WO2024051437A1 - 一种路径规划方法、相关装置及系统 - Google Patents

一种路径规划方法、相关装置及系统 Download PDF

Info

Publication number
WO2024051437A1
WO2024051437A1 PCT/CN2023/112155 CN2023112155W WO2024051437A1 WO 2024051437 A1 WO2024051437 A1 WO 2024051437A1 CN 2023112155 W CN2023112155 W CN 2023112155W WO 2024051437 A1 WO2024051437 A1 WO 2024051437A1
Authority
WO
WIPO (PCT)
Prior art keywords
inspection
points
point
path
inspected
Prior art date
Application number
PCT/CN2023/112155
Other languages
English (en)
French (fr)
Inventor
杨磊
刘小武
郑鹏鹏
鄢文刚
肖凡
Original Assignee
华为云计算技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为云计算技术有限公司 filed Critical 华为云计算技术有限公司
Publication of WO2024051437A1 publication Critical patent/WO2024051437A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/242—Means based on the reflection of waves generated by the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/243—Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/246—Arrangements for determining position or orientation using environment maps, e.g. simultaneous localisation and mapping [SLAM]
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/40—Control within particular dimensions
    • G05D1/43—Control of position or course in two dimensions
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60—Intended control result
    • G05D1/617—Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards
    • G05D1/622—Obstacle avoidance
    • G05D1/633—Dynamic obstacles
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60—Intended control result
    • G05D1/648—Performing a task within a working area or space, e.g. cleaning
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00—Types of controlled vehicles
    • G05D2109/10—Land vehicles

