CN111239768A - Method for automatically constructing map and searching inspection target by electric power inspection robot - Google Patents
Method for automatically constructing map and searching inspection target by electric power inspection robot Download PDFInfo
- Publication number
- CN111239768A CN111239768A CN202010029541.2A CN202010029541A CN111239768A CN 111239768 A CN111239768 A CN 111239768A CN 202010029541 A CN202010029541 A CN 202010029541A CN 111239768 A CN111239768 A CN 111239768A
- Authority
- CN
- China
- Prior art keywords
- robot
- map
- inspection
- point
- area
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to a method for an electric power inspection robot to independently construct a map and search an inspection target, which comprises the following steps: surveying and mapping the surrounding environment through a sensor carried by the robot to construct a map; finding out a target to be identified, and setting a routing inspection stop point; generating a routing inspection path on the constructed map according to the stop points, and generating a robot routing inspection point table; the robot patrols and examines according to the point table and photographs the patrolled screen cabinet; and analyzing the object to be identified and generating a polling report. The invention belongs to an intelligent inspection robot serving the power industry, and combines an autonomous map construction technology and a deep learning identification meter technology, so that the intelligent robot can autonomously construct a map, autonomously plan a path and autonomously detect an object, and real full-autonomous inspection is realized.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method for automatically constructing a map and searching a routing inspection target by an electric power routing inspection robot.
Background
With the progress of the technology level, the artificial intelligence robot is applied more and more in life. The robot can survey and draw its environment of locating through the software and hardware of self, constructs the map, for example through laser radar, camera and SLAM algorithm realization map construction work, and such robot has products such as indoor robot, unmanned aerial vehicle, unmanned vehicle of sweeping the floor. Certainly, the robot can also obtain models of different types of products through a deep learning algorithm, the models are used for identifying the same type of products at the later stage, manual identification is replaced, the cost is saved, and the working efficiency is improved.
In the electric power inspection industry, because the indoor place that the switch board of transformer substation installation was located is less, and the cabinet body outward appearance is similar, but inside various equipment table meters are numerous and more concentrated, generally adopt the manual work to check the record, and the later stage still need input into the computer and report and analyze, consumes a large amount of manpowers and time. For a narrow space area, due to the restriction of the physical size and the motion performance of the robot, the existing robot is difficult to adapt to the environment, so that a map cannot be completely constructed, and the task of searching a meter needing to be inspected cannot be realized.
Disclosure of Invention
The invention aims to provide a method for an electric power inspection robot to autonomously construct a map and search an inspection target, so as to solve the problems in the background technology.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a method for an electric power inspection robot to automatically construct a map and search an inspection target comprises the following steps:
s1, surveying and mapping the surrounding environment through a sensor carried by the robot to construct a map;
s2, finding out the target to be identified, and setting the inspection stop point;
s3, generating a patrol route on the constructed map according to the stop points, and generating a robot patrol point table;
s4, the robot patrols according to the point table and photographs the patrolled screen cabinet;
and S5, analyzing the object to be identified and generating a patrol inspection report.
Preferably, in step S1, the area where the robot is requested to construct the map must be a closed area, and the robot determines that the condition for completing the map construction is to obtain a closed map.
Preferably, in the step S1, the robot is limited in the number of iterations in the process of constructing the map.
Preferably, the step S1 includes the following steps:
s6: the robot uses laser radar to scan the peripheral area, the area scanned by the laser is set as a known area, the encountered obstacles are set as boundaries, the area not scanned by the laser is an unknown area, and a first map is obtained at the moment;
s7: the robot carries out system processing on the map, firstly removes interference items, then processes a known area on the map, and calculates to obtain a safe area by taking the length of the robot as a limit;
s8: finding the boundary of the unknown region and the known region;
s9: screening the selected junction;
s10: the robot starts to set a stop point for constructing a map for the next time, marks the screened target point, finds out a pixel point closest to the target point in the safety area, sets the point as the stop point, and so on;
s11: after the setting of the stop points is finished, the robot connects the stop points into a path, and the stop points are arranged in the connected path at equal intervals;
s12: and the robot scans the next map according to the path set by the robot, and iteration is carried out until the map is complete.
