Robot performance testing methods, devices, electronic equipment and storage media

Abstract

This invention relates to a robot performance testing method, apparatus, electronic device, and storage medium, belonging to the field of performance testing technology. A robot performance testing method includes: controlling a robot to travel along a reference path based on signal tags; executing a localization algorithm to obtain an estimated pose on a map when the robot reaches a first position, wherein the first position is located on the reference path; mapping the first position to the map to determine the robot's actual pose on the map at the first position; and evaluating the robot's localization performance based on the actual pose and the estimated pose. The robot performance testing method of this invention can be performed on a set reference path, thus controlling the testing process within a reasonable range and improving the efficiency of robot localization performance testing.

Description

Technical Field

[0001] This invention relates to the field of performance testing technology, and in particular to a method, apparatus, electronic device, and storage medium for testing robot performance. Background Technology

[0002] With the rapid development of artificial intelligence technology, the robotics industry has grown rapidly in recent years, finding wide application in various fields and permeating all aspects of social life. Before a robot is put into use, it must undergo performance testing to verify whether its software and hardware meet factory standards.

[0003] Currently, when performing performance testing on robots, the method of leaving the robots to undergo aging tests in the application environment is adopted. This results in a large workload for robot testing and the inability to conduct multiple robot tests simultaneously on a large scale, leading to low efficiency in performance testing. Summary of the Invention

[0004] This invention provides a robot performance testing method, apparatus, electronic device, and storage medium, aiming to improve the efficiency of robot performance testing.

[0005] In a first aspect, the present invention proposes a method for testing robot performance, the method comprising:

[0006] The robot is controlled to travel along a baseline path based on signal tags;

[0007] When the robot reaches the first position, a localization algorithm is executed to obtain an estimated pose in the map, wherein the first position is located on the reference path;

[0008] Map the first position to the map to determine the robot's actual pose on the map when it is in the first position;

[0009] The robot's localization performance is evaluated based on the actual pose and the estimated pose.

[0010] In other embodiments, the step of controlling the robot to travel along a reference path based on signal tags includes:

[0011] The robot is controlled to travel along a reference path based on the magnetic field signal of the magnetic strip. The magnetic strip is set in the application environment, and the extension direction of the magnetic strip is consistent with the extension direction of the reference path.

[0012] In other embodiments, the step of executing a localization algorithm to obtain an estimated pose in the map when the robot reaches the first position includes:

[0013] When the robot reaches the first position, the LiDAR under test is activated to scan the external environment to obtain radar data;

[0014] Based on the radar data and the executed localization algorithm, the estimated pose of the robot in the map is calculated.

[0015] In other embodiments, prior to the step of performing the localization algorithm to obtain an estimated pose in the map, the method includes:

[0016] The robot scans the external environment based on a reference LiDAR and constructs a map corresponding to the application environment according to the SLAM algorithm.

[0017] In other embodiments, the step of mapping the first position to a map to determine the robot's actual pose on the map at the first position includes:

[0018] Map the first location to a map to obtain its coordinates on the map;

[0019] Based on the coordinates, the first position, and the robot's fixed posture while traveling along the reference path, the robot's actual pose on the map is determined.

[0020] In other embodiments, the step of evaluating the robot's localization performance based on the actual pose and the estimated pose includes:

[0021] When the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is greater than a first threshold, and / or when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is greater than a second threshold, the robot's positioning performance is determined to be unqualified.

[0022] When the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is less than or equal to a first threshold, and when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is less than or equal to a second threshold, the robot's positioning performance is determined to be qualified.

[0023] In other embodiments, the method further includes:

[0024] When the robot reaches the first position, the drive control of the robot chassis is detected;

[0025] The robot's driving performance is evaluated based on the drive control results.

[0026] Secondly, the present invention also provides a robot performance testing device, the device comprising:

[0027] The driving module is used to control the robot to travel along a reference path based on signal tags;

[0028] An estimation module is used to execute a localization algorithm to obtain an estimated pose in a map when the robot reaches a first position, wherein the first position is located on the reference path;

[0029] The mapping module is used to map the first position to the map to determine the robot's actual pose in the map when it is in the first position.

