Indoor inspection robot and inspection method

Abstract

The invention provides an indoor inspection robot and an inspection method, and the indoor inspection robot comprises an instruction receiving module which is used for receiving instruction information of a control center, the instruction information comprises information of an inspection task, and the information of the inspection task comprises a plurality of inspection points; the robot confirmation module is used for selecting a robot to execute the processing of the area path selection module, the area path planning module and the inspection path planning module based on the positions of a plurality of inspection points in the information of the inspection task; the area path selection module is used for determining at least one selected inspection area based on the positions of a plurality of inspection points in the information of the inspection task; the area path planning module is used for determining a first inspection sequence of inspection areas based on the position of the selected robot; and the routing inspection path planning module is used for performing path planning on the routing inspection areas one by one based on the first routing inspection sequence, and planning a routing inspection path according to the position of the routing inspection point in each routing inspection area.

Description

Technical Field

[0001] The present invention relates to the technical field of power station inspection, and in particular to an indoor inspection robot and an inspection method. Background Art

[0002] The existing power plants have concentrated equipment, widely distributed pipelines, small spaces, and complex environments. In order to ensure the safe and stable operation of the power plants, regular inspections are required. Power plants or power stations have a variety of large electrical equipment, such as distribution cabinets and distribution boxes. In order to prevent safety hazards caused by equipment failures, the electrical equipment needs to be inspected regularly.

[0003] Currently, power plants or power stations usually adopt manual inspection methods, but manual inspection has high safety risks. In the prior art, inspection robots that can inspect in power plants have appeared, replacing manual operations and regularly moving to the vicinity of specific equipment to collect images.

[0004] However, for large power plants or power stations, each inspection needs to inspect a large number of locations. In the existing inspection robot inspections, all inspection points are usually assigned to one inspection robot. Therefore, when the robot is planning the path, all inspection points need to be taken into account in each calculation, resulting in low efficiency in robot path planning.

[0005] In view of this, the present invention is proposed. Summary of the invention

[0006] The purpose of the present invention is to provide an indoor inspection robot and an inspection method, which reduce the calculation amount of path planning and improve the efficiency of robot path planning.

[0007] The present invention provides an indoor inspection robot, the indoor inspection robot comprising:

[0008] An instruction receiving module, used to receive instruction information from a control center, wherein the instruction information includes information about an inspection task, and the information about the inspection task includes multiple inspection points;

[0009] A robot confirmation module, used to determine whether the current robot is a selected robot based on the positions of multiple inspection points in the information of the inspection task, and if the current robot is a selected robot, execute the processing of the regional path selection module, the regional path planning module and the inspection path planning module;

[0010] An area path selection module, used to determine at least one selected inspection area based on the positions of multiple inspection points in the information of the inspection task;

[0011] An area path planning module, used to determine a first inspection sequence of the inspection area based on the position of the selected robot;

[0012] The inspection path planning module is used to plan paths for each inspection area based on the first inspection sequence, and plan an inspection path for the location of the inspection point in each inspection area.

[0013] By adopting the above scheme, this scheme first determines the selected inspection area in the current scene map based on the position of the inspection point in the inspection task, and splits all the inspection points into inspection points in each inspection area according to the position of the inspection point, and then determines the first inspection order of the inspection area based on the position of the robot and the position of each inspection area. In the final path planning process, it is only necessary to perform path planning for the inspection points in each inspection area based on the first inspection order, which ensures that the calculation amount is within one inspection area, reduces the calculation amount of path planning, and improves the efficiency of robot path planning.

[0014] In some embodiments of the present invention, the inspection scene includes a plurality of inspection waiting areas, each of which has at least one robot, and the robots in the inspection waiting areas include a standby robot. If the robot is a standby robot, the robot receives instruction information from a control center through an instruction receiving module, and in the step of determining whether the current robot is a selected robot based on the positions of a plurality of inspection points in the information of the inspection task,

[0015] Calculating the inspection center point of the inspection task based on the two-dimensional coordinate data of the inspection point;

[0016] Based on the position of the inspection center point and the positions of multiple inspection waiting areas, a selected inspection waiting area is determined, and the standby robot in the inspection waiting area is used as the selected robot.