Preferably, the method used by the robot set path in step S11 is a dynamic planning method.
Preferably, in the step S2, the robot searches for a point closest to the mark point in the security area, and sets the point as a patrol stop point.
Preferably, the inspection point table in step S3 includes the number of the power distribution cabinets and the number of the meters included in each power distribution cabinet.
Preferably, in step S4, the robot takes multiple pictures of the power distribution cabinet, and each picture is one third of the previous picture.
Preferably, the robot analyzes the obtained image after shooting, and removes the repeated meter.
Preferably, in step S5, the robot performs deep learning on the meters to be identified, identifies the states of the meters and the names of the meters, and generates the inspection report.
Compared with the prior art, the invention has the beneficial effects that: the invention belongs to an intelligent inspection robot serving the power industry, and combines an autonomous map construction technology and a deep learning identification meter technology, so that the intelligent robot can autonomously construct a map, autonomously plan a path and autonomously detect an object, and real full-autonomous inspection is realized.
Drawings
FIG. 1 is a schematic flow chart of a method for an electric power inspection robot to autonomously construct a map and search an inspection target according to the present invention;
FIG. 2 is a schematic diagram of a map construction process in the method for the power inspection robot to autonomously construct a map and search an inspection target according to the present invention;
Detailed Description
The technical solution of the present invention is further described in detail with reference to the accompanying drawings and examples.
As shown in fig. 1 and 2, a method for an electric inspection robot to autonomously construct a map and search an inspection target includes the following steps:
and S1, surveying and mapping the surrounding environment through the sensors of the robot, and constructing a map.
The first task of the robot in an unfamiliar environment is to construct a map, and the robot knows the environment in which the robot faces and the safe area which the robot can reach. The invention requires that the area of the robot for constructing the map must be a closed area, and the condition that the robot judges the end of constructing the map is to obtain a closed map.
In order to prevent the robot from being placed in a scene with an overlarge area or an unclosed area, the machine construction map has the limitation of iteration times, if the iteration times of the robot construction map exceed a threshold value, an unknown area needs to be processed at the moment, and the robot stops constructing the map.
The step S1 of the robot automatically constructing the map comprises the following steps:
when the power inspection robot is used, the robot is firstly placed in a space where a map is to be constructed, the space is necessarily an enclosed area, and the robot is parallel to the wall surface.
S6: the robot uses the laser radar to scan the peripheral area, sets the area scanned by the laser to be a known area, sets the encountered obstacles to be a boundary, and sets the area not scanned by the laser to be an unknown area, thereby obtaining a first map.
In order to not affect the map frame, the robot needs to walk forward by 50cm and then return to the original point, and after the robot rotates 360 degrees in situ, a program is started to start laser scanning to obtain a first map.
S7: after the map is obtained, in order to enable the robot to build the map completely and quickly, the robot performs system processing on the map, and firstly removes interference items, such as denoising and thinning the map. Then, the known area on the map is processed, the length of the robot is taken as the limit, and a safety area is obtained through calculation, so that the robot can freely move in the safety area.
The robot carries out system processing on the map, and specifically comprises the following steps:
firstly, the robot running program selects a gray boundary (gray is an unknown area, white is a known area, and black is an obstacle), iteration is carried out, and if the iteration number exceeds the set maximum iteration number, the robot stops scanning the map if the white boundary exists on the map. In this step, the number of iterations is set to prevent the scene scanned by the robot from being an unclosed region.
