Testing Method, System and Related Devices for Floor Sweeping Robot

Abstract

The present application discloses a testing method, system and related device for a floor cleaning robot. The testing method for the floor cleaning robot is applied to a target testing system, and the target testing system includes a target acquisition device arranged in a testing scenario. The method includes: obtaining the actual running trajectory of the floor cleaning robot in the testing scenario by using the target acquisition device; obtaining the index information of the floor cleaning robot during the running process based on the actual running trajectory; wherein, the index information is determined based on the cleaning area of the floor cleaning robot, the actual position information of the obstacles in the testing scenario and the position deviation, and the position deviation is determined based on the actual running trajectory and the target running trajectory under the perspective of the floor cleaning robot; obtaining the test result corresponding to the floor cleaning robot based on the index information. By the above method, the present application can improve the efficiency of testing the floor cleaning robot.

Description

Technical Field

[0001] This application relates to the technical field of floor cleaning robots, in particular to a testing method, system and related devices for floor cleaning robots. Background Art

[0002] With the continuous development of the floor cleaning robot industry, floor cleaning robots are currently widely used in household life. As the application of floor cleaning robots becomes more and more extensive, all aspects of the performance of floor cleaning robots have attracted wide attention. At present, the main testing method for floor cleaning robots is to observe the working state of the floor cleaning robot by relevant technical personnel, so as to systematically evaluate the performance of the floor cleaning robot. This testing method requires a large amount of labor cost, and the test results are easily affected subjectively.

[0003] In view of this, how to propose an efficient and accurate testing method for floor cleaning robots has become an urgent problem to be solved. Summary of the Invention

[0004] The main technical problem to be solved by this application is to provide a testing method, system and related devices for floor cleaning robots, which can improve the efficiency of testing floor cleaning robots.

[0005] To solve the above technical problem, a technical solution adopted by this application is: to provide a testing method for a floor cleaning robot, the testing method for the floor cleaning robot is applied to a target testing system, the target testing system includes a target acquisition device arranged in a testing scenario, and the method includes: using the target acquisition device to obtain the actual running trajectory of the floor cleaning robot in the testing scenario; based on the actual running trajectory, obtaining the index information of the floor cleaning robot during the running process; wherein, the index information is determined based on the cleaning area of the floor cleaning robot, the actual position information of obstacles in the testing scenario, and the position deviation, and the position deviation is determined based on the actual running trajectory and the target running trajectory under the perspective of the floor cleaning robot; based on the index information, obtaining the test result corresponding to the floor cleaning robot.

[0006] To solve the above technical problems, another technical solution adopted by this application is: to provide a test device for a floor cleaning robot, including: an acquisition module, configured to use a target acquisition device to acquire the actual running trajectory of the floor cleaning robot in a test scenario; a first processing module, configured to obtain index information of the floor cleaning robot during the running process based on the actual running trajectory; wherein, the index information is determined based on the cleaning area of the floor cleaning robot, the actual position information of obstacles in the test scenario, and a position deviation, and the position deviation is determined based on the actual running trajectory and a target running trajectory under the perspective of the floor cleaning robot; a second processing module, configured to obtain a test result corresponding to the floor cleaning robot based on the index information.

[0007] To solve the above technical problems, another technical solution adopted by this application is: to provide an electronic device, including: a memory and a processor coupled to each other, wherein program instructions are stored in the memory, and the processor is configured to execute the program instructions to implement the method mentioned in the above technical solution.

[0008] To solve the above technical problems, another technical solution adopted by this application is: to provide a computer-readable storage medium, on which program instructions are stored, and when the program instructions are executed by a processor, the method mentioned in the above technical solution is implemented.

[0009] The beneficial effect of this application is: different from the prior art, the test method for the floor cleaning robot proposed by this application constructs a target test system including a test scenario and a target acquisition device. By using the target acquisition device in the target test system to acquire the actual running trajectory of the floor cleaning robot in the test scenario, and determining the index information of the floor cleaning robot during the running process according to the actual running trajectory. Using the index information to realize the automatic test of the floor cleaning robot in the test scenario, improving the test efficiency and at the same time enhancing the objectivity of the test result. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0011] Figure 1 is a flowchart of an implementation manner of the test method for the floor cleaning robot of this application;

[0012] Figure 2 is Figure 1 a flowchart of another implementation manner corresponding to step S102 in

[0013] Figure 3 is Figure 1 The flowchart of step S102 in [document] corresponding to another embodiment;

