Work environment state detection method, robot navigation control method, and related devices

Abstract

The application provides a working environment state detection method, a robot navigation control method and related equipment, and relates to the technical field of robot control. Based on target frame environment perception data collected by a target mobile robot, the application extracts an effective perception point cloud set within the effective perception distance range of the target mobile robot, counts the actual point number of all target perception points with an actual distance not less than a maximum narrow scene mapping search distance value, and the average distance between all target perception points. Then, based on the actual point number and the average distance, the application identifies the environment space state type based on the effective perception point cloud set to determine whether the current working environment of the target mobile robot belongs to a narrow environment state or a spacious environment state, so as to facilitate the timely switching of a robot navigation positioning strategy adapted to the actual environment width condition, improve the robot navigation positioning success rate, and ensure the autonomous navigation performance of the robot.

Description

Technical Field

[0001] This application relates to the field of robot control technology, and more specifically, to a working environment state detection method, a robot navigation control method, and related equipment. Background Technology

[0002] With the continuous development of science and technology, robotics has received widespread attention from various industries (such as home services, manufacturing, emergency rescue, etc.) due to its great research and application value. Mobile robots (such as logistics robots, sweeping robots, etc.) are often required to use Simultaneous Localization and Mapping (SLAM) technology in conjunction with navigation and relocation operations in complex working environments to achieve autonomous navigation.

[0003] SLAM technology is primarily suitable for spacious working environments, relying on abundant environmental geometric features to ensure reliable navigation and localization results. However, it's important to note that mobile robots often enter confined working environments with limited space in practical applications. This drastically reduces the number of useful environmental geometric features perceived by the robot. Navigation and localization results obtained using traditional mapping and localization algorithms are highly susceptible to environmental changes, leading to localization drift. Furthermore, during robot navigation and relocalization, structurally similar areas often exist in different confined working environments, causing navigation and relocalization errors and severely impacting the robot's autonomous navigation performance. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a working environment state detection method, a robot navigation control method, and a robot control device, which can accurately identify the width and narrowness of the actual working environment in which the mobile robot is located, so as to switch to the robot navigation and positioning strategy adapted to the width and narrowness of the actual environment in a timely manner, thereby improving the success rate of robot navigation and positioning and ensuring the autonomous navigation performance of the robot.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: Firstly, this application provides a method for detecting the state of a working environment, the detection method comprising: The target mobile robot acquires target frame environmental perception data collected in real time in the current working environment, and performs horizontal plane point cloud mapping processing on the target frame environmental perception data to obtain the corresponding target horizontal plane point cloud data. Extract the effective sensing point cloud set from the target horizontal plane point cloud data that matches the effective sensing distance range of the target mobile robot, wherein the actual distance from each effective sensing point in the effective sensing point cloud set to the target mobile robot is within the effective sensing distance range; The actual number of all target sensing points in the effective sensing point cloud is counted, as well as the average distance between all target sensing points, wherein the actual distance corresponding to each target sensing point is not less than the maximum narrow scene mapping search distance of the target mobile robot. Based on the actual number of points and the average spacing, environmental spatial state type identification is performed on the effective sensing point set to determine whether the current working environment is a narrow environment or a spacious environment.

[0006] In an optional implementation, the step of identifying the environmental spatial state type based on the effective sensing point set according to the actual number of points and the average spacing, to determine whether the current working environment belongs to a narrow environment or a spacious environment, includes: The ratio of the actual number of points to the total number of sensing points in the effective sensing point cluster is calculated to obtain the corresponding long-range detection ratio value. Detect whether the long-distance detection ratio exceeds a preset ratio threshold, and whether the average spacing is greater than a first spacious environment state distance threshold; If the detected long-distance detection ratio exceeds the preset ratio threshold and the average spacing is greater than the first spacious environment state distance threshold, then the current working environment is determined to be a spacious environment state; otherwise, the effective sensing point set is subjected to distance downsampling processing to obtain the corresponding target sensing sampling point set. Based on the total number of sampling points in the target perception sampling point set, the long-distance detection ratio, and the average spacing, a narrow or spacious environment state matching is performed to determine whether the current working environment belongs to a narrow or spacious environment state.

[0007] In an optional implementation, the step of performing distance downsampling on the effective sensing point set to obtain the corresponding target sensing sampling point set includes: Initialize the original sampling point set, and randomly select one valid sensing point from the valid sensing point cloud set as the initial sampling point to add to the original sampling point set; Iterate through each valid sensing point in the valid sensing point cloud except for the initial sampling point, and detect whether the relative distance between the corresponding valid sensing point and the target sampling point that was recently added to the original sampling point set is less than the robot mapping cell size. When the relative distance is detected to be not less than the robot mapping cell size, add the valid sensing point as a sampling point to the original sampling point set. After traversing all valid sensing points, the original set of sampling points is directly used as the target sensing sampling point set.