Definitions

  • the present application relates to the field of communications, and in particular, to a path planning method, related devices and systems.
  • Inspection equipment (such as inspection robots) is required to inspect the power equipment in the power station regularly or irregularly. Through inspection, photos of the power equipment are collected so that the power equipment can be inspected based on the collected photos. Management and operation of power equipment.
  • the method of inspecting equipment is to use the computing device to generate an inspection path based on each point to be inspected, where the point to be inspected refers to the location of the point to be inspected, that is, the power source to be inspected.
  • the location of the equipment or manually mark the inspection path according to each inspection point on the computing device, and then the computing device sends the inspection path to the inspection device, and the inspection device analyzes each inspection path to be inspected based on the inspection path. Click for inspection.
  • This inspection method has the following disadvantages: when the inspection point is located in a location with complex or special road conditions, such as a right-angle turn, a fork in the road, a narrow road, a slope, etc., the inspection equipment will When taking pictures of the electrical equipment at these locations along the inspection route, there may be cases where the pictures fail or the pictures are unqualified.
  • This application provides a path planning method, related devices and systems.
  • the inspection path generated according to the method is more accurate. Inspection is carried out based on the inspection path generated by this application, and the success rate of image shooting is high.
  • this application provides a path planning method. From the perspective of a computing device, the method includes: the computing device receives information input by a user, and the information input by the user includes a plurality of points to be inspected; The computing device generates one or more correction points based on the plurality of points to be inspected and the map, where the correction points are points set at specific road conditions in the map; the computing device An inspection path is generated based on the multiple points to be inspected and the one or more correction points. The inspection path includes the inspection sequence of each point, and each point includes the multiple points.
  • the computing device sends the inspection path to the inspection device, so that the inspection device determines the inspection path according to the inspection path and real-time traffic information.
  • An inspection route is generated, where the inspection route refers to the actual route taken by the inspection equipment to inspect the multiple points to be inspected.
  • this application provides a path planning method.
  • the computing device uses the method described in this application, the computing device generates an inspection path based on the points to be inspected and the corrected points, and the inspection equipment then generates an inspection path based on real-time road condition information and inspection
  • the path determines the inspection route.
  • the correction point is a point set at a specific traffic position in the map to make the inspection route more accurate.
  • the inspection path generated by the computing device is more accurate, making the inspection more accurate.
  • the inspection route determined by the equipment based on the inspection path and real-time traffic information is more accurate, thereby increasing the success rate of the inspection equipment taking pictures at the points to be inspected.
  • the information input by the user also includes task requirements, and the task requirements include the shortest inspection route; the based on the plurality of points to be inspected and the One or more correction points and generating an inspection path include: generating the inspection path according to the multiple points to be inspected, the one or more correction points and the task requirements.
  • the inspection path or inspection line can be generated according to the actual needs of the user, where the user's need may, for example, require the shortest inspection line.
  • the computing device When generating an inspection path, the computing device generates an inspection path according to the user's needs based on multiple points to be inspected and one or more correction points. The method described in this application is used to improve the user experience and satisfy the user. Actual demand.
  • the task requirement further includes an access time allowed for at least one of the plurality of points to be inspected.
  • points to be inspected have access time requirements, and the task requirements may also include the access time allowed for one or more points to be inspected.
  • the correction point is located at one or more locations near a turn, a fork, a slope section, or a narrower section.
  • the inspection path is only generated based on multiple points to be inspected, and the inspection equipment only performs inspection based on multiple points to be inspected or performs inspection based on the inspection path generated from multiple points to be inspected.
  • the inspection equipment due to the insufficient accuracy of the inspection route, there are shooting conditions at some specific road conditions. Failure to take photos or taking unqualified photos.
  • this application adds correction points.
  • the inspection path and inspection route are generated based on the points to be inspected and the correction points, which improves the accuracy of the inspection route.
  • the specific road condition location includes, for example, one or more locations near a turn, near a fork in the road, a sloped road section, or a narrower road section.
  • the method further includes: the computing device receives a user The user's operation includes adding and/or deleting the correction point.
  • the user can modify the generated correction points, such as adding correction points or deleting correction points.
  • the "wall penetration" problem can be better solved, making inspection paths and inspection lines more accurate.
  • this application provides a path planning method. From the perspective of inspection equipment, the method includes: the inspection equipment receives an inspection path sent by a computing device, and the inspection path includes inspection paths at each point. Inspection sequence, each point includes a plurality of points to be inspected and one or more correction points, wherein the one or more correction points are determined by the computing device according to the plurality of points to be inspected and a map, set at a point at a specific road condition location in the map; the inspection equipment acquires real-time traffic information while walking according to the inspection path, and determines the inspection route based on the real-time traffic information, The inspection route refers to the actual route taken by the inspection equipment to inspect the multiple points to be inspected.
  • the inspection route is generated based on the inspection path, and the inspection path is generated based on the points to be inspected and the correction points.
  • the inspection equipment can fine-tune the inspection route based on real-time traffic information. In the face of different road conditions, the inspection equipment has different fine-tuning methods to further ensure the accuracy of the inspection route and improve the shooting success rate.
  • the correction point is located at one or more locations near a turn, a fork, a slope section, or a narrower section.
  • the inspection equipment acquires real-time traffic information while walking according to the inspection path, and determines the inspection route based on the real-time traffic information, including: When the inspection equipment is located at any point in the inspection path, the inspection equipment determines a shortest path from at least one path from the current point to the next point, as the shortest path from the current point to the next point. The inspection route to the next point; wherein, the inspection equipment acquires real-time traffic information during the inspection process from the current point to the next point, and adjusts the inspection route according to the real-time traffic information.
  • the real-time road condition information includes one or more of road conditions with obstacles and uneven road conditions.
  • the inspection equipment automatically adjusts the inspection route according to the real-time traffic information.
  • the inspection equipment can ensure the normal progress of the inspection work and ensure the successful image capture of each point to be inspected. Rate.
  • this application provides a path planning device, including:
  • An interactive module configured to receive user-input information, where the user-input information includes multiple points to be inspected;
  • a generation module configured to generate one or more correction points based on the plurality of points to be inspected and the map, wherein the correction points are points set at specific road conditions in the map;
  • the generating module is also configured to generate an inspection path based on the plurality of points to be inspected and the one or more correction points, where the inspection path includes the inspection sequence of each point, so Each of the points includes the plurality of points to be inspected and the one or more correction points;
  • a communication module configured to send the inspection path to the inspection equipment, so that the inspection equipment generates an inspection line based on the inspection path and real-time traffic information, where the inspection line refers to the inspection line.
  • the information input by the user also includes task requirements, and the task requirements include the shortest inspection route; the generating module is configured to: according to the plurality of inspection lines to be inspected, Points, the one or more correction points and the task requirements generate the inspection path.
  • the task requirements further include the access time allowed for at least one of the plurality of points to be inspected.
  • the correction point is located at one or more locations near a turn, a fork, a slope section, or a narrower section.
  • the interaction module is further configured to receive a user's operation, where the user's operation includes adding and/or deleting the correction point.
  • Each functional module of the third aspect is used to implement the method described in the above-mentioned first aspect or any possible implementation manner of the first aspect.
  • this application provides a path planning device, including:
  • a communication module configured to receive an inspection path sent by the computing device.
  • the inspection path includes the inspection sequence of each point, and each point includes a plurality of points to be inspected and one or more correction points. , wherein the one or more correction points are points set by the computing device at specific road conditions in the map based on the multiple points to be inspected and the map;
  • a processing module configured to obtain real-time road condition information during walking according to the inspection path, and determine an inspection route based on the real-time road condition information.
  • the inspection route refers to the inspection station of the inspection equipment. Describe the actual routes taken during the process of multiple points to be inspected.
  • the correction point is located at one or more locations near a turn, a fork, a slope section, or a narrower section.
  • the processing module is configured to: when the inspection equipment is located at any point in the inspection path, at least one point from the current point to the next point Determine a shortest path in a path as an inspection route from the current point to the next point;
  • the processing module is also configured to: the inspection equipment obtain real-time traffic information during the inspection process from the current point to the next point, and adjust the location from the current point according to the real-time traffic information.
  • the real-time road condition information includes one or more of road conditions with obstacles and uneven road conditions.
  • Each functional module of the fourth aspect is used to implement the method described in the above-mentioned second aspect or any possible implementation manner of the second aspect.
  • the present application provides a computing device cluster, including at least one computing device, each of the at least one computing device including a processor and a memory, and the processor of the at least one computing device is configured to execute the The instructions stored in the memory of the at least one computing device enable the cluster of computing devices to execute the method described in the first aspect or any possible implementation of the first aspect.
  • the present application provides a computer-readable storage medium, including computer program instructions.
  • the computer program instructions When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the above first aspect or any of the first aspects.
  • One possible implementation is the method described.
  • the present application provides a computer program product containing instructions, characterized in that, when the instructions are executed by a computing device cluster, the computing device cluster causes the computing device cluster to execute the first aspect or any one of the first aspects. possible implementation methods.
  • the present application provides an inspection device, including a processor and a memory.
  • the memory is used to store instructions.
  • the processor is used to run the instructions stored in the memory to execute the above second aspect or the second aspect. any possible implementation method.
  • the present application provides a computer-readable storage medium, which is characterized by including program instructions.
  • the program instructions are executed by the inspection equipment, the inspection equipment executes the above second aspect or the second aspect. any possible implementation method.
  • the present application provides a computer program product containing instructions, characterized in that when the instructions are run by the inspection equipment, the inspection equipment is caused to execute the above second aspect or any one of the second aspects. possible implementation methods.
  • the present application provides a system, which includes a computing device and an inspection device.
  • the computing device is the computing device described in the above first aspect or any possible implementation of the first aspect.
  • Equipment the inspection equipment is the inspection equipment described in the above second aspect or any possible implementation of the second aspect, or the computing device is the above third aspect or any one of the third aspects
  • the path planning device described in a possible implementation manner the inspection equipment is the path planning device described in the above fourth aspect or any possible implementation manner of the fourth aspect.
  • Figure 1 is a schematic diagram of a system architecture provided by this application.
  • FIG. 2 is a schematic diagram of another system architecture provided by this application.
  • Figure 3 is a schematic flow chart of a path planning method provided by this application.
  • Figure 4A is an example diagram provided by this application.
  • Figure 4B is an example diagram provided by this application.
  • Figure 4C is an example diagram provided by this application.
  • Figure 4D is an example diagram provided by this application.
  • Figure 4E is an example diagram provided by this application.
  • Figure 4F is an example diagram provided by this application.
  • Figure 5 is an example diagram of a scenario provided by this application.
  • Figure 6 is a schematic structural diagram of a path planning device provided by this application.
  • Figure 7 is a schematic structural diagram of a computing device provided by this application.
  • Figure 8 is a schematic structural diagram of a computing device cluster provided by this application.
  • FIG. 9 is a schematic structural diagram of another computing device cluster provided by this application.
  • Figure 10 is a schematic structural diagram of another path planning device provided by this application.
  • Figure 11 is a schematic structural diagram of an inspection equipment provided by this application.
  • FIG. 1 is a schematic diagram of a system architecture provided by this application.
  • the system involves at least one inspection device 110, a network device 120, and at least one computing device 130.
  • the computing device 130 may be, for example, a desktop computer, a notebook, a server, etc.
  • the computing device 130 may be a computing device 130 located in a cloud, such as a central server, where the cloud may be a private cloud, a public cloud, or a hybrid cloud.
  • Computing device 130 may also be a computing device 130 located in an edge environment, such as an edge server.
  • the cloud environment refers to the central computing device 130 cluster owned by the cloud service provider for providing computing, storage, and communication resources.
  • the computing device 130 cluster is usually far away from the inspection device 110.
  • the edge environment refers to the geographical location. A cluster of edge computing devices 130 that are close to the inspection device 110 and used to provide computing, storage, and communication resources.
  • the computing device 130 is configured to receive information input by the user, where the information input by the user includes multiple points to be inspected.
  • the information input by the user can also include task requirements.
  • the task requirements include, for example, the shortest inspection route, inspection access within the time allowed for access to the point to be inspected, etc., where the inspection route refers to the inspection.
  • the computing device 130 is also configured to generate one or more correction points based on the information input by the user and the map, and generate an inspection path based on the multiple points to be inspected and the one or more correction points.
  • the inspection path includes passing through The inspection sequence of each point, where each point includes multiple points to be inspected and one or more correction points.
  • the map is stored locally on the computing device 130 .
  • Correction points are points set at specific road conditions in order to make the inspection route more accurate.
  • the specific road condition locations include one or more locations near turns, forks, slope sections, and narrow road sections.
  • the point to be inspected refers to the location of the power equipment.
  • the inspection equipment 110 needs to take pictures at the point to be inspected.
  • the corrected point is used to assist in generating an inspection path or inspection route. Device 110 does not need to take a picture at the correction point.
  • the inspection path is the inspection sequence of each point.
  • each point includes point A, point B, point C and point D
  • the inspection path is point A-point B-point C-point D.
  • the meaning of this inspection path is, First visit point A, then visit point B, then visit point C, and finally visit point D.
  • the inspection path does not need to specify which inspection line is between adjacent points.
  • the inspection path may include the specific inspection lines between adjacent points. For how to determine which inspection lines between adjacent points, please refer to the method below. The description of the embodiment will not be introduced here.
  • the computing device 130 is also configured to receive the user's correction operation on the correction point, such as adding a correction point or deleting a correction point.
  • the network device 120 is used to communicate between the computing device 130 and the inspection device 110 through a communication network of any communication mechanism/communication standard.
  • the communication network may be a wide area network, a local area network, a point-to-point connection, or any combination thereof.
  • the computing device 130 sends the generated inspection path to the inspection device 110 through the network device 120.
  • the computing device 130 can also send a task requirement to the inspection device 110.
  • the task requirement is, for example, the shortest inspection route.
  • the inspection device 110 may be a robot, for example.