[0017] By adopting the above scheme, each inspection task only needs one robot to perform. In the step of selecting the specified robot, this scheme first calculates the inspection center point of the inspection task based on the two-dimensional coordinate data of all inspection points. The calculation of the inspection center point takes all inspection points into consideration. Then, based on the inspection waiting area where the robot is located, the robot in the inspection waiting area that is most suitable for inspecting all inspection points is calculated. In the process of selecting the robot, this scheme not only takes into consideration all inspection points, but also takes into consideration the inspection waiting area where the robot is located, thereby ensuring that the selected robot can efficiently perform the inspection task.

[0018] In some embodiments of the present invention, in the step of determining at least one selected inspection area based on the positions of multiple inspection points in the information of the inspection task, the inspection area where the inspection points are located is used as the selected inspection area.

[0019] In some embodiments of the present invention, in the step of determining a first inspection sequence of the inspection area based on the position of the selected robot,

[0020] Calculating a region center point of each selected inspection region based on the inspection points in each selected inspection region;

[0021] Calculate the distance between the selected robot and the area center point of each selected inspection area respectively, determine the first sequence area in the first inspection sequence, calculate the distance between the area center point of the first sequence area and the area center points of other selected inspection areas, determine the second sequence area in the first inspection sequence, and determine the order of each inspection area in the first inspection sequence one by one.

[0022] Using the above scheme, this scheme first determines the inspection order of each inspection area one by one based on the position of the area center point of each selected inspection area, ensuring that the robot operates efficiently between inspection areas when performing inspection tasks according to the first inspection order.

[0023] In some embodiments of the present invention, the inspection points are marked in a scene map, which includes multiple driving paths. The locations where the driving paths intersect are driving intersections, and the driving paths between adjacent driving intersections are used as sub-paths. In the step of planning inspection paths for the locations of the inspection points in each inspection area, each time the selected robot drives to the driving intersection during the inspection process, a sub-path decision is made based on historical driving data and shortest path data, and a sub-path is selected based on the sub-path decision.

[0024] In some embodiments of the present invention, each time the selected robot drives to the driving intersection during the inspection process, in the step of making a sub-path decision based on the historical driving data and the shortest path data,

[0025] The previous inspection point is used as the starting point, and the next inspection point is used as the target point;

[0026] Acquire the number of travel trajectories with the target point as the end point and the number of travel trajectories including the sub-path in the historical travel data;

[0027] Calculating the ratio of the number of travel trajectories including the sub-path to the number of travel trajectories with the target point as the end point, and calculating the shortest distance from the travel intersection to the target point;

[0028] A first driving parameter of each sub-path is calculated based on the ratio and the shortest distance from the driving intersection point to the target point, and a sub-path to be driven is determined based on the first driving parameter.

[0029] By adopting the above scheme, when the robot moves on a sub-path, it can directly drive along the sub-path. Whenever the robot drives to a driving intersection, it makes a sub-path decision and obtains the sub-path for the next driving step. This ensures that each time the inspection robot drives to a driving intersection, it can make the best decision to ensure the efficiency of the robot's operating path.

[0030] In some embodiments of the present invention, in the step of calculating the first driving parameter of each sub-path based on the ratio and the shortest distance from the driving intersection to the target point, the first driving parameter is calculated based on the following formula:

[0031]

[0032] Among them, δ(a, b) represents the first travel parameter of the sub-path composed of the two driving intersections a and b, a is the starting point of the sub-path, and b is the end point of the sub-path; D(a, e) represents the distance of the shortest path from the driving intersection a to the target point e; D(b, e) represents the shortest distance from the driving intersection b to the target point e; D(a, b) represents the distance of the sub-path composed of the two driving intersections a and b; α(a, b) represents the ratio corresponding to the sub-path composed of the two intersections a and b.

