Inspection method, device, equipment, storage medium and product for closed area

Abstract

The application discloses a closed area searching and patrolling method, device, equipment, storage medium and product, and relates to the technical field of robot control. The method comprises the following steps: acquiring a three-dimensional point cloud map of a closed searching and patrolling area; generating a planned searching and patrolling path according to a searching and patrolling task and the three-dimensional point cloud map; after navigating to each target searching and patrolling point along the planned searching and patrolling path, sensing environmental data of the target searching and patrolling point through a sensor, and uploading the environmental data to a control center. The method can realize intelligent searching and patrolling in a closed scene, has certain processing capacity for dynamic scenes in complex environments, does not need manual intervention, and improves searching and patrolling efficiency.

Description

Technical Field

[0001] This invention relates to the field of robot control technology, and in particular to methods, devices, equipment, storage media, and products for inspecting enclosed areas. Background Technology

[0002] With the continuous development of robotics technology, mobile robots are being used more and more widely in various fields. Among them, intelligent inspection technology in closed scenarios has received increasing attention as an important application scenario.

[0003] In enclosed environments such as warehouses and factory workshops, traditional inspection methods can no longer meet actual needs due to the limited space, complex layout, and frequent personnel movement.

[0004] Existing autonomous inspection technologies have limited ability to handle dynamic scenarios in complex environments, often requiring manual intervention or pre-set rules, thus failing to achieve truly intelligent inspection. Summary of the Invention

[0005] This invention provides a method, apparatus, device, storage medium, and product for inspecting enclosed areas, in order to solve the problem that existing autonomous inspection technologies have limited processing capabilities for dynamic scenes in complex environments and require manual intervention.

[0006] In a first aspect, embodiments of the present invention provide a method for inspecting a closed area, applied to a mobile robot within the closed inspection area, the method comprising:

[0007] Obtain a 3D point cloud map of the closed inspection area;

[0008] A planned inspection route is generated based on the inspection task and the aforementioned 3D point cloud map;

[0009] Navigate to each target inspection point along the planned inspection route;

[0010] Upon reaching each target inspection point, the system uses the sensors to sense the environmental data of the target inspection point and uploads the environmental data to the control center.

[0011] Furthermore, the step of obtaining a 3D point cloud map of the closed inspection area includes:

[0012] The mobile robot is controlled to move within the closed inspection area, and the surrounding environment is scanned by a lidar mounted on the mobile robot to obtain point cloud data.

[0013] The motion trajectory is estimated based on the odometry data of the mobile robot;

[0014] Based on the real-time positioning and mapping algorithm, a three-dimensional point cloud map of the closed inspection area is generated according to the motion trajectory, the odometer data and the point cloud data.

[0015] Furthermore, the step of generating a planned inspection path based on the inspection task and the 3D point cloud map includes:

[0016] The target inspection point set is determined according to the inspection task, and the target inspection point set is marked on the three-dimensional point cloud map;

[0017] On the three-dimensional point cloud map, a constrained optimization algorithm is used to generate the planned inspection path of the mobile robot based on the target inspection point set and the operation parameters of the mobile robot.

[0018] Furthermore, the constrained optimization algorithm includes: an objective function and constraints;

[0019] The objective function is:

[0020] min p(x,y) = (C + λL + μT + εD);

[0021]

[0022] The constraints are:

[0023] min(R(s)-Ri)≤γ;

[0024] g(P(x,y))≤A;

[0025] Where C represents the total energy consumption of the mobile robot along the planned inspection path, P(x,y) is the position of the mobile robot on the 3D point cloud map, f(P(x,y)) represents the energy consumption function of the mobile robot at position P(x,y), L represents the length of the planned inspection path; T represents the total time consumption of the mobile robot along the planned inspection path, v represents the speed of the mobile robot, v(P(x,y)) represents the speed function of the mobile robot at position P(x,y); D represents the total deviation between the planned inspection path and the target inspection point set, R(s) represents the trajectory points on the planned inspection path, Ri represents the i-th target inspection point in the target inspection point set, and γ represents the set threshold; (x j ,y j ) represents the j-th boundary point of the closed inspection area; g(P(x,y)) represents the constraint function of the mobile robot at position P(x,y).