[0008] In an optional implementation, the step of performing narrow / spacious environment state matching based on the total number of sampling points in the target perception sampling point set, the long-range detection ratio, and the average spacing to determine whether the current working environment belongs to a narrow or spacious environment state includes: Detect whether the total number of sampling points in the target perception sampling point set is greater than the minimum threshold for the number of spacious environment perception points; If the total number of sampling points is detected to be greater than the minimum spacious environment sensing point threshold, then the current working environment is determined to be a spacious environment state. Otherwise, it is detected whether the long-distance detection ratio is less than a preset ratio threshold and whether the average spacing is less than the second spacious environment state distance threshold. At the same time, it is detected whether the total number of sampling points in the target sensing sampling point set is less than the maximum narrow environment sensing point threshold, wherein the second spacious environment state distance threshold is greater than the first spacious environment state distance threshold, and the maximum narrow environment sensing point threshold is less than the minimum spacious environment sensing point threshold. When the detection ratio is less than a preset ratio threshold and the average spacing is less than the second spacious environment state distance threshold, or when the total number of sampling points is less than the maximum narrow environment sensing point threshold, the current working environment is determined to be a narrow environment state; otherwise, the current working environment is determined to be a spacious environment state.

[0009] In an optional implementation, before the step of counting the actual number of all target sensing points in the effective sensing point cloud, the detection method further includes: Detect whether the total number of sensing points in the effective sensing point cluster is less than the minimum threshold for the number of sensing points in a spacious environment; If the total number of sensing points is less than the minimum threshold for the number of sensing points in a spacious environment, then the current working environment is determined to be a narrow environment; otherwise, the step of counting the actual number of all target sensing points in the effective sensing point cloud continues.

[0010] Secondly, this application provides a robot navigation control method, the control method comprising: During the execution of the target navigation task, the control target mobile robot collects environmental information in real time about the current working environment, and determines whether the actual environmental state of the current working environment is a narrow environment or a wide environment based on the collected real-time environmental information according to any of the aforementioned embodiments of the working environment state detection method. Based on the actual environmental conditions of the current working environment and the actual task type of the target navigation task, the navigation operation parameters used by the target mobile robot during the execution of the target navigation task are dynamically adjusted.

[0011] In an optional implementation, when the actual task type of the target navigation task is a robot mapping and localization task, the navigation operation parameter matching the target navigation task is the actual mapping search distance of the target mobile robot. In this case, the step of dynamically adjusting the navigation operation parameters used by the target mobile robot during the execution of the target navigation task includes: When the actual environmental state of the current working environment is a spacious environment, the actual mapping search distance of the target mobile robot is configured according to the maximum perception and detection distance of the target mobile robot; When the actual environmental state of the current working environment is a narrow environment, the actual mapping search distance is configured according to the maximum narrow scene mapping search distance value of the target mobile robot, wherein the maximum narrow scene mapping search distance value is less than the maximum sensing detection distance.

[0012] In an optional implementation, when the actual task type of the target navigation task is a robot navigation relocation task, the navigation operation parameters matched with the target navigation task are the navigation relocation matching threshold of the target mobile robot. The step of dynamically adjusting the navigation operation parameters used by the target mobile robot during the execution of the target navigation task includes: If the actual environmental condition of the current working environment is a spacious environment, detect whether the relocation prediction position of the target mobile robot is located at the edge of the current navigation map where the mapping is incomplete; If the relocation prediction position is detected to be at an edge where the mapping is incomplete, the default relocation matching threshold is reduced according to the first matching attenuation magnitude, and the navigation relocation matching threshold is configured according to the first theoretical relocation matching threshold obtained by the reduction. Otherwise, it is checked whether the actual offset distance between the relocation prediction position and the latest mapping interruption position of the current navigation map is less than the preset offset distance threshold. When the actual offset distance is detected to be less than the preset offset distance threshold, the default relocation matching threshold is reduced according to the second matching attenuation magnitude, and the navigation relocation matching threshold is configured according to the second theoretical relocation matching threshold obtained by the reduction magnitude; otherwise, the navigation relocation matching threshold is configured directly according to the default relocation matching threshold, wherein the first matching attenuation magnitude is greater than the second matching attenuation magnitude.

[0013] In an optional implementation, the step of dynamically adjusting the navigation operation parameters used by the target mobile robot during the execution of the target navigation task further includes: When the actual environmental state of the current working environment is a narrow environment, the default relocation matching threshold is increased according to the third matching superposition amplitude, and the navigation relocation matching threshold is configured according to the third theoretical relocation matching threshold obtained by the decrease amplitude. Then, when the navigation relocation matching fails, the target mobile robot is controlled to move away from the current working environment.

[0014] Thirdly, this application provides a robot control device, including a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the working environment state detection method or the robot navigation control method described in any of the foregoing embodiments for a target mobile robot.

[0015] In this case, the beneficial effects of the embodiments of this application may include the following: This application maps the target frame environmental perception data collected by the target mobile robot to a horizontal plane point cloud, and extracts an effective set of perception points within the effective perception distance range of the target mobile robot from the mapped target horizontal plane point cloud data. Then, it counts the actual number of all target perception points in the effective perception point cloud whose actual distance is not less than the maximum narrow scene mapping search distance value, as well as the average distance between all target perception points. Then, based on the aforementioned actual number of points and the aforementioned average distance, it identifies the environmental space state type based on the aforementioned effective perception point cloud to determine whether the current working environment of the target mobile robot is a narrow environment or a wide environment. This allows for accurate identification of the width and narrowness of the actual working environment of the mobile robot, facilitating timely switching to a robot navigation and positioning strategy adapted to the actual environmental width and narrowness, thereby improving the success rate of robot navigation and positioning and ensuring the robot's autonomous navigation performance.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the composition of the robot control device provided in the embodiments of this application; Figure 2 One of the flowcharts for the working environment status detection method provided in the embodiments of this application; Figure 3 for Figure 2 A flowchart illustrating the sub-steps included in step S240; Figure 4 for Figure 3 A flowchart illustrating the sub-steps included in neutron step S245; Figure 5 A second schematic flowchart illustrating the working environment status detection method provided in this application embodiment; Figure 6 A flowchart illustrating the robot navigation and control method provided in an embodiment of this application; Figure 7 for Figure 6 One of the flowcharts illustrating the sub-steps included in step S320; Figure 8 for Figure 6 The second flowchart illustrates the sub-steps included in step S320.

