Inspection path planning method based on multi-layer map
By constructing multi-layer maps and addressing multi-objective optimization problems, the problem of balancing path length, inspection priority, and energy consumption in existing inspection path planning technologies has been solved, achieving efficient planning and endurance for multi-device inspection tasks.
Patent Information
- Application Number
- CN202511166511.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-20
- Publication Date
- 2025-12-02
AI Technical Summary
Existing inspection path planning methods cannot achieve a balance between path length, inspection priority, and energy consumption. In particular, in inspection tasks involving multiple devices, it is difficult to meet the needs of different devices based on their importance and terrain differences.
Based on a multi-layer map construction method, this method constructs maps with multiple information levels, including equipment information, obstacle information, and terrain information, to determine inspection priorities. It then solves path planning through a multi-objective optimization problem, combining the traveling salesman algorithm and genetic algorithm to optimize path length, inspection order, and energy consumption.
It achieves a balance and rationality in path length, inspection priority and energy consumption in multi-device inspection tasks, and enhances the planning ability and endurance of the inspection robot.
Smart Images
Figure CN121048619A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of inspection path planning technology, and in particular to an inspection path planning method based on multi-layer maps. Background Technology
[0002] Manual inspection is labor-intensive and results in inconsistent work quality. Therefore, the need for automated, unmanned equipment inspection by inspection robots, replacing manual labor, has become urgent. Compared to fixed-track inspection robots, autonomous navigation inspection robots, which do not rely on fixed tracks, offer advantages such as higher path freedom and real-time adjustment of inspection strategies, and are gradually becoming a research hotspot in the field of inspection robots.
[0003] Autonomous navigation inspection robots perform inspections based on planned paths. The relevant path planning methods only consider environmental geometry, aiming to plan a route that minimizes collisions with obstacles and minimizes the overall path length. However, this approach cannot meet the inspection objectives of multi-device inspection robots. Because different devices have varying degrees of importance and different terrains, multi-device inspection robots require further trade-offs during path planning to achieve a balance between path length, inspection priority, and energy consumption.
[0004] There is currently no effective solution to the problem that the inspection path planning method of related technologies cannot achieve a balance between path length, inspection priority and energy consumption when dealing with multiple devices. Summary of the Invention
[0005] The present invention provides an inspection path planning method based on a multi-layer map, which at least solves the problem that related inspection path planning methods cannot achieve a balance between path length, inspection priority and energy consumption when dealing with multiple devices.
[0006] This invention provides a multi-layer map-based inspection path planning method, comprising: constructing an inspection map with multiple information levels based on equipment information of each device to be inspected, obstacle information of the target area, and terrain information, wherein each information level corresponds to a different information type; determining the inspection priority of each device to be inspected based on the equipment information; determining a multi-objective optimization problem based on the inspection map and the inspection priority, wherein the multi-objective optimization problem is used to characterize the inspection path planning strategy; and solving the multi-objective optimization problem to obtain the target inspection path.
[0007] The present invention provides a multi-layer map-based inspection path planning method. Equipment information includes equipment geometry, equipment type, and current equipment status. The equipment type and current status are used to determine the inspection priority of each piece of equipment to be inspected. Based on the equipment information of each piece of equipment to be inspected, obstacle information of the target area, and terrain information, an inspection map with multiple information levels is constructed, including: determining the equipment information level of the inspection map based on the equipment geometry of each piece of equipment to be inspected; determining the obstacle information level of the inspection map based on obstacle information; determining the terrain information level of the inspection map based on terrain information; and constructing the inspection map based on the equipment information level, obstacle information level, and terrain information level.
[0008] The inspection path planning method based on multi-layer maps provided by this invention includes equipment information such as the number of historical equipment failures. The method determines the inspection priority of each device to be inspected based on the equipment information, including: determining a first inspection order for each device based on its equipment type; after determining the first inspection order, adjusting the inspection order of devices of the same equipment type based on their current status to determine a second inspection order for each device; and after determining the second inspection order, adjusting the inspection order of devices of the same equipment type and current status based on their historical equipment failures to determine the inspection priority of each device.
[0009] The inspection path planning method based on multi-layer maps provided by the present invention determines a multi-objective optimization problem based on the inspection map and inspection priority, including: determining the constraints of the multi-objective optimization problem based on the inspection map; determining the optimization objective of the multi-objective optimization problem based on the inspection map and inspection priority; and determining the multi-objective optimization problem based on the constraints and optimization objective.