[0026] Furthermore, the step of navigating along the planned inspection path to each target inspection point includes:

[0027] The planned inspection route is divided into multiple path points according to spatial order;

[0028] The sensors can detect in real time whether there are obstacles on the planned inspection route between two adjacent waypoints;

[0029] If obstacles exist, local path planning is performed on the planned inspection route to obtain obstacle avoidance routes;

[0030] If there are no obstacles, proceed along the planned inspection route to the next path point until reaching each of the target inspection points.

[0031] Furthermore, after the step of performing local path planning on the planned inspection route to obtain obstacle avoidance routes if obstacles exist, the method further includes:

[0032] Calculate the deviation distance between the obstacle avoidance section and the planned inspection section;

[0033] If the deviation distance is greater than the set distance threshold, the planned patrol route to the next path point will be regenerated;

[0034] If the deviation distance is not greater than the set threshold, then after walking along the obstacle avoidance section, return to the planned inspection section.

[0035] Secondly, embodiments of the present invention provide a patrol device for a closed area, applied to a mobile robot within a closed patrol area, wherein the mobile robot is equipped with sensors, and the device includes:

[0036] The map acquisition module is used to acquire a 3D point cloud map of the closed inspection area;

[0037] The path planning module is used to generate a planned inspection path based on the inspection task and the 3D point cloud map.

[0038] The inspection module is used to navigate along the planned inspection path to each target inspection point, perceive the environmental data of the target inspection point through the sensor, and upload the environmental data to the control center.

[0039] Thirdly, embodiments of the present invention provide a mobile robot, the mobile robot comprising:

[0040] At least one processor; and

[0041] A memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the closed area inspection method according to any embodiment of the present invention.

[0043] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement the closed area inspection method described in any embodiment of the present invention.

[0044] Fifthly, embodiments of the present invention provide a computer program product including a computer program, which, when executed by a processor, implements the closed area inspection method described in any embodiment of the present invention.

[0045] The technical solution of this invention acquires a 3D point cloud map of a closed inspection area; generates a planned inspection path based on the inspection task and the 3D point cloud map; navigates along the planned inspection path to each target inspection point, and then uses sensors to perceive the environmental data of the target inspection points and uploads the environmental data to the control center. This enables intelligent inspection within a closed environment and has a certain processing capability for dynamic scenes in complex environments without human intervention. Existing autonomous inspection technologies have limited processing capabilities for dynamic scenes in complex environments and require human intervention. This solution improves inspection efficiency and reduces labor costs.

[0046] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a closed area inspection method provided in Embodiment 1 of the present invention;

[0049] Figure 2 This is a flowchart of a closed area inspection method provided in Embodiment 2 of the present invention;

[0050] Figure 3 This is a schematic diagram of the structure of a closed area inspection device provided in Embodiment 3 of the present invention;

[0051] Figure 4 This is a schematic diagram of the structure of a mobile robot that implements the closed area inspection method of this invention. Detailed Implementation

[0052] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0053] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product or device.

[0054] Example 1

[0055] Figure 1 This is a flowchart of a closed area inspection method provided in Embodiment 1 of the present invention. This embodiment is applicable to inspections based on mobile robots within closed areas. The method can be executed by a closed area inspection device, which can be implemented in hardware and / or software. The closed area inspection device can be configured in [location missing]. Figure 1 As shown, the method includes:

[0056] S110. Obtain a 3D point cloud map of the closed inspection area.

[0057] In this context, a closed inspection area can be understood as a closed area that needs to be inspected, such as an underground parking lot, stadium, or library. A 3D point cloud map can be understood as a map drawn from 3D point clouds. It should be noted that a 3D point cloud map can include inspectable areas as well as uninspectable areas where obstacles are located.

[0058] Specifically, obtaining a 3D point cloud map of a closed inspection area can be achieved by collecting the 3D point cloud data of the closed inspection area and drawing a map, or by directly obtaining a pre-generated 3D point cloud map from a third-party database or the cloud.

[0059] S120. Generate a planned inspection route based on the inspection task and the 3D point cloud map.