[0033] By adopting the above scheme, in the process of calculating the first driving parameter, the historical utilization of the sub-path and the shortest distance of the path are fully considered. The use of historical data can better utilize historical experience, and the use of the shortest distance can take into account the maximum efficiency of the inspection, thereby ensuring the efficiency and reliability of the inspection.

[0034] In some embodiments of the present invention, in the step of calculating the first driving parameter of each sub-path based on the ratio and the shortest distance from the driving intersection to the target point, and determining the sub-path to be traveled based on the first driving parameter, the sub-path corresponding to the maximum first driving parameter is selected as the sub-path to be traveled.

[0035] In some embodiments of the present invention, in the step of performing path planning for inspection areas one by one based on the first inspection sequence and planning inspection paths for the positions of inspection points in each inspection area, when the selected robot drives from one inspection area to another inspection area based on the first inspection sequence, the last completed inspection point in the previous inspection area is taken as the starting point, and the shortest distance between the last completed inspection point in the previous inspection area and each inspection point in the next inspection area is calculated, the inspection point with the shortest distance to the inspection points in the next inspection area is taken as the first inspection point in the next inspection area, and the first inspection point in the next inspection area is taken as the target point, and in the process of driving from the starting point to the target point, the selected robot makes sub-path decisions based on historical driving data and shortest path data each time it drives to the driving intersection.

[0036] Another aspect of the present invention also relates to an inspection method, the method comprising the steps of:

[0037] Receiving instruction information from a control center, the instruction information including information of an inspection task, the information of the inspection task including a plurality of inspection points;

[0038] Based on the positions of multiple inspection points in the information of the inspection task, determine whether the current robot is the selected robot, and if the current robot is the selected robot, execute the processing of the regional path selection module, the regional path planning module and the inspection path planning module;

[0039] Determining at least one selected inspection area based on the locations of a plurality of inspection points in the information of the inspection task;

[0040] Determining a first inspection order of the inspection area based on the position of the selected robot;

[0041] Path planning is performed for each inspection area based on the first inspection sequence, and an inspection path is planned for the location of the inspection point in each inspection area.

[0042] In summary, the present invention has the following beneficial effects:

[0043] 1. This solution first determines the selected inspection area in the current scene map based on the position of the inspection point in the inspection task, and splits all the inspection points into inspection points in each inspection area based on the position of the inspection point, and then determines the first inspection order of the inspection area based on the position of the robot and the position of each inspection area. In the final path planning process, it is only necessary to plan the path for the inspection points in each inspection area based on the first inspection order, so that the calculation amount is guaranteed to be in one inspection area, which reduces the calculation amount of path planning and improves the efficiency of robot path planning;

[0044] 2. In this scheme, each inspection task only needs one robot to perform. In the step of selecting a designated robot, this scheme first calculates the inspection center point of the inspection task based on the two-dimensional coordinate data of all inspection points. The calculation of the inspection center point takes all inspection points into consideration. Then, based on the inspection waiting area where the robot is located, the robot in the inspection waiting area that is most suitable for inspecting all inspection points is calculated. In the process of selecting a robot, this scheme not only takes into consideration all inspection points, but also takes into consideration the inspection waiting area where the robot is located, thereby ensuring that the selected robot can efficiently perform the inspection task.