[0030] An evaluation module is used to evaluate the robot's positioning performance based on the actual pose and the estimated pose.

[0031] Thirdly, the present invention also provides an electronic device comprising:

[0032] At least one processor; and

[0033] A memory that is communicatively connected to the at least one processor;

[0034] The memory stores instructions that can be executed by the at least one processor, which, when executed, enable the at least one processor to perform the steps of the robot performance testing method as described in the first aspect above.

[0035] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the robot performance testing method described in the first aspect above.

[0036] Fifthly, embodiments of the present invention provide a computer program product that, when run on an electronic device, causes the electronic device to perform the steps of the robot performance testing method described in the first aspect.

[0037] Unlike related technologies, in this invention, the robot is controlled to travel along a reference path based on signal tags. When the robot reaches a first position, a localization algorithm is executed to obtain an estimated pose on a map, where the first position is located on the reference path. The first position is mapped onto the map to determine the robot's actual pose on the map at the first position. The robot's localization performance is evaluated based on the actual pose and the estimated pose. Thus, during robot performance testing, the robot is first controlled to travel along the reference path; that is, the robot's autonomous localization and navigation functions are not used during the performance testing process. When the robot reaches the first position, a localization algorithm is executed to obtain the robot's estimated pose on the map. The estimated pose is compared with the robot's actual pose on the reference path to evaluate the robot's localization performance. The robot performance testing method of this invention can be performed on a set reference path, thus controlling the testing process within a reasonable range and improving the efficiency of robot localization performance testing. Attached Figure Description

[0038] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements having 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.

[0039] Figure 1 This is a schematic diagram of the application environment of a robot performance testing method provided in an embodiment of the present invention;

[0040] Figure 2 This is a flowchart illustrating a robot performance testing method according to an embodiment of the present invention;

[0041] Figure 3 This is a functional block diagram of a robot performance testing device provided in an embodiment of the present invention;

[0042] Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0044] It should be noted that, unless otherwise specified, the various features in the embodiments of the present invention can be combined with each other, and all are within the protection scope of the present invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different module division or in a different order than that shown in the device schematic diagram or the flowchart.

[0045] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items.

[0046] Please see Figure 1 , Figure 1This is a schematic diagram illustrating the application environment of a robot performance testing method provided in an embodiment of the present invention. The executing entity of the robot performance testing method of the present invention is an electronic device, which can be a mobile service robot. Mobile service robots can provide various robot services such as delivery of goods, greeting and guiding guests, handling, cleaning, inspection, and advertising in application scenarios such as hotels and KTVs. The function and shape of the robot are not limited herein. Figure 1 As shown, a fixed reference path is laid out in the application environment, and the robot only travels on the reference path. A first position is set on the reference path, and this first position is used to detect the robot's performance. For example, the robot is equipped with a LiDAR, and it uses LiDAR SLAM (Simultaneous Localization and Mapping) to build a map in the application environment for localization and navigation. This invention evaluates the performance of the LiDAR to determine whether a robot equipped with this LiDAR is suitable for use. As another example, the robot is equipped with a visual sensor (such as a depth camera), and it uses visual SLAM to build a map in the application environment for localization and navigation. This invention evaluates the performance of the visual sensor to determine whether a robot equipped with this visual sensor is suitable for use.

[0047] Please see Figure 2 , Figure 2 This is a flowchart illustrating a robot performance testing method according to an embodiment of the present invention. In a first aspect, this embodiment of the present invention proposes a robot performance testing method, wherein the executing entity of the robot performance testing method is an electronic device, such as... Figure 1 The robot shown is equipped with a LiDAR. It uses LiDAR-based SLAM (Simultaneous Localization and Mapping) to build a map in the application environment for localization and navigation. This invention evaluates the performance of the LiDAR to determine whether the robot equipped with it is suitable for use. The robot performance testing method includes the following steps S21-S24:

[0048] Step S21: Control the robot to travel along the baseline path based on the signal tags.

