by replaying the coverage data, the coverage rate of the work area and the number of times the grid cells are covered after one or more operations can be determined based on the values ​​in the grid cells. This provides more comprehensive coverage data support and solves the technical problem in the prior art that it can only count the coverage rate during the robot's task execution, but cannot count the number of times the same area is covered.

[0081] In some implementations, the second processing module may further include:

[0082] The first processing unit is configured to acquire the current value of a grid cell in the current work area and determine the number of times the grid cell is covered based on the current value. Specifically, each time the robot passes through a grid cell during task execution, the value within that grid cell increases by one unit.

[0083] The second processing unit is configured to obtain the number of target rasters whose values ​​have changed in the work area, and to determine the coverage rate as the ratio of the number of target rasters to the total number of rasters in the work area.

[0084] In some implementations, the setting module may further include:

[0085] The setting unit is configured to set a first number in the grid of the working area of ​​the target map and a second number in the grid of the non-working area of ​​the target map, wherein the first number and the second number are different.

[0086] In some implementations, the second processing module may further include:

[0087] The third processing unit is configured to simulate the robot's work trajectory in the work area based on time sequence, and to increment the value in the current grid by one unit each time it passes through the same grid, so as to obtain the value of the current grid as the third number.

[0088] In some implementations, the device for processing the coverage of the robot's operating area also includes:

[0089] The third processing module is configured to determine the parameters to be optimized associated with the robot and construct solution vectors in the solution space based on the parameters to be optimized.

[0090] The simulation module is configured to perform simulation optimization on the solution vectors in the solution space based on the particle swarm optimization algorithm to obtain optimized parameters; and

[0091] The optimization module is configured to optimize the robot's parameters based on the optimized parameters.

[0092] In some implementations, the simulation module includes:

[0093] The initialization unit is configured to initialize the solution vectors in the solution space with particles to obtain a particle swarm.

[0094] The simulation unit is configured to input the particles in the particle swarm into the simulation system sequentially and obtain the output result of each particle.

[0095] The fourth processing unit is configured to determine the fitness of the output result based on a preset evaluation function, and update the particles in the particle swarm based on the fitness; and

[0096] The fifth processing unit is configured to input the updated particle swarm back into the simulation system until the optimal result is output, and to determine the optimized parameters based on the optimal result. The optimal result represents the highest coverage of the robot's task execution based on the updated particles.

[0097] In some implementations, the third processing module includes:

[0098] The unit is configured to determine the parameters to be optimized as target parameters, where the target parameters are the robot's backward distance range when encountering obstacles during task execution, and the range of rotation angle adjustment when encountering obstacles; and

[0099] The construction unit is configured to build a corresponding two-dimensional vector based on the range of backward distance and the range of rotation angle adjustment, so as to obtain the solution vector.

[0100] As shown in Figure 6, one embodiment of this disclosure provides an electronic device, which includes a processor 611, a communication interface 612, a memory 613, and a communication bus 614. The processor 611, communication interface 612, and memory 613 communicate with each other via the communication bus 614.

[0101] The memory 613 is configured to store computer programs;

[0102] When the processor 611 is configured to execute the program stored in the memory 613, it implements the method for processing the coverage of the robot's working area as described in this disclosure.

[0103] An embodiment of this disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for processing the robot's work area coverage as described in this disclosure.

[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0105] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0106] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0107] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for handling robot operating area coverage issues, including: The loop of the work area is determined in the target map based on the edge ground truth, and the loop is expanded in the target map based on the robot's width to obtain the edge of the work area. The edge ground truth includes real-time dynamic data generated by the robot running along the edge of the target map. Different values ​​are set for the grid cells inside and outside the edge, respectively; and The robot's coverage data is replayed in the work area, and the coverage status of the work area is determined based on the current values ​​in the grids of the work area. The coverage data includes the trajectory of the robot performing the task in the work area and a value representing the number of times the robot passes through the current grid during the task. The coverage status includes the number of times the grids in the work area are covered and the coverage rate of the work area.

2. The method for processing robot work area coverage as described in claim 1, wherein determining the coverage of the work area based on the current value within a grid in the work area includes: Obtain the current value of a grid cell in the work area at the current moment, and determine the number of times the grid cell is covered based on the current value, wherein the value of the grid cell increases by one unit each time the robot passes through it during the task execution; and The number of target grid cells whose values ​​change in the work area is obtained, and the ratio of the target number to the total number of grid cells in the work area is determined as the coverage rate.

3. The method for processing robot operation area coverage as described in claim 1 or 2, wherein different values ​​are set in the grid cells inside and outside the edge, including: A first number is set in the grid of the work area of ​​the target map, and a second number is set in the grid of the non-work area of ​​the target map, wherein the first number and the second number are different.

4. The method for processing robot work area coverage as described in any one of claims 1 to 3, wherein replaying the robot's coverage data in the work area includes: The robot's work trajectory is simulated in the work area based on time sequence, and the value in the current grid is increased by one unit each time it passes through the same grid, so that the value of the current grid is the third number.

5. The method for processing the robot's operating area coverage as described in any one of claims 1 to 4, further comprising: Determine the parameters to be optimized associated with the robot, and construct a solution vector in the solution space based on the parameters to be optimized; The solution vectors in the solution space are simulated and optimized based on the particle swarm optimization algorithm to obtain the optimized parameters; as well as The parameters of the robot are optimized based on the optimized parameters.

6. The method for processing robot operation area coverage as described in claim 5, wherein the optimized parameters are obtained by simulating and optimizing the solution vectors in the solution space based on the particle swarm optimization algorithm, including: The solution vectors in the solution space are initialized with particles to obtain a particle swarm; The particles in the particle swarm are input into the simulation system sequentially to obtain the output result of each particle. The fitness of the output result is determined based on a preset evaluation function, and the particles in the particle swarm are updated based on the fitness. as well as The updated particle swarm is input into the simulation system again until the optimal result is output. Based on the optimal result, the optimized parameters are determined, wherein the optimal result represents the highest coverage of the task performed by the robot based on the updated particles.

7. The method for processing robot operation area coverage as described in claim 5 or 6, wherein determining the parameters to be optimized associated with the robot and constructing a solution vector in the solution space based on the parameters to be optimized includes: The parameters to be optimized are determined as target parameters, wherein the target parameters are the range of backward movement distance when the robot encounters an obstacle during task execution, and the range of rotation angle adjustment when encountering an obstacle; and Based on the retraction distance range and the rotation angle adjustment range, a corresponding two-dimensional vector is constructed to obtain the solution vector.

8. A device for processing the coverage of the robot's operating area, comprising: The first processing module is configured to determine the loop of the work area in the target map based on the edge ground truth, and to expand the loop in the target map based on the robot's width to obtain the edge of the work area, wherein the edge ground truth includes real-time dynamic data generated by the robot running along the edge of the target map; The setting module is configured to set different values ​​in the grid cells inside and outside the edge, respectively; and The second processing module is configured to replay the robot's coverage data in the work area and determine the coverage status of the work area based on the current values ​​in the grids of the work area. The coverage data includes the trajectory of the robot performing a task in the work area and a value representing the number of times the robot passes through the current grid during the task. The coverage status includes the number of times the grids in the work area are covered and the coverage rate of the work area.

9. An electronic device comprising: At least one communication interface; At least one bus connected to the at least one communication interface; At least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to execute the processing method for the robot working area coverage as described in any one of claims 1 to 7.

10. A computer storage medium storing computer-executable instructions for performing the robot operation area coverage processing method according to any one of claims 1 to 7.