[0019] Icons: 10-Robot control equipment; 11-Memory; 12-Processor; 13-Communication unit. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0023] In the description of this application, it should be understood that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are used only for the convenience of describing this application and simplifying the description, and are not intended to indicate or imply that the equipment or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0024] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0025] Furthermore, it is understood in the description of this application that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0026] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0027] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the robot control device 10 provided in this application embodiment. In this application embodiment, the robot control device 10 can communicate with any mobile robot (e.g., a robotic vacuum cleaner) to acquire real-time environmental information collected by the mobile robot in its working environment, and perform robot navigation and positioning based on the acquired real-time environmental information, so as to drive the mobile robot to a designated location for operation based on the corresponding navigation and positioning results. The robot control device 10 can be a computer device independent of the mobile robot, or it can be a hardware module device integrated with the mobile robot. The computer device can be, but is not limited to, a personal computer, cloud server, laptop, tablet, etc. The mobile robot is equipped with environmental perception sensors (which can be, but is not limited to, RGB-D cameras, multi-line LiDAR, single-line LiDAR, etc.) to achieve the function of perceiving the robot's surrounding environment through the environmental perception sensors.

[0028] In this embodiment, the robot control device 10 may include a memory 11, a processor 12, and a communication unit 13. The memory 11, the processor 12, and the communication unit 13 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines.

[0029] In this embodiment, the memory 11 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The memory 11 is used to store computer programs, and the processor 12 can execute the computer programs accordingly after receiving execution instructions.

[0030] In this embodiment, the processor 12 can be an integrated circuit chip with signal processing capabilities. The processor 12 can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in this embodiment.

[0031] In this embodiment, the communication unit 13 is used to establish a communication connection between the robot control device 10 and other electronic devices via a network, and to send and receive data via the network, wherein the network includes wired communication networks and wireless communication networks. For example, the robot control device 10 can obtain real-time environmental information collected by the corresponding mobile robot using its own environmental perception sensors regarding its working environment through the communication unit 13; the robot control device 10 can also issue movement control commands to the mobile robot through the communication unit 13 to drive the mobile robot to move.

[0032] Optionally, in this embodiment, the robot control device 10 may pre-store a specific computer program related to the working environment status detection function in the memory 11, and by driving the processor 12 to execute the specific computer program, accurately identify the width and narrowness of the actual working environment where the mobile robot is currently located, so as to switch to the robot navigation and positioning strategy adapted to the width and narrowness of the actual environment in a timely manner, thereby improving the success rate of robot navigation and positioning and ensuring the robot's autonomous navigation performance.

[0033] Optionally, in this embodiment, the robot control device 10 may pre-store a specific computer program related to the robot navigation control function in the memory 11, and by driving the processor 12 to execute the specific computer program, during the process of controlling the corresponding mobile robot to perform the user-specified navigation task (i.e., the target navigation task), the device may dynamically switch to use an appropriate robot navigation and positioning strategy according to the working environment conditions, so as to dynamically adjust the robot navigation operation parameters to improve the success rate of robot navigation and positioning, thereby improving the robot's autonomous navigation performance.

[0034] Understandable Figure 1 The block diagram shown is only a schematic diagram of one composition of the robot control device 10. The robot control device 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0035] In this application, to ensure that the robot control device 10 can accurately identify the width and narrowness of the actual working environment of the mobile robot, and to facilitate timely switching to a robot navigation and positioning strategy adapted to the actual environmental width and narrowness, thereby improving the success rate of robot navigation and positioning, this application provides a working environment state detection method to achieve the aforementioned objective. The working environment state detection method provided in this application will be described in detail below.

[0036] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the working environment status detection method provided in this application embodiment. In this application embodiment, the working environment status detection method may include steps S210 to S240.

[0037] Step S210: Obtain the target frame environment perception data collected in real time by the target mobile robot in the current working environment, and perform horizontal plane point cloud mapping processing on the target frame environment perception data to obtain the corresponding target horizontal plane point cloud data.