[0045] 3. This scheme first determines the inspection order of each inspection area one by one based on the position of the regional center point of each selected inspection area, so as to ensure that the robot can operate efficiently between the inspection areas when performing the inspection task according to the first inspection order;

[0046] 4. In the process of calculating the first driving parameter, this scheme fully considers the historical utilization of the sub-path and the shortest distance of the path. The use of historical data can better utilize historical experience, and the use of the shortest distance can take into account the maximum efficiency of the inspection, thereby ensuring the efficiency and reliability of the inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is a schematic diagram of a first embodiment of the indoor inspection robot of the present invention;

[0049] Figure 2 A schematic diagram of a processing step of the indoor inspection robot of the present invention;

[0050] Figure 3 A schematic diagram of another processing step of the indoor inspection robot of the present invention;

[0051] Figure 4 It is a structural schematic diagram of the indoor inspection robot of the present invention. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0053] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0054] like Figure 1 , 2 As shown in 4, the present invention provides an indoor inspection robot, the indoor inspection robot comprising:

[0055] The instruction receiving module 100 is used to execute step S100 to receive instruction information from the control center, wherein the instruction information includes information of an inspection task, and the information of the inspection task includes multiple inspection points;

[0056] During the specific implementation process, the control center can use a computer to issue instruction information to the robot. The instruction information also includes scene map information. The scene map information includes obstacles and sub-paths in the scene map. The robot travels on the sub-path to complete the inspection task.

[0057] The robot confirmation module 200 is used to execute step S200, determine whether the current robot is the selected robot based on the positions of multiple inspection points in the information of the inspection task, and if the current robot is the selected robot, execute the processing of the regional path selection module, the regional path planning module and the inspection path planning module;

[0058] The area path selection module 300 is used to execute step S300 to determine at least one selected inspection area based on the positions of multiple inspection points in the information of the inspection task;

[0059] In the specific implementation process, the inspection areas where the inspection points are located are all selected inspection areas.

[0060] The area path planning module 400 is used to execute step S400 and determine a first inspection sequence of the inspection area based on the position of the selected robot;

[0061] The inspection path planning module 500 is used to execute step S500, plan paths for each inspection area based on the first inspection sequence, and plan an inspection path for the location of the inspection point in each inspection area.

[0062] During the specific implementation process, the robot confirmation module is used to determine the selected robot, the area path selection module is used to determine the inspection area involved in the inspection task, the area path planning module is used to determine the inspection order of the inspection area, and the inspection path planning module is used to determine the final inspection path.

[0063] By adopting the above scheme, this scheme first determines the selected inspection area in the current scene map based on the position of the inspection point in the inspection task, and splits all the inspection points into inspection points in each inspection area according to the position of the inspection point, and then determines the first inspection order of the inspection area based on the position of the robot and the position of each inspection area. In the final path planning process, it is only necessary to perform path planning for the inspection points in each inspection area based on the first inspection order, which ensures that the calculation amount is within one inspection area, reduces the calculation amount of path planning, and improves the efficiency of robot path planning.

[0064] like Figure 3 As shown, in some embodiments of the present invention, the inspection scene includes multiple inspection waiting areas, each of the inspection waiting areas has at least one robot, and the robots in the inspection waiting areas include a standby robot. If the robot is a standby robot, the robot receives instruction information from a control center through an instruction receiving module, and based on the positions of multiple inspection points in the information of the inspection task, the step of determining whether the current robot is a selected robot includes:

[0065] Step S210, calculating the inspection center point of the inspection task based on the two-dimensional coordinate data of the inspection point;

[0066] Step S220, based on the position of the inspection center point and the positions of multiple inspection waiting areas, determine the selected inspection waiting area, and use the standby robot in the inspection waiting area as the selected robot.

[0067] In the specific implementation process, in the step of calculating the inspection center point of the inspection task, the coordinate average value of all inspection points is calculated, and the coordinate position corresponding to the coordinate average value of all inspection points is used as the inspection center point.

[0068] In the specific implementation process, in the step of determining the selected inspection waiting area based on the position of the inspection center point and the positions of multiple inspection waiting areas, and using the standby robot in the inspection waiting area as the selected robot, the distance between the position of the inspection center point and each of the multiple inspection waiting areas is calculated, the inspection waiting area closest to the inspection center point is used as the selected inspection waiting area, and the standby robot in the inspection waiting area is used as the selected robot.

[0069] In a specific implementation process, in the step of calculating the distance between the position of the inspection center point and each of the plurality of inspection waiting areas, a method of calculating the cosine distance is adopted.