[0060] The inspection task can be understood as a task requiring the mobile robot to perform inspection work. An inspection task may include: inspection content, such as target inspection points; and may also include: inspection time, inspection method, and other information. The planned query path can be understood as the path planned based on the inspection task. It is understood that planning the inspection path requires passing through each target inspection point included in the inspection task.

[0061] Specifically, based on the task information contained in the inspection and patrol mission and the 3D point cloud map of the closed inspection and patrol area, the planned inspection and patrol path corresponding to the inspection and patrol mission is planned on the 3D point cloud map.

[0062] S130. After navigating along the planned inspection route to each target inspection point, the system uses sensors to detect environmental data at the target inspection points and uploads the environmental data to the control center.

[0063] The target inspection point can be understood as the location that needs to be specified for arrival and inspection.

[0064] Specifically, after determining the planned query path, the mobile robot automatically navigates to each target query point along the planned query path to perform a query on each target query point.

[0065] S140. Upon reaching each target inspection point, the system uses sensors to perceive the environmental data of the target inspection point and uploads the environmental data to the control center.

[0066] Environmental data can be understood as data about the environment surrounding the target inspection point, such as static target data and dynamic target data. Environmental data can be image data, video data, or point cloud data; this embodiment does not impose any limitations on this.

[0067] Specifically, after the mobile robot arrives at each target inspection point in sequence along the planned inspection path, it uses sensors on the mobile robot to perceive the surrounding environment and data at the target inspection point and uploads the environmental data to the control center, thereby completing the fully automated inspection within the closed inspection area.

[0068] The technical solution of this invention acquires a three-dimensional point cloud map of a closed inspection area; generates a planned inspection path based on the inspection task and the three-dimensional point cloud map; navigates along the planned inspection path to each target inspection point, and then uses sensors to perceive the environmental data of the target inspection point and uploads the environmental data to the control center. This enables intelligent inspection in a closed environment and has a certain processing capability for dynamic scenes in complex environments. It does not require manual intervention, thus improving inspection efficiency and reducing labor costs.

[0069] Example 2

[0070] Figure 2This is a flowchart of a closed area inspection method provided in Embodiment 2 of the present invention. This embodiment further refines the above embodiment:

[0071] The step of generating a planned inspection path based on the inspection task and the three-dimensional point cloud map includes: determining a target inspection point set based on the inspection task and marking the target inspection point set on the three-dimensional point cloud map; and generating a planned inspection path for the mobile robot on the three-dimensional point cloud map using a constrained optimization algorithm based on the target inspection point set and the mobile robot's operating parameters.

[0072] like Figure 2 As shown, the method includes:

[0073] S210. Obtain a 3D point cloud map of the closed inspection area.

[0074] In one optional embodiment, the step of obtaining a three-dimensional point cloud map of the closed inspection area includes: controlling the robot to move in the closed inspection area, while scanning the surrounding environment with a lidar mounted on the mobile robot to obtain point cloud data; estimating the motion trajectory based on the odometer data of the mobile robot; and generating a three-dimensional point cloud map of the closed inspection area based on the motion trajectory, the odometer data, and the point cloud data using a real-time localization and mapping algorithm.

[0075] Specifically, based on the scene characteristics and task requirements of the closed inspection area, the parameters of the LiDAR on the mobile robot are adjusted, such as scanning frequency, resolution, and field of view. The mobile robot is controlled to move slowly within the closed inspection area, and the LiDAR on the robot scans the surrounding environment during movement, collecting point cloud data of the surrounding environment in real time and recording the robot's odometry data. To improve the quality of the collected data, noise reduction and other preprocessing can be performed on the point cloud data. Using the robot's odometry data, the robot's trajectory is estimated. Based on the trajectory, odometry data, and point cloud data, a simultaneous localization and mapping (SLAM) algorithm is run to estimate the robot's pose in the global coordinate system and continuously accumulate local point clouds, ultimately generating a 3D point cloud map of the closed inspection area.

[0076] S220. Determine the target inspection point set based on the inspection task, and mark the target inspection point set on the three-dimensional point cloud map.

[0077] The target inspection point set can be understood as the set of target inspection points that need to be inspected, such as R = {R1, R2, ..., R...} n},R nThis is the nth target inspection point.