[0038] In this embodiment, the target mobile robot is a mobile robot that is communicatively connected to the robot control device 10. When the target mobile robot uses a single-line lidar to collect environmental information, the single-line lidar can be installed horizontally so that its radar detection plane is parallel to the horizontal plane. At this time, any frame of lidar data collected by the single-line lidar after rotating once in the actual working environment is the target frame environmental perception data. The target frame environmental perception data can be converted into a frame of target horizontal plane point cloud data by performing point cloud data conversion in a horizontal Cartesian coordinate system (the origin of which coincides with the vertical projection of the center of the target mobile robot's base). When the target mobile robot uses a multi-line lidar or an RGB-D camera to collect environmental information, any frame of working environment information collected (i.e., the working environment information collected by the corresponding environmental perception sensor after rotating once) is three-dimensional information when used as target frame environmental perception data. At this time, the target frame environmental perception data can be mapped to a horizontal Cartesian coordinate system after point cloud conversion to obtain a frame of target horizontal plane point cloud data. In other words, any frame of target horizontal point cloud data for the actual working environment can be used to describe the projection distribution of various objects around the target mobile robot in the horizontal plane.

[0039] Step S220: Extract the effective perception point cloud set from the target horizontal plane point cloud data that matches the effective perception distance range of the target mobile robot.

[0040] In this embodiment, the effective sensing distance range is used to describe the reliable detection length of the target mobile robot. It involves a lower limit and an upper limit. The lower limit represents the radius of the target mobile robot's blind spot (e.g., 0.05 meters), and the upper limit is determined based on the target mobile robot's maximum detection distance (e.g., the upper limit is obtained by subtracting 0.1 meters from the maximum detection distance of 0.5 meters). The actual distance from each effective sensing point in the effective sensing point cloud to the target mobile robot falls within the effective sensing distance range.

[0041] Step S230: Calculate the actual number of all target sensing points in the effective sensing point cloud and the average distance between all target sensing points.

[0042] In this embodiment, the actual distance between each target sensing point in the effective sensing point cloud is not less than the maximum narrow scene mapping search distance value of the target mobile robot, wherein the maximum narrow scene mapping search distance value is used to represent the maximum effective search distance (e.g., 0.5 meters) of the target mobile robot when building a map in a narrow working scene. The average distance between all target sensing points is obtained by averaging the actual distances corresponding to each target sensing point.

[0043] Step S240: Based on the actual number of points and the average spacing, identify the environmental spatial state type based on the effective sensing point cloud to determine whether the current working environment is a narrow environment or a spacious environment.

[0044] In this embodiment, the robot control device 10 can accurately identify the width of the current working environment by statistically analyzing the specific point cloud composition of the effective sensing point cloud, the actual number of points involving the target sensing point in the effective sensing point cloud, and the average spacing. This allows for further determination of whether the current working environment is narrow or spacious, facilitating timely switching to a robot navigation and positioning strategy that adapts to the actual width of the environment, thereby improving the success rate of robot navigation and positioning.

[0045] Alternatively, please refer to Figure 3 , Figure 3 yes Figure 2 A flowchart illustrating the sub-steps included in step S240. In this embodiment, step S240 may include sub-steps S241 to S245 to accurately identify the actual width and narrowness of the robot's working environment.

[0046] Sub-step S241 calculates the ratio between the actual number of points and the total number of effective sensing points to obtain the corresponding long-range detection ratio value.

[0047] In this embodiment, the long-range detection ratio is the ratio between the actual number of all target sensing points and the total number of sensing points in the corresponding effective sensing point cloud. It can characterize the proportion of far-end point clouds in the current target horizontal plane point cloud data that exceed the traditional narrow scene range.

[0048] Sub-step S242: Detect whether the long-distance detection ratio exceeds the preset ratio threshold, and whether the average spacing is greater than the first spacious environment state distance threshold.

[0049] In this embodiment, the preset ratio threshold is a decimal not less than 0.5, and the first spacious environment state distance threshold (which describes the minimum possible distance between any object and the robot in a traditional spacious work scenario (e.g., 0.9 meters)) is within the aforementioned effective sensing distance range. When the detected long-distance detection ratio exceeds the preset ratio threshold, and the average spacing is greater than the first spacious environment state distance threshold, it indicates that the current working environment has a large spatial size, and sub-step S243 can be executed accordingly; when the detected long-distance detection ratio does not exceed the preset ratio threshold, and / or the average spacing is not greater than the first spacious environment state distance threshold, it indicates that the current working environment needs further confirmation of its width, and sub-step S244 can be executed accordingly.

[0050] Sub-step S243: Determine that the current working environment is a spacious environment.

[0051] Sub-step S244 involves performing distance downsampling on the effective sensing point cloud to obtain the corresponding target sensing sampling point set.

[0052] In this embodiment, traditional distance downsampling algorithms such as voxel grid downsampling, uniform random sampling, and farthest point sampling can be used to ensure that the target perception sampling point set extracted from the effective perception point cloud can effectively describe the overall environmental condition of the current working environment in the horizontal plane.

[0053] Optionally, in one embodiment of this example, to ensure that the corresponding target perception sampling point set can effectively adapt to the navigation and positioning function of the target mobile robot, a navigation map cell size constraint (i.e., robot mapping cell size constraint) can be introduced during the distance downsampling process. In this case, sub-step S244 may include: Initialize the original sampling point set, and randomly select one valid sensing point from the valid sensing point cloud set as the initial sampling point to add to the original sampling point set, wherein the original sampling point set is in an empty set state when the initialization is completed; Traverse each valid sensing point in the valid sensing point cloud except for the initial sampling point, and detect whether the relative distance between the corresponding valid sensing point and the target sampling point most recently added to the original sampling point set is less than the robot mapping cell size (e.g., 0.05 meters). When the relative distance is detected to be not less than the robot mapping cell size, add the valid sensing point as a sampling point to the original sampling point set. After traversing all valid sensing points, the original set of sampling points is directly used as the target sensing sampling point set.