[0070] By adopting the above scheme, each inspection task only needs one robot to perform. In the step of selecting the specified robot, this scheme first calculates the inspection center point of the inspection task based on the two-dimensional coordinate data of all inspection points. The calculation of the inspection center point takes all inspection points into consideration. Then, based on the inspection waiting area where the robot is located, the robot in the inspection waiting area that is most suitable for inspecting all inspection points is calculated. In the process of selecting the robot, this scheme not only takes into consideration all inspection points, but also takes into consideration the inspection waiting area where the robot is located, thereby ensuring that the selected robot can efficiently perform the inspection task.

[0071] In some embodiments of the present invention, in the step of determining at least one selected inspection area based on the positions of multiple inspection points in the information of the inspection task, the inspection area where the inspection points are located is used as the selected inspection area.

[0072] In the specific implementation process, the scene map includes multiple inspection areas, including high-pressure areas and low-pressure areas. The robot uses a first speed when driving in the high-pressure area and a second speed when driving in the low-pressure area. The second speed is greater than the first speed.

[0073] In some embodiments of the present invention, during the process of the robot driving from an inspection area in a high-pressure area to an inspection area in a low-pressure area, the robot monitors the distance between the robot and the boundary of the inspection area in the low-pressure area in real time, and when the distance is less than a preset distance threshold, the driving speed begins to be changed from the first speed to the second speed; during the process of the robot driving from an inspection area in a low-pressure area to an inspection area in a high-pressure area, the robot monitors the distance between the robot and the boundary of the inspection area in the high-pressure area in real time, and when the distance is less than a preset distance threshold, the driving speed begins to be changed from the second speed to the first speed.

[0074] By adopting the above solution, the robot can accelerate and decelerate in advance to ensure the safety of speed when entering the high-pressure area, and can ensure the efficiency of inspection when entering the low-pressure area.

[0075] like Figure 3 As shown, in some embodiments of the present invention, the step of determining the first inspection sequence of the inspection area based on the position of the selected robot includes:

[0076] Step S410, calculating the area center point of each selected inspection area based on the inspection points in each selected inspection area;

[0077] Step S420, respectively calculate the distance between the selected robot and the area center point of each selected inspection area, determine the first sequence area in the first inspection sequence, calculate the distance between the area center point of the first sequence area and the area center points of other selected inspection areas, determine the second sequence area in the first inspection sequence, and determine the order of each inspection area in the first inspection sequence one by one.

[0078] In a specific implementation process, the area center point of each selected inspection area is calculated based on the inspection points in each selected inspection area, and the coordinate average value of the inspection points in each inspection area is calculated as the area center point position of the corresponding inspection area.

[0079] In a specific implementation process, the distance between the selected robot and the center point of each selected inspection area is calculated by calculating the cosine distance.

[0080] During the specific implementation process, the distance between the selected robot and the area center point of each selected inspection area is calculated respectively, and the inspection area corresponding to the minimum distance is used as the first sequence area in the first inspection sequence; the distance between the area center point of the first sequence area and the area center points of other selected inspection areas is calculated, and the inspection area corresponding to the minimum distance is used as the second sequence area in the first inspection sequence, and the order of each inspection area in the first inspection sequence is determined one by one in the manner of determining the second sequence area.

[0081] Using the above scheme, this scheme first determines the inspection order of each inspection area one by one based on the position of the area center point of each selected inspection area, ensuring that the robot operates efficiently between inspection areas when performing inspection tasks according to the first inspection order.

[0082] In some embodiments of the present invention, the inspection points are marked in a scene map, which includes multiple driving paths. The locations where the driving paths intersect are driving intersections, and the driving paths between adjacent driving intersections are used as sub-paths. In the step of planning inspection paths for the locations of the inspection points in each inspection area, each time the selected robot drives to the driving intersection during the inspection process, a sub-path decision is made based on historical driving data and shortest path data, and a sub-path is selected based on the sub-path decision.