  • the inspection device 110 is used to receive the inspection path sent by the computing device 130, and determine the inspection route based on the inspection path and the collected real-time traffic information, so as to implement inspection of each point to be inspected.
  • FIG. 2 is a schematic diagram of yet another system architecture provided by this application.
  • the user inputs multiple points to be inspected and task requirements (for example, in Figure 2, the shortest inspection path, the time allowed to access one or more points to be inspected) into the computing device, and the computing device determines the number of points to be inspected based on the number of points to be inspected.
  • the inspection points and the map generate correction points, and the inspection path is planned based on multiple points to be inspected, correction points and task requirements, and the computing device sends the generated inspection path to the inspection device. After the computing device generates the correction point, the user can modify the correction point.
  • the inspection equipment determines the inspection lines between adjacent points based on the inspection path.
  • the inspection equipment determines the inspection lines between adjacent points.
  • the inspection equipment may determine the inspection lines between adjacent points before inspection, or the inspection equipment may be located at each When the point is on, determine the inspection route from the current point to the next point. For example, when the inspection equipment is located at a certain inspection point, determine the inspection route from the current point to the next point, and then Inspection is carried out according to the inspection route. When reaching the next point, the inspection route between this point and the next point is calculated again.
  • the inspection equipment can adaptively determine the local line during the inspection process from the current point to the next point.
  • how to adaptively determine the local line please refer to the relevant description in the method embodiment below, which will not be elaborated here. describe.
  • Figure 3 is a schematic flow chart of a path planning method provided by this application. The methods include, but are not limited to, the description below.
  • the computing device receives information input by the user.
  • the information input by the user includes multiple points to be inspected.
  • the information input by the user includes multiple points to be inspected.
  • the information input by the user can also include task requirements.
  • the task requirements include task goals.
  • the task goal can be, for example, the shortest inspection route or the shortest inspection consumption time.
  • the inspection consumption time refers to the inspection equipment walking from the starting point to The elapsed time to the end point.
  • the task goal can also be the shortest time it takes for the inspection equipment to calculate the inspection path.
  • the task goal can be set to the shortest time it takes for the inspection equipment to calculate the inspection path between two adjacent points.
  • the task The goal can also be set to the shortest time it takes for the inspection equipment to calculate the local path while walking from the current point to the next point.
  • the time it takes for the inspection equipment to calculate the inspection path details will be given in step S105 below. Introduction, the description will not be expanded here. For related content, please refer to the description in step S105.
  • the task requirements may also include the access time allowed for at least one of the multiple points to be inspected.
  • one or more points to be inspected can be set with access time allowed.
  • the time allowed for access to a certain point to be inspected can be a time window, such as 10:00 am-11:00 am; it can also be the latest time allowed for access, for example, the latest time allowed for access every day is 11:00 a.m., which means that the inspection equipment needs to complete access to the point to be inspected before 11:00 a.m. every day; it can also be the earliest time allowed for access, for example, the earliest time allowed for access every day is 10 a.m. :00, which means that the inspection equipment needs to access the point to be inspected after 10:00 am every day.
  • the computing device may include a user interaction interface.
  • the user interaction interface may be used to display information.
  • the user interaction interface may be used to display multiple points to be inspected.
  • the user interaction interface may also be used to display task requirements, such as displaying tasks.
  • Target can also be used to display the access time allowed to one or more points to be inspected, etc.
  • the computing device generates one or more correction points based on multiple points to be inspected and the map.
  • the computing device stores the map locally, and the computing device generates one or more correction points based on the map and multiple points to be inspected, where the one or more correction points are used to assist in generating the points based on the multiple points to be inspected. Inspection path.
  • This application does not limit the algorithm for generating correction points.
  • the correction point is located at one or more locations near turns, forks, slope sections, or narrow road sections.
  • the turning point means the area centered on the turning point and a certain distance from the turning point.
  • the vicinity of the turning point includes the turning point.
  • a certain distance can be set according to actual road conditions or actual application scenarios.
  • the certain distance can be 0.5 meters, 0.8 meters, 1 meter, 1.3 meters, etc. This application does not limit a certain distance.
  • the turning point refers to the location where the direction of the road changes significantly or the direction of the vehicle changes significantly when driving on the road. .
  • the location where the vehicle's driving direction changes significantly when the vehicle is driving on the road is used as an example for explanation.
  • the driving direction of the vehicle in Figure 4A and Figure 4B is from driving eastward and turning to driving north.
  • Point a in Figure 4A is the turning point
  • point b in Figure 4B is the turning point.
  • Figure 4A is a right-angle turn
  • Figure 4B is a non-right-angle turn; refer to the schematic diagram shown in Figure 4C, at point c, the driving direction changes from driving north to driving east
  • point c is the turning point.
  • how much change is called a major change, it can be determined by setting different angle thresholds or latitude and longitude thresholds according to different application scenarios or different road conditions. For example, when the difference in longitude and latitude of two connected roads exceeds the threshold , it is determined that the road direction has changed significantly, and it is determined to be near the turning point, and a correction point can be generated. For example, when the angle between two connected roads exceeds the threshold, it is determined that the road direction has changed significantly. If it is changed and determined to be near the turning point, a correction point can be generated.
  • This application does not limit the angle threshold or latitude and longitude threshold.
  • Turns include right-angle turns, as shown in Figure 4A, and non-right-angle turns, as shown in Figures 4B, 4E, and 4F.
  • the schematic diagrams shown in Figures 4A to 4F are only for examples and do not limit the application. , the turn can also be other forms of turns, which are not limited in this application.
  • the fork in the road can be a T-shaped fork in the road, as shown in Figure 4C, or a Y-shaped fork in the road, as shown in Figure 4D, or a cross-shaped intersection, or other forms of forks in the road, which are not included in this application. limited.
  • the area near the fork intersection refers to the area centered on the bifurcation point and a certain distance away from the bifurcation point.
  • the vicinity of the fork intersection includes the bifurcation point.
  • a certain distance can be set according to actual road conditions or actual application scenarios. For example, a certain distance can It is 0.5 meters, 0.8 meters, 1 meter, 1.4 meters, etc. This application does not limit certain distances.
  • a slope road section refers to a road section with a certain slope. This application does not limit the length of the road section. Slope here is a relative concept. A certain road has a certain slope relative to adjacent roads or connected roads, or a certain road section has a certain slope relative to adjacent road sections or connected road sections. In this application, the slope section can refer to an uphill section, a downhill section, or an uneven road section. Road sections (rugged road sections can be understood as including both uphill sections and downhill sections) are not limited in this application.
  • a narrower road section refers to a road section with a smaller width. This application does not limit the width smaller than a narrower road section.
  • Narrow road sections can be determined by setting a width threshold. For example, the threshold can be set to 0.5 meters or 0.8 meters. When the road width is less than the width threshold, the road is determined to be a narrow road section. This application does not limit the width threshold. In actual application, it can be determined based on specific application scenarios and specific circumstances.
  • the correction points are located at one or more locations near turns, forks, slope sections, or narrow road sections, so that accurate patrols can be generated later based on the correction points and the points to be inspected.
  • the inspection equipment travels to a location with more complex or special road conditions, such as corners, forks, narrow roads, slopes, etc., it can walk according to the precise inspection path to achieve power monitoring.
  • the image collection of the equipment avoids the failure or unqualified image collection, and improves the image shooting efficiency and inspection success rate.
  • the map in the computing device may contain some damaged areas. For example, in real life, there is a wall between two roads or a wall between two electrical devices. However, due to loopholes (bugs) in the map, this The blocked wall is not displayed on the map.
  • the generated inspection path may be a "through-wall" path. If you follow the "through-wall” path, the inspection equipment It may hit or hit a wall, causing the inspection to fail.
  • MN represents a wall with a certain thickness. Due to the damage to the map, the wall at MN is not displayed.
  • the generated one or more correction points can be displayed through the user interaction interface.
  • the user can correct the generated correction points, for example, add correction points.
  • the user can add some correction points on the map, or delete the correction points, and the computing device receives the user's correction Point correction operation.
  • the processing process of this step is roughly as follows: 1) Voxelize the map, that is, convert the vector model of the map into lattice information; 2) Based on the lattice information (voxelized map), determine the plane that can be passed by the inspection equipment , filter out inaccessible planes; 3) Divide the determined plane accessible to inspection equipment into multiple areas that do not overlap and have no holes; 4) For the multiple areas obtained in step 3), generate each The outline of the area, and merge the outlines of multiple areas into one outline; 5) Divide the generated outline into multiple convex polygons. Any two convex polygons among the multiple convex polygons can be reached through line segments, so Obtain a polyhedral plot. After multiple points to be inspected are input into the computing device, the computing device marks the multiple points to be inspected on the polyhedron map and generates one or more correction points based on the algorithm.
  • the computing device generates an inspection path based on multiple points to be inspected and one or more correction points.
  • the inspection path includes the inspection sequence of each point.
  • the inspection path is the inspection sequence of each point.
  • the inspection path does not include the inspection lines between adjacent points. Which one specifically. In this implementation, when there is only one line between adjacent points, the inspection lines between adjacent points are determined.
  • the information input by the user includes the access time allowed for one or more points to be inspected, and the computing device determines the patrol time of each point based on the access time allowed for one or more points to be inspected.
  • Check sequence In one implementation, a mathematical model can be established to determine the inspection sequence of each point through an algorithm. Setting constraints when building a mathematical model includes:
  • Constraint 1 The access time allowed to one or more points to be inspected
  • Constraint 2 All points are accessed in one inspection task, and all points include all points to be inspected and all correction points;
  • the inspection sequence of each point is determined through algorithm solution.
  • the algorithm can be a genetic algorithm. This application does not limit the algorithm used to determine the inspection sequence.
  • the above constraints are just examples. During specific implementation, the constraints can be modified according to actual application requirements.
  • the information input by the user includes a task goal, for example, the task goal is the shortest inspection route, and the computing device determines the inspection path based on each point and the task goal.
  • the computing device determines the inspection order of each point, and then selects a shortest path from multiple paths between adjacent points as the shortest path between adjacent points.
  • the inspection route is obtained, and thus the inspection path is obtained.
  • the inspection path includes the inspection sequence of each point and the specific inspection lines between adjacent points.
  • the information input by the user includes the mission goal and the time allowed to access one or more points to be inspected.
  • the mission goal is the shortest inspection path.
  • the computing device determines the mission goal and the one or more points to be inspected.
  • the access time allowed by a point determines the order of each point.
  • the computing device sends the inspection path to the inspection device, and accordingly, the inspection device receives the inspection path sent by the computing device.
  • Wireless communication can be carried out between the computing device and the inspection device.
  • the computing device sends the inspection path to the inspection device.
  • the inspection device receives the inspection path sent by the computing device.
  • the inspection equipment obtains real-time traffic information and determines the inspection route based on the real-time traffic information.
  • Some road conditions are relatively simple, such as there are no obstacles on the road, no uneven roads, no forked roads, etc. Some road conditions are more complex, such as there are one or more of obstacles, uneven roads, forked roads, etc. on the road. .
  • Sensors are installed on the inspection equipment and can collect road condition data.
  • the data can be, for example, images, radar data, or infrared data.
  • the inspection equipment can determine real-time road condition information based on the data collected by the sensors.
  • the inspection path only includes the inspection sequence of each point.
  • the inspection equipment walks according to the inspection sequence, if there are multiple paths between adjacent points, the inspection equipment needs to select one from the multiple paths as the inspection route between adjacent points. , conduct inspections based on the screened inspection routes.
  • a first algorithm library is set up in the inspection equipment.
  • the inspection equipment can select an algorithm from the first algorithm library and determine a path as an inspection route between adjacent points based on the selected algorithm.
  • the first algorithm library includes algorithms based on graph search algorithms, random sampling algorithms, heuristic algorithms and other types of algorithms. This application does not limit the algorithms included in the first algorithm library.
  • the inspection equipment can determine the algorithm used based on historical data to determine the inspection route between adjacent points.
  • the historical data includes the algorithm and basis used for the adjacent points during the historical inspection process.
  • the algorithm determines the mapping relationship between the traffic conditions of the inspection line between the adjacent points.
  • the computing device can also send a task target to the inspection equipment.
  • the task target is the shortest inspection route.
  • the inspection equipment determines the inspection route between adjacent points based on the task target and the inspection sequence of each point. . For example, when determining the inspection line between any two adjacent points, based on the principle of the shortest inspection line, a shortest path is determined from multiple paths from the current point to the next point. Inspection route from the current point to the next point.
  • the task goal can also be for the inspection equipment to calculate the shortest time consumed by the inspection route between two adjacent points. Then the inspection equipment calculates which path to choose from the current point to the next point. , select the algorithm with the shortest calculation time to determine.
  • the task goal can also be that the inspection equipment calculates the shortest time consumed by the local line during the process of walking from the current point to the next point. Then the inspection equipment uses the algorithm that calculates the shortest time consumption when calculating the local line. to make sure.
  • the user can also pre-specify which algorithm to use when calculating the inspection route from the current point to the next point.
  • the user can pre-specify the algorithm to use when calculating the inspection route from point A to point B.
  • Algorithm a, algorithm b is used when calculating the inspection path from point B to point C
  • algorithm c is used when calculating the inspection path from point B to point C, and so on.
  • point A is adjacent to point B
  • point B is adjacent to point C.
  • algorithm a, algorithm b, and algorithm c can be the same algorithm or different algorithms.
  • the inspection equipment determines the algorithm used to calculate the inspection route from the current point to the next point, it can send a confirmation message to the computing device.
  • the confirmation message is used to confirm to the user whether to use the algorithm.
  • the user can A confirmation operation is performed on the computing device.
  • the computing device sends a response message to the inspection device.
  • the inspection device receives the response message.
  • the response message is used to indicate the use of the algorithm.
  • the user performs a denial operation on the computing device and specifies a certain algorithm.
  • the computing device sends a response message to the inspection device, and the inspection device receives the response message, and the response message includes the algorithm specified by the user.
  • the inspection equipment will obtain real-time traffic information and adjust the process from the current point to the next point based on the real-time traffic information.
  • Local inspection lines in .
  • the inspection equipment includes a second algorithm library, and the second algorithm library includes a variety of algorithms, and the multiple algorithms are set for different traffic condition information. For example, for roads with obstacles, Algorithm 1 can be used to adjust the local inspection route from the current point to the next point. For uneven roads, Algorithm 2 can be used to adjust the process from the current point to the next point. Local inspection lines in , etc.
  • the various algorithms in the second algorithm library may include, for example, genetic algorithm, ant colony algorithm, particle swarm algorithm, depth first search (DFS) algorithm, rapidly expanding random number (rapidly-exploring random tree, RRT) algorithm, etc. any variety of them.
  • genetic algorithm ant colony algorithm
  • particle swarm algorithm particle swarm algorithm
  • DFS depth first search
  • RRT rapidly expanding random number