[0014] Figure 4 is Figure 1 The flowchart of step S103 in [document] corresponding to another embodiment;

[0015] Figure 5 The structural schematic diagram of a test device for a floor cleaning robot according to an embodiment of the present application;

[0016] Figure 6 The structural schematic diagram of an electronic device according to an embodiment of the present application;

[0017] Figure 7 The structural schematic diagram of a computer-readable storage medium according to an embodiment of the present application. Specific Embodiments

[0018] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments, and different embodiments can be adaptively combined. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0019] Please refer to Figure 1 , Figure 1 is the flowchart of a test method for a floor cleaning robot according to an embodiment of the present application. The test method for the floor cleaning robot is applied to a target test system, and the target test system includes a target acquisition device disposed in a test scenario. The method specifically includes:

[0020] S101: Use the target acquisition device to obtain the actual running trajectory of the floor cleaning robot in the test scenario.

[0021] In one embodiment, the floor cleaning robot is disposed in the test scenario, and the passable ground in the test scenario is cleaned by the floor cleaning robot. The target acquisition device performs continuous image acquisition on the test scenario, and by analyzing the acquired images, the driving path of the floor cleaning robot in the test scenario is extracted. The driving path of the floor cleaning robot is mapped to a ground coordinate system matching the test scenario to obtain the actual running trajectory of the floor cleaning robot in the ground coordinate system.

[0022] In one implementation scenario, the target acquisition device is a camera, and the target acquisition device is disposed above the test scenario for acquiring images of the entire test scenario.

[0023] S102: Obtain the metric information of the sweeping robot during operation based on the actual operation trajectory; wherein, the metric information is determined based on the cleaning area of the sweeping robot, the actual position information of the obstacles in the test scenario, and the position deviation, and the position deviation is determined based on the actual operation trajectory and the target operation trajectory from the perspective of the sweeping robot.

[0024] In one embodiment, analyze the images collected by the target acquisition device to determine the obstacles in the test scenario. Map the obstacles to the ground coordinate system matching the test scenario, so as to use the coordinates of the obstacles in the ground coordinate system as the actual position information. And, determine the cleaning area corresponding to the cleanable area according to the actual operation trajectory of the sweeping robot in the ground coordinate system. Among them, the obstacles can be determined by target recognition, and the specific implementation process can refer to existing open-source algorithms, which will not be elaborated in detail here.

[0025] Further, determine the metric information of the sweeping robot during operation based on at least the cleaning area of the sweeping robot, the actual position information of the obstacles in the test scenario, and the position deviation of the sweeping robot. Among them, the above-mentioned metric information includes the test data of the sweeping robot matching different test items.

[0026] S103: Obtain the test result corresponding to the sweeping robot based on the metric information.

[0027] In one embodiment, determine the test result corresponding to the sweeping robot according to the obtained metric information. Among them, the test result is used to characterize at least one of the cleaning coverage rate, cleaning efficiency, obstacle avoidance rate, and self-positioning accuracy when the sweeping robot is operating.

[0028] Specifically, compare the obtained metric information with the pre-set reference information, and use the comparison result as the test result of the sweeping robot.

[0029] In another embodiment, input the obtained metric information into the intelligent analysis model to analyze the metric information by using the intelligent analysis model, so as to output the test result corresponding to the sweeping robot. The test result includes the interpretation text for interpreting each test item.

[0030] In one implementation scenario, the intelligent analysis model is a large language model with relatively good data analysis capabilities. By inputting the metric information and the description information of the corresponding test item into the intelligent analysis model, and prompting the intelligent analysis model to analyze and interpret the metric information, the test result of the sweeping robot is generated. Among them, the above-mentioned description information is used to explain the corresponding test item. For example, the above-mentioned description information is "the test item corresponding to this data is used to test the coverage rate of the sweeping robot for the area to be cleaned during cleaning".

[0031] In a specific application scenario, the above large language models may include, but are not limited to, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Generative Pretrained Transformer models, etc. There are no specific restrictions on the specific structure and specific deployment of the large language model here.

[0032] The test method for the floor cleaning robot proposed in this application constructs a target test system including a test scenario and a target acquisition device. By using the target acquisition device in the target test system to obtain the actual running trajectory of the floor cleaning robot in the test scenario, and determining the index information of the floor cleaning robot during the running process according to the actual running trajectory. Using the index information to realize the automatic test of the floor cleaning robot in the test scenario improves the test efficiency and enhances the objectivity of the test results at the same time.