[0083] In the specific implementation process, when the robot drives to the driving intersection, there are often multiple sub-paths to choose from. For example, when the robot drives to an intersection, there are three sub-paths to choose from, and a sub-path decision needs to be made at this time.

[0084] In some embodiments of the present invention, each time the selected robot drives to the driving intersection during the inspection process, in the step of making a sub-path decision based on the historical driving data and the shortest path data,

[0085] The previous inspection point is used as the starting point, and the next inspection point is used as the target point;

[0086] In the specific implementation process, if the inspection order of the inspection points in the inspection task is A, B, C, D, if in the process from B to C, it drives to the driving intersection, then B is the starting point and C is the target point.

[0087] In a specific implementation process, the number of travel trajectories with the target point as the end point and the number of travel trajectories including the sub-path are obtained from the historical driving data.

[0088] In a specific implementation process, the historical driving data includes a plurality of driving trajectories, and the driving trajectory is a driving route from one inspection point to another inspection point in the historical records.

[0089] In a specific implementation process, the ratio of the number of travel trajectories including the sub-path to the number of travel trajectories with the target point as the end point is calculated, and the shortest distance from the driving intersection to the target point is calculated.

[0090] In a specific implementation process, the ratio is calculated by the number of travel trajectories including the sub-path / the number of travel trajectories with the target point as the end point.

[0091] In a specific implementation process, the first driving parameter of each sub-path is calculated based on the ratio and the shortest distance from the driving intersection to the target point, and the sub-path to be driven is determined based on the first driving parameter.

[0092] By adopting the above scheme, when the robot moves on a sub-path, it can directly drive along the sub-path. Whenever the robot drives to a driving intersection, it makes a sub-path decision and obtains the sub-path for the next driving step. This ensures that each time the inspection robot drives to a driving intersection, it can make the best decision to ensure the efficiency of the robot's operating path.

[0093] In the specific implementation process, during the inspection process, after completing an inspection point, the robot continues to drive along the sub-path where the inspection point is located, and makes a sub-path decision when it drives to a driving intersection.

[0094] In some embodiments of the present invention, in the step of calculating the first driving parameter of each sub-path based on the ratio and the shortest distance from the driving intersection to the target point, the first driving parameter is calculated based on the following formula:

[0095]

[0096] Among them, δ(a, b) represents the first travel parameter of the sub-path composed of the two driving intersections a and b, a is the starting point of the sub-path, and b is the end point of the sub-path; D(a, e) represents the distance of the shortest path from the driving intersection a to the target point e; D(b, e) represents the shortest distance from the driving intersection b to the target point e; D(a, b) represents the distance of the sub-path composed of the two driving intersections a and b; α(a, b) represents the ratio corresponding to the sub-path composed of the two intersections a and b.

[0097] By adopting the above scheme, in the process of calculating the first driving parameter, the historical utilization of the sub-path and the shortest distance of the path are fully considered. The use of historical data can better utilize historical experience, and the use of the shortest distance can take into account the maximum efficiency of the inspection, thereby ensuring the efficiency and reliability of the inspection.

[0098] In some embodiments of the present invention, in the step of calculating the first driving parameter of each sub-path based on the ratio and the shortest distance from the driving intersection to the target point, and determining the sub-path to be traveled based on the first driving parameter, the sub-path corresponding to the maximum first driving parameter is selected as the sub-path to be traveled.

[0099] In some embodiments of the present invention, in the step of performing path planning for each inspection area based on the first inspection sequence and planning an inspection path for the location of the inspection point in each inspection area, the step of the selected robot driving from one inspection area to another inspection area based on the first inspection sequence includes: taking the last completed inspection point in the previous inspection area as the starting point, and calculating the shortest distance between the last completed inspection point in the previous inspection area and each inspection point in the next inspection area; taking the inspection point with the shortest distance to the inspection points in the next inspection area as the first inspection point in the next inspection area, and taking the first inspection point in the next inspection area as the target point; in the process of driving from the starting point to the target point, the selected robot makes a sub-path decision based on the historical driving data and the shortest path data each time it drives to the driving intersection.