[0049] Signal tags are used to guide and control the robot's movement. These tags can be magnetic strips laid on the ground, Bluetooth tethers, QR code tags, etc. The baseline path is a fixed path used to restrict the robot's movement to only that path. Taking a test area with magnetic strips as an example, the robot's movement along the baseline path is controlled by the magnetic field signal of the magnetic strips. During the testing of the robot's own positioning performance, an additional guidance system (such as magnetic strip guidance) is used to guide the robot along the baseline path; positioning and navigation are not performed using estimated poses obtained from the robot's positioning algorithm.

[0050] Step S22: When the robot reaches the first position, a localization algorithm is executed to obtain an estimated pose in the map, wherein the first position is located on the reference path.

[0051] A first position is set on the baseline path, which can be determined and selected by technicians. Taking LiDAR SLAM as an example, the localization algorithm is used to estimate the robot's current pose in the map based on the SLAM map and radar data obtained from the LiDAR. Taking Visual SLAM as an example, the localization algorithm is used to estimate the robot's current pose in the map based on the SLAM map and perception data obtained from the visual sensor.

[0052] For example, the robot starts moving from the initial detection position and travels towards the first position. When the robot reaches the first position, it executes a localization algorithm and calculates the robot's estimated pose on the map based on the radar data obtained from the LiDAR.

[0053] Step S23: Map the first position to the map to determine the robot's actual pose on the map when it is in the first position.

[0054] When the reference path is a straight line, the robot's attitude angle is a fixed value, and the robot's actual trajectory on the map is also a straight line. Optionally, the first position corresponds to a certain coordinate position on the map. Based on the coordinate position on the map corresponding to the first position and the robot's fixed attitude angle, the robot's actual pose on the map at the first position is determined. Understandably, technicians can pre-determine the coordinate position on the map corresponding to the first position and the robot's fixed attitude angle before testing the robot's performance.

[0055] Step S24: Evaluate the robot's positioning performance based on the actual pose and the estimated pose.

[0056] The result of evaluating the robot's positioning performance is either qualified or unqualified. That is, based on the robot's actual pose and estimated pose at the first position, the robot's positioning performance is evaluated to determine whether it is qualified. If the robot's positioning performance is qualified, the robot can be put into use; if the robot's positioning performance is unqualified, the robot cannot be put into use. In this case, the robot can be maintained and repaired until its positioning performance is qualified.

[0057] In this embodiment, during robot performance testing, the robot is first controlled to travel along a reference path. That is, the robot's autonomous localization and navigation functions are not used during the performance testing process. When the robot reaches a first position, a localization algorithm is executed to obtain the estimated pose of the robot on the map. The estimated pose is compared with the robot's actual pose on the reference path to evaluate the robot's localization performance. The robot performance testing method of this invention can be performed on a set reference path, thus keeping the testing process within a reasonable range and improving the efficiency of robot localization performance testing.

[0058] In some other embodiments, step S21, the step of controlling the robot to travel along a reference path based on the signal tag, includes: controlling the robot to travel along the reference path according to the magnetic field signal of the magnetic strip, wherein the magnetic strip is provided in the application environment and the extension direction of the magnetic strip is consistent with the extension direction of the reference path.

[0059] Magnetic strips are installed in the application environment, extending in the same direction as the reference path; that is, the magnetic strips extend along the reference path. By detecting the magnetic field signal of the path, the robot's positional deviation relative to the target tracking path is obtained. The robot is then controlled to move along the direction of the magnetic strips, i.e., along the reference path, thus achieving navigation control. Magnetic strip navigation offers high control precision, good repeatability, and its magnetism is not easily affected by changes in light. During robot movement, the magnetic sensor system exhibits high reliability and robustness. Furthermore, the maintenance cost of laying magnetic strips is extremely low, their service life is long, and the path is easily added and modified.

[0060] In some other embodiments, step S22, the step of executing a localization algorithm to obtain an estimated pose in the map when the robot reaches the first position, includes: when the robot reaches the first position, activating the LiDAR to be tested to scan the external environment to obtain radar data; and calculating the estimated pose of the robot in the map based on the radar data and the executed localization algorithm.