[0010] The present invention provides an inspection path planning method based on a multi-layer map, which determines the constraints of a multi-objective optimization problem based on the inspection map, including: determining obstacle constraints based on the obstacle information hierarchy of the inspection map; determining starting point position constraints based on a preset inspection starting point; determining discrete position constraints based on the equipment information hierarchy of the inspection map, wherein the discrete position constraints are used to characterize the inspection points corresponding to each piece of equipment to be inspected by the inspection robot; and determining the constraints of the multi-objective optimization problem based on the obstacle constraints, starting point position constraints, and discrete position constraints.
[0011] The inspection path planning method based on multi-layer maps provided by the present invention determines the starting point position constraint based on a preset inspection starting point when the inspection robot performs a single inspection task. The method includes: taking the position of the robot charging station on the inspection map as the inspection starting point; and determining the starting point position constraint based on the inspection starting point. The starting point position constraint is used to characterize that the inspection robot passes through the inspection starting point only once during the execution of a single inspection task.
[0012] The present invention provides an inspection path planning method based on a multi-layer map, which determines the optimization objective of a multi-objective optimization problem based on the inspection map and inspection priority, including: determining the inspection sequence objective based on the inspection priority; determining the path length objective based on the obstacle information hierarchy of the inspection map; determining the path flatness objective based on the terrain information hierarchy of the inspection map, wherein the path flatness objective is used to characterize the inspection energy consumption of the inspection robot; and determining the optimization objective of the multi-objective optimization problem based on the inspection sequence objective, the path length objective, and the path flatness objective.
[0013] The inspection path planning method based on a multi-layer map provided by the present invention solves a multi-objective optimization problem and obtains a target inspection path. The method further includes: updating the inspection map based on updated equipment information during the inspection process of the inspection robot based on the target inspection path; determining a new multi-objective optimization problem based on the updated inspection map and obtaining a new inspection path; wherein, after the inspection robot completes the inspection based on the target inspection path, it performs the next inspection based on the inspection command and the new inspection path.
[0014] The inspection path planning method based on multi-layer maps provided by the present invention, before constructing an inspection map including multiple information layers based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area, the method further includes: acquiring the initial information data of each of the equipment information, obstacle information and terrain information; and performing standardization processing, data cleaning processing and spatiotemporal alignment processing on the initial information data in sequence to obtain the equipment information, obstacle information and terrain information.
[0015] An embodiment of the present invention provides an electronic device comprising: a processor, and a memory storing a program, the program including instructions which, when executed by the processor, cause the processor to perform any of the methods described above.
[0016] This invention provides a multi-layer map-based inspection path planning method. By adjusting the constraints and optimization objectives in a multi-objective optimization problem, the target inspection path can take into account the importance of different inspected devices, the energy loss of the inspection robot due to different terrains, and the length of the inspection path. This satisfies the practical requirements of multi-device inspection tasks, exhibiting high balance and rationality, and helps enhance the planning and endurance capabilities of the inspection robot. This addresses the problem of related inspection path planning methods failing to achieve a balance between path length, inspection priority, and energy loss when dealing with multiple devices. Attached Figure Description
[0017] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other embodiments based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the steps of an inspection path planning method based on a multi-layer map in an embodiment of the present invention.
[0019] Figure 2 This is a schematic diagram illustrating the principle of a multi-objective optimization problem in an embodiment of the present invention.
[0020] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0021] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.
[0022] Autonomous navigation inspection robots perform inspections based on planned paths. The relevant path planning methods only consider environmental geometry, aiming to plan a route that minimizes collisions with obstacles and minimizes the overall path length. However, this approach cannot meet the inspection objectives of multi-device inspection robots. Because different devices have varying degrees of importance and different terrains, multi-device inspection robots require further trade-offs during path planning to achieve a balance between path length, inspection priority, and energy consumption.
[0023] Therefore, the present invention provides an inspection path planning method based on a multi-layer map, including steps S101 to S104.
[0024] Step S101: Based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area, construct an inspection map including multiple information levels, wherein the information types corresponding to each information level are different.
[0025] Step S102: Determine the inspection priority of each device to be inspected based on the device information.