[0054] Sub-step S245: Based on the total number of sampling points in the target perception sampling point set, the long-distance detection ratio, and the average spacing, perform narrow and spacious environment state matching to determine whether the current working environment belongs to a narrow environment state or a spacious environment state.

[0055] In this embodiment, the width of the current working environment can be further confirmed by detecting whether the total number of sampling points, the long-distance detection ratio, and the average spacing meet the conditions for distinguishing between narrow and spacious environments.

[0056] Alternatively, please refer to Figure 4 , Figure 4 yes Figure 3 A flowchart illustrating the sub-steps included in neutron step S245. In this embodiment, sub-step S245 may include sub-steps S2451 to S2455 to accurately determine the width and narrowness of the current working environment.

[0057] Sub-step S2451: Detect whether the total number of sampling points in the target perception sampling point set is greater than the minimum threshold for the number of spacious environment perception points.

[0058] In this embodiment, the minimum spacious environment perception point threshold is used to describe the minimum number of perception points (e.g., 100) in a traditional spacious work scenario. When the total number of sampling points in the target perception sampling point set is detected to be greater than the minimum spacious environment perception point threshold, it indicates that the spatial size of the current working environment is substantially large, and sub-step S2452 can be executed accordingly. When the total number of sampling points in the target perception sampling point set is detected to be less than or equal to the minimum spacious environment perception point threshold, it indicates that the spatial size of the current working environment cannot be directly determined, and sub-steps S2453 and S2454 can be executed simultaneously accordingly.

[0059] Sub-step S2452: Determine that the current working environment is a spacious environment.

[0060] Sub-step S2453: Detect whether the long-distance detection ratio is less than the preset ratio threshold and whether the average spacing is less than the second spacious environment state distance threshold.

[0061] In this embodiment, the second spacious environment state distance threshold (which describes the maximum distance (e.g., 1.1 meters) that is likely to exist between any object and the robot in a traditional spacious working scenario) is within the aforementioned effective sensing distance range, and the second spacious environment state distance threshold is greater than the first spacious environment state distance threshold. When the long-distance detection ratio is less than the preset ratio threshold, and the average spacing is less than the second spacious environment state distance threshold, it indicates that the current working environment has a small spatial size, and sub-step S2455 can be executed accordingly; while when the long-distance detection ratio is not less than the preset ratio threshold, and / or the average spacing is not less than the second spacious environment state distance threshold, it indicates that the current working environment has a relatively spacious spatial size, and sub-step S2452 can be executed accordingly.

[0062] Sub-step S2454: Detect whether the total number of sampling points in the target perception sampling point set is less than the maximum narrow environment perception point threshold.

[0063] In this embodiment, the maximum narrow environment sensing point threshold is used to describe the maximum number of sensing points in a traditional narrow working scenario (e.g., 60), wherein the maximum narrow environment sensing point threshold is less than the minimum spacious environment sensing point threshold. When the total number of sampling points in the target sensing sampling point set is less than the maximum narrow environment sensing point threshold, it indicates that the current working environment has a small spatial size, and sub-step S2455 can be executed accordingly; while when the total number of sampling points in the target sensing sampling point set is not less than the maximum narrow environment sensing point threshold, it indicates that the current working environment has a relatively spacious spatial size, and sub-step S2452 can be executed accordingly.

[0064] Sub-step S2455: Determine that the current working environment is a spacious environment.

[0065] Therefore, this application can accurately identify the actual spatial width of the robot's working environment by executing the above sub-steps S241 to S245 (which involve the above sub-steps S2451 to S2455).

[0066] This application can accurately identify the width and narrowness of the actual working environment of the mobile robot by executing the above steps S210 to S240, so as to switch to the robot navigation and positioning strategy that is adapted to the width and narrowness of the actual environment in a timely manner, thereby improving the success rate of robot navigation and positioning and ensuring the robot's autonomous navigation performance.

[0067] Alternatively, please refer to Figure 5 , Figure 5 This is the second flowchart illustrating the working environment status detection method provided in this application embodiment. In this application embodiment, [the method is related to...]. Figure 2 Compared to the working environment status detection method shown, Figure 5 The working environment status detection method shown may also include steps S250 to S260 between steps S220 and S230, so as to avoid occupying a lot of computing resources to perform unnecessary working environment width and narrowness recognition functions and improve the working environment width and narrowness detection efficiency.

[0068] Step S250: Detect whether the total number of valid sensing points in the cluster is less than the minimum threshold for the number of sensing points in a spacious environment.

[0069] In this embodiment, when the total number of sensing points in the effective sensing point set is less than the minimum spacious environment sensing point threshold, it indicates that the current working environment is substantially small. The total number of sampling points in the corresponding target sensing sampling point set will be much smaller than the minimum spacious environment sensing point threshold, and usually also less than the maximum narrow environment sensing point threshold. In this case, the current working environment can be directly identified as a narrow environment by executing step S260. When the total number of sensing points in the effective sensing point set is not less than the minimum spacious environment sensing point threshold, it indicates that the current working environment may be small or large, and further detection of the space width and narrowness of the current working environment is required. In this case, step S230 will continue to be executed.