[0061] When the robot reaches the first position, a control signal is triggered to record the robot's execution of a localization algorithm to obtain an estimated pose in the map. For example, when the robot's wheels encounter a step, pit, or slope, it is determined that the robot has reached the first position, and a control signal is triggered. For example, when the robot navigates using magnetic strips and reaches the first position, the LiDAR device configured on the robot is activated to scan the external environment to obtain radar data. The radar data is matched and estimated with the SLAM map to estimate the robot's current estimated pose in the map. Optionally, before the robot reaches the first position, the LiDAR device configured on the robot is activated to scan the external environment to obtain radar data, and a localization algorithm is executed based on the SLAM map to estimate the robot's estimated pose in the map. The estimated poses before and upon reaching the first position are recorded, and the position coordinates in the estimated poses are connected to form the robot's localization trajectory. The deviation between the localization trajectory and the reference path is used to evaluate the robot's localization performance. For example, if the positioning trajectory does not intersect with the reference path, or if the deviation of the positioning trajectory from the reference path is greater than a preset threshold, the robot's positioning performance is determined to be unqualified; if the positioning trajectory intersects with the reference path, or partially overlaps with it, the robot's positioning performance is determined to be qualified; if the deviation of the positioning trajectory from the reference path is less than or equal to the preset threshold, the robot's positioning performance is determined to be qualified.

[0062] In other embodiments, prior to the step of performing a localization algorithm to obtain an estimated pose in the map, the robot scans external environment information based on a reference LiDAR and constructs a map corresponding to the application environment according to a SLAM algorithm.

[0063] The reference LiDAR is a standard, usable LiDAR. The LiDAR under test (DUT) is the LiDAR being tested. Before performing performance testing on the DUT, external environmental information can be scanned based on the reference LiDAR, and a map corresponding to the application environment can be constructed according to the SLAM algorithm. The installation location of the reference LiDAR during map construction is consistent with the installation location of the DUT during performance testing.

[0064] For example, when building a map corresponding to the application environment (i.e., the test environment), the robot is pushed to move along the baseline path, and the external environment information is scanned by the baseline LiDAR to build the map, thereby completing the site survey task before deploying the robot.

[0065] In some other embodiments, step S23, mapping the first position to a map to determine the robot's actual pose on the map at the first position, includes: mapping the first position to a map to obtain coordinates on the map; and determining the robot's actual pose on the map based on the coordinates, the first position, and the robot's fixed posture while traveling along a reference path.

[0066] Understandably, the first position is the robot's actual location within the application environment. Mapping this first position onto a map determines the robot's actual coordinates on the map at that position. Since the robot travels along a fixed baseline path, its fixed pose is known. Thus, the robot's actual pose on the map is determined, where pose includes both position and orientation.

[0067] In some other embodiments, step S24, the step of evaluating the robot's positioning performance based on the actual pose and the estimated pose, includes: determining that the robot's positioning performance is unqualified when the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is greater than a first threshold, and / or when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is greater than a second threshold; and determining that the robot's positioning performance is qualified when the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is less than or equal to the first threshold, and when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is less than or equal to the second threshold.

[0068] Specifically, taking laser SLAM as an example, if the difference between the first position coordinates in the actual pose and the second position coordinates in the estimated pose is greater than a first threshold, the robot's localization performance is deemed unqualified, indicating that the laser radar on the robot does not meet the usage requirements. Similarly, if the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is greater than a second threshold, the robot's localization performance is deemed unqualified, indicating that the laser radar on the robot does not meet the usage requirements. Alternatively, if both the difference between the first position coordinates in the actual pose and the second position coordinates in the estimated pose are greater than the first threshold and the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose are greater than the second threshold, the robot's localization performance is deemed unqualified, indicating that the laser radar on the robot does not meet the usage requirements. Finally, if the difference between the first position coordinates in the actual pose and the second position coordinates in the estimated pose is less than or equal to the first threshold and the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is less than or equal to the second threshold, the robot's localization performance is deemed qualified, indicating that the laser radar on the robot meets the usage requirements.