[0026] Step S103: Determine the multi-objective optimization problem based on the inspection map and inspection priority. The multi-objective optimization problem is used to characterize the inspection path planning strategy.
[0027] Step S104: Solve the multi-objective optimization problem to obtain the target inspection path.
[0028] The equipment to be inspected may be, but is not limited to, substation equipment, transmission line equipment, and power distribution network equipment.
[0029] Substation equipment includes transformers, switchgear, instrument transformers, surge arresters and insulators, reactive power compensation equipment, secondary equipment, and auxiliary facilities. Transmission line equipment includes poles, conductors, ground wires, insulator strings, and accessories. Distribution network equipment includes distribution transformers, distribution cabinets, ring main units, and cables.
[0030] Equipment information includes, but is not limited to, the number of devices, their geometric dimensions, type, and status. In this embodiment, the equipment information hierarchy of the inspection map is determined based on the device's geometric dimensions, and the inspection priority of each device to be inspected is determined based on its type and current status, effectively incorporating device priority into the inspection path planning. Furthermore, this embodiment further adjusts the inspection priority based on the number of historical equipment failures, resulting in a more reasonable and accurate inspection priority, which will be described in detail later.
[0031] The target area is the area that includes all the equipment to be inspected.
[0032] Obstacle information includes, but is not limited to, obstacle size and obstacle location information.
[0033] In practical application scenarios, the terrain environment of the target area includes, but is not limited to, plains and grasslands, river beaches, gravel areas, gentle slopes with a gradient of 5°-15°, and steep slopes with a gradient of 15°-30°.
[0034] Terrain information can be, but is not limited to, static terrain data of the aforementioned terrain environment, as well as dynamic terrain data after rain or snow.
[0035] Equipment information, obstacle information, and terrain information can all be acquired by sensors.
[0036] The sensor may be, but is not limited to, a fixed sensor set at a preset position in the target area.
[0037] Inspection robots can be equipped with portable sensors to acquire real-time environmental data to update the inspection map.
[0038] With the widespread application of satellite technology and the development of high-precision positioning technology, those skilled in the art can consider using satellite positioning and satellite imagery to obtain the aforementioned equipment information, obstacle information and terrain information, which will not be elaborated further in this embodiment.
[0039] The different information types corresponding to each information level mean that equipment information is set as the equipment information level, obstacle information as the obstacle information level, and terrain information as the terrain information level. Those skilled in the art can introduce corresponding information levels based on other information types to construct a more comprehensive inspection map, depending on the specific application scenario. However, based on the inspection path planning method provided in this embodiment, the inspection map needs to include at least three information levels: equipment information level, obstacle information level, and terrain information level.
[0040] Since the three information levels mentioned above can be further subdivided—for example, the equipment information level can be further divided into equipment geometric dimension information level, equipment type information level, and equipment status information level—the number of "three" in these three categories is not limited to a specific quantity. In practical applications, the specific number of information levels in an inspection map depends not only on the information type but also on the map's construction method and application requirements.
[0041] The inspection map can be constructed in the following ways, but not limited to, raster maps, vector maps, and hybrid maps.
[0042] Raster maps divide space into regular grids, such as squares or hexagons, with each grid storing one or more attribute values. Vector maps represent geographic entities using points, lines, and polygons, with each entity accompanied by an attribute table. Hybrid maps can use rasters to represent continuous attributes and vectors to represent precise entities. This embodiment will subsequently use a raster map as an example, overlaying raster layers with different attributes. The physical coordinates of each raster layer are aligned, but different types of information are stored.
[0043] The inspection priority of each device indicates the order in which the inspection robot inspects each device. Devices with higher inspection priority are inspected first.
[0044] To reduce the calculation time for determining the inspection sequence, multiple inspection priority levels can be established. Even if the number of possible combinations of data such as the quantity, size, type, status, and historical failure count of the equipment to be inspected exceeds the number of inspection priority levels, each piece of equipment to be inspected can still be assigned to a specific inspection priority level based on a unified classification standard. This will be further explained in this embodiment.
[0045] Algorithms for determining multi-objective optimization problems can include, but are not limited to, the Traveling Salesman Problem (TSP), the Rapidly-exploring Random Tree (RRT), and the Orienteering Problem (OP) algorithm. This embodiment will subsequently use the TSP as an example for detailed explanation. Building upon related TSP algorithms, the method provided in this embodiment, based on inspection maps and inspection priorities, determines the multi-objective optimization problem, thus overcoming the limitation of related TSP algorithms that only require finding a shortest path.