  • the road conditions can be divided into multiple levels or types in advance.
  • no forks and no obstacles are one level/type
  • no forks and obstacles are one level/type
  • there are forks in the road and no obstacles are one level/type
  • there are forks in the road and there are obstacles are one level/one type
  • each level or each type corresponds to an algorithm, during the actual walking process, according to the sensor collection
  • the data determines the level/type of the road condition, thereby selecting the corresponding algorithm to determine the local inspection route from the current point to the next point.
  • This example is only an example, and actual road conditions include many more possible situations. This example is only used as an example and does not constitute a limitation of the present application.
  • the algorithm used by the inspection equipment when determining the inspection path from the current point to the next point and the algorithm used when facing different road conditions in the process of walking from the current point to the next point It can also be determined based on the characteristics of the inspection equipment itself.
  • the characteristics of the inspection equipment itself include, for example, the maximum steering angle of the inspection equipment.
  • the maximum steering angle of some inspection equipment is 90 degrees; It's 180 degrees.
  • the characteristics of the inspection equipment itself can also be other performances, which are not limited in this application.
  • this application provides a path planning method to generate one or more correction points based on the map and multiple points to be inspected,
  • the correction point is located at one or more locations near turns, forks, slope sections, narrow road sections, etc.
  • the inspection path generated based on multiple points to be inspected and one or more correction points is more accurate. It is accurate and can improve the shooting success rate; in addition, adding correction points to the map also solves the "wall penetration" problem caused by map damage; when calculating the inspection route, the actual mission needs are taken into account, such as what the mission goal is, What is the access time allowed for special inspection points?
  • the inspection path determined based on task requirements meets the needs of users; the inspection equipment provides a variety of algorithms for determining inspection paths, which can be determined based on actual road conditions. The situation determines an algorithm from a variety of algorithms to calculate the inspection path, and the inspection equipment has strong applicability.
  • the path planning device 600 can be configured as the computing device in Figure 1 or Figure 2.
  • Figure 6 is a schematic structural diagram of a path planning device 600 provided by this application.
  • the path planning device 600 includes:
  • the interaction module 601 is used to receive information input by the user.
  • the information input by the user includes multiple points to be inspected;
  • the generation module 602 is used to generate one or more correction points based on multiple points to be inspected and the map, where the correction points are points set at specific road conditions in the map;
  • the generation module 602 is also configured to generate an inspection path based on multiple points to be inspected and one or more correction points.
  • the inspection path includes the inspection sequence of each point, and each point includes multiple points to be inspected. Checkpoint and one or more correction points;
  • the communication module 603 is used to send the inspection path to the inspection equipment, so that the inspection equipment generates an inspection line based on the inspection path and real-time traffic information.
  • the inspection line refers to the inspection equipment inspecting multiple to-be-inspected inspections. The actual route taken during the positioning process.
  • the information input by the user also includes task requirements, and the task requirements include the shortest inspection route; the generation module 602 is used to: based on multiple points to be inspected, one or more correction points and task requirements, Generate inspection paths.
  • the task requirements also include the access time allowed for at least one of the multiple points to be inspected.
  • the correction point is located at one or more locations near a turn, a fork in the road, a sloped road section, or a narrower road section.
  • the interaction module 601 is also configured to receive user operations, and the user operations include adding and/or deleting correction points.
  • the interaction module 601, the generation module 602, and the communication module 603 can all be implemented by software, or can be implemented by hardware.
  • the following takes the generation module 602 as an example to introduce the implementation of the generation module 602.
  • the implementation of the interaction module 601 and the communication module 603 can refer to the implementation of the generation module 602.
  • the generation module 602 may include code running on a computing device.
  • the computing device may be a computing device in a cloud service, where the computing device may be, for example, a bare metal server, a virtual machine, a container, etc. Further, the computing device may be one or more.
  • generation module 602 may include code that runs on multiple computing devices. It should be noted that multiple computing devices used to run the code can be distributed in the same region (region) or in different regions. Further, multiple computing devices used to run the code can be distributed in the same availability zone (AZ) or in different AZs. Each AZ includes a data center or multiple geographically close locations. of data centers. Among them, usually a region can include multiple availability zones AZ.
  • VPC virtual private cloud
  • multiple computing devices used to run the code can be distributed in the same virtual private cloud (VPC) or across multiple VPCs.
  • VPC virtual private cloud
  • Cross-region communication between two VPCs in the same region and between VPCs in different regions requires a communication gateway in each VPC, and the interconnection between VPCs is realized through the communication gateway. .
  • the generation module 602 may include at least one computing device.
  • the generation module 602 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD).
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • the above-mentioned PLD can be a complex programmable logical device (CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general array logic (generic array logic, GAL), or any combination thereof.
  • CPLD complex programmable logical device
  • FPGA field-programmable gate array
  • GAL general array logic
  • Multiple computing devices included in the generation module 602 may be distributed in the same region or in different regions. Multiple computing devices included in the generation module 602 may be distributed in the same AZ or in different AZs. Similarly, multiple computing devices included in the generation module 602 may be distributed in the same VPC or in multiple VPCs.
  • the plurality of computing devices may be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.
  • the generation module 602 can be used to perform any steps in a path planning method
  • the interaction module 601 and the communication module 603 can be used to perform any steps in a path planning method.
  • the steps responsible for implementation by the interaction module 601, the generation module 602 and the communication module 603 can be specified as needed.
  • the interaction module 601, the generation module 602 and the communication module 603 respectively implement different steps in a path planning method to implement the path planning device 600 all functions.
  • FIG 7 is a schematic structural diagram of a computing device 700 provided by this application.
  • the computing device 700 can be, for example, a bare metal server, a virtual machine, a container, etc.
  • the computing device 700 can be configured as a computing device in the method embodiment.
  • computing device 700 includes: bus 702, processor 704, memory 706, and communication interface 708.
  • the processor 704, the memory 706 and the communication interface 708 communicate through the bus 702. It should be understood that this application does not limit the number of processors and memories in the computing device 700.
  • the bus 702 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • the bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one line is used in Figure 7, but it does not mean that there is only one bus or one type of bus.
  • Bus 702 may include a path that carries information between various components of computing device 700 (eg, memory 706, processor 704, communications interface 708).
  • the processor 704 may include a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (micro processor, MP) or a digital signal processor (digital signal processor, DSP). any one or more of them.
  • CPU central processing unit
  • GPU graphics processing unit
  • MP microprocessor
  • DSP digital signal processor
  • Memory 706 may include volatile memory, such as random access memory (RAM).
  • the processor 704 may also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, hard disk drive (HDD) or solid state drive (solid state drive). drive, SSD).
  • non-volatile memory such as read-only memory (ROM), flash memory, hard disk drive (HDD) or solid state drive (solid state drive). drive, SSD).
  • the memory 706 stores executable program code
  • the processor 704 executes the executable program code to respectively realize the functions of the aforementioned interaction module 601, generation module 602 and communication module 603, thereby implementing a path planning method. That is, the memory 706 stores instructions for executing a path planning method.
  • the communication interface 708 uses transceiver modules such as, but not limited to, network interface cards and transceivers to implement communication between the computing device 700 and other devices or communication networks.
  • the communication module 603 may be located in the communication interface 708.
  • An embodiment of the present application also provides a computing device cluster.
  • the computing device cluster includes at least one computing device.
  • the computing device may be a server, such as a central server, an edge server, or a local server in a local data center.
  • the computing device may also be a desktop computer, laptop computer, or other device.
  • FIG. 8 is a schematic structural diagram of a computing device cluster provided by this application.
  • the computing device cluster includes at least one computing device 700 .
  • the same instructions for performing a path planning method may be stored in the memory 706 of one or more computing devices 700 in a cluster of computing devices.
  • the memory 706 of one or more computing devices 700 in the computing device cluster may also store partial instructions for executing a path planning method.
  • a combination of one or more computing devices 700 may be used to jointly execute the instructions of a path planning method.
  • the memory 706 in different computing devices 700 in the computing device cluster can store different instructions, respectively used to execute part of the functions of the computing device 700 . That is, the instructions stored in the memory 706 in different computing devices 700 can implement the functions of one or more modules among the interaction module 601, the generation module 602, and the communication module 603.
  • one or more computing devices in a cluster of computing devices may be connected through a network.
  • the network may be a wide area network or a local area network, etc.
  • Figure 9 shows a possible implementation. As shown in Figure 9, two computing devices 700A and 700B are connected through a network. Specifically, the connection to the network is made through a communication interface in each computing device.
  • instructions for executing the functions of the interaction module 601 and the generation module 602 are stored in the memory 706 of the computing device 700A. At the same time, instructions for performing the functions of the generation module 602 and the communication module 603 are stored in the memory 706 in the computing device 700B.
  • the generation module 602 in the computing device 700A is used to implement the function of generating one or more correction points based on multiple points to be inspected and the map
  • the generation module 602 in the computing device 700B is used to implement the function of generating one or more correction points based on multiple points to be inspected.
  • the functions of the computing device 700A shown in FIG. 9 can also be completed by multiple computing devices 700, or the computing device cluster includes multiple computing devices that have the same functions as the computing device 700A.
  • the functions of the computing device 700B can also be completed by multiple computing devices 700, or the computing device cluster includes multiple computing devices that have the same functions as the computing device 700B.
  • the embodiment of the present application also provides another computing device cluster.
  • the connection relationship between the computing devices in the computing device cluster can be similar to the connection method of the computing device cluster described in FIG. 8 and FIG. 9 .
  • the difference is that the memory 706 in one or more computing devices 700 in the computing device cluster may store different instructions for executing a path planning method.
  • the memory 706 of one or more computing devices 700 in the computing device cluster may also store partial instructions for executing a path planning method.
  • a combination of one or more computing devices 700 may collectively execute instructions for performing a path planning method.
  • FIG. 10 is a schematic structural diagram of yet another path planning device 800 provided by the present application.
  • the path planning device 800 can be configured as a patrol device in the system architecture of Figure 1 or Figure 2.
  • Inspection equipment can also be configured as the inspection equipment in the method embodiment of Figure 3.
  • the path planning device 800 includes:
  • the communication module 801 is used to receive the inspection path sent by the computing device.
  • the inspection path includes the inspection sequence of each point.
  • Each point includes multiple points to be inspected and one or more correction points, where, One or more correction points are points set by the computing device at specific traffic conditions in the map based on multiple points to be inspected and the map;
  • the processing module 802 is used to obtain real-time road condition information during the process of walking according to the inspection path, and determine the inspection route based on the real-time road condition information.
  • the inspection route refers to the process of inspection equipment inspecting multiple points to be inspected. The actual route taken.
  • the correction point is located at one or more locations near a turn, a fork in the road, a sloped road section, or a narrower road section.
  • the processing module 802 is configured to: when the inspection equipment is located at any point in the inspection path, determine a shortest path from at least one path from the current point to the next point, as Inspection route from the current point to the next point;
  • the processing module 802 is also used for: the inspection equipment obtains real-time traffic information during the inspection process from the current point to the next point, and adjusts the local inspection process from the current point to the next point based on the real-time traffic information.
  • real-time traffic information includes one or more of road conditions with obstacles and uneven road conditions.
  • Each functional module in the method embodiment of Figure 10 is specifically used to perform the steps performed by the inspection equipment in the method embodiment of Figure 3, and is specifically used to perform steps S104 and S105 in the method embodiment of Figure 3.
  • steps S104 and S105 in the method embodiment of Figure 3.
  • FIG. 11 is a schematic structural diagram of an inspection equipment 900 provided by this application.
  • the inspection equipment 900 may be a robot, for example.
  • the inspection equipment 900 can be configured as an inspection device in the method embodiment.
  • the inspection device 900 includes: a bus 902, a processor 904, a memory 906, and a communication interface 908.
  • the processor 904, the memory 906 and the communication interface 908 communicate through the bus 902. It should be understood that this application does not limit the number of processors and memories in the inspection equipment 900.
  • the bus 902 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • the bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one line is used in Figure 11, but it does not mean that there is only one bus or one type of bus.
  • Bus 902 may include a path for transmitting information between various components of inspection device 900 (eg, memory 906, processor 904, communication interface 908).
  • the processor 904 may include a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP) or a digital signal processor (DSP). any one or more of them.
  • CPU central processing unit
  • GPU graphics processing unit
  • MP microprocessor
  • DSP digital signal processor
  • Memory 906 may include volatile memory, such as random access memory (RAM).
  • the processor 904 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD) or solid state drive (solid state drive). drive, SSD).
  • ROM read-only memory
  • flash memory flash memory
  • HDD hard disk drive
  • solid state drive solid state drive
  • the memory 906 stores executable program code, and the processor 904 executes the executable program code to implement the functions of the aforementioned communication module 801 and processing module 802 respectively, thereby implementing a path planning method. That is, the memory 906 stores instructions for executing a path planning method.
  • the communication interface 908 uses transceiver modules such as, but not limited to, network interface cards and transceivers to implement communication between the inspection device 900 and other devices or communication networks.
  • the communication module 801 may be located in the communication interface 908.
  • An embodiment of the present application also provides a computer program product containing instructions.
  • the computer program product may be a software or program product containing instructions capable of running on a computing device or stored in any available medium.
  • the computer program product is run on at least one computing device, at least one computing device is caused to execute a path planning method.
  • An embodiment of the present application also provides a computer program product containing instructions.
  • the computer program product may be a software or program product that contains instructions and can be run on the inspection equipment or stored in any available medium.
  • the inspection equipment is caused to execute a path planning method.
  • An embodiment of the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium may be any available medium that a computing device can store or a data storage device such as a data center that contains one or more available media.
  • the available media may be magnetic media (eg, floppy disk, hard disk, tape), optical media (eg, DVD), or semiconductor media (eg, solid state drive), etc.
  • the computer-readable storage medium includes instructions that instruct a computing device or cluster of computing devices to perform a path planning method.
  • This application also provides a computer-readable storage medium, which includes program instructions.
  • the inspection equipment executes a path planning method.
  • This application provides a system, which includes at least one computing device and an inspection device.
  • the computing device can be the path planning device 600 in Figure 6 or the computing device 700 in Figure 7 .
  • the at least one computing device can be the one in Figure 8
  • the computing device cluster in can also be the computing device 700A and the computing device 700B in Figure 9.
  • the inspection device can be the path planning device 800 in Figure 10 or the inspection device 900 in Figure 11.
  • the system is used to jointly Execute a path planning method in the method embodiment of Figure 3.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Navigation (AREA)