[0069] It is understood that in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. The numerical values ​​of the first and second thresholds can be set by those skilled in the art.

[0070] In some other embodiments, the robot performance detection method of the present invention further includes the following steps: when the robot reaches the first position, detecting the drive control of the robot chassis; and evaluating the driving performance of the robot according to the drive control result.

[0071] Specifically, there is one of a step, a pit or a slope set at the first position. When the robot reaches the first position, that is, when the robot wheels act on the step, the pit or the slope, it is determined that the robot has reached the first position and is in trouble. At the first position, drive control parameters are sent to the robot chassis to enable the robot to get out of trouble. For example, control parameters for controlling the robot to drive straight are sent to the robot chassis, and the control parameters are test parameters within a reasonable range, so that the robot tries to drive over the step, the pit or the slope. When the robot can successfully get out of trouble, it means that the driving performance of the robot is qualified; on the contrary, when the robot cannot successfully get out of trouble, it means that the driving performance of the robot is unqualified. Another example is that control parameters for controlling the robot to turn and drive are sent to the robot chassis, and the control parameters are test parameters within a reasonable range, so that the robot tries to turn at the step, the pit or the slope. When the robot can successfully turn and get out of trouble, it means that the driving performance of the robot is qualified; on the contrary, when the robot cannot successfully turn and get out of trouble, it means that the driving performance of the robot is unqualified.

[0072] Please refer to Figure 3 , second aspect, an embodiment of the present invention proposes a robot performance detection device 30, and the device 30 can be deployed on the robot. The device 30 includes:

[0073] A driving module 31, configured to control the robot to drive along a reference path based on a signal tag;

[0074] An estimation module 32, configured to execute a positioning algorithm to obtain an estimated pose in the map when the robot reaches the first position, where the first position is located on the reference path;

[0075] A mapping module 33, configured to map the first position to the map to determine the actual pose of the robot in the map when at the first position;

[0076] An evaluation module 34, configured to evaluate the positioning performance of the robot according to the actual pose and the estimated pose.

[0077] In some other embodiments, the driving module 31 is further configured to control the robot to drive along a reference path according to the magnetic field signal of a magnetic stripe, where a magnetic stripe is arranged in the application environment, and the extending direction of the magnetic stripe is consistent with the extending direction of the reference path.

[0078] In other embodiments, the estimation module 32 is further configured to, when the robot arrives at the first position, activate the LiDAR to be tested to scan the external environment to obtain radar data; and calculate the estimated pose of the robot in the map based on the radar data and the execution of a positioning algorithm.

[0079] In other embodiments, the estimation module 32 is also used for the robot to scan external environment information based on a reference lidar and to construct a map corresponding to the application environment according to the SLAM algorithm.

[0080] In other embodiments, the mapping module 33 is further configured to map the first position to a map to obtain the coordinate position in the map; and to determine the actual pose of the robot in the map based on the coordinate position, the first position, and the fixed posture of the robot traveling along the reference path.

[0081] In other embodiments, the evaluation module 34 is further configured to determine that the robot's positioning performance is unqualified when the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is greater than a first threshold, and / or when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is greater than a second threshold; and to determine that the robot's positioning performance is qualified when the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is less than or equal to the first threshold, and when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is less than or equal to the second threshold.

[0082] In other embodiments, the evaluation module 34 is also configured to detect the drive control of the robot chassis when the robot reaches the first position; and evaluate the robot's driving performance based on the drive control result.

[0083] It is understood that the implementation principle and technical effects of the robot performance testing device 30 proposed in the second aspect of the present invention can be found in the implementation principle and technical effects of the robot performance testing method proposed in the first aspect, and will not be repeated here.