[0046] The inspection path planning strategy provided in this embodiment is embodied in the constraints and optimization objectives of a multi-objective optimization problem. Algorithms for solving multi-objective optimization problems can be, but are not limited to, genetic algorithms, particle swarm optimization algorithms, and ant colony optimization algorithms. This embodiment subsequently uses a genetic algorithm to solve the multi-objective optimization problem.
[0047] The inspection path planning method provided in this embodiment constructs an inspection map with multiple information levels based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area; determines the inspection priority of each device to be inspected based on the equipment information; determines a multi-objective optimization problem based on the inspection map and the inspection priority; and solves the multi-objective optimization problem to obtain the target inspection path. By adjusting the constraints and optimization objectives in the multi-objective optimization problem, the target inspection path can take into account the importance of different devices to be inspected, the energy loss of the inspection robot due to different terrains, and the length of the inspection path, thereby meeting the actual requirements of inspection tasks involving multiple devices. It has high balance and rationality, and helps to enhance the planning ability and endurance of the inspection robot.
[0048] The above method can solve the problem that the inspection path planning method of related technologies cannot achieve a balance between path length, inspection priority and energy consumption when dealing with multiple devices.
[0049] Preferably, before constructing an inspection map including multiple information levels based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area in step S101, the above method further includes: acquiring the initial information data of each of the equipment information, obstacle information and terrain information; and performing standardization processing, data cleaning processing and spatiotemporal alignment processing on the initial information data in sequence to obtain the equipment information, obstacle information and terrain information.
[0050] Standardization refers to processing initial information data with a unified format, unit, naming rules, and data structure. It can eliminate format differences and ambiguities in the expression of information from different sources, enabling equipment, obstacle, and terrain information to have a unified data language, avoiding processing interruptions or misreading of information due to format chaos, and improving the efficiency of information processing.
[0051] Data cleaning refers to the quality optimization of standardized data, including outlier handling, missing value imputation, and redundant data removal. This improves the accuracy, completeness, and conciseness of information data, reducing the interference of erroneous and invalid data on subsequent analysis.
[0052] Spatiotemporal alignment processing refers to the unified calibration of cleaned equipment, obstacle, and terrain information in both time and space based on the spatiotemporal characteristics of the inspection scenario. This helps resolve the misalignment of different information in time and space, ensuring that equipment, obstacle, and terrain information can be correlated and integrated within the same spatiotemporal dimension.
[0053] Preferably, the equipment information includes the equipment geometry, equipment type, and current equipment status. The equipment type and current equipment status are used to determine the inspection priority of each piece of equipment to be inspected.
[0054] Step S101: Based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area, construct an inspection map including multiple information levels, including: determining the equipment information level of the inspection map based on the equipment geometry of each device to be inspected; determining the obstacle information level of the inspection map based on the obstacle information; determining the terrain information level of the inspection map based on the terrain information; and constructing the inspection map based on the equipment information level, obstacle information level and terrain information level.
[0055] Constructing a hierarchical inspection map helps to accurately match information characteristics, enabling independent management and updates of information, and avoiding hierarchical confusion caused by mixed information. By switching or overlaying information levels, it is possible to meet the information needs of different scenarios, such as preliminary route planning, on-site inspection navigation, and post-inspection data review.
[0056] Furthermore, the equipment information also includes the number of historical equipment failures.
[0057] Step S102, determining the inspection priority of each device to be inspected based on the equipment information, includes: determining the first inspection sequence corresponding to each device to be inspected based on the equipment type; after determining the first inspection sequence, adjusting the inspection sequence of devices to be inspected with the same equipment type based on the current status of the equipment, and determining the second inspection sequence corresponding to each device to be inspected; after determining the second inspection sequence, adjusting the inspection sequence of devices to be inspected with the same equipment type and current status based on the number of historical failures of the equipment, and determining the inspection priority of each device to be inspected.
[0058] Different equipment types have different levels of importance. Determining the first inspection order based on equipment type is to take the importance of the equipment into account in the inspection sequence. For example, transformers are more important than isolation cabinets and instrument transformer cabinets, so transformers need to be inspected first compared to isolation cabinets and instrument transformer cabinets.
