Mobile robot labyrinth type scene task reachability test method

Abstract

The invention belongs to the technical field of robot testing, and discloses a mobile robot labyrinth type scene task reachability testing method, which comprises the following steps: operating a mobile robot to enable the mobile robot to run from a starting point to an arrival point in an autonomous mode; real-time pose information of the mobile robot is obtained through a laser radar tracking triggering device, the pose information of the mobile robot in single-time autonomous operation is analyzed, and the number of the mobile robot passing through division adding points and division reducing points and the dead time of each area are judged; and if the stagnation time in the mobile robot testing process exceeds the set time, ending the test, and if not, calculating the total score of the single optimal path execution capability of the mobile robot and the single task execution time result, and outputting. According to the method, a typicality labyrinth type test scene containing multiple scenarized feature test elements can be constructed, and the execution capability of the mobile robot for completing a specified task is comprehensively evaluated.

Description

Technical Field

[0001] The invention belongs to the technical field of robot testing, and in particular relates to a method for testing the reachability of a mobile robot in a maze-type scenario. Background Art

[0002] With the rapid development of artificial intelligence technology, the intelligence level of mobile robots has been continuously improved in recent years. In addition to human-machine interaction functions such as voice interaction and face recognition, its basic mobility and path planning capabilities are also particularly important. The environmental conditions of mobile robots in different fields are complex and changeable. Typical complex application scenarios include narrow straight road passage, U-turn passage, on-the-spot turning passage, and escape from concave areas. The self-adaptation and task-reachability of mobile robots in complex application scenarios have become important research directions. There is currently no relevant evaluation system and method for testing the ability of mobile robots to achieve the expected target task execution under the aforementioned complex application scenario conditions. Summary of the invention

[0003] The present invention aims to solve the above technical problems at least to a certain extent. To this end, the present invention aims to provide a method for testing the reachability of a mobile robot in a maze-type scenario task.

[0004] The technical solution adopted by the present invention is:

[0005] A method for testing the reachability of a mobile robot in a maze-type scenario task, comprising:

[0006] Preparation process: Build a maze-type scenario task accessibility test scene on the application working condition environment test road surface. There is at least one bonus zone on the optimal path in the test scene, and each bonus zone has at least one bonus point. There is a deduction zone on the non-optimal path in the test scene, and each deduction zone has at least one deduction point. Install a tracking trigger device at an appropriate position of the mobile robot; set the number of tests N; operate the mobile robot, and set the starting point and arrival point of the mobile robot in the maze-type scenario task accessibility test scene;

[0007] Test process: operate the mobile robot to run from the starting point to the arrival point in autonomous mode; obtain the real-time position information of the mobile robot through the laser radar tracking trigger device, analyze the position information of the mobile robot in a single autonomous operation, and determine the number of bonus points and deduction points it passes, as well as the stagnation time in each area; if the stagnation time of the mobile robot during the test exceeds the set time, the test ends; otherwise, calculate the total score of the mobile robot's single optimal path execution ability and the single task execution time result, and output them.

[0008] Preferably, the test process is repeated N times, and the average optimal path execution ability total score and the average single task execution time after N tests are used to output the results to characterize the robot's complex maze scene task accessibility.

[0009] Preferably, the test scene includes a simulated wall device and a positioning system, the narrow side of the simulated wall device is equipped with a magnetic docking tooling, and the bottom of the simulated wall device is arranged on the moving wheel. The positioning system includes four laser radars, four poles, and a tracking trigger device. The laser radars are installed around the test scene through the poles, and the tracking trigger is installed on the mobile robot.

[0010] The beneficial effects of the present invention are:

[0011] The mobile robot maze-type scenario task reachability testing method provided by the present invention can construct a typical maze-type test scenario that includes multiple scenario-based feature test elements, and use test indicators such as "optimal path execution capability" and "task execution time" to characterize the mobile robot's task reachability in a complex environment, thereby comprehensively evaluating the mobile robot's execution capability to complete specified tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of the method for testing the reachability of a mobile robot maze-type scenario task of the present invention.

[0013] Figure 2 Schematic diagram of the test scenario of the present invention. DETAILED DESCRIPTION

[0014] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention. The components of the embodiments of the present invention generally described and shown in the drawings herein may be arranged and designed in a variety of different configurations.

[0015] In the present invention, unless otherwise clearly stipulated and limited, terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal connection of two elements.