[0070] Step S260: Determine that the current working environment is a confined environment.

[0071] Therefore, by executing the above steps S210-S220 and S250-S260, this application can avoid occupying a large amount of computing resources to perform unnecessary working environment width and narrowness recognition functions, thereby improving the working environment width and narrowness detection efficiency.

[0072] In this application, to ensure that the robot control device 10 can dynamically switch between appropriate robot navigation and positioning strategies based on the working environment conditions during the process of controlling the corresponding mobile robot to perform user-specified navigation tasks (i.e., target navigation tasks), thereby dynamically adjusting robot navigation operation parameters to improve the success rate of robot navigation and positioning, this application embodiment achieves the aforementioned objective by providing a robot navigation control method. The robot navigation control method provided in this application will be described in detail below.

[0073] Please refer to Figure 6 , Figure 6 This is a schematic flowchart of a robot navigation control method provided in an embodiment of this application. In this embodiment, the robot navigation control method may include steps S310 to S320.

[0074] Step S310: During the execution of the target navigation task, the target mobile robot is controlled to collect environmental information in real time about the current working environment, and based on the collected real-time environmental information, it is determined whether the actual environmental state of the current working environment is a narrow environment or a wide environment according to the working environment state detection method.

[0075] In this embodiment, the target navigation task is used to instruct the target mobile robot to perform traversal movement in the current mobile operation scenario, so as to cooperate with other operation tools of the target mobile robot (e.g., wiping cloth, cleaning tools, etc.) to achieve the ideal operation effect in the current mobile operation scenario.

[0076] Step S320: Based on the actual environmental conditions of the current working environment and the actual task type of the target navigation task, dynamically adjust the navigation operation parameters used by the target mobile robot during the execution of the target navigation task.

[0077] In this embodiment, during the navigation and localization process of the target mobile robot, the actual task type of the target navigation task often changes with the robot's working stage (for example, the task type corresponding to the navigation map building stage is a robot mapping and localization task, while the task type corresponding to the robot position localization stage based on the built map is a robot navigation relocalization task). Simultaneously, the environmental conditions of the robot's working environment also change as the robot moves. Therefore, it is necessary to dynamically adjust the navigation operation parameters used by the target mobile robot during the navigation task execution based on the actual environmental conditions and the actual task type to improve the robot's navigation and localization success rate and ensure the robot's autonomous navigation performance.

[0078] Alternatively, please refer to Figure 7 , Figure 7 yes Figure 6 One of the flowcharts for the sub-steps included in step S320 is shown below. In this embodiment of the application, when the actual task type of the target navigation task is a robot mapping and localization task, the navigation operation parameter matched with the target navigation task is the actual mapping search distance of the target mobile robot. In this case, step S320 may include sub-steps S321 to S322 to improve the success rate of robot mapping and localization, thereby enhancing the robot's autonomous navigation performance.

[0079] Sub-step S321: When the actual environmental state of the current working environment is a spacious environment, configure the actual mapping search distance of the target mobile robot according to the maximum perception and detection distance of the target mobile robot.

[0080] Sub-step S322: When the actual environmental state of the current working environment is a narrow environment state, configure the actual mapping search distance according to the maximum narrow scene mapping search distance value of the target mobile robot.

[0081] In this embodiment, the maximum narrow scene mapping search distance is less than the maximum sensing detection distance.

[0082] Therefore, this application can improve the robot's autonomous navigation performance by executing the above sub-steps S321 to S322 and dynamically adjusting the navigation operation parameters according to changes in the working environment.

[0083] Alternatively, please refer to Figure 8 , Figure 8 yes Figure 6 The second flowchart illustrates the sub-steps included in step S320. In this embodiment, when the actual task type of the target navigation task is a robot navigation relocation task, the navigation operation parameter matched with the target navigation task is the navigation relocation matching threshold of the target mobile robot. In this case, step S320 may include sub-steps S323 to S327 to improve the success rate of robot navigation relocation and thus enhance the robot's autonomous navigation performance.

[0084] Sub-step S323: If the actual environment of the current working environment is a spacious environment, detect whether the relocalization prediction position of the target mobile robot is located at the edge of the current navigation map where the mapping is incomplete.

[0085] In this embodiment, the relocation prediction position represents the robot position predicted by the target mobile robot in the current working environment through navigation relocation operation, and the current navigation map is the navigation map actually used by the target mobile robot during the navigation relocation process. Specifically, when the relocation prediction position is located at an incomplete edge mapping position on the current navigation map, sub-step S324 can be executed to adjust the navigation relocation matching threshold to a matching threshold state suitable for the incomplete edge mapping position; conversely, when the relocation prediction position is not located at an incomplete edge mapping position, sub-step S325 can be executed to determine what matching threshold state the navigation relocation matching threshold needs to be adjusted to.

[0086] Sub-step S324: Reduce the default relocation matching threshold according to the first matching attenuation magnitude, and configure the navigation relocation matching threshold according to the first theoretical relocation matching threshold obtained by the reduction.

[0087] In this embodiment, the first theoretical relocation matching threshold is obtained by subtracting the first matching attenuation magnitude (e.g., 0.2) from the default relocation matching threshold.