[0033] In an implementation manner, to achieve the automatic test of the floor cleaning robot, the target test system further includes a transformation matrix between the target acquisition device and the test scenario, and this transformation matrix is determined based on the calibration marks set in the test scenario. The determination process of the transformation matrix matching between the target acquisition device and the test scenario includes:

[0034] Obtain the calibration image collected by the target acquisition device for the calibration marks, and based on the calibration image, obtain the transformation matrix between the camera coordinate system of the target acquisition device and the ground coordinate system of the test scenario.

[0035] Specifically, perform internal parameter calibration on the target acquisition device. Construct a ground coordinate system that matches the ground of the test scenario, and determine the first reference coordinate of the calibration mark in the ground coordinate system according to the position of the calibration mark in the test scenario. Obtain the calibration image collected by the target acquisition device for the calibration marks, and determine the second reference coordinate of the calibration mark in the camera coordinate system of the target acquisition device according to the calibration image. Determine the transformation matrix for realizing the transformation between the above camera coordinate system and the above ground coordinate system according to the second reference coordinate and the first reference coordinate.

[0036] In an implementation scenario, the process of performing internal parameter calibration on the target acquisition device includes: using the target acquisition device to collect a calibration image, and determining the internal parameters of the target acquisition device according to the collected image. According to the above internal parameters, determine the relationship matrix between the camera coordinate system and the pixel coordinate system of the target acquisition device, and this relationship matrix is used to map the three-dimensional coordinates collected by the target acquisition device to two-dimensional pixel coordinates for the display of the image.

[0037] Moreover, the construction process of the above-mentioned ground coordinate system includes: determining a target point within the ground of the test scenario, and using this target point as the coordinate origin of the ground coordinate system, and establishing the ground coordinate system based on the coordinate origin.

[0038] In addition, it should be noted that the determination process of the above conversion matrix is executed before testing the sweeping robot. And, to improve the efficiency of testing, after determining the conversion matrix, different sweeping robots are set in the test scenario to automatically test different sweeping robots using the target test system, thereby improving the testing efficiency of different sweeping robots.

[0039] In another embodiment, in response to determining the conversion matrix for the conversion between the camera coordinate system and the ground coordinate system through the above corresponding embodiment, and there is a positioning identifier that can be collected by a target acquisition device provided on the sweeping robot, then Figure 1 The implementation process of step S101 in includes: obtaining the video frame collected by the target acquisition device, and based on the positioning identifier and the conversion matrix in the video frame, determining the actual running trajectory of the sweeping robot in the ground coordinate system.

[0040] Specifically, obtain the video frame collected by the target acquisition device, identify the positioning identifier in the video frame, and determine the pose and the first position coordinate of the sweeping robot in the camera coordinate system at the corresponding moment according to the positioning identifier. Using the conversion matrix, convert the first position coordinate to the ground coordinate system to obtain the corresponding pose and the second position coordinate of the sweeping robot.

[0041] Furthermore, according to the second position coordinates of the sweeping robot determined from multiple consecutive video frames, determine the actual running trajectory of the sweeping robot in the ground coordinate system.

[0042] Please refer to Figure 2 , Figure 2 is Figure 1 The flowchart of another embodiment corresponding to step S102 in. Specifically, the implementation process of step S102 includes:

[0043] S201: Based on the actual running trajectory, determine the cleaning area of the sweeping robot.

[0044] In an implementation scenario, after obtaining the actual running trajectory corresponding to the sweeping robot, according to this actual running trajectory, determine the cleaning area of the sweeping robot in the test scenario.

[0045] Specifically, according to the area of the mopping cloth at the bottom of the sweeping robot, determine the unit area cleaned by the mopping cloth at the bottom of the sweeping robot when it travels a unit distance. According to the unit area, determine the cleaning area corresponding to the above actual running trajectory.

[0046] S202: Determine a first reference index based on the cleaning area.

[0047] In one embodiment, obtain the area to be cleaned in the test scenario and determine the reference area of the area to be cleaned. Obtain the first ratio of the cleaning area to the reference area, and use this first ratio as the first reference index.

[0048] Specifically, the area in the test scenario excluding obstacles is used as the area to be cleaned. According to the image collected by the target acquisition device, calculate the reference area of the area to be cleaned. Use the first ratio of the cleaning area calculated in step S201 to the reference area as the first reference index. This first reference index is used to intuitively represent the cleaning coverage rate of the sweeping robot during the cleaning process.