[0078] Specifically, based on the inspection and patrol task, such as the task requirement being full coverage scanning or monitoring of key areas, a set of inspection and patrol target points is determined, and each inspection and patrol target point in the set is marked on the map.

[0079] S230. On the 3D point cloud map, the constrained optimization algorithm is used to generate the planned inspection path of the mobile robot based on the target inspection point set and the operation parameters of the mobile robot.

[0080] Specifically, when planning inspection routes, factors such as the mobile robot's operating radius, operating space constraints, energy consumption, and distance to the target inspection point are comprehensively considered, and a more reasonable and efficient planned inspection route is generated with the help of constraint optimization algorithms.

[0081] Optionally, the constrained optimization algorithm includes: an objective function and constraints;

[0082] The objective function is:

[0083] min p(x,y) = (C + λL + μT + εD);

[0084]

[0085] The constraints are:

[0086] min(R(s)-Ri)≤γ;

[0087] g(P(x,y))≤A;

[0088] Where C represents the total energy consumption of the mobile robot along the planned inspection path, P(x,y) is the position of the mobile robot on the 3D point cloud map, f(P(x,y)) represents the energy consumption function of the mobile robot at position P(x,y), L represents the length of the planned inspection path; T represents the total time consumption of the mobile robot along the planned inspection path, v represents the speed of the mobile robot, v(P(x,y)) represents the speed function of the mobile robot at position P(x,y); D represents the total deviation between the planned inspection path and the target inspection point set, R(s) represents the trajectory points on the planned inspection path, Ri represents the i-th target inspection point in the target inspection point set, and γ represents the set threshold; (x j ,y j ) represents the j-th boundary point of the closed inspection area; g(P(x,y)) represents the constraint function of the mobile robot at position P(x,y).

[0089] Specifically, during the optimization process, the constraint g(P(x,y))≤A is introduced to consider the impact of the workspace constraint A on the path, ensuring that the path does not traverse impassable areas and does not exceed the scope of the workspace, thus meeting the constraints on the workspace in practical applications. Additionally, the constraint min(R(s)-Ri)≤γ is introduced, requiring the planned path to pass through the neighborhood of the target inspection point, thereby constraining the points along the planned inspection path.

[0090] S240: After navigating along the planned inspection route to each target inspection point, the system uses sensors to sense the environmental data of the target inspection point and uploads the environmental data to the control center.

[0091] In an optional embodiment, the step of navigating along the planned inspection path to each target inspection point includes: dividing the planned inspection path into multiple path points in spatial order; using sensors to obtain in real time whether there are obstacles on the planned inspection road segment between two adjacent path points; if there are obstacles, performing local path planning on the planned inspection road segment to obtain an obstacle avoidance road segment; if there are no obstacles, proceeding along the planned inspection road segment to the next path point until reaching each of the target inspection points.

[0092] Specifically, the planned inspection path is decomposed spatially into a series of path points and a series of planned inspection segments between adjacent path points. Based on the mobile robot's kinematic model, inverse kinematics is performed on each path point to obtain the corresponding joint angle or velocity commands. LiDAR or vision sensors are used to detect obstacles on the mobile robot's path in real time. Once an obstacle is detected, an obstacle avoidance strategy is immediately triggered. By adjusting the mobile robot's speed and direction, the local path is dynamically planned to avoid the obstacle. If no obstacle is found, the robot proceeds along the planned inspection segment to the next path point until it reaches each of the target inspection points.

[0093] Based on the mobile robot's pose feedback, the system determines whether the robot has reached the target path point. Navigation stops when certain threshold conditions are met. Throughout the navigation process, motion control is continuously adjusted based on pose feedback, enabling the robot to accurately track the corrected local path. The mobile robot precisely stops and aligns itself at the target path point, preparing for subsequent environmental perception. Using sensors on the mobile robot, such as RGB-D cameras and infrared thermal imagers, the system perceives the target point and its surrounding environment, acquiring detailed information about the target point and sending the current viewpoint's check completion status to the control center, awaiting the next instruction.