[0100] By adopting the above scheme, the path planning of the robot's movement between the inspection areas is carried out to ensure the efficiency of the robot's movement in the middle of the inspection area.

[0101] In the specific implementation process, in the step of performing path planning for the inspection areas one by one based on the first inspection sequence and planning the inspection path for the position of the inspection point in each inspection area, path planning is performed for the inspection areas one by one to determine the second inspection sequence of the inspection points in the inspection area to be inspected. In the step of determining the second inspection sequence, the first inspection point in the latter inspection area described in the above step is used as the first inspection point in the second inspection sequence, and the shortest distance to each inspection point in the current inspection area is calculated again. The inspection point corresponding to the smallest shortest distance is used as the next inspection point in the second inspection sequence, and each inspection point in the second inspection sequence is determined one by one.

[0102] In a specific implementation process, the shortest distance is the distance of the shortest path obtained by calculating the shortest path.

[0103] Another aspect of the present invention also relates to an inspection method, the method comprising the steps of:

[0104] Receiving instruction information from a control center, the instruction information including information of an inspection task, the information of the inspection task including a plurality of inspection points;

[0105] Based on the positions of multiple inspection points in the information of the inspection task, determine whether the current robot is the selected robot, and if the current robot is the selected robot, execute the processing of the regional path selection module, the regional path planning module and the inspection path planning module;

[0106] Determining at least one selected inspection area based on the locations of a plurality of inspection points in the information of the inspection task;

[0107] Determining a first inspection order of the inspection area based on the position of the selected robot;

[0108] Path planning is performed for each inspection area based on the first inspection sequence, and an inspection path is planned for the location of the inspection point in each inspection area.

[0109] The embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned model building method based on network architecture search. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0110] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0111] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0112] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An indoor inspection robot, characterized in that: The indoor inspection robot comprises: An instruction receiving module, used to receive instruction information from a control center, wherein the instruction information includes information about an inspection task, and the information about the inspection task includes multiple inspection points; A robot confirmation module, used to determine whether the current robot is a selected robot based on the positions of multiple inspection points in the information of the inspection task, and if the current robot is a selected robot, execute the processing of the regional path selection module, the regional path planning module and the inspection path planning module; An area path selection module, used to determine at least one selected inspection area based on the positions of multiple inspection points in the information of the inspection task; An area path planning module, used to determine a first inspection sequence of the inspection area based on the position of the selected robot; The inspection path planning module is used to plan the paths of the inspection areas one by one based on the first inspection sequence, and plan the inspection paths according to the positions of the inspection points in each inspection area.

2. The indoor inspection robot according to claim 1, characterized in that: The inspection scene includes multiple inspection waiting areas, each of which has at least one robot, and the robots in the inspection waiting areas include a standby robot. If the robot is a standby robot, the robot receives instruction information from a control center through an instruction receiving module, and in the step of determining whether the current robot is a selected robot based on the positions of multiple inspection points in the information of the inspection task, Calculating the inspection center point of the inspection task based on the two-dimensional coordinate data of the inspection point; Based on the position of the inspection center point and the positions of multiple inspection waiting areas, a selected inspection waiting area is determined, and the standby robot in the inspection waiting area is used as the selected robot.

3. The indoor inspection robot according to claim 1, characterized in that: In the step of determining at least one selected inspection area based on the positions of a plurality of inspection points in the information of the inspection task, the inspection area where the inspection points are located is taken as the selected inspection area.