[0049] In another embodiment, obtain the first ratio of the cleaning area to the reference area. And, based on the actual running trajectory, determine the repeated cleaning area of the sweeping robot during operation, and obtain the second ratio of the repeated cleaning area to the reference area. Use the first ratio and the second ratio as the first reference index.

[0050] Specifically, according to the actual running trajectory of the sweeping robot, use the area of the area that is repeatedly cleaned as the repeated cleaning area. Calculate the second ratio between the repeated cleaning area and the reference area. This second ratio is used to intuitively represent the repeated cleaning rate of the sweeping robot during the cleaning process. Use both the obtained first ratio and the second ratio as the first reference index.

[0051] In yet another embodiment, in response to obtaining the first ratio and the second ratio through the above corresponding embodiments, convert the first ratio into a first value and convert the second ratio into a second value. Among them, the larger the first value, the higher the cleaning coverage rate of the sweeping robot during the cleaning process; the larger the second value, the lower the repeated cleaning rate.

[0052] Furthermore, perform a weighted sum of the first value and the second value, and use the obtained result as the first reference index. Among them, the higher the value corresponding to the first reference index, the higher the efficiency of the sweeping robot during cleaning.

[0053]

[0054] Among them, represents the first reference index, represents the first value, represents the first value corresponding weight, represents the second value, represents the second value corresponding weight. Among them, the above weights and weights The specific values can be obtained by relevant technicians through estimation, or can also be obtained by reverse deduction through multiple experiments.

[0055] S203: Obtain the actual position information of the obstacles in the test scenario, and based on the actual position information and the actual running trajectory, divide the actual running trajectory into trajectory segments matching different trajectory categories.

[0056] In one embodiment, obtain the actual position information of the obstacles in the test scenario in the ground coordinate system, and divide the actual running trajectory according to the actual position information of the obstacles and the actual running trajectory of the sweeping robot to obtain corresponding multiple trajectory segments. Among them, each trajectory segment is matched with a corresponding trajectory category.

[0057] In one implementation scenario, the trajectory categories include a straight-line category, a turning category, and an obstacle-avoiding category. The straight-line part in the actual running trajectory is used as the trajectory segment corresponding to the straight-line category; the part of the actual running trajectory that turns is used as the trajectory segment corresponding to the turning category; and the part of the actual running trajectory that is close to the obstacle and travels along the edge contour of the obstacle is used as the trajectory segment corresponding to the obstacle-avoiding category. By dividing the actual running trajectory into multiple trajectory segments, it helps to respectively count the efficiency of the sweeping robot when running along the corresponding trajectory segments according to the corresponding trajectory categories.

[0058] S204: For each trajectory category, determine the second reference data based on the running distance and running time of the matched trajectory segment.

[0059] In one embodiment, for each trajectory category, determine the running distance and running time of the matched trajectory segment, and determine the second reference data according to the running distance and running time. The second reference data is used to intuitively characterize the cleaning efficiency when the sweeping robot runs.

[0060] In one implementation scenario, for the trajectory segment corresponding to the straight-line category, obtain the third ratio between the corresponding running distance and running time; for the trajectory segment corresponding to the turning category, obtain the fourth ratio between the corresponding running distance and running time; and for the trajectory segment corresponding to the obstacle-avoiding category, obtain the obstacle-avoiding area of the ground covered by the sweeping robot when traveling around the obstacle and the corresponding obstacle-avoiding time, and obtain the fifth ratio between the obstacle-avoiding area and the obstacle-avoiding time. Take the above third ratio, fourth ratio, and fifth ratio as the second reference data.

[0061] Alternatively, the determination process of the above fifth ratio can also be: for the trajectory segment corresponding to the obstacle-avoiding category, obtain the obstacle-avoiding distance of the sweeping robot when traveling around the obstacle and the corresponding obstacle-avoiding time, and take the ratio between the obstacle-avoiding distance and the obstacle-avoiding time as the fifth ratio.

[0062] In another embodiment, after obtaining the third ratio, the fourth ratio, and the fifth ratio, the above three are weighted and summed to obtain the second reference data.

[0063] S205: Obtain the target running trajectory from the perspective of the floor cleaning robot, and determine the third reference index based on the target running trajectory and the actual running trajectory.

[0064] In one embodiment, obtain the target running trajectory from the perspective of the floor cleaning robot. Based on the target running trajectory and the actual running trajectory, determine the position deviation of the floor cleaning robot at each position in the test scenario. Based on the position deviation, obtain the third reference index.