Abstract

一种路径规划方法、相关装置及系统，方法包括：计算设备接收用户输入的信息，用户输入的信息包括多个待巡检点位（S101）；计算设备根据多个待巡检点位和地图，生成一个或多个修正点位（S102），其中，修正点位是设置在地图中特定路况位置处的点位；计算设备根据多个待巡检点位和一个或多个修正点位，生成巡检路径（S103），巡检路径中包括各个点位的巡检顺序，各个点位包括多个待巡检点位和一个或多个修正点位；计算设备将巡检路径发送至巡检设备，相应地，巡检设备接收计算设备发送的巡检路径（S104）；巡检设备在根据巡检路径行走的过程中，获取实时路况信息，并基于实时路况信息确定巡检线路（S105），巡检线路指的是巡检设备巡检多个待巡检点位过程所走的实际线路。使得规划的业务路径更加精准，提高了巡检过程中图像拍摄成功率。

Description

一种路径规划方法、相关装置及系统
本申请要求于2022年09月08日提交中国专利局、申请号为202211096416.9、申请名称为“一种路径规划方法、相关装置及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信领域，尤其涉及一种路径规划方法、相关装置及系统。
背景技术
电力站中设置了很多电力设备，需要巡检设备(例如巡检机器人)对电力站中的电力设备定期或不定期地进行巡检，通过巡检采集电力设备的照片，以便根据采集的照片对电力设备进行管理和运维。
目前，巡检设备巡检的方法是，由计算设备根据各个待巡检点位生成巡检路径，其中，待巡检点位指的是待巡检点所在的位置，即待巡检的电力设备所在的位置，或者，人为在计算设备上根据各个巡检点位标注出巡检路径，然后计算设备将巡检路径下发至巡检设备，巡检设备根据巡检路径对各个待巡检点进行巡检。这种巡检方式存在如下弊端：当待巡检点位于路况较复杂或较特殊的位置时，比如直角转弯处、岔路口处、较狭窄的道路处、斜坡处等位置，巡检设备根据巡检路径对这些位置的电力设备进行拍摄时，存在拍摄失败或拍摄照片不合格的情况。
发明内容
本申请提供了一种路径规划方法、相关装置及系统，根据所述方法生成的巡检路径更加精准，基于本申请生成的巡检路径进行巡检，图像拍摄成功率高。
第一方面，本申请提供了一种路径规划方法，从计算设备方面看，所述方法包括：计算设备接收用户输入的信息，所述用户输入的信息包括多个待巡检点位；所述计算设备根据所述多个待巡检点位和地图，生成一个或多个修正点位，其中，所述修正点位是设置在所述地图中特定路况位置处的点位；所述计算设备根据所述多个待巡检点位和所述一个或多个修正点位，生成巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括所述多个待巡检点位和所述一个或多个修正点位；所述计算设备将所述巡检路径发送至巡检设备，以使所述巡检设备根据所述巡检路径和实时路况信息生成巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
可以看到，本申请提供了一种路径规划方法，采用本申请所述的方法，计算设备根据待巡检点位和修正点位生成巡检路径，巡检设备再根据实时路况信息和巡检路径确定巡检线路。其中，修正点位是为使巡检线路更加准确而设置在地图中的特定路况位置处的点位，通过在地图中设置修正点位，使得计算设备生成的巡检路径更加准确，使得巡检设备基于巡检路径和实时路况信息确定的巡检线路更加精准，从而增加了巡检设备在待巡检点位处的拍照成功率。
基于第一方面，在可能的实现方式中，所述用户输入的信息还包括任务需求，所述任务需求包括所述巡检线路最短；所述根据所述多个待巡检点位和所述一个或多个修正点位，生成巡检路径，包括：根据所述多个待巡检点位、所述一个或多个修正点位和所述任务需求，生成所述巡检路径。
可以理解，可以根据用户的实际需求生成巡检路径或巡检线路，其中，用户的需求例如可以是要求巡检线路最短。计算设备在生成巡检路径时，基于多个待巡检点位和一个或多个修正点位，根据用户的需求生成巡检路径，采用本申请所述的方法，提高用户使用体验，满足用户实际需求。
基于第一方面，在可能的实现方式中，所述任务需求还包括所述多个待巡检点位中至少一个待巡检点位所允许访问的时间。
可以理解，有的待巡检点位有访问时间的要求，任务需求还可以包括一个或多个待巡检点位所允许访问的时间。
基于第一方面，在可能的实现方式中，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
可以理解，仅仅根据多个待巡检点位生成巡检路径，巡检设备仅仅根据多个待巡检点位进行巡检或者根据由多个待巡检点位生成的巡检路径进行巡检，由于巡检线路不够精准，在一些特定路况位置处存在拍 照失败或拍摄照片不合格的情况。针对这个问题，本申请增加了修正点位，巡检路径和巡检线路是基于待巡检点位和修正点位生成的，提高了巡检线路的准确性。其中，特定路况位置例如包括转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
基于第一方面，在可能的实现方式中，在所述根据所述多个待巡检点位和地图，生成一个或多个修正点位之后，所述方法还包括：所述计算设备接收用户的操作，所述用户的操作包括增加和/或删除所述修正点位。
可以理解，用户可以对生成的修正点位进行修正，比如增加修正点位或删除修正点位。通过用户与计算设备进行交互，可以更好地解决“穿墙”问题，使得巡检路径和巡检线路更加精准。
第二方面，本申请提供了一种路径规划方法，从巡检设备方面看，所述方法包括：巡检设备接收计算设备发送的巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括多个待巡检点位和一个或多个修正点位，其中，所述一个或多个修正点位是所述计算设备根据所述多个待巡检点位和地图，设置在所述地图中特定路况位置处的点位；巡检设备在根据所述巡检路径行走的过程中，获取实时路况信息，并基于所述实时路况信息确定巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
可以看到，巡检线路是基于巡检路径生成的，巡检路径是基于待巡检点位和修正点位生成的。通过设置修正点位，提高了巡检线路的准确性。另外，巡检设备能够根据实时路况信息微调巡检线路，面对不同的路况，巡检设备的微调处理方法不同，以进一步保障巡检线路的精准，提高拍摄成功率。
基于第二方面，在可能的实现方式中，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
基于第二方面，在可能的实现方式中，所述巡检设备在根据所述巡检路径行走的过程中，获取实时路况信息，并基于所述实时路况信息确定巡检线路，包括：在所述巡检设备位于所述巡检路径中的任意一个点位时，所述巡检设备从由当前点位至下一点位的至少一条路径中确定出一条最短路径，作为由所述当前点位至所述下一点位的巡检线路；其中，所述巡检设备在由所述当前点位至所述下一点位巡检过程中，获取实时路况信息，并根据所述实时路况信息，调整由所述当前点位至所述下一点位过程中的局部巡检线路，所述实时路况信息包括存在障碍物的路况、凹凸不平的路况中的一种或多种。
可以理解，通过获取实时路况信息，巡检设备根据实时路况信息自动调整巡检线路，面临不同的路况情况时，均能保证巡检工作的正常进行，保证各个待巡检点位的图像拍摄成功率。
第三方面，本申请提供了一种路径规划装置，包括：
交互模块，用于接收用户输入的信息，所述用户输入的信息包括多个待巡检点位；
生成模块，用于根据所述多个待巡检点位和地图，生成一个或多个修正点位，其中，所述修正点位是设置在所述地图中特定路况位置处的点位；
所述生成模块还用于，根据所述多个待巡检点位和所述一个或多个修正点位，生成巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括所述多个待巡检点位和所述一个或多个修正点位；
通信模块，用于将所述巡检路径发送至巡检设备，以使所述巡检设备根据所述巡检路径和实时路况信息生成巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
基于第三方面，在可能的实现方式中，所述用户输入的信息还包括任务需求，所述任务需求包括所述巡检线路最短；所述生成模块用于：根据所述多个待巡检点位、所述一个或多个修正点位和所述任务需求，生成所述巡检路径。
基于第三方面，在可能的实现方式中，所述任务需求还包括所述多个待巡检点位中至少一个待巡检点位所允许访问的时间。
基于第三方面，在可能的实现方式中，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
基于第三方面，在可能的实现方式中，所述交互模块还用于，接收用户的操作，所述用户的操作包括增加和/或删除所述修正点位。
第三方面的各个功能模块用于实现上述第一方面或第一方面的任意一种可能的实现方式所述的方法。
第四方面，本申请提供了一种路径规划装置，包括：
通信模块，用于接收计算设备发送的巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括多个待巡检点位和一个或多个修正点位，其中，所述一个或多个修正点位是所述计算设备根据所述多个待巡检点位和地图，设置在所述地图中特定路况位置处的点位；
处理模块，用于在根据所述巡检路径行走的过程中，获取实时路况信息，并基于所述实时路况信息确定巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
基于第四方面，在可能的实现方式中，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
基于第四方面，在可能的实现方式中，所述处理模块用于：在所述巡检设备位于所述巡检路径中的任意一个点位时，从由当前点位至下一点位的至少一条路径中确定出一条最短路径，作为由所述当前点位至所述下一点位的巡检线路；
所述处理模块还用于：所述巡检设备在由所述当前点位至所述下一点位巡检过程中，获取实时路况信息，并根据所述实时路况信息，调整由所述当前点位至所述下一点位过程中的局部巡检线路，所述实时路况信息包括存在障碍物的路况、凹凸不平的路况中的一种或多种。
第四方面的各个功能模块用于实现上述第二方面或第二方面的任意一种可能的实现方式所述的方法。
第五方面，本申请提供了一种计算设备集群，包括至少一个计算设备，所述至少一个计算设备中的每个计算设备包括处理器和存储器，所述至少一个计算设备的处理器用于执行所述至少一个计算设备的存储器中存储的指令，以使得所述计算设备集群执行上述第一方面或第一方面的任意一种可能的实现方式所述的方法。
第六方面，本申请提供了一种计算机可读存储介质，包括计算机程序指令，当所述计算机程序指令由计算设备集群执行时，所述计算设备集群执行上述第一方面或第一方面的任意一种可能的实现方式所述的方法。
第七方面，本申请提供了一种包含指令的计算机程序产品，其特征在于，当所述指令被计算设备集群运行时，使得所述计算设备集群执行上述第一方面或第一方面的任意一种可能的实现方式所述的方法。
第八方面，本申请提供了一种巡检设备，包括处理器和存储器，所述存储器用于存储指令，所述处理器用于运行所述存储器中存储的指令执行上述第二方面或第二方面的任意一种可能的实现方式所述的方法。
第九方面，本申请提供了一种计算机可读存储介质，其特征在于，包括程序指令，当所述程序指令被巡检设备执行时，所述巡检设备执行上述第二方面或第二方面的任意一种可能的实现方式所述的方法。
第十方面，本申请提供了一种包含指令的计算机程序产品，其特征在于，当所述指令被巡检设备运行时，使得所述巡检设备执行上述第二方面或第二方面的任意一种可能的实现方式所述的方法。
第十一方面，本申请提供了一种系统，所述系统包括计算设备和巡检设备，所述计算设备为上述第一方面或第一方面的任意一种可能的实现方式中所述的计算设备，所述巡检设备为上述第二方面或第二方面的任意一种可能的实现方式中所述的巡检设备，或者，所述计算设备为上述第三方面或第三方面的任意一种可能的实现方式中所述的路径规划装置，所述巡检设备为上述第四方面或第四方面的任意一种可能的实现方式中所述的路径规划装置。
附图说明
图1为本申请提供的一种系统架构示意图；
图2为本申请提供的又一种系统架构示意图；
图3为本申请提供的一种路径规划方法的流程示意图；
图4A为本申请提供的一种示例图；
图4B为本申请提供的一种示例图；
图4C为本申请提供的一种示例图；
图4D为本申请提供的一种示例图；
图4E为本申请提供的一种示例图；
图4F为本申请提供的一种示例图；
图5为本申请提供的一种场景示例图；
图6为本申请提供的一种路径规划装置的结构示意图；
图7为本申请提供的一种计算设备的结构示意图；
图8为本申请提供的一种计算设备集群的结构示意图；
图9为本申请提供的又一种计算设备集群的结构示意图；
图10为本申请提供的又一种路径规划装置的结构示意图；
图11为本申请提供的一种巡检设备的结构示意图。
具体实施方式
本申请提供了一种系统，参见图1，图1为本申请提供的一种系统架构示意图，所述系统涉及至少一个巡检设备110、网络设备120和至少一个计算设备130。
计算设备130，例如可以是台式电脑、笔记本、服务器等。可选的，计算设备130可以是位于云中的计算设备130，例如中心服务器，其中，云可以是私有云，也可以是公有云，也可以是混合云。计算设备130也可以位于边缘环境中的计算设备130，例如边缘服务器。云环境指的是云服务提供商拥有的用于提供计算、存储、通信资源的中心计算设备130集群，该计算设备130集群通常离巡检设备110较远，边缘环境指的是在地理位置上距离巡检设备110较近的用于提供计算、存储、通信资源的边缘计算设备130集群。
计算设备130用于接收用户输入的信息，用户输入的信息包括多个待巡检点位。可选的，用户输入的信息还可以包括任务需求，任务需求例如包括巡检线路最短、在待巡检点位所允许访问的时间内进行巡检访问等，其中巡检线路指的是巡检设备110巡检多个待巡检点位过程所走的实际线路。
计算设备130还用于根据用户输入的信息和地图生成一个或多个修正点位，并根据多个待巡检点位和一个或多个修正点位生成巡检路径，巡检路径中包括经过各个点位的巡检顺序，其中，各个点位包括多个待巡检点位和一个或多个修正点位。其中地图是存储在计算设备130本地的。修正点位是为使巡检线路更加准确而设置在特定路况位置处的点位，特定路况位置处包括转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。关于修正点位的更多描述可参考下文方法实施例中的描述。需要说明的是，待巡检点位指的是电力设备所在的位置，巡检设备110需要在待巡检点位处拍照，修正点位用于辅助生成巡检路径或巡检线路，巡检设备110不需要在修正点位处拍照。
在一种实现方式中，巡检路径即为各个点位的巡检顺序。比如，各个点位包括点位A、点位B、点位C和点位D，巡检路径为点位A-点位B-点位C-点位D，该巡检路径的意思是，先访问点位A然后访问点位B再访问点位C最后访问点位D，但是相邻点位之间可能存在一条或多条线路，当相邻点位之间存在多条线路的情况下，巡检路径中可以不指明相邻点位之间的巡检线路具体是哪条。在又一种实现方式中，巡检路径中可以包括相邻点位之间的巡检线路具体是哪条，关于如何确定相邻点位之间的巡检线路是哪条，可以参见下文方法实施例的描述，在此不展开介绍。
可选的，计算设备130还用于接收用户对修正点位的修正操作，比如增加修正点位或删除修正点位。