Secondly, after the map is scanned, a program needs to be started to build the map of the obtained data, and the built map needs to be operated as follows:
a. removing noise points, and taking isolated black points on the map as noise points;
b. erasing, namely erasing black points which are not in contact with the white area;
c. setting a safe area, and processing a gray point which is connected with the white area as a dangerous area to protect the safety of the user;
d. the area where the robot is marked is a main area, two white areas are possibly scanned from the map, and the other white area is possibly scanned by laser through a door (the width of the door may be smaller than that of the robot), but the width of the robot limits the walking path of the robot, and the robot cannot penetrate through the door.
S8: finding out the boundary between the unknown area and the known area, judging the distance between the boundary and the safe area, if the distance is within the length range of the laser of the robot, continuing the processing, otherwise, temporarily not processing, and waiting for the next processing.
S9: and screening the selected junction, wherein the scanned map is composed of pixel points, so that the center of the junction, namely the pixel points around the target point, is judged. And as long as the iteration times of the robot for constructing the map do not exceed the set threshold value, the robot continues to process the screening work. In this step, lime boundaries are extracted, and the center of each boundary is found out for screening. Some boundaries are short, and the robot scans the scene by using laser, and the distance of the laser is long, so that it is not necessary for the robot to specially plan the path to run through.
S10: after the current map is processed, the robot starts to set a stop point for constructing the map next time, the screened target point is marked, and the stop point is required to be in a safe area. And finding out the pixel point closest to the target point in the safety area, setting the pixel point as a stop point, and so on.
S11: after the setting of the stop points is completed, the robot connects the stop points into a path, and the stop points are set at equal intervals in the connected path. The method adopted by the path set by the robot is a dynamic planning method, and stopping points are set at equal intervals, so that the marking is convenient, and the emergency stop is convenient when an emergency situation occurs.
S12: and the robot scans the next map according to the path set by the robot, and iteration is carried out until the map is complete.
At this time, the position where the robot is located at the end of robot mapping is marked. The path is dynamically planned for later iterations.
Through the operation, the power inspection robot automatically constructs a map and finishes the map, and then continues to finish the task of searching the target of the inspection table:
and S2, finding out the target to be identified and setting the inspection stop point.
After the map scanning is finished, the robot searches for an object in the scanned map and sets a routing inspection stop point. The main searched objects of the invention are power distribution cabinets, the robot has been deeply learned, when the laser scans the power distribution cabinets, the robot marks the centers of the power distribution cabinets, and points nearest to the marked points are searched in a safety area and set as routing inspection stop points.
And S3, generating an inspection path on the constructed map according to the stop points, and generating an inspection point table of the robot.
And after the routing inspection stop points are determined, connecting the stop points into a path according to a dynamic path planning mode. When the map is scanned, the robot counts the searched power distribution cabinets to generate a point table, the point table comprises the number of the power distribution cabinets and the number of meters in each power distribution cabinet, and the specific numerical values are conveniently filled in the later period.
And S4, the robot patrols according to the point table and takes a picture of the patrolled screen cabinet.
The robot can carry out inspection after the path is planned, and the robot mainly inspects the meter state in the power distribution cabinet. So the robot need shoot the switch board of patrolling and examining to need discernment table meter on the switch board, in order to prevent to shoot the table meter and have the omission, the robot shoots the switch board many times, can set up five times and shoot, shoot at every turn all with the partial coincidence third of shooing last time. And after shooting, analyzing the obtained image and removing the repeated meter. Through the operation, the situation that the meter obtained by photographing is incomplete can be avoided.
And S5, analyzing the object to be identified and generating a patrol inspection report.
And finally, the robot carries out deep learning on the meters needing to be identified, identifies the states of the meters and the names of the meters and generates an inspection report.
The deep learning program function of the robot is to obtain a deep learning model by training collected picture samples, and then to identify a newly collected picture by using the model.
In this embodiment, a deep learning algorithm adopted by the power inspection robot performs feature extraction on a picture by using a convolutional neural network, and then performs classification and regression on a feature map by using a multilayer perceptron, wherein the classification can obtain a specific identity of a target, for example, what picture is specific, and the regression can obtain a position of the target in the picture.