[0065] Specifically, use the positioning technology of the floor cleaning robot to record its target running trajectory in the ground coordinate system according to its driving process in the test scenario. Compare the target running trajectory with the actual running trajectory to determine the position deviation of the floor cleaning robot at each position during driving. According to this position deviation, determine the third reference index. Among them, the positioning technology of the above floor cleaning robot is SLAM (Simultaneous Localization and Mapping) technology.

[0066] In one implementation scenario, use the existing Evo evaluation tool to calculate the position deviation between the target running trajectory and the actual running trajectory. According to the position deviation, calculate the deviation parameters, and the deviation parameters include at least some of the mean position deviation, the maximum deviation, the root mean square error, and the standard deviation. Further, in response to obtaining multiple different types of deviation parameters, all the deviation parameters are used as the third reference index; or, all the deviation parameters are weighted and summed, and the obtained result is used as the third reference index.

[0067] In another embodiment, calculate the corresponding position deviation according to the trajectory category. The position deviations corresponding to different trajectory categories are used as the third reference index.

[0068] Specifically, the straight line category is used as the first category, and the turning category and the obstacle avoidance category are used as the second category. For the trajectory segments corresponding to the first category in the target running trajectory and the actual running trajectory, calculate the first position deviation; and, for the trajectory segments corresponding to the second category in the target running trajectory and the actual running trajectory, calculate the second position deviation. The first position deviation and the second position deviation are used as the third reference index. Among them, the above first position deviation and second position deviation respectively include at least some of the corresponding mean position deviation, the maximum deviation, the root mean square error, and the standard deviation, and the specific acquisition process can refer to the above corresponding embodiments.

[0069] S206: Obtain the contour information and risk coefficient matching the obstacle, and determine the fourth reference index based on the contour information, risk coefficient, and actual operation trajectory.

[0070] In an implementation, according to the images collected by the target acquisition device, extract the contour information corresponding to each obstacle in the test scenario, and determine the risk coefficient matching each obstacle.

[0071] Specifically, analyze the images collected by the target acquisition device to determine the contour information according to the projections of each obstacle on the ground. Also, use the trained classification model to identify the categories of each obstacle, and determine the risk coefficient matching each obstacle according to the category. For example, set a higher risk coefficient for fragile obstacles.

[0072] Further, according to the contour information of each obstacle and the actual operation trajectory of the sweeping robot, obtain the corresponding intersection trajectory. Determine the fourth reference index according to the intersection trajectory and risk coefficient corresponding to each obstacle. The fourth index is used to characterize the safety of the sweeping robot during operation.

[0073] Specifically, for each obstacle, extract the corresponding intersection trajectory from the actual operation trajectory, and the distance between the intersection trajectory and the corresponding contour information is less than the distance threshold. Determine the fourth reference index according to the length of the intersection trajectory and the risk coefficient. Among them, the above distance threshold can be obtained by estimation by relevant technicians, or can also be obtained by reverse deduction through multiple tests.

[0074] In an implementation scenario, for each obstacle, obtain the reference product between the length of the corresponding intersection trajectory and the risk coefficient. Take the sum value of the reference products corresponding to all obstacles as the fourth reference index.

[0075] In the above solution, the different reference indexes obtained are used to test the performance of the sweeping robot from multiple test dimensions, which helps to improve the comprehensiveness of the test of the sweeping robot in the future. In addition, it should be noted that during the actual test process, the index information may also only include some of the above multiple reference indexes, and the acquisition order of the above different reference indexes may also be other. For example, different reference indexes can be obtained simultaneously, or can be obtained in sequence one by one.

[0076] Please refer to Figure 3 , Figure 3 is Figure 1 the schematic flowchart of another implementation corresponding to step S102 in

[0077] S301: Obtain the target scene information collected by the floor cleaning robot, and based on the target scene information, determine the target position information of the obstacle from the perspective of the floor cleaning robot.

[0078] In one embodiment, use the positioning technology of the floor cleaning robot to construct a map of the test scene as the target scene information for test scene matching. According to the target scene information, map the obstacle from the perspective of the floor cleaning robot to the ground coordinate system to obtain the corresponding target position information. The target position information includes the coordinates of the obstacle from the perspective of the floor cleaning robot in the ground coordinate system.

[0079] S302: Determine the fifth reference index based on the target position information and the actual position information of the obstacle.

[0080] In one embodiment, compare the target position information and the actual position information of the obstacle to determine the fifth reference index, which is used to characterize the map construction accuracy of the floor cleaning robot.