[0094] Optionally, after the step of performing local path planning on the planned inspection route segment to obtain the obstacle avoidance route segment if there is an obstacle, the method further includes: calculating the deviation distance between the obstacle avoidance route segment and the planned inspection route segment; if the deviation distance is greater than a set distance threshold, regenerating the planned inspection route segment to the next path point; if the deviation distance is not greater than the set threshold, walking along the obstacle avoidance route segment and returning to the planned inspection route segment.

[0095] Specifically, let D(a,b) represent the dynamic obstacle detection function of the mobile robot at position (a,b). If there is a dynamic obstacle, then D(a,b) = 1; otherwise, D(a,b) = 0.

[0096] Furthermore, let V(a,b) represent the velocity of the mobile robot at position (a,b), and θ(a,b) represent the orientation angle of the mobile robot at position (a,b). When a dynamic obstacle is detected, an obstacle avoidance strategy needs to be triggered. Obstacle avoidance can be achieved by adjusting the velocity and orientation angle, for example:

[0097] V new (a,b)=V max -k v .D(a,b);

[0098] θ new (a,b)=θ old (a,b)+k θ .sign(θ obs -θ old );

[0099] Among them, V max It is the maximum speed of the mobile robot; k v It is the speed adjustment coefficient, used to adjust the speed according to the distance to the obstacle; θ old It is the current orientation angle of the mobile robot; θ obs It is the angle of the obstacle relative to the mobile robot; k θ It is the angle adjustment coefficient, used to adjust the orientation angle according to the position of the obstacle; sign() is the sign function, used to determine the adjustment direction.

[0100] By adjusting the speed and orientation angle of the mobile robot, the mobile robot can avoid obstacles in real time when it detects dynamic obstacles and continue to move along the original planned inspection path, thereby realizing dynamic planning of local paths.

[0101] If there is a significant deviation between the obstacle avoidance path and the planned inspection path, it needs to be matched with the global path to regenerate a local path passing through the viewpoint; if there is no significant deviation, the path will be followed along the obstacle avoidance path and then returned to the planned inspection path.

[0102] The deviation between the obstacle avoidance path and the planned inspection path can be represented by the Fréchet distance between them. If the deviation exceeds the set threshold Q, it is determined that there is a large deviation between the obstacle avoidance path and the planned inspection path.

[0103] In a specific example, deep learning technology is used to process the environmental data of the uploaded target inspection point to achieve intelligent detection and judgment of abnormal situations such as fire, smoke, and suspicious objects, and the detection results are sent to the control center.

[0104] The technical solution of this invention involves acquiring a 3D point cloud map of a closed inspection area; determining a set of target inspection points based on the inspection task and marking the set of target inspection points on the 3D point cloud map; using a constraint optimization algorithm on the 3D point cloud map to generate a planned inspection path for the mobile robot based on the set of target inspection points and the mobile robot's operating parameters; navigating along the planned inspection path to each target inspection point, sensing environmental data of the target inspection points through sensors, and uploading the environmental data to the control center. This enables real-time path adjustment in a dynamic environment to avoid obstacles, achieving intelligent inspection tasks. This improves the mobile robot's environmental perception and comprehensiveness, enhances its autonomy and adaptability, improves the efficiency and safety of inspection tasks, and increases the response speed and real-time performance of inspection tasks, providing reliable technical support for intelligent inspection in closed scenarios.

[0105] Example 3

[0106] Figure 3 This is a schematic diagram of a closed area inspection device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a map acquisition module 310, a route planning module 320, and a patrol module 330; wherein,

[0107] Map acquisition module 310 is used to acquire a 3D point cloud map of the closed inspection area;

[0108] The path planning module 320 is used to generate a planned inspection path based on the inspection task and the three-dimensional point cloud map.

[0109] The inspection module 330 is used to navigate along the planned inspection path to each target inspection point, perceive the environmental data of the target inspection point through the sensor, and upload the environmental data to the control center.

[0110] The technical solution of this invention acquires a three-dimensional point cloud map of a closed inspection area; generates a planned inspection path based on the inspection task and the three-dimensional point cloud map; navigates along the planned inspection path to each target inspection point, senses the environmental data of the target inspection point through sensors, and uploads the environmental data to the control center. This enables intelligent inspection in a closed environment and has a certain processing capability for dynamic scenes in complex environments, without the need for manual intervention, thus improving inspection efficiency.