[0084] Please see Figure 4 , Figure 4 This is a schematic diagram of the hardware structure of an electronic device 400 according to an embodiment of the present invention. The electronic device 400 can be a robot. The electronic device 400 includes: at least one processor 401, and a memory 402 communicatively connected to the at least one processor 401. Figure 4Taking a processor 401 as an example, the memory 402 stores instructions (or programs) executable by at least one processor 401. These instructions, when executed by at least one processor 401, enable the at least one processor 401 to perform the steps of the robot performance detection method of the first aspect of the present invention. The processor 401 and the memory 402 can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0085] The memory 402, as a readable storage medium, can be used to store software programs, executable programs, and modules, such as the program instructions / modules corresponding to the robot performance testing method to be executed by the electronic device in this embodiment of the invention. The processor 401 executes various functional applications and data processing by running the software programs, instructions, and modules stored in the memory 402, thereby implementing the steps of the robot performance testing method proposed in the first aspect of this embodiment of the invention.

[0086] Memory 402 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by executing the robot performance testing method, etc. Memory 402 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 402 may optionally include memory remotely located relative to processor 401, and these remote memories can be connected to electronic devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0087] One or more modules are stored in memory 402. When executed by one or more processors 401, they implement the steps of the robot performance testing method proposed in the first aspect of the present invention. For example, memory 402 stores the driving module 31, estimation module 32, mapping module 33 and evaluation module 34 in the robot performance testing device 30 proposed in the second aspect of the present invention.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for testing robot performance, characterized in that, The method includes: The robot scans the external environment based on a reference LiDAR and constructs a map corresponding to the application environment according to the SLAM algorithm; The robot is controlled to travel along a baseline path based on signal tags; When the robot reaches the first position, a localization algorithm is executed to obtain an estimated pose in the map, including: when the robot reaches the first position, the LiDAR under test is activated to scan the external environment to obtain radar data; based on the radar data and the executed localization algorithm, the estimated pose of the robot in the map is calculated; wherein, the first position is located on the reference path; The first position is mapped to a map to determine the robot's actual pose on the map when it is in the first position, where the first position corresponds to a coordinate position on the map. The robot's localization performance is evaluated based on the actual pose and the estimated pose.

2. The robot performance testing method according to claim 1, characterized in that, The steps of controlling the robot to travel along a reference path based on signal tags include: The robot is controlled to travel along a reference path based on the magnetic field signal of the magnetic strip. The magnetic strip is set in the application environment, and the extension direction of the magnetic strip is consistent with the extension direction of the reference path.

3. The robot performance testing method according to claim 1, characterized in that, The step of mapping the first position to a map to determine the robot's actual pose on the map at the first position includes: Map the first location to a map to obtain its coordinates on the map; Based on the coordinates, the first position, and the robot's fixed posture while traveling along the reference path, the robot's actual pose on the map is determined.

4. The robot performance testing method according to claim 1, characterized in that, The steps for evaluating the robot's localization performance based on the actual pose and the estimated pose include: When the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is greater than a first threshold, and / or when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is greater than a second threshold, the robot's positioning performance is determined to be unqualified. When the difference between the first position coordinate in the actual pose and the second position coordinate in the estimated pose is less than or equal to a first threshold, and when the difference between the first attitude angle in the actual pose and the second attitude angle in the estimated pose is less than or equal to a second threshold, the robot's positioning performance is determined to be qualified.

5. The robot performance testing method according to claim 1, characterized in that, The method further includes: When the robot reaches the first position, the drive control of the robot chassis is detected; The robot's driving performance is evaluated based on the drive control results.

6. A robot performance testing device, characterized in that, The device includes: The driving module is used to control the robot to travel along a reference path based on signal tags; An estimation module is used to execute a localization algorithm to obtain an estimated pose in the map when the robot reaches a first position. The module includes: when the robot reaches the first position, activating the LiDAR under test to scan the external environment to obtain radar data; and calculating the estimated pose of the robot in the map based on the radar data and the executed localization algorithm. The first position is located on the reference path. The estimation module is also used by the robot to scan the external environment based on the reference LiDAR and to build a map corresponding to the application environment according to the SLAM algorithm. The mapping module is used to map the first position to a map to determine the robot's actual pose in the map when it is in the first position, where the first position corresponds to a coordinate position in the map. An evaluation module is used to evaluate the robot's positioning performance based on the actual pose and the estimated pose.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the steps of the robot performance testing method as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the robot performance testing method as described in any one of claims 1 to 5.

Images