In this embodiment, after the robot backend system obtains the object information identified by the image system, the information is organized into a table, that is, a point table, and each object is represented as a patrol point in the point table.
In this embodiment, the program adopted by the robot to autonomously construct the map by photographing includes an image processing algorithm, and the image processing algorithm is an actual algorithm program, that is, a pointer region is obtained after preprocessing and transforming a picture, and the position of the pointer in the dial is located.
The invention combines the autonomous map construction technology and the deep learning identification meter technology, so that the intelligent robot can autonomously construct a map, autonomously plan a path and autonomously detect an object, thereby realizing real fully autonomous inspection.
The invention belongs to an intelligent inspection robot serving the power industry, replaces manual identification, saves cost, manpower and working time, improves working efficiency and realizes real intelligence. The robot can realize the autonomous map construction and deep learning identification meter, and also can autonomously set a stop point, plan a path, calibrate, match a model, patrol and generate a point meter.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for automatically constructing a map and searching for a patrol target by a power patrol robot is characterized by comprising the following steps:
s1, surveying and mapping the surrounding environment through a sensor carried by the robot to construct a map;
s2, finding out the target to be identified, and setting the inspection stop point;
s3, generating a patrol route on the constructed map according to the stop points, and generating a robot patrol point table;
s4, the robot patrols according to the point table and photographs the patrolled screen cabinet;
and S5, analyzing the object to be identified and generating a patrol inspection report.
2. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 1, wherein the method comprises the following steps: in step S1, the area where the robot is required to construct the map must be a closed area, and the robot determines that the condition for completing the map construction is to obtain a closed map.
3. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 2, wherein the method comprises the following steps: in the step S1, the robot is limited in the number of iterations in the process of constructing the map.
4. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 1, wherein the step S1 comprises the following steps:
s6: the robot uses laser radar to scan the peripheral area, the area scanned by the laser is set as a known area, the encountered obstacles are set as boundaries, the area not scanned by the laser is an unknown area, and a first map is obtained at the moment;
s7: the robot carries out system processing on the map, firstly removes interference items, then processes a known area on the map, and calculates to obtain a safe area by taking the length of the robot as a limit;
s8: finding the boundary of the unknown region and the known region;
s9: screening the selected junction;
s10: the robot starts to set a stop point for constructing a map for the next time, marks the screened target point, finds out a pixel point closest to the target point in the safety area, sets the point as the stop point, and so on;
s11: after the setting of the stop points is finished, the robot connects the stop points into a path, and the stop points are arranged in the connected path at equal intervals;
s12: and the robot scans the next map according to the path set by the robot, and iteration is carried out until the map is complete.
5. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 4, wherein the method comprises the following steps: the method adopted by the path set by the robot in the step S11 is a dynamic planning method.
6. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 1, wherein the method comprises the following steps: in the step S2, the robot searches for a point closest to the mark point in the security area and sets the point as a patrol stop point.
7. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 1, wherein the method comprises the following steps: the inspection point table in step S3 includes the number of the power distribution cabinets and the number of meters included in each power distribution cabinet.
8. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 1, wherein the method comprises the following steps: in the step S4, the robot takes pictures of the power distribution cabinet for multiple times, and each picture is one third of the picture taken last time.
9. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 8, wherein the method comprises the following steps: and after the robot shoots, analyzing the obtained image and removing the repeated meter.
10. The method for the power inspection robot to autonomously construct the map and search the inspection target according to claim 1, wherein the method comprises the following steps: in the step S5, the robot performs deep learning on the meters to be identified, identifies the states of the meters and the names of the meters, and generates the inspection report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010029541.2A CN111239768A (en) | 2020-01-13 | 2020-01-13 | Method for automatically constructing map and searching inspection target by electric power