[0111] Optional, map acquisition module 310, specifically used for:

[0112] The mobile robot is controlled to move within the closed inspection area, and the surrounding environment is scanned by a lidar mounted on the mobile robot to obtain point cloud data.

[0113] The motion trajectory is estimated based on the odometry data of the mobile robot;

[0114] Based on the real-time positioning and mapping algorithm, a three-dimensional point cloud map of the closed inspection area is generated according to the motion trajectory, the odometer data and the point cloud data.

[0115] Optional, the path planning module 320 includes:

[0116] The patrol point marking unit is used to determine the target patrol point set according to the patrol task, and mark the target patrol point set on the three-dimensional point cloud map;

[0117] The inspection path generation unit is used to generate the planned inspection path of the mobile robot on the three-dimensional point cloud map by using a constrained optimization algorithm based on the target inspection point set and the operation parameters of the mobile robot.

[0118] Optionally, the constrained optimization algorithm includes: an objective function and constraints;

[0119] The objective function is:

[0120] min p(x,y) = (C + λL + μT + εD);

[0121]

[0122] The constraints are:

[0123] min(R(s)-Ri)≤γ;

[0124] g(P(x,y))≤A;

[0125] Where C represents the total energy consumption of the mobile robot along the planned inspection path, P(x,y) is the position of the mobile robot on the 3D point cloud map, f(P(x,y)) represents the energy consumption function of the mobile robot at position P(x,y), L represents the length of the planned inspection path; T represents the total time consumption of the mobile robot along the planned inspection path, v represents the speed of the mobile robot, v(P(x,y)) represents the speed function of the mobile robot at position P(x,y); D represents the total deviation between the planned inspection path and the target inspection point set, R(s) represents the trajectory points on the planned inspection path, Ri represents the i-th target inspection point in the target inspection point set, and γ represents the set threshold; (x j ,y j ) represents the j-th boundary point of the closed inspection area; g(P(x,y)) represents the constraint function of the mobile robot at position P(x,y).

[0126] Optional, the inspection module 330 is specifically used for:

[0127] The planned inspection route is divided into multiple path points according to spatial order;

[0128] The sensors can detect in real time whether there are obstacles on the planned inspection route between two adjacent waypoints;

[0129] If obstacles exist, local path planning is performed on the planned inspection route to obtain obstacle avoidance routes;

[0130] If there are no obstacles, proceed along the planned inspection route to the next path point until reaching each of the target inspection points.

[0131] Optionally, after the step of performing local path planning on the planned inspection route to obtain obstacle avoidance route if obstacles exist, the method further includes:

[0132] The path return module is used to calculate the deviation distance between the obstacle avoidance section and the planned inspection section; if the deviation distance is greater than a set distance threshold, a new planned inspection section to the next path point is generated; if the deviation distance is not greater than the set threshold, the path returns to the planned inspection section after walking along the obstacle avoidance section.

[0133] The closed area inspection device provided in this embodiment of the invention can execute the closed area inspection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0134] Example 4

[0135] Figure 4A schematic diagram of a mobile robot 10, which can be used to implement embodiments of the present invention, is shown. The mobile robot is intended to represent various forms of digital computers, such as laptops, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The mobile robot can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] like Figure 4 As shown, the mobile robot 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the mobile robot 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in the mobile robot 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the mobile robot 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the closed-area inspection method.