[0059] The current status of equipment can characterize the health of the equipment under inspection. The current status includes, but is not limited to, normal, abnormal, and faulty states. The status of the equipment under inspection can be determined based on its key indicators. For example, the status of a transformer can be determined based on the top oil temperature and winding temperature.
[0060] When equipment is of equal importance, priority should be given to inspecting faulty or abnormal equipment to promptly eliminate false alarms and arrange for maintenance.
[0061] When importance and current status are comparable, equipment with a higher number of historical failures is more likely to have problems than equipment with fewer historical failures. Therefore, it is necessary to prioritize its inspection to help identify faulty or problematic equipment as early as possible.
[0062] Preferably, step S103, determining the multi-objective optimization problem based on the inspection map and inspection priority, includes: determining the constraints of the multi-objective optimization problem based on the inspection map; determining the optimization objective of the multi-objective optimization problem based on the inspection map and inspection priority; and determining the multi-objective optimization problem based on the constraints and optimization objective.
[0063] Determining constraints based on inspection maps helps to anchor feasibility boundaries and ensure that optimization results align with real-world application environments. Using inspection maps and priorities to define optimization objectives allows for a balance and optimization of multi-dimensional needs, including safety and efficiency, as well as completeness and specificity.
[0064] Preferably, the constraints for determining the multi-objective optimization problem based on the inspection map include: determining obstacle constraints based on the obstacle information hierarchy of the inspection map; determining starting point position constraints based on a preset inspection starting point; determining discrete position constraints based on the equipment information hierarchy of the inspection map, wherein the discrete position constraints are used to characterize the inspection points corresponding to each piece of equipment to be inspected that the inspection robot passes through; and determining the constraints for the multi-objective optimization problem based on the obstacle constraints, starting point position constraints, and discrete position constraints.
[0065] Setting obstacle constraints helps ensure path safety and avoid physical conflicts. Setting starting position constraints helps standardize task start and end logic and reduce path redundancy. Setting discrete position constraints helps ensure task integrity and cover core objectives. Obstacle constraints are the baseline, discrete position constraints are the core, and starting position constraints are the benchmark. These three constraints form a mutually supportive logical loop, providing clear input boundaries for multi-objective optimization problems. This allows optimization algorithms to focus on improving efficiency, such as shortening paths and reducing energy consumption, while ensuring that the results conform to the physical limitations and task requirements of the actual scenario.
[0066] Furthermore, when the inspection robot performs a single inspection task, the starting point position constraint is determined based on the preset inspection starting point, including: taking the position of the robot charging station on the inspection map as the inspection starting point; and determining the starting point position constraint based on the inspection starting point; wherein, the starting point position constraint is used to characterize that the inspection robot only passes through the inspection starting point once during the execution of a single inspection task.
[0067] Using robot charging stations as inspection starting points helps ensure the stability of energy supply and the standardization of task processes. Combined with the processing logic of the Traveling Salesman Algorithm, it helps reduce unnecessary backtracking, avoid path redundancy, and improve the efficiency of inspection resource utilization.
[0068] Preferably, the optimization objectives of the multi-objective optimization problem are determined based on the inspection map and inspection priority, including: determining the inspection sequence objective based on the inspection priority; determining the path length objective based on the obstacle information hierarchy of the inspection map; determining the path flatness objective based on the terrain information hierarchy of the inspection map, wherein the path flatness objective is used to characterize the inspection energy consumption of the inspection robot; and determining the optimization objectives of the multi-objective optimization problem based on the inspection sequence objective, the path length objective, and the path flatness objective.
[0069] The inspection sequence objective requires that equipment be inspected in descending order of priority. Determining the inspection sequence objective helps improve the responsiveness of inspection tasks.
[0070] The path length target requires minimizing the total inspection path. Determining the path length target helps improve inspection efficiency and save on inspection energy and time costs.
[0071] The path flatness target requires the inspection path to be as flat as possible. By setting a path flatness target, the energy consumption and inspection difficulty of the inspection robot can be further reduced.
[0072] The schematic diagram of the above multi-objective optimization problem can be referred to... Figure 2 As shown, the inspection sequence target, path length target, and path flatness target constitute the evaluation system of the inspection path from different dimensions. This can avoid the situation where optimizing a single target leads to neglecting one aspect, and enable the inspection path to achieve a comprehensive balance while meeting equipment priority, environmental safety, and resource economy, thereby improving the execution quality of the inspection task.