网络设备120用于计算设备130通过任何通信机制/通信标准的通信网络与巡检设备110之间进行通信。其中，通信网络可以是广域网、局域网、点对点连接等方式，或它们的任意组合。比如，计算设备130将生成的巡检路径通过网络设备120发送至巡检设备110，可选的，计算设备130还可以将任务需求发送至巡检设备110，任务需求比如是巡检线路最短。
巡检设备110例如可以是机器人。巡检设备110用于接收计算设备130发送的巡检路径，并根据巡检路径和采集的实时路况信息确定巡检线路，实现对各个待巡检点位的巡检。
图1所示的系统架构仅仅是一种示例，并不构成对本申请的限定。
为了便于理解，本申请提供了又一种系统架构，如图2所示，图2为本申请提供的又一种系统架构示意图。用户将多个待巡检点位、任务需求(例如图2中，巡检路径最短、一个或多个待巡检点位所允许访问的时间)输入至计算设备，计算设备根据多个待巡检点位和地图生成修正点位，并根据多个待巡检点位、修正点位和任务需求，规划巡检路径，计算设备将生成的巡检路径发送至巡检设备。其中，计算设备在生成修正点位之后，用户可以对修正点位进行修改。
巡检设备基于巡检路径，确定相邻点位之间的巡检线路。可选的，巡检设备确定相邻点位之间的巡检线路，可以是巡检设备在巡检之前确定各个相邻的点位之间的巡检线路，也可以是巡检设备位于各个点位上时确定当前点位至下一点位之间的巡检线路，例如，巡检设备位于某一个巡检点位上时，确定当前点位至下一点位之间的巡检线路，然后根据巡检线路进行巡检，到达下一点位时，再次计算由此点位至下一点位之间的巡检线路。其中，巡检设备在由当前点位至下一点位的巡检过程中，能够自适应确定局部线路，关于如何自适应确定局部线路，可参见下文方法实施例中的相关描述，在此不展开描述。
本申请提供了一种路径规划方法，参见图3，图3为本申请提供的一种路径规划方法的流程示意图， 所述方法包括但不限于以下内容的描述。
S101、计算设备接收用户输入的信息，用户输入的信息包括多个待巡检点位。
用户输入的信息包括多个待巡检点位。可选的，用户输入的信息还可以包括任务需求，任务需求包括任务目标，任务目标例如可以是巡检线路最短或者巡检消耗时长最短，巡检消耗时长指的是巡检设备从起点行走至终点所消耗的时长。任务目标还可以是巡检设备计算巡检路径时所消耗的时长最短，具体的，任务目标可以设置为巡检设备计算相邻两个点位之间的巡检路径所消耗的时长最短，任务目标还可以设置为巡检设备在由当前点位行走至下一点位的过程中计算局部路径所消耗的时长最短，关于巡检设备计算巡检路径时所消耗的时长，具体在下文步骤S105中介绍，在此不展开描述，相关内容可参见步骤S105中的描述。
可选的，任务需求还可以包括多个待巡检点位中至少一个待巡检点位所允许访问的时间。多个待巡检点位中可以有一个或多个待巡检点位设置有允许访问的时间。某个待巡检点位所允许访问的时间可以是一个时间窗，比如上午10:00-上午11:00；也可以是只有允许访问的最晚时间，比如，每天允许访问的最晚时间是上午11:00，这意味着，巡检设备每天需要在上午11:00之前访问完该待巡检点位；也可以是只有允许访问的最早时间，比如，每天允许访问的最早时间是上午10:00，这意味着，巡检设备每天需要在上午10:00之后才可以访问该待巡检点位。
可以理解，计算设备上可以包括用户交互界面，用户交互界面可用于显示信息，比如，用户交互界面可用于显示多个待巡检点位，用户交互界面还可以用于显示任务需求，比如显示任务目标，还可以用于显示一个或多个待巡检点位所允许访问的时间，等等。
S102、计算设备根据多个待巡检点位和地图，生成一个或多个修正点位。
计算设备本地存储了地图，计算设备根据地图和多个待巡检点位，生成一个或多个修正点位，其中，一个或多个修正点位用于辅助根据多个待巡检点位生成巡检路径。本申请对生成修正点位的算法不做限定。
修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
转弯处附近，表示以转弯点为中心，距离转弯点一定距离的区域，转弯处附近包括转弯点，这里，一定距离可以根据实际路况或实际应用场景来设置，比如，一定距离可以是0.5米、0.8米、1米、1.3米等等，本申请对一定距离不做限定，转弯点指的是道路方向发生了较大改变的位置或者车辆在道路上行驶时行驶方向发生了较大改变的位置。
为了便于描述，这里采用车辆在道路上行驶时行驶方向发生了较大改变的位置为例，进行说明。参见图4A和图4B所示的示意图，图4A和图4B中车辆行驶方向均是由向东行驶转弯至向北行驶，图4A中a点即为转弯点，图4B中b点即为转弯点，不同的是，图4A为直角转弯，图4B为非直角转弯；参见图4C所示的示意图，在c点处，行驶方向由向北行驶转弯至向东行驶，c点即为转弯点；参见图4D所示的示意图，从道路1上行驶转弯至道路2上行驶，d点即为转弯点；在图4E所示的示意图中，e点为转弯点；在图4F所示的示意图中，在车辆行驶至f点之前与行驶至f点之后，行驶方向发生了较大改变，可以理解为f点为转弯点，在车辆行驶至g点之前和行驶至g点之后，行驶方向也发生了较大改变，g点也为转弯点。这里，关于道路方向是否发生了较大改变或者行驶方向是否发生了较大改变，可以通过东、西、南、北、东南、东北、西南、西北等模糊方向来判断，也可以通过地图上相连接的两条道路所在位置的经纬度来判断，也可以通过相连接的两条道路之间的夹角来判断。关于多大程度的改变称之为较大改变，可以根据不同应用场景或不同路况设置不同的角度阈值或经纬度阈值来确定，比如，当相连接的两条道路的经纬度的差值超过阈值的情况下，确定道路方向发生了较大改变，确定为转弯处附近，可以生成修正点位，又比如，当相连接的两条道路之间的夹角超过阈值的情况下，确定道路方向发生了较大改变，确定为转弯处附近，可以生成修正点位。本申请对角度阈值或经纬度阈值不做限定。
转弯包括直角转弯，如图4A所示,也包括非直角转弯，如图4B、图4E和图4F所示，上述图4A至图4F所示的示意图仅仅用于举例，并不是对本申请的限定，转弯还可以是其他形式的转弯，本申请不做限定。
岔路口，可以是T型岔路口，如图4C所示，也可以是Y型岔路口，如图4D所示，也可以十字型交叉路口，还可以是其他形式的岔路口，本申请不做限定。岔路口附近指的是以分岔点为中心，距离分岔点一定距离的区域，岔路口附近包括分岔点，这里，一定距离可以根据实际路况或实际应用场景来设置，比如，一定距离可以是0.5米、0.8米、1米、1.4米等等，本申请对一定距离不做限定。
坡度路段指的是具有一定坡度的路段，本申请对路段的长度不做限定。这里坡度是一个相对的概念，某条道路相对于相邻道路或相连接的道路具有一定的坡度，或者，道路上某个路段相对于相邻路段或相连接的路段具有一定的坡度。本申请中，坡度路段可以指上坡路段，也可以指下坡路段，也可以指凹凸不平 的路段(凹凸不平的路段可以理解为既包括上坡路段，又包括下坡路段)，本申请不做限定。
较狭窄的路段指的是道路的宽度较小的路段，关于宽度小于多少称为较狭窄的路段，本申请不做限定。可以通过设置宽度阈值来确定较狭窄的路段，比如阈值可以设置为0.5米或0.8米，当道路宽度小于宽度阈值时，即判定该道路为较狭窄的路段，关于宽度阈值本申请不做限定，实际应用中，可以根据具体应用场景、具体情况具体确定。
通过增加修正点位，修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置，以便后续根据修正点位和待巡检点位，生成精准的巡检路径，在巡检设备行走至路况较复杂或较特殊的位置时，比如，转弯处、岔路口、较狭窄的道路处、斜坡处等，可以根据精准的巡检路径行走，从而实现对电力设备的图像采集，避免了图像采集失败或不合格的情况，提高了图像拍摄效率和巡检成功率。
另外，计算设备中的地图中可能包含一些破损处，比如，实际生活中，两条道路中间存在一堵墙或两个电力设备之间隔着一堵墙，但由于地图存在漏洞(bug)，这堵墙并未显示在地图中，如果直接根据多个待巡检点位生成巡检路径，则生成的巡检路径可能是“穿墙”路径，按照“穿墙”路径行走的话，巡检设备可能会碰壁、撞墙，导致巡检失败。例如，参见图5所示，在实际中MN表示具有一定厚度的墙，由于地图破损，MN处的墙并未显示，计算设备在生成巡检路径时，有可能生成从P点至Q点的直线“穿墙”路径，但是实际从P点无法通过该直线路径到达Q点，而是需要通过图5中的虚线绕行至Q点，因此可以在图5中虚线所在的路径上增加一些修正点位，来避免“穿墙”问题。通过增加修正点位，可以避免“穿墙”问题，使生成的巡检路径更加精准，巡检成功率更高。
可选的，计算设备生成一个或多个修正点位后，可以通过用户交互界面显示生成的一个或多个修正点位。用户可以对生成的修正点位进行修正，比如，增加修正点位，例如为了避免穿墙问题，用户可以在地图上增加一些修正点位，又比如，删除修正点位，计算设备接收用户对修正点位的修正操作。
该步骤的处理过程大致如下：1)将地图体素化，即将地图的矢量模型转化为点阵信息；2)根据点阵信息(体素化的地图)，确定可以供巡检设备通行的平面，过滤掉不可通行的平面；3)将确定出的可供巡检设备通行的平面划分为不重叠且没有洞的多个区域；4)对于步骤3)中获得的多个区域，生成每一个区域的轮廓，并将多个区域的轮廓合并为一个轮廓；5)将生成的轮廓切分为多个凸多边形，多个凸多边形中的任意两个凸边形是可以通过线段到达的，因此获得多面体图。将多个待巡检点位输入计算设备后，计算设备将多个待巡检点位标注在多面体图上，并根据算法生成一个或多个修正点位。
S103、计算设备根据多个待巡检点位和一个或多个修正点位，生成巡检路径。
如图1系统中关于巡检路径内容所示，巡检路径中包括各个点位的巡检顺序。一种实现方式中，巡检路径即为各个点位的巡检顺序，在相邻点位之间包括多条线路的情况下，巡检路径中不包括相邻点位之间的巡检线路具体是哪条。这种实现方式中，在各相邻点位之间仅包括一条线路的情况下，相邻点位之间的巡检线路也就是确定的了。
在一种示例中，用户输入的信息包括一个或多个待巡检点位所允许访问的时间，计算设备根据一个或多个待巡检点位所允许访问的时间，确定各个点位的巡检顺序。在一种实现方式中，可以建立数学模型通过算法确定各个点位的巡检顺序。在建立数学模型时设置约束条件包括：
约束条件一：一个或多个待巡检点位所允许访问的时间；
约束条件二：所有点位在一次巡检任务中访问完成，所有点位包括所有待巡检点位和所有修正点位；
约束条件三：每个点位不重复访问；
基于上述约束条件，通过算法求解，确定各个点位的巡检顺序，例如算法可以是遗传算法，本申请对确定巡检顺序所使用的算法不做限定。上述约束条件只是一种示例，具体实现时，可以根据实际应用需求修改约束条件。
在一种示例中，用户输入的信息包括任务目标，例如任务目标为巡检线路最短，计算设备根据各个点位和任务目标，确定巡检路径。在这种示例中，依照巡检线路最短的原则，计算设备确定出各个点位的巡检顺序，再从相邻点位之间的多条路径中选择一条最短路径作为相邻点位之间的巡检线路，因此获得巡检路径，这种实现方式中，巡检路径中包括了各个点位的巡检顺序和相邻点位之间的巡检线路具体是哪条。
在一种示例中，用户输入的信息包括任务目标和一个或多个待巡检点位所允许访问的时间，任务目标为巡检路径最短，计算设备根据任务目标和一个或多个待巡检点位所允许访问的时间，确定各个点位的排列顺序。
S104、计算设备将巡检路径发送至巡检设备，相应地，巡检设备接收计算设备发送的巡检路径。
计算设备与巡检设备之间可以进行无线通信，计算设备将巡检路径发送至巡检设备，相应地，巡检设 备接收计算设备发送的巡检路径。
S105、巡检设备在根据巡检路径行走的过程中，获取实时路况信息，并基于实时路况信息确定巡检线路。
有的路况比较简单，比如道路上无障碍物、无凹凸不平的路、无岔路口等，有的路况比较复杂，比如道路上存在障碍物、凹凸不平、岔路口等中的一种或多种。巡检设备上安装有传感器，能够采集路况数据，数据例如可以是图像或雷达数据或红外数据等，巡检设备根据传感器采集的数据能够确定实时路况信息。
在一种实现方式中，巡检路径中只包括各个点位的巡检顺序。巡检设备在根据巡检顺序行走的过程中，在相邻点位之间包括多条路径的情况下，巡检设备需要从多条路径中筛选一条作为相邻点位之间的巡检线路，根据筛选的巡检线路进行巡检。
可选的，巡检设备中设置了第一算法库，巡检设备可以从第一算法库中选择一种算法，根据选择出的算法确定一条路径作为相邻点位之间的巡检线路，第一算法库中包括基于图搜索算法、随机抽样算法、启发式算法等类型的算法，本申请对第一算法库中包括的算法不做限定。可选的，巡检设备可以基于历史数据确定所采用的算法，从而确定相邻点位之间的巡检线路，其中历史数据包括历史巡检过程中该相邻点位所采用的算法与根据所述算法确定的该相邻点位之间的巡检线路的路况情况之间的映射关系。
可选的，计算设备还可以将任务目标发送至巡检设备，任务目标为巡检线路最短，巡检设备基于任务目标和各个点位的巡检顺序确定相邻点位之间的巡检线路。比如，在确定任意相邻的两个点位之间的巡检线路时，基于巡检线路最短的原则，从由当前点位至下一点位的多条路径中确定出一条最短路径，作为由当前点位至下一点位的巡检线路。
可选的，任务目标还可以为巡检设备计算相邻两个点位之间的巡检线路所消耗的时长最短，则巡检设备在计算由当前点位至下一点位选择哪一条路径时，选择计算消耗时长最短的算法来确定。可选的，任务目标还可以为巡检设备在由当前点位行走至下一点位的过程中计算局部线路所消耗的时长最短，则巡检设备在计算局部线路时采用计算消耗时长最短的算法来确定。
可选的，计算当前点位至下一点位的巡检线路时采用哪种算法，还可以由用户预先指定，例如，用户可预先指定计算由A点位至B点位的巡检路径时采用算法a，计算由B点位至C点位的巡检路径时采用算法b，计算由B点位至C点位的巡检路径时采用算法c，等等。其中，A点位与B点位相邻，B点位和C点位相邻，这里，算法a、算法b和算法c可以是相同的算法，也可以是不同的算法。或者，巡检设备在确定出计算当前点位至下一点位的巡检线路所采用的算法的情况下，可以向计算设备发送确认消息，确认消息用于向用户确认是否采用该算法，用户可以在计算设备上进行确认操作，计算设备向巡检设备发送响应消息，巡检设备接收到响应消息，响应消息用于指示采用该算法，或者，用户在计算设备上进行否认操作并指定某一算法，计算设备向巡检设备发送响应消息，巡检设备接收到响应消息，响应消息中包括用户指定的算法。
在巡检设备根据确定出的相邻点位之间的巡检线路进行巡检的过程中，巡检设备会获取实时路况信息，并根据实时路况信息，调整由当前点位至下一点位过程中的局部巡检线路。可选的，巡检设备中包括第二算法库，第二算法库中包括多种算法，多种算法是针对不同的路况信息而设置的。比如，针对存在障碍物的道路，可以采用算法一调整由当前点位至下一点位过程中的局部巡检线路，针对凹凸不平的道路，可以采用算法二调整由当前点位至下一点位过程中的局部巡检线路，等等。第二算法库中的多种算法例如可以包括遗传算法、蚁群算法、粒子群算法、深度优先搜索(depth first search，DFS)算法、快速扩展随机数(rapidly-exploring random tree，RRT)算法等中的任意多种。
可选的，可以预先将路况情况划分为多个等级或多个类型，比如，无岔路口、无障碍物为一个等级/一种类型，无岔路口、有障碍物为一个等级/一种类型，有岔路口、无障碍物为一个等级/一个类型，有岔路口、有障碍物为一个等级/一种类型，每个等级或每种类型对应一种算法，实际行走过程中，根据传感器采集的数据确定路况所处的等级/类型，从而选择对应的算法，确定出由当前点位至下一点位的局部巡检线路。本示例仅仅是一种举例，实际路况包括更多种可能的情况，这里仅仅用于举例，并不构成对本申请的限定。