[0088] Sub-step S325: Detect whether the actual offset distance between the relocation prediction position and the latest map building interruption position of the current navigation map is less than a preset offset distance threshold.

[0089] In this embodiment, the latest mapping interruption position is used to characterize the actual robot position of the target mobile robot when it last constructed the current navigation map before performing the navigation relocation operation. When the actual offset distance between the relocation prediction position and the latest mapping interruption position of the current navigation map is less than a preset offset distance threshold (e.g., 1.5 meters), it indicates that the positional offset between the relocation prediction position and the latest mapping interruption position is not large. Sub-step S326 can be executed to adjust the navigation relocation matching threshold to a matching threshold state that is compatible with the latest mapping interruption position. When the actual offset distance is not less than the preset offset distance threshold, sub-step S327 can be executed to adjust the navigation relocation matching threshold to adapt to the normal working state.

[0090] Sub-step S326: Reduce the default relocation matching threshold according to the second matching attenuation magnitude, and configure the navigation relocation matching threshold according to the second theoretical relocation matching threshold obtained by the reduction.

[0091] In this embodiment, the first matching attenuation magnitude is greater than the second matching attenuation magnitude (e.g., 0.12).

[0092] Sub-step S327: Configure the navigation relocation matching threshold directly according to the default relocation matching threshold.

[0093] Furthermore, when the actual environmental condition of the current working environment is a narrow environment, the default relocation matching threshold is increased by a third matching superposition amplitude (e.g., 0.1), and the navigation relocation matching threshold is configured according to the third theoretical relocation matching threshold obtained by the decrease amplitude. Then, when the navigation relocation matching fails, the target mobile robot is controlled to move away from the current working environment. The third theoretical relocation matching threshold is the navigation relocation matching threshold suitable for narrow working environments, in order to improve positioning accuracy during robot navigation relocation. If any pre-marked narrow environmental area in the current navigation map cannot be matched within the current working environment, or if multiple narrow environmental areas are matched within the current working environment, it indicates that the robot navigation relocation matching has failed. In this case, a new target navigation position (exceeding the location coverage of the current working environment) needs to be planned for the target mobile robot, and then the target mobile robot is driven to the target navigation position to perform the navigation relocation operation.

[0094] Therefore, this application can improve the robot's autonomous navigation performance by executing the above sub-steps S323 to S327 and dynamically adjusting the navigation operation parameters according to changes in the working environment.

[0095] This application can improve the success rate of robot navigation and positioning by dynamically switching between appropriate robot navigation and positioning strategies according to the working environment conditions during the process of controlling the corresponding mobile robot to perform user-specified navigation tasks by executing the above steps S310 to S320. This is achieved by dynamically adjusting the robot navigation operation parameters to improve the robot navigation and positioning success rate, thereby improving the robot's autonomous navigation performance.

[0096] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0097] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. If the various functions provided in this application are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, including several instructions to cause a computer device (e.g., a laptop, a mobile robot, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application as a robot control device 10. The aforementioned readable storage medium includes: USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0098] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting the condition of a working environment, characterized in that, The detection method includes: The target mobile robot acquires target frame environmental perception data collected in real time in the current working environment, and performs horizontal plane point cloud mapping processing on the target frame environmental perception data to obtain the corresponding target horizontal plane point cloud data. Extract the effective sensing point cloud set from the target horizontal plane point cloud data that matches the effective sensing distance range of the target mobile robot, wherein the actual distance from each effective sensing point in the effective sensing point cloud set to the target mobile robot is within the effective sensing distance range; The actual number of all target sensing points in the effective sensing point cloud is counted, as well as the average distance between all target sensing points. The actual distance corresponding to each target sensing point is not less than the maximum narrow scene mapping search distance of the target mobile robot. The average distance between all target sensing points is obtained by averaging the actual distances corresponding to each target sensing point. Based on the actual number of points and the average spacing, environmental spatial state type identification is performed on the effective sensing point set to determine whether the current working environment belongs to a narrow environment state or a spacious environment state. Specifically, a corresponding long-distance detection ratio value is obtained by proportionally calculating the actual number of points to the total number of sensing points in the effective sensing point set. It is then checked whether the long-distance detection ratio value exceeds a preset ratio threshold and whether the average spacing is greater than a first spacious environment state distance threshold. If the long-distance detection ratio value exceeds the preset ratio threshold and the average spacing is greater than the first spacious environment state distance threshold, the current working environment is determined to be a spacious environment state. Otherwise, distance downsampling processing is performed on the effective sensing point set to obtain a corresponding target sensing sampling point set. Narrow-spamming is then performed based on the total number of sampling points in the target sensing sampling point set, the long-distance detection ratio value, and the average spacing value to determine whether the current working environment belongs to a narrow environment state or a spacious environment state.

2. The detection method according to claim 1, characterized in that, The step of performing distance downsampling processing on the effective sensing point cloud to obtain the corresponding target sensing sampling point set includes: Initialize the original sampling point set, and randomly select one valid sensing point from the valid sensing point cloud set as the initial sampling point to add to the original sampling point set; Iterate through each valid sensing point in the valid sensing point cloud except for the initial sampling point, and detect whether the relative distance between the corresponding valid sensing point and the target sampling point that was recently added to the original sampling point set is less than the robot mapping cell size. When the relative distance is detected to be not less than the robot mapping cell size, add the valid sensing point as a sampling point to the original sampling point set. After traversing all valid sensing points, the original set of sampling points is directly used as the target sensing sampling point set.