[0016] like Figure 1 and Figure 2 As shown, a method for testing the reachability of a maze-type scenario task of a mobile robot in this embodiment includes:

[0017] 1. Preparation process:

[0018] A maze-type scene task accessibility test scene is built on a test road surface suitable for the application conditions of the mobile robot (such as a flat tiled road surface, carpeted road surface, floor paint road surface, etc. that meet the application conditions of the mobile robot being tested). The test scene includes a simulated wall device and a positioning system. The narrow side of the simulated wall device is equipped with a magnetic docking tooling, which can facilitate the splicing and combination of multiple simulated wall devices, and can realize the reconstruction of the test scene space on demand; the bottom of the simulated wall device is set on the moving wheel, and the minimum ground clearance is less than 10mm, which can conveniently move the simulated wall device. At the same time, the simulated wall device has high-strength impact and collision resistance. The positioning system includes four laser radars, four poles, and a tracking trigger device. The laser radar is installed around the test scene through the poles, and the tracking trigger is installed on the mobile robot.

[0019] The test scenario is built to set the optimal path, add zones, and reduce zones, which can monitor the optimal path travel time of the mobile robot, the residence time in the reduced zone, and track the real-time position of the mobile robot. Figure 2 As shown, in the test scene of this embodiment, L1, L2, L3, and L4 are the positions where the laser radar is placed. Figure 2 In the figure, P0 and P1 are the starting point and arrival point of the test respectively. The black area in the figure represents the test fence, the dark gray represents the test ground, the light gray area marked with a minus sign is the minus zone, there are 4 of them, and there are 10 minus points in total. The white area marked with a plus sign is the plus zone, there are 5 of them, and there are 10 plus points in total. The dotted line in the figure represents the optimal path for the mobile robot to reach P1 from P0 in one test.

[0020] Install a tracking trigger device at a suitable position of the mobile robot; set the number of tests N; operate the mobile robot and set the starting point and arrival point of the mobile robot in the maze-type scene task reachability test scenario;

[0021] 2. Test process:

[0022] Operate the mobile robot to run from the starting point to the arrival point in autonomous mode; obtain the real-time position information of the mobile robot through the laser radar tracking trigger device, analyze the position information of the mobile robot in a single autonomous operation, and determine the number of bonus points and deduction points it passes, as well as the stagnation time in each area; if the stagnation time of the mobile robot during the test exceeds 5 minutes, the test ends. Otherwise, calculate the total score of the mobile robot's single optimal path execution ability and the single task execution time result, and output them.

[0023] The test process is repeated N times (N≥10 times), and the average optimal path execution ability total score and average single task execution time after N trials are used to output the robot's complex maze scene task accessibility.

[0024] The present invention summarizes the mobile service requirements of mobile robots under complex application scenarios, including narrow straight road passage, U-turn passage, on-the-spot turning passage, concave area escape and other scenarios, and can comprehensively evaluate the optimal path execution capability, task execution time and other task execution capability indicators of mobile robots under complex application scenarios. Through this comprehensive test scenario system, objective testing and experimentation can provide scientific and objective test data support for the construction of standardized test specifications, and on the other hand, it is also of great significance to the development of mobile robot motion intelligence technology.

[0025] The present invention is not limited to the above-mentioned optional implementation modes. Anyone can derive other various forms of products under the inspiration of the present invention. However, no matter what changes are made in the shape or structure, all technical solutions that fall within the scope defined by the claims of the present invention fall within the protection scope of the present invention.

Claims

1. A method for testing the reachability of a mobile robot in a maze-type scenario, characterized in that: include: Preparation process: Build a maze-type scenario task accessibility test scenario on the application working condition environment test road surface. There is at least one bonus zone on the optimal path in the test scenario, and each bonus zone has at least one bonus point. There is a deduction zone on the non-optimal path in the test scenario, and each deduction zone has at least one deduction point. Install a tracking trigger device at an appropriate position of the mobile robot; Set the number of tests N; operate the mobile robot and set the starting point and arrival point of the mobile robot in the maze-type scene task reachability test scenario; Test process: Operate the mobile robot to run from the starting point to the arrival point in autonomous mode; obtain the real-time position information of the mobile robot through the laser radar tracking trigger device, analyze the position information of the mobile robot in a single autonomous operation, determine the number of points it passes through, the number of points it passes through, and the stagnation time in each area; If the stagnation time of the mobile robot during the test exceeds the set time, the test ends. Otherwise, the total score of the mobile robot's single optimal path execution ability and the single task execution time result are calculated and output.

2. The mobile robot maze scenario task reachability testing method according to claim 1, characterized in that: The test process is repeated N times, and the average optimal path execution ability total score and average single task execution time after N trials are used to output the robot's complex maze scene task accessibility.

3. The mobile robot maze scenario task reachability testing method according to claim 1, characterized in that: The test scene includes a simulated wall device and a positioning system. The narrow side of the simulated wall device is equipped with a magnetic docking tooling, and the bottom of the simulated wall device is arranged on a moving wheel.

4. The mobile robot maze scenario task reachability testing method according to claim 3, characterized in that: The positioning system includes four laser radars, four poles, and a tracking trigger device. The laser radars are installed around the test scene through the poles, and the tracking trigger is installed on the mobile robot.

Images