4. The indoor inspection robot according to any one of claims 1 to 3, characterized in that: In the step of determining a first inspection sequence of the inspection area based on the position of the selected robot, Calculating a region center point of each selected inspection region based on the inspection points in each selected inspection region; Calculate the distance between the selected robot and the area center point of each selected inspection area respectively, determine the first sequence area in the first inspection sequence, calculate the distance between the area center point of the first sequence area and the area center points of other selected inspection areas, determine the second sequence area in the first inspection sequence, and determine the order of each inspection area in the first inspection sequence one by one.

5. The indoor inspection robot according to claim 4, characterized in that: The inspection points are all marked in the scene map, which includes multiple driving paths. The locations where the driving paths intersect are driving intersections, and the driving paths between adjacent driving intersections are used as sub-paths. In the step of planning the inspection path for the location of the inspection point in each inspection area, each time the selected robot drives to the driving intersection during the inspection process, a sub-path decision is made based on historical driving data and shortest path data, and a sub-path is selected based on the sub-path decision.

6. The indoor inspection robot according to claim 5, characterized in that: In the step of making a sub-path decision based on historical driving data and shortest path data each time the selected robot drives to the driving intersection during the inspection process, The previous inspection point is used as the starting point, and the next inspection point is used as the target point; Acquire the number of travel trajectories with the target point as the end point and the number of travel trajectories including the sub-path in the historical travel data; Calculating the ratio of the number of travel trajectories including the sub-path to the number of travel trajectories with the target point as the end point, and calculating the shortest distance from the travel intersection to the target point; A first driving parameter of each sub-path is calculated based on the ratio and the shortest distance from the driving intersection point to the target point, and a sub-path to be driven is determined based on the first driving parameter.

7. The indoor inspection robot according to claim 6, characterized in that: In the step of calculating the first driving parameter of each sub-path based on the ratio and the shortest distance from the driving intersection point to the target point, the first driving parameter is calculated based on the following formula: Among them, δ(a, b) represents the first travel parameter of the sub-path composed of the two driving intersections a and b, a is the starting point of the sub-path, and b is the end point of the sub-path; D(a, e) represents the distance of the shortest path from the driving intersection a to the target point e; D(b, e) represents the shortest distance from the driving intersection b to the target point e; D(a, b) represents the distance of the sub-path composed of the two driving intersections a and b; α(a, b) represents the ratio corresponding to the sub-path composed of the two intersections a and b.

8. The indoor inspection robot according to claim 7, characterized in that: In the step of calculating the first driving parameter of each sub-path based on the ratio and the shortest distance from the driving intersection to the target point, and determining the sub-path to be traveled based on the first driving parameter, the sub-path corresponding to the maximum first driving parameter is selected as the sub-path to be traveled.

9. The indoor inspection robot according to claim 7 or 8, characterized in that: In the step of performing path planning for each inspection area based on the first inspection sequence and planning an inspection path for the position of the inspection point in each inspection area, when the selected robot drives from one inspection area to another inspection area based on the first inspection sequence, the last completed inspection point in the previous inspection area is taken as the starting point, and the shortest distance between the last completed inspection point in the previous inspection area and each inspection point in the next inspection area is calculated, the inspection point with the shortest distance to the inspection points in the next inspection area is taken as the first inspection point in the next inspection area, and the first inspection point in the next inspection area is taken as the target point, and in the process of driving from the starting point to the target point, the selected robot makes a sub-path decision based on the historical driving data and the shortest path data each time it drives to the driving intersection.

10. A patrol inspection method, characterized in that: The steps of the method include: Receiving instruction information from a control center, the instruction information including information of an inspection task, the information of the inspection task including a plurality of inspection points; Based on the positions of multiple inspection points in the information of the inspection task, determine whether the current robot is the selected robot, and if the current robot is the selected robot, execute the processing of the regional path selection module, the regional path planning module and the inspection path planning module; Determining at least one selected inspection area based on the locations of a plurality of inspection points in the information of the inspection task; Determining a first inspection order of the inspection area based on the position of the selected robot; Path planning is performed for each inspection area based on the first inspection sequence, and an inspection path is planned for the location of the inspection point in each inspection area.

Images