[0081] Specifically, according to the target position information and the actual position information, determine the position deviation of the obstacle in the test scene from the perspective of the floor cleaning robot, and use this position deviation as the fifth reference index.

[0082] In yet another embodiment, Figure 1 before step S103, it further includes: obtaining the motion state information of the floor cleaning robot based on the actual running trajectory. The motion state information includes at least one of the running speed and running acceleration of the floor cleaning robot.

[0083] Specifically, according to the determined actual running trajectory, determine the running speed and running acceleration of the floor cleaning robot at each position in the test scene. The running speed is used to characterize the cleaning efficiency of the floor cleaning robot, and the running acceleration is used to characterize the stability of the floor cleaning robot during cleaning; by using the obtained motion state information of the floor cleaning robot as a reference for generating the test result, the finally obtained test result has higher authority.

[0084] Please refer to Figure 4 , Figure 4 is Figure 1 the flow chart of yet another embodiment corresponding to step S103. Specifically, the implementation process of step S103 includes:

[0085] S401: Obtain the test score corresponding to the floor cleaning robot based on the index information and the motion state information.

[0086] In one embodiment, for each reference index in the index information and each piece of data in the motion state information, a corresponding sub-score is obtained. Among them, the higher the sub-score, the better the performance of the sweeping robot under the corresponding test item.

[0087] Further, all the obtained sub-scores are weighted and summed to obtain the test score corresponding to the sweeping robot.

[0088] S402: Based on the test score, determine the test result corresponding to the sweeping robot.

[0089] In one embodiment, a preset score threshold is obtained, and based on the score threshold and the above test score, the test result corresponding to the sweeping robot is determined.

[0090] Specifically, when the test score is greater than or equal to the score threshold, the test result corresponding to the sweeping robot is determined as "test passed". Or, when the test score is less than the score threshold, it indicates that the sweeping robot does not meet the test passing conditions and the test result is "test failed".

[0091] In the above solution, by converting the index information and motion state information of the sweeping robot into a test score, the overall cleaning effect of the sweeping robot is intuitively displayed according to the test score, improving the efficiency of obtaining the test result.

[0092] In another embodiment, by analyzing the images collected by the target acquisition device, the behavior information of the sweeping robot during the test is obtained. Among them, the above behavior information is used to characterize the behavior of the sweeping robot as straight-line cleaning, obstacle avoidance cleaning, or collision generation, etc.

[0093] Further, in combination with the visualization image of the sweeping robot generated by the Rviz (Robotics Visualization) tool, the behavior information of the sweeping robot is analyzed to determine the cause of the failure when the sweeping robot fails. The cause of the failure is used as the test result of the sweeping robot.

[0094] Please refer to Figure 5 , Figure 5 FIG. is a schematic structural diagram of an embodiment of the test device for the sweeping robot of the present application. Specifically, the test device of the robot includes an acquisition module 10, a first processing module 20, and a second processing module 30 that are mutually coupled.

[0095] Specifically, the acquisition module 10 is used to obtain the actual running trajectory of the sweeping robot in the test scenario by using the target acquisition device.

[0096] The first processing module 20 is configured to obtain the index information of the sweeping robot during operation based on the actual operation trajectory; wherein, the index information is determined based on the cleaning area of the sweeping robot, the actual position information of the obstacles in the test scenario, and the position deviation, and the position deviation is determined based on the actual operation trajectory and the target operation trajectory from the perspective of the sweeping robot.

[0097] The second processing module 30 is configured to obtain the test result corresponding to the sweeping robot based on the index information.

[0098] In one embodiment, please continue to refer to Figure 5 , the test device for the robot proposed in this application further includes a conversion module 40 coupled to the acquisition module 10. A calibration identifier is set in the test scenario, and the target test system includes a conversion matrix between the target acquisition device and the test scenario. The process of the conversion module 40 determining the conversion matrix includes: obtaining the calibration image collected by the target acquisition device for the calibration identifier, and based on the calibration image, obtaining the conversion matrix between the camera coordinate system of the target acquisition device and the ground coordinate system of the test scenario.

[0099] In one embodiment, the sweeping robot is provided with a positioning identifier. The first processing module 20 uses the target acquisition device to obtain the actual operation trajectory of the sweeping robot in the test scenario, including: obtaining the video frame collected by the target acquisition device, and based on the positioning identifier and the conversion matrix in the video frame, determining the actual operation trajectory of the sweeping robot in the ground coordinate system.