[0139] In some embodiments, the closed area inspection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the mobile robot 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the closed area inspection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the closed area inspection method by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] In some embodiments, the closed-area inspection method can be implemented as a computer program, which is implicitly included in a computer program product. When executed by a processor, the computer program implements the closed-area inspection method of the present invention. The computer program product can be understood as a software product that primarily implements its solution through a computer program. The computer program used to implement the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer program causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0143] To provide interaction with a user, the systems and techniques described herein can be implemented on a mobile robot having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the mobile robot. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0144] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0145] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0146] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0147] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for inspecting a closed area, characterized in that, A mobile robot applied to a closed inspection area, the mobile robot being equipped with sensors, the method comprising: Obtain a 3D point cloud map of the closed inspection area; A planned inspection route is generated based on the inspection task and the aforementioned 3D point cloud map; After navigating to each target inspection point along the planned inspection route, the system uses the sensors to sense the environmental data of the target inspection point and uploads the environmental data to the control center. The step of navigating along the planned inspection path to each target inspection point includes: The planned inspection route is divided into multiple path points according to spatial order; The sensors can be used to detect in real time whether there are obstacles on the planned inspection route between two adjacent waypoints; If obstacles exist, local path planning is performed on the planned inspection route to obtain obstacle avoidance routes; Calculate the deviation distance between the obstacle avoidance section and the planned inspection section; If the deviation distance is greater than the set distance threshold, the planned patrol route to the next path point will be regenerated after matching with the global path. If the deviation distance is not greater than the set threshold, then after walking along the obstacle avoidance section, return to the planned inspection section; If there are no obstacles, proceed along the planned inspection route to the next path point until reaching each of the target inspection points.

2. The method for inspecting a closed area according to claim 1, characterized in that, The step of obtaining a 3D point cloud map of the closed inspection area includes: The mobile robot is controlled to move within the closed inspection area, while the surrounding environment is scanned by a lidar mounted on the mobile robot to obtain point cloud data. The motion trajectory is estimated based on the odometry data of the mobile robot; Based on the real-time positioning and mapping algorithm, a three-dimensional point cloud map of the closed inspection area is generated according to the motion trajectory, the odometer data and the point cloud data.

3. The method for inspecting a closed area according to claim 1, characterized in that, The step of generating a planned inspection route based on the inspection task and the 3D point cloud map includes: The target inspection point set is determined according to the inspection task, and the target inspection point set is marked on the three-dimensional point cloud map; On the three-dimensional point cloud map, a constrained optimization algorithm is used to generate the planned inspection path of the mobile robot based on the target inspection point set and the operation parameters of the mobile robot.

4. The method for inspecting a closed area according to claim 3, characterized in that, The constrained optimization algorithm includes: an objective function and constraints; The objective function is: ； ， ； ， ； ； The constraints are: ； ； Where C represents the total energy consumption of the mobile robot along the planned inspection path. To determine the position of the mobile robot on a 3D point cloud map, Indicates the location of the mobile robot The energy consumption function is given by L, where L represents the length of the planned inspection path; T represents the total time consumed by the mobile robot along the planned inspection path; and v represents the speed of the mobile robot. Indicates the location of the mobile robot The velocity function at the location; D represents the total deviation between the planned inspection path and the target inspection point set. This indicates the trajectory points along the planned inspection route. This represents the i-th target inspection point in the target inspection point set. This indicates that a threshold value has been set. This represents the j-th boundary point of the closed inspection area; Indicates the location of the mobile robot The constraint function at that location.

5. A device for inspecting and patrolling a closed area, characterized in that, A mobile robot used in closed inspection areas, the mobile robot being equipped with sensors, the device comprising: The map acquisition module is used to acquire a 3D point cloud map of the closed inspection area; The path planning module is used to generate a planned inspection path based on the inspection task and the 3D point cloud map. The inspection module is used to navigate along the planned inspection path to each target inspection point, perceive the environmental data of the target inspection point through the sensor, and upload the environmental data to the control center. The inspection module is specifically used for: The planned inspection route is divided into multiple path points according to spatial order; The sensors can be used to detect in real time whether there are obstacles on the planned inspection route between two adjacent waypoints; If obstacles exist, local path planning is performed on the planned inspection route to obtain obstacle avoidance routes; Calculate the deviation distance between the obstacle avoidance section and the planned inspection section; If the deviation distance is greater than the set distance threshold, the planned patrol route to the next path point will be regenerated after matching with the global path. If the deviation distance is not greater than the set threshold, then after walking along the obstacle avoidance section, return to the planned inspection section; If there are no obstacles, proceed along the planned inspection route to the next path point until reaching each of the target inspection points.

6. A mobile robot, characterized in that, The mobile robot includes: At least one processor and sensor; and A memory communicatively connected to the at least one processor and sensor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the closed area inspection method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the closed area inspection method according to any one of claims 1-4.

8. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for inspecting a closed area according to any one of claims 1-4.

Images