[0073] When the inspection map is a grid map and the multi-objective optimization problem is based on the Traveling Salesman Algorithm, the above multi-objective optimization problem can be expressed as: ; ; ; ; ; ; ; ; ; ; ; ; ; In the formula, Represents the objective function vector. This indicates the inspection sequence target, i.e., priority indicators; This represents the target for path length and the target for path flatness, i.e., the path length index and the terrain index; This indicates the total number of inspection points, which corresponds to the number of equipment to be inspected. and All are weighting coefficients.
[0074] and All are decision variables and satisfy: ; ; This indicates that the order of inspection point 1 is 1, meaning that inspection point 1 is assigned to be inspected first.
[0075] Continuing, Indicates the inspection priority of inspection point i; This represents the coordinates of the k-th point in the path sequence from inspection point i to inspection point j; This represents the path sequence from inspection point i to inspection point j. This represents the number of points contained in the path sequence from inspection point i to inspection point j; Represents a set of obstacles; Represents a set of map grids; Represents the terrain coefficient, satisfying: ; For example, the inspection priority of inspection point i Values range from 1 to 4, indicating four inspection priority levels, corresponding to inspection priorities from highest to lowest. A value of 1 indicates the highest inspection priority. A score of 4 indicates the lowest inspection priority.
[0076] Preferably, after solving the multi-objective optimization problem and obtaining the target inspection path in step S104, the method further includes: updating the inspection map based on updated equipment information during the inspection process of the inspection robot based on the target inspection path. A new multi-objective optimization problem is determined based on the updated inspection map, and a new inspection path is obtained. After the inspection robot completes its inspection based on the target inspection path, it performs the next inspection based on the inspection command and the new inspection path.
[0077] By dynamically updating the map and generating new paths during the inspection process, it is possible to achieve adaptive adjustments to the inspection task. The aforementioned inspection instructions can be automatically generated by the inspection robot or inspection system based on the inspection results of the target inspection path, or they can be issued by technicians.
[0078] refer to Figure 3The present invention will now describe a structural block diagram of an electronic device that can serve as an embodiment of the present invention, serving as an example of a hardware device applicable to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, 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 present invention described and / or claimed herein.
[0079] like Figure 3 As shown, the electronic device includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0080] Multiple components in the electronic device are connected to I / O interface 305, including: input unit 306, output unit 307, storage unit 308, and communication unit 309. Input unit 306 can be any type of device capable of inputting information into the electronic device. Input unit 306 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device. Output unit 307 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 308 may include, but is not limited to, disks and optical discs. Communication unit 309 allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, and / or wireless communication transceivers, such as Bluetooth devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.
[0081] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, CPUs, graphics processing units (GPUs), various special-purpose artificial intelligence (AI) computing units, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above. For example, in some embodiments, the method embodiments of the present invention can be implemented as computer programs tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 302 and / or communication unit 309. In some embodiments, the computing unit 301 can be configured to perform the methods described above by any other suitable means (e.g., by means of firmware).
[0082] The present invention also provides a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of the present invention.
[0083] The present invention also provides a computer program product, including a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform the method of the embodiments of the present invention.
[0084] This invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, causes the electronic device to perform the method of this invention.
[0085] Computer programs for implementing the methods of embodiments of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0086] In the context of embodiments of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable signal medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, or infrared systems, apparatus, or devices, or any suitable combination of the foregoing. 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 of the foregoing.
[0087] It should be noted that the term "comprising" and its variations used in the embodiments of this invention are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "a plurality" mentioned in the embodiments of this invention are illustrative and not restrictive, and those skilled in the art should understand that unless explicitly indicated otherwise in the context, they should be understood as "one or more". The descriptions of terms such as "first", "second", etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of indicated technical features.
[0088] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this invention are all information and data authorized by the user or fully authorized by all parties.
[0089] The steps described in the method embodiments provided by the present invention can be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.
[0090] The term "embodiment" in this specification refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily imply the same embodiment, nor does it imply independence or alternativeity from other embodiments. The various embodiments in this specification are described in a related manner, with reference to each other for similar or identical parts. In particular, for apparatus, device, and system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, and relevant details are referred to in the description of the method embodiments.
[0091] The above-described embodiments are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the inventive concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.