[0100] In one embodiment, the first processing module 20 obtains the index information of the sweeping robot during operation based on the actual operation trajectory, including: determining the cleaning area of the sweeping robot based on the actual operation trajectory; determining a first reference index based on the cleaning area; and obtaining the actual position information of the obstacles in the test scenario, and based on the actual position information and the actual operation trajectory, dividing the actual operation trajectory into trajectory segments matching different trajectory categories; for each trajectory category, determining a second reference data based on the running distance and running time of the matching trajectory segment; and obtaining the target operation trajectory from the perspective of the sweeping robot, and based on the target operation trajectory and the actual operation trajectory, determining a third reference index; and obtaining the contour information and danger coefficient matching the obstacle, and based on the contour information, the danger coefficient and the actual operation trajectory, determining a fourth reference index.

[0101] In one embodiment, the first processing module 20 determines a first reference index based on the cleaning area, including: obtaining the area to be cleaned in the test scenario, and determining the reference area of the area to be cleaned; obtaining a first ratio of the cleaning area to the reference area; and, based on the actual running trajectory, determining the repeated cleaning area of the sweeping robot during operation, and obtaining a second ratio of the repeated cleaning area to the reference area; using the first ratio and the second ratio as the first reference index.

[0102] In one embodiment, the first processing module 20 obtains the target running trajectory from the perspective of the sweeping robot, and determines a third reference index based on the target running trajectory and the actual running trajectory, including: obtaining the target running trajectory from the perspective of the sweeping robot; based on the target running trajectory and the actual running trajectory, determining the position deviation of the sweeping robot at each position in the test scenario; and obtaining the third reference index based on the position deviation.

[0103] In one embodiment, the target running trajectory is determined based on the target scenario information that matches the test scenario constructed by the sweeping robot. The first processing module 20 obtains the index information of the sweeping robot during operation based on the actual running trajectory, and further includes: obtaining the target scenario information collected by the sweeping robot, and determining the target position information of the obstacle from the perspective of the sweeping robot based on the target scenario information; and determining a fifth reference index based on the target position information and the actual position information of the obstacle.

[0104] In one embodiment, before obtaining the test result corresponding to the sweeping robot based on the index information, the first processing module 20 is further configured to obtain the motion state information of the sweeping robot based on the actual running trajectory; wherein, the motion state information includes at least one of the running speed and the running acceleration of the sweeping robot.

[0105] In one embodiment, the second processing module 30 obtains the test result corresponding to the sweeping robot based on the index information, including: obtaining the test score corresponding to the sweeping robot based on the index information and the motion state information; and determining the test result corresponding to the sweeping robot based on the test score.

[0106] Please refer to Figure 6 , Figure 6It is a schematic structural diagram of an embodiment of the electronic device of the present application. The electronic device includes a memory 50 and a processor 60 that are coupled to each other. Program instructions are stored in the memory 50, and the processor 60 is configured to execute the program instructions to implement the method described in any of the above embodiments. Specifically, the electronic device includes, but is not limited to, a desktop computer, a laptop computer, a tablet computer, a server, etc., which are not limited herein. In addition, the processor 60 may also be referred to as a CPU (Center Processing Unit, central processing unit). The processor 60 may be an integrated circuit chip with signal processing capabilities. The processor 60 may also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Additionally, the processor 60 may be implemented jointly by integrated circuit chips.

[0107] Please refer to Figure 7 , Figure 7 It is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. Program instructions 80 that can be run by a processor are stored on the computer-readable storage medium 70, and when the program instructions 80 are executed by the processor, the method described in any of the above embodiments is implemented.

[0108] In several embodiments provided by the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0109] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] In addition, in each embodiment of the present application, the functional units may be integrated into one processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0112] The above are only the embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for testing a sweeping robot, characterized in that: The testing method of the sweeping robot is applied to a target testing system, the target testing system includes a target acquisition device arranged in a test scene, and the method includes: Using the target acquisition device to obtain the actual running trajectory of the sweeping robot in the test scene; Based on the actual running trajectory, obtaining index information of the sweeping robot during operation; wherein the index information is determined based on the cleaning area of ​​the sweeping robot, the actual position information of obstacles in the test scene, and the position deviation, and the position deviation is determined based on the actual running trajectory and the target running trajectory from the perspective of the sweeping robot; Based on the indicator information, obtaining the test result corresponding to the sweeping robot; Among them, the indicator information includes second reference data, and the indicator information of the sweeping robot during operation is obtained based on the actual operation trajectory, including: obtaining the actual position information of the obstacle in the test scene, and dividing the actual operation trajectory into trajectory segments matching different trajectory categories based on the actual position information and the actual operation trajectory; for each trajectory category, determining the second reference data based on the running distance and running time of the matching trajectory segment.