可选的，巡检设备在确定由当前点位至下一点位的巡检路径所使用的算法时和由当前点位行走至下一点位的过程中面对不同的路况所使用的算法时，还可以根据巡检设备自身的特性来确定，巡检设备自身的特性例如包括巡检设备的最大转向角，例如，有的巡检设备最大转向角是90度，有的巡检设备最大转向角是180度。巡检设备自身的特性还可以是其他性能，本申请不做限定。
可以看到，本申请提供了一种路径规划方法，根据地图和多个待巡检点位生成一个或多个修正点位， 修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段等中的一个或多个位置，根据多个待巡检点位和一个或多个修正点位生成的巡检路径更加精准，能够提高拍摄成功率；另外，在地图中增加修正点位，还解决了地图破损导致的“穿墙”问题；在计算巡检路径时，考虑到了实际任务需求，比如任务目标是什么，特殊巡检点位允许的访问时间是什么时候，根据任务需求确定出的巡检路径，满足了用户的需求；巡检设备中提供了用于确定巡检路径的多种算法，可以根据实际路况情况从多种算法中确定一种算法来计算巡检路径，巡检设备的应用性较强。
本申请提供了一种路径规划装置600，路径规划装置600可以配置为图1或图2中的计算设备。参见图6，图6为本申请提供的路径规划装置600的结构示意图，路径规划装置600包括：
交互模块601，用于接收用户输入的信息，用户输入的信息包括多个待巡检点位；
生成模块602，用于根据多个待巡检点位和地图，生成一个或多个修正点位，其中，修正点位是设置在地图中特定路况位置处的点位；
生成模块602还用于，根据多个待巡检点位和一个或多个修正点位，生成巡检路径，巡检路径中包括各个点位的巡检顺序，各个点位包括多个待巡检点位和一个或多个修正点位；
通信模块603，用于将巡检路径发送至巡检设备，以使巡检设备根据巡检路径和实时路况信息生成巡检线路，巡检线路指的是巡检设备巡检多个待巡检点位过程所走的实际线路。
在可能的实现方式中，用户输入的信息还包括任务需求，任务需求包括巡检线路最短；生成模块602用于：根据多个待巡检点位、一个或多个修正点位和任务需求，生成巡检路径。
在可能的实现方式中，任务需求还包括多个待巡检点位中至少一个待巡检点位所允许访问的时间。
在可能的实现方式中，修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
在可能的实现方式中，交互模块601还用于，接收用户的操作，用户的操作包括增加和/或删除修正点位。
其中，交互模块601、生成模块602、通信模块603均可以通过软件实现，或者可以通过硬件实现。示例性的，接下来以生成模块602为例，介绍生成模块602的实现方式。类似的，交互模块601、通信模块603的实现方式可以参考生成模块602的实现方式。
模块作为软件功能单元的一种举例，生成模块602可以包括运行在计算设备上的代码。其中，计算设备可以是云服务中的计算设备，其中计算设备例如可以是裸金属服务器、虚拟机、容器等，进一步地，计算设备可以是一台或多台。例如，生成模块602可以包括运行在多个计算设备上的代码。需要说明的是，用于运行该代码的多个计算设备可以分布在相同的区域(region)中，也可以分布在不同的region中。进一步地，用于运行该代码的多个计算设备可以分布在相同的可用区(availability zone，AZ)中，也可以分布在不同的AZ中，每个AZ包括一个数据中心或多个地理位置相近的数据中心。其中，通常一个区域region可以包括多个可用区AZ。
同样，用于运行该代码的多个计算设备可以分布在同一个虚拟私有云(virtual private cloud，VPC)中，也可以分布在多个VPC中。其中，通常一个VPC设置在一个region内，同一region内两个VPC之间，以及不同region的VPC之间跨区通信需在每个VPC内设置通信网关，经通信网关实现VPC之间的互连。
模块作为硬件功能单元的一种举例，生成模块602可以包括至少一个计算设备。或者，生成模块602也可以是利用专用集成电路(application-specific integrated circuit，ASIC)实现、或可编程逻辑器件(programmable logic device，PLD)实现的设备等。其中，上述PLD可以是复杂程序逻辑器件(complex programmable logical device，CPLD)、现场可编程门阵列(field-programmable gate array，FPGA)、通用阵列逻辑(generic array logic，GAL)或其任意组合实现。
生成模块602包括的多个计算设备可以分布在相同的region中，也可以分布在不同的region中。生成模块602包括的多个计算设备可以分布在相同的AZ中，也可以分布在不同的AZ中。同样，生成模块602包括的多个计算设备可以分布在同一个VPC中，也可以分布在多个VPC中。其中，所述多个计算设备可以是服务器、ASIC、PLD、CPLD、FPGA和GAL等计算设备的任意组合。
需要说明的是，在其他实施例中，生成模块602可以用于执行一种路径规划方法中的任意步骤，交互模块601、通信模块603均可以用于执行一种路径规划方法中的任意步骤,交互模块601、生成模块602和通信模块603负责实现的步骤可根据需要指定，通过交互模块601、生成模块602和通信模块603分别实现一种路径规划方法中不同的步骤，来实现路径规划装置600的全部功能。
参见图7，图7为本申请提供的一种计算设备700的结构示意图，计算设备700例如可以是裸金属服务器、虚拟机、容器等，该计算设备700可以配置为方法实施例中的计算设备，计算设备700包括：总线702、处理器704、存储器706和通信接口708。处理器704、存储器706和通信接口708之间通过总线702通信。应理解，本申请不限定计算设备700中的处理器、存储器的个数。
总线702可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图7中仅用一条线表示，但并不表示仅有一根总线或一种类型的总线。总线702可包括在计算设备700各个部件(例如，存储器706、处理器704、通信接口708)之间传送信息的通路。
处理器704可以包括中央处理器(central processing unit，CPU)、图形处理器(graphics processing unit，GPU)、微处理器(micro processor，MP)或者数字信号处理器(digital signal processor，DSP)等处理器中的任意一种或多种。
存储器706可以包括易失性存储器(volatile memory)，例如随机存取存储器(random access memory，RAM)。处理器704还可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)，快闪存储器，机械硬盘(hard disk drive，HDD)或固态硬盘(solid state drive，SSD)。
存储器706中存储有可执行的程序代码，处理器704执行该可执行的程序代码以分别实现前述交互模块601、生成模块602和通信模块603的功能，从而实现一种路径规划方法。也即，存储器706上存有用于执行一种路径规划方法的指令。
通信接口708使用例如但不限于网络接口卡、收发器一类的收发模块，来实现计算设备700与其他设备或通信网络之间的通信。可选的，通信模块603可以位于通信接口708中。
本申请实施例还提供了一种计算设备集群。该计算设备集群包括至少一台计算设备。该计算设备可以是服务器，例如是中心服务器、边缘服务器，或者是本地数据中心中的本地服务器。在一些实施例中，计算设备也可以是台式机、笔记本电脑等设备。
如图8所示，图8为本申请提供的一种计算设备集群的结构示意图，所述计算设备集群包括至少一个计算设备700。计算设备集群中的一个或多个计算设备700中的存储器706中可以存有相同的用于执行一种路径规划方法的指令。
在一些可能的实现方式中，该计算设备集群中的一个或多个计算设备700的存储器706中也可以分别存有用于执行一种路径规划方法的部分指令。换言之，一个或多个计算设备700的组合可用于共同执行一种路径规划方法的指令。
需要说明的是，计算设备集群中的不同的计算设备700中的存储器706可以存储不同的指令，分别用于执行计算设备700的部分功能。也即，不同的计算设备700中的存储器706存储的指令可以实现交互模块601、生成模块602和通信模块603中的一个或多个模块的功能。
在一些可能的实现方式中，计算设备集群中的一个或多个计算设备可以通过网络连接。其中，所述网络可以是广域网或局域网等等。图9示出了一种可能的实现方式。如图9所示，两个计算设备700A和700B之间通过网络进行连接。具体地，通过各个计算设备中的通信接口与所述网络进行连接。在这一类可能的实现方式中，计算设备700A中的存储器706中存有执行交互模块601和生成模块602功能的指令。同时，计算设备700B中的存储器706中存有执行生成模块602和通信模块603的功能的指令。其中，计算设备700A中的生成模块602用于实现根据多个待巡检点位和地图生成一个或多个修正点位的功能，计算设备700B中的生成模块602用于实现根据多个待巡检点位和一个或多个修正点位生成巡检路径的功能。
应理解，图9中示出的计算设备700A的功能也可以由多个计算设备700完成，或者计算设备集群中包括多个与计算设备700A具有相同功能的计算设备。同样，计算设备700B的功能也可以由多个计算设备700完成，或者计算设备集群中包括多个与计算设备700B具有相同功能的计算设备。
本申请实施例还提供了另一种计算设备集群。该计算设备集群中各计算设备之间的连接关系可以类似的参考图8和图9所述计算设备集群的连接方式。不同的是，该计算设备集群中的一个或多个计算设备700中的存储器706中可以存有不同的用于执行一种路径规划方法的指令。在一些可能的实现方式中，该计算设备集群中的一个或多个计算设备700的存储器706中也可以分别存有用于执行一种路径规划方法的部分指令。换言之，一个或多个计算设备700的组合可以共同执行用于执行一种路径规划方法的指令。
本申请提供了又一种路径规划装置，参见图10，图10为本申请提供的又一种路径规划装置800的结构示意图，路径规划装置800可以配置为图1或图2系统架构中的巡检设备，也可以配置为图3方法实施例中的巡检设备，路径规划装置800包括：
通信模块801，用于接收计算设备发送的巡检路径，巡检路径中包括各个点位的巡检顺序，各个点位包括多个待巡检点位和一个或多个修正点位，其中，一个或多个修正点位是计算设备根据多个待巡检点位和地图，设置在地图中特定路况位置处的点位；
处理模块802，用于在根据巡检路径行走的过程中，获取实时路况信息，并基于实时路况信息确定巡检线路，巡检线路指的是巡检设备巡检多个待巡检点位过程所走的实际线路。
在可能的实现方式中，修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
在可能的实现方式中，处理模块802用于：在巡检设备位于巡检路径中的任意一个点位时，从由当前点位至下一点位的至少一条路径中确定出一条最短路径，作为由当前点位至下一点位的巡检线路；
处理模块802还用于：巡检设备在由当前点位至下一点位巡检过程中，获取实时路况信息，并根据实时路况信息，调整由当前点位至下一点位过程中的局部巡检线路，实时路况信息包括存在障碍物的路况、凹凸不平的路况中的一种或多种。
图10方法实施例中的各个功能模块具体用于执行图3方法实施例中巡检设备所执行的步骤，具体用于执行图3方法实施例中的步骤S104和S105，具体参见图3方法实施例的描述，为了说明书的简洁，在此不再赘述。
本申请还提供了一种巡检设备的结构示意图，参见图11所示，图11为本申请提供的一种巡检设备900的结构示意图，巡检设备900例如可以是机器人，该巡检设备900可以配置为方法实施例中的巡检设备，巡检设备900包括：总线902、处理器904、存储器906和通信接口908。处理器904、存储器906和通信接口908之间通过总线902通信。应理解，本申请不限定巡检设备900中的处理器、存储器的个数。
总线902可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图11中仅用一条线表示，但并不表示仅有一根总线或一种类型的总线。总线902可包括在巡检设备900各个部件(例如，存储器906、处理器904、通信接口908)之间传送信息的通路。
处理器904可以包括中央处理器(central processing unit，CPU)、图形处理器(graphics processing unit，GPU)、微处理器(micro processor，MP)或者数字信号处理器(digital signal processor，DSP)等处理器中的任意一种或多种。
存储器906可以包括易失性存储器(volatile memory)，例如随机存取存储器(random access memory，RAM)。处理器904还可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)，快闪存储器，机械硬盘(hard disk drive，HDD)或固态硬盘(solid state drive，SSD)。
存储器906中存储有可执行的程序代码，处理器904执行该可执行的程序代码以分别实现前述通信模块801和处理模块802的功能，从而实现一种路径规划方法。也即，存储器906上存有用于执行一种路径规划方法的指令。
通信接口908使用例如但不限于网络接口卡、收发器一类的收发模块，来实现巡检设备900与其他设备或通信网络之间的通信。可选的，例如通信模块801可以位于通信接口908中。
本申请实施例还提供了一种包含指令的计算机程序产品。所述计算机程序产品可以是包含指令的，能够运行在计算设备上或被储存在任何可用介质中的软件或程序产品。当所述计算机程序产品在至少一个计算设备上运行时，使得至少一个计算设备执行一种路径规划方法。
本申请实施例还提供了一种包含指令的计算机程序产品。所述计算机程序产品可以是包含指令的，能够运行在巡检设备上或被储存在任何可用介质中的软件或程序产品。当所述计算机程序产品在巡检设备上运行时，使得巡检设备执行一种路径规划方法。
本申请实施例还提供了一种计算机可读存储介质。所述计算机可读存储介质可以是计算设备能够存储的任何可用介质或者是包含一个或多个可用介质的数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘)等。该计算机可读存储介质包括指令，所述指令指示计算设备或计算设备集群执行一种路径规划方法。
本申请还提供了一种计算机可读存储介质，包括程序指令，当程序指令在巡检设备上执行时，使得所述巡检设备执行一种路径规划方法。
本申请提供了一种系统，所述系统包括至少一个计算设备和巡检设备，计算设备可以是图6中的路径规划装置600或者图7中的计算设备700，至少一个计算设备可以是图8中的计算设备集群，也可以是图9中的计算设备700A和计算设备700B，巡检设备可以是图10中的路径规划装置800或者图11中的巡检设备900，所述系统用于共同执行图3方法实施例中的一种路径规划方法。
以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的保护范围。