Claims
1. A method for planning inspection paths based on multi-layer maps, characterized in that, include: Based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area, an inspection map with multiple information levels is constructed, where each information level corresponds to a different information type. The inspection priority of each device to be inspected is determined based on the equipment information. Based on the inspection map and the inspection priority, a multi-objective optimization problem is determined, which is used to characterize the inspection path planning strategy. Solve the multi-objective optimization problem to obtain the target inspection path.
2. The method according to claim 1, characterized in that, The equipment information includes the equipment's geometric dimensions, equipment type, and current equipment status. The equipment type and current equipment status are used to determine the inspection priority of each piece of equipment to be inspected. Based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area, an inspection map with multiple information levels is constructed, including: The equipment information hierarchy of the inspection map is determined based on the equipment geometry of each device to be inspected. The obstacle information hierarchy of the inspection map is determined based on the obstacle information. The terrain information level of the inspection map is determined based on the terrain information. The inspection map is constructed based on the device information level, the obstacle information level, and the terrain information level.
3. The method according to claim 2, characterized in that, The equipment information also includes the number of historical equipment failures; Based on the equipment information, the inspection priority of each piece of equipment to be inspected is determined, including: The first inspection sequence corresponding to each device to be inspected is determined based on the device type. After determining the first inspection sequence, the inspection sequence of the devices with the same type is adjusted based on the current status of the devices to determine the second inspection sequence for each device. After determining the second inspection sequence, the inspection sequence of the devices to be inspected that are the same in terms of equipment type and current status is adjusted based on the number of historical failures of the equipment, and the inspection priority of each device to be inspected is determined.
4. The method according to claim 1, characterized in that, Based on the inspection map and the inspection priority, a multi-objective optimization problem is determined, including: The constraints of the multi-objective optimization problem are determined based on the inspection map. The optimization objective of the multi-objective optimization problem is determined based on the inspection map and the inspection priority. The multi-objective optimization problem is determined based on the constraints and the optimization objective.
5. The method according to claim 4, characterized in that, The constraints of the multi-objective optimization problem are determined based on the inspection map, including: Obstacle constraints are determined based on the obstacle information hierarchy of the inspection map; The starting point position constraint is determined based on the preset inspection starting point; Discrete position constraints are determined based on the device information hierarchy of the inspection map, wherein the discrete position constraints are used to characterize the inspection points corresponding to each device to be inspected that the inspection robot passes through. Based on the obstacle constraints, the starting position constraints, and the discrete position constraints, the constraints of the multi-objective optimization problem are determined.
6. The method according to claim 5, characterized in that, When the inspection robot performs a single inspection task, the starting position constraints are determined based on the preset inspection starting point, including: The location of the robot charging station on the inspection map is taken as the starting point of the inspection. The starting point position constraint is determined based on the inspection starting point; The starting point position constraint condition is used to characterize that the inspection robot only passes through the inspection starting point once during the execution of the single inspection task.
7. The method according to claim 4, characterized in that, The optimization objective of the multi-objective optimization problem is determined based on the inspection map and the inspection priority, including: The inspection sequence target is determined based on the inspection priority. The target path length is determined based on the obstacle information hierarchy of the inspection map; The path flatness target is determined based on the terrain information hierarchy of the inspection map, wherein the path flatness target is used to characterize the inspection energy consumption of the inspection robot. Based on the inspection sequence objective, the path length objective, and the path flatness objective, the optimization objective of the multi-objective optimization problem is determined.
8. The method according to claim 1, characterized in that, After solving the multi-objective optimization problem and obtaining the target inspection path, the method further includes: During the inspection process of the inspection robot based on the target inspection path, the inspection map is updated based on the updated equipment information; Based on the updated inspection map, a new multi-objective optimization problem is determined, and a new inspection path is obtained. After the inspection robot completes the inspection based on the target inspection path, it performs the next inspection based on the inspection command and the new inspection path.
9. The method according to claim 1, characterized in that, Before constructing an inspection map with multiple information levels based on the equipment information of each device to be inspected, the obstacle information and terrain information of the target area, the method further includes: Acquire the initial information data of the device information, the obstacle information, and the terrain information; The initial information data is then subjected to standardization, data cleaning, and spatiotemporal alignment processes in sequence to obtain the device information, obstacle information, and terrain information.
10. An electronic device, comprising: A processor and a memory storing a program, characterized in that the program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 9.