2. The method according to claim 1, characterized in that: The test scene is provided with a calibration mark, the target test system includes a conversion matrix between a target acquisition device and the test scene, and the determination process of the conversion matrix includes: A calibration image is obtained by acquiring the calibration mark by the target acquisition device, and based on the calibration image, the conversion matrix between the camera coordinate system of the target acquisition device and the ground coordinate system of the test scene is acquired.

3. The method according to claim 2, characterized in that The sweeping robot is provided with a positioning mark, and the using the target acquisition device to obtain the actual running track of the sweeping robot in the test scene includes: The video frame collected by the target collection device is obtained, and based on the positioning mark and the transformation matrix in the video frame, the actual running trajectory of the sweeping robot in the ground coordinate system is determined.

4. The method according to claim 1, characterized in that: The step of obtaining the index information of the sweeping robot during operation based on the actual operation trajectory further includes: Determining a cleaning area of ​​the cleaning robot based on the actual running trajectory; Based on the cleaning area, determining a first reference indicator; and, Acquire a target running trajectory from the perspective of the sweeping robot, and determine a third reference index based on the target running trajectory and the actual running trajectory; and Obtain the contour information and hazard factor of the obstacle match, and determine a fourth reference index based on the contour information, the hazard factor and the actual running trajectory.

5. The method according to claim 4, characterized in that The determining of a first reference index based on the cleaning area includes: Acquire the area to be cleaned in the test scene, and determine the reference area of ​​the area to be cleaned; acquiring a first ratio of the cleaning area to the reference area; and, Based on the actual running trajectory, determining the repeated cleaning area of ​​the cleaning robot during operation, and obtaining a second ratio of the repeated cleaning area to the reference area; The first ratio and the second ratio are used as the first reference index.

6. The method according to claim 4, characterized in that The acquiring the target running trajectory from the perspective of the sweeping robot and determining a third reference index based on the target running trajectory and the actual running trajectory includes: Obtaining the target running trajectory from the perspective of the sweeping robot; Based on the target running trajectory and the actual running trajectory, determining the position deviation of the sweeping robot at various positions in the test scene; Based on the position deviation, the third reference index is acquired.

7. The method according to claim 6, characterized in that The target running trajectory is determined based on the target scene information constructed by the sweeping robot and matching the test scene, and the obtaining of the index information of the sweeping robot during the running process based on the actual running trajectory also includes: Acquire the target scene information collected by the cleaning robot, and determine the target position information of the obstacle from the perspective of the cleaning robot based on the target scene information; Based on the target position information and the actual position information of the obstacle, a fifth reference index is determined.

8. The method according to claim 1, characterized in that Before obtaining the test result corresponding to the sweeping robot based on the indicator information, the method includes: Based on the actual running trajectory, obtaining the motion state information of the cleaning robot; wherein the motion state information includes at least one of the running speed and the running acceleration of the cleaning robot; The obtaining, based on the indicator information, a test result corresponding to the sweeping robot, comprises: Based on the indicator information and the motion state information, obtaining a test score corresponding to the sweeping robot; Based on the test score, a test result corresponding to the cleaning robot is determined.

9. A testing device for a sweeping robot, characterized in that: include: An acquisition module is used to acquire the actual running trajectory of the sweeping robot in the test scene using a target acquisition device; A first processing module, configured to obtain index information of the sweeping robot during operation based on the actual operation trajectory; wherein the index information is determined based on the cleaning area of ​​the sweeping robot, the actual position information of obstacles in the test scene, and the position deviation, and the position deviation is determined based on the actual operation trajectory and the target operation trajectory from the perspective of the sweeping robot; A second processing module, configured to obtain a test result corresponding to the sweeping robot based on the indicator information; Among them, the indicator information includes second reference data, and the indicator information of the sweeping robot during operation is obtained based on the actual operation trajectory, including: obtaining the actual position information of the obstacle in the test scene, and dividing the actual operation trajectory into trajectory segments matching different trajectory categories based on the actual position information and the actual operation trajectory; for each trajectory category, determining the second reference data based on the running distance and running time of the matching trajectory segment.

10. An electronic device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images