Claims (21)

  1. 一种路径规划方法，其特征在于，包括：
    计算设备接收用户输入的信息，所述用户输入的信息包括多个待巡检点位；
    所述计算设备根据所述多个待巡检点位和地图，生成一个或多个修正点位，其中，所述修正点位是设置在所述地图中特定路况位置处的点位；
    所述计算设备根据所述多个待巡检点位和所述一个或多个修正点位，生成巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括所述多个待巡检点位和所述一个或多个修正点位；
    所述计算设备将所述巡检路径发送至巡检设备，以使所述巡检设备根据所述巡检路径和实时路况信息生成巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
  2. 根据权利要求1所述的方法，其特征在于，所述用户输入的信息还包括任务需求，所述任务需求包括所述巡检线路最短；
    所述根据所述多个待巡检点位和所述一个或多个修正点位，生成巡检路径，包括：
    根据所述多个待巡检点位、所述一个或多个修正点位和所述任务需求，生成所述巡检路径。
  3. 根据权利要求2所述的方法，其特征在于，所述任务需求还包括所述多个待巡检点位中至少一个待巡检点位所允许访问的时间。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，在所述根据所述多个待巡检点位和地图，生成一个或多个修正点位之后，所述方法还包括：
    所述计算设备接收用户的操作，所述用户的操作包括增加和/或删除所述修正点位。
  6. 一种路径规划方法，其特征在于，包括：
    巡检设备接收计算设备发送的巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括多个待巡检点位和一个或多个修正点位，其中，所述一个或多个修正点位是所述计算设备根据所述多个待巡检点位和地图，设置在所述地图中特定路况位置处的点位；
    巡检设备在根据所述巡检路径行走的过程中，获取实时路况信息，并基于所述实时路况信息确定巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
  7. 根据权利要求6所述的方法，其特征在于，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
  8. 根据权利要求6或7所述的方法，其特征在于，所述巡检设备在根据所述巡检路径行走的过程中，获取实时路况信息，并基于所述实时路况信息确定巡检线路，包括：
    在所述巡检设备位于所述巡检路径中的任意一个点位时，所述巡检设备从由当前点位至下一点位的至少一条路径中确定出一条最短路径，作为由所述当前点位至所述下一点位的巡检线路；
    其中，
    所述巡检设备在由所述当前点位至所述下一点位巡检过程中，获取实时路况信息，并根据所述实时路况信息，调整由所述当前点位至所述下一点位过程中的局部巡检线路，所述实时路况信息包括存在障碍物的路况、凹凸不平的路况中的一种或多种。
  9. 一种路径规划装置，其特征在于，包括：
    交互模块，用于接收用户输入的信息，所述用户输入的信息包括多个待巡检点位；
    生成模块，用于根据所述多个待巡检点位和地图，生成一个或多个修正点位，其中，所述修正点位是设置在所述地图中特定路况位置处的点位；
    所述生成模块还用于，根据所述多个待巡检点位和所述一个或多个修正点位，生成巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括所述多个待巡检点位和所述一个或多个修正点位；
    通信模块，用于将所述巡检路径发送至巡检设备，以使所述巡检设备根据所述巡检路径和实时路况信息生成巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
  10. 根据权利要求9所述的装置，其特征在于，所述用户输入的信息还包括任务需求，所述任务需求包括所述巡检线路最短；
    所述生成模块用于：根据所述多个待巡检点位、所述一个或多个修正点位和所述任务需求，生成所述巡检路径。
  11. 根据权利要求10所述的装置，其特征在于，所述任务需求还包括所述多个待巡检点位中至少一个 待巡检点位所允许访问的时间。
  12. 根据权利要求9-11任一项所述的装置，其特征在于，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
  13. 根据权利要求9-12任一项所述的装置，其特征在于，所述交互模块还用于，接收用户的操作，所述用户的操作包括增加和/或删除所述修正点位。
  14. 一种路径规划装置，其特征在于，包括：
    通信模块，用于接收计算设备发送的巡检路径，所述巡检路径中包括各个点位的巡检顺序，所述各个点位包括多个待巡检点位和一个或多个修正点位，其中，所述一个或多个修正点位是所述计算设备根据所述多个待巡检点位和地图，设置在所述地图中特定路况位置处的点位；
    处理模块，用于在根据所述巡检路径行走的过程中，获取实时路况信息，并基于所述实时路况信息确定巡检线路，所述巡检线路指的是所述巡检设备巡检所述多个待巡检点位过程所走的实际线路。
  15. 根据权利要求14所述的装置，其特征在于，所述修正点位位于转弯处附近、岔路口附近、坡度路段、较狭窄的路段中的一个或多个位置。
  16. 根据权利要求14或15所述的装置，其特征在于，
    所述处理模块用于：在所述巡检设备位于所述巡检路径中的任意一个点位时，从由当前点位至下一点位的至少一条路径中确定出一条最短路径，作为由所述当前点位至所述下一点位的巡检线路；
    所述处理模块还用于：所述巡检设备在由所述当前点位至所述下一点位巡检过程中，获取实时路况信息，并根据所述实时路况信息，调整由所述当前点位至所述下一点位过程中的局部巡检线路，所述实时路况信息包括存在障碍物的路况、凹凸不平的路况中的一种或多种。
  17. 一种计算设备集群，其特征在于，包括至少一个计算设备，所述至少一个计算设备中的每个计算设备包括处理器和存储器，所述至少一个计算设备的处理器用于执行所述至少一个计算设备的存储器中存储的指令，以使得所述计算设备集群执行如权利要求1至5任一项所述的方法。
  18. 一种计算机可读存储介质，其特征在于，包括计算机程序指令，当所述计算机程序指令由计算设备集群执行时，所述计算设备集群执行如权利要求1至5任一项所述的方法。
  19. 一种巡检设备，其特征在于，包括处理器和存储器，所述存储器用于存储指令，所述处理器用于运行所述存储器中存储的指令执行如权利要求6至8任一项所述的方法。
  20. 一种计算机可读存储介质，其特征在于，包括程序指令，当所述程序指令被巡检设备执行时，所述巡检设备执行如权利要求6至8任一项所述的方法。
  21. 一种系统，其特征在于，包括计算设备和巡检设备，所述计算设备为如权利要求1-5任一项所述的计算设备，所述巡检设备为如权利要求6-8任一项所述的巡检设备。
PCT/CN2023/112155 2022-09-08 2023-08-10 一种路径规划方法、相关装置及系统 WO2024051437A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211096416.9 2022-09-08
CN202211096416.9A CN117724467A (zh) 2022-09-08 2022-09-08 一种路径规划方法、相关装置及系统

Publications (1)

Publication Number Publication Date
WO2024051437A1 true WO2024051437A1 (zh) 2024-03-14

Family

ID=90192024

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/112155 WO2024051437A1 (zh) 2022-09-08 2023-08-10 一种路径规划方法、相关装置及系统

Country Status (2)

Country Link
CN (1) CN117724467A (zh)
WO (1) WO2024051437A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007280251A (ja) * 2006-04-11 2007-10-25 Yaskawa Electric Corp 移動ロボット
CN102183959A (zh) * 2011-04-21 2011-09-14 深圳市银星智能电器有限公司 移动机器人的自适应路径控制方法
WO2020233155A1 (zh) * 2019-05-23 2020-11-26 中国银联股份有限公司 一种巡检设备的方法及装置
US20210041243A1 (en) * 2019-08-06 2021-02-11 Boston Dynamics, Inc. Intermediate Waypoint Generator
CN112418532A (zh) * 2020-11-25 2021-02-26 杭州凯达电力建设有限公司 输电线路的巡检路径规划方法、装置、设备及存储介质
CN112697162A (zh) * 2020-12-23 2021-04-23 千方捷通科技股份有限公司 一种巡检路线规划方法、装置、存储介质及终端
CN114089770A (zh) * 2021-11-23 2022-02-25 广东电网有限责任公司 一种变电站巡检机器人的巡检点位生成方法及相关装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007280251A (ja) * 2006-04-11 2007-10-25 Yaskawa Electric Corp 移動ロボット
CN102183959A (zh) * 2011-04-21 2011-09-14 深圳市银星智能电器有限公司 移动机器人的自适应路径控制方法
WO2020233155A1 (zh) * 2019-05-23 2020-11-26 中国银联股份有限公司 一种巡检设备的方法及装置
US20210041243A1 (en) * 2019-08-06 2021-02-11 Boston Dynamics, Inc. Intermediate Waypoint Generator
CN112418532A (zh) * 2020-11-25 2021-02-26 杭州凯达电力建设有限公司 输电线路的巡检路径规划方法、装置、设备及存储介质
CN112697162A (zh) * 2020-12-23 2021-04-23 千方捷通科技股份有限公司 一种巡检路线规划方法、装置、存储介质及终端
CN114089770A (zh) * 2021-11-23 2022-02-25 广东电网有限责任公司 一种变电站巡检机器人的巡检点位生成方法及相关装置

Also Published As

Publication number Publication date
CN117724467A (zh) 2024-03-19

Similar Documents

Publication Publication Date Title
US9852639B2 (en) Generating a mission plan for capturing aerial images with an unmanned aerial vehicle
CN104596526B (zh) 一种定位点匹配方法及装置
US11183071B2 (en) Drone flight optimization using drone-to-drone permissioning
CN107644273B (zh) 一种导航路径规划方法及设备
CN111656135A (zh) 基于高清地图的定位优化
Hamledari et al. Automation of inspection mission planning using 4D BIMs and in support of unmanned aerial vehicle–based data collection
CN110914870B (zh) 图像网络的注释生成
US11829135B2 (en) Tuning autonomous vehicle dispatch using vehicle performance
CN112527932A (zh) 道路数据处理的方法、装置、设备及存储介质
US11269356B2 (en) Edge computing for clusters of vehicles
KR20230007256A (ko) 도로 데이터 융합의 지도 생성 방법, 장치 및 전자 기기
CN110542425B (zh) 导航路径选择方法、导航装置、计算机设备及可读介质
US20180033314A1 (en) Automated vehicle control
WO2024051437A1 (zh) 一种路径规划方法、相关装置及系统
US20240086828A1 (en) Aerial vehicle delivery of items
CN116661479B (zh) 建筑巡检路径规划方法、设备和可读存储介质
CN115793715B (zh) 一种无人机辅助飞行方法、系统、装置及存储介质
US11846517B2 (en) Vector tile navigation
US10955251B2 (en) Identifying incorrect coordinate prediction using route information
Ikeuchi et al. Uav surveillance optimization for networks in disaster-stricken areas
JP7478395B2 (ja) 軌道算出装置、軌道算出方法およびプログラム
US20230175851A1 (en) Data-analysis-based navigation system assistance
CN113761990B (zh) 一种道路边界检测方法、装置、无人车及存储介质
CN112462764B (zh) 车辆约束图的构建方法及装置
CN114339155B (zh) 抓拍漏洞路线确定方法和相关装置