3. The detection method according to claim 1, characterized in that, The step of matching the narrow and spacious environment states based on the total number of sampling points in the target perception sampling point set, the long-range detection ratio, and the average spacing to determine whether the current working environment belongs to a narrow or spacious environment state includes: Detect whether the total number of sampling points in the target perception sampling point set is greater than the minimum threshold for the number of spacious environment perception points; If the total number of sampling points is detected to be greater than the minimum spacious environment sensing point threshold, then the current working environment is determined to be a spacious environment state. Otherwise, it is detected whether the long-distance detection ratio is less than a preset ratio threshold and whether the average spacing is less than the second spacious environment state distance threshold. At the same time, it is detected whether the total number of sampling points in the target sensing sampling point set is less than the maximum narrow environment sensing point threshold, wherein the second spacious environment state distance threshold is greater than the first spacious environment state distance threshold, and the maximum narrow environment sensing point threshold is less than the minimum spacious environment sensing point threshold. When the detection ratio is less than a preset ratio threshold and the average spacing is less than the second spacious environment state distance threshold, or when the total number of sampling points is less than the maximum narrow environment sensing point threshold, the current working environment is determined to be a narrow environment state; otherwise, the current working environment is determined to be a spacious environment state.

4. The detection method according to any one of claims 1-3, characterized in that, Before the step of counting the actual number of all target sensing points in the effective sensing point cloud, the detection method further includes: Detect whether the total number of sensing points in the effective sensing point cluster is less than the minimum threshold for the number of sensing points in a spacious environment; If the total number of sensing points is less than the minimum threshold for the number of sensing points in a spacious environment, then the current working environment is determined to be a narrow environment; otherwise, the step of counting the actual number of all target sensing points in the effective sensing point cloud continues.

5. A robot navigation control method, characterized in that, The control method includes: The control target mobile robot collects environmental information in real time during the execution of the target navigation task, and determines whether the actual environmental state of the current working environment is a narrow environment state or a wide environment state based on the collected real-time environmental information according to the working environment state detection method of any one of claims 1-4. Based on the actual environmental conditions of the current working environment and the actual task type of the target navigation task, the navigation operation parameters used by the target mobile robot during the execution of the target navigation task are dynamically adjusted.

6. The control method according to claim 5, characterized in that, When the actual task type of the target navigation task is a robot mapping and localization task, the navigation operation parameters matched with the target navigation task are the actual mapping search distance of the target mobile robot. The steps for dynamically adjusting the navigation operation parameters used by the target mobile robot during the execution of the target navigation task include: When the actual environmental state of the current working environment is a spacious environment, the actual mapping search distance of the target mobile robot is configured according to the maximum perception and detection distance of the target mobile robot; When the actual environmental state of the current working environment is a narrow environment, the actual mapping search distance is configured according to the maximum narrow scene mapping search distance value of the target mobile robot, wherein the maximum narrow scene mapping search distance value is less than the maximum sensing detection distance.

7. The control method according to claim 5, characterized in that, When the actual task type of the target navigation task is a robot navigation relocation task, the navigation operation parameters matched with the target navigation task are the navigation relocation matching threshold of the target mobile robot. The step of dynamically adjusting the navigation operation parameters used by the target mobile robot during the execution of the target navigation task includes: If the actual environmental condition of the current working environment is a spacious environment, detect whether the relocation prediction position of the target mobile robot is located at the edge of the current navigation map where the mapping is incomplete; If the relocation prediction position is detected to be at an edge where the mapping is incomplete, the default relocation matching threshold is reduced according to the first matching attenuation magnitude, and the navigation relocation matching threshold is configured according to the first theoretical relocation matching threshold obtained by the reduction. Otherwise, it is checked whether the actual offset distance between the relocation prediction position and the latest mapping interruption position of the current navigation map is less than the preset offset distance threshold. When the actual offset distance is detected to be less than the preset offset distance threshold, the default relocation matching threshold is reduced according to the second matching attenuation magnitude, and the navigation relocation matching threshold is configured according to the second theoretical relocation matching threshold obtained by the reduction magnitude; otherwise, the navigation relocation matching threshold is configured directly according to the default relocation matching threshold, wherein the first matching attenuation magnitude is greater than the second matching attenuation magnitude.

8. The control method according to claim 7, characterized in that, The step of dynamically adjusting the navigation operation parameters used by the target mobile robot during the execution of the target navigation task further includes: When the actual environmental state of the current working environment is a narrow environment, the default relocation matching threshold is increased according to the third matching superposition amplitude, and the navigation relocation matching threshold is configured according to the third theoretical relocation matching threshold obtained by the decrease amplitude. Then, when the navigation relocation matching fails, the target mobile robot is controlled to move away from the current working environment.

9. A robot control device, characterized in that, It includes a processor and a memory, the memory storing a computer program executable by the processor, the processor executing the computer program to implement the working environment state detection method according to any one of claims 1-4, or the robot navigation control method according to any one of claims 5-8, for a target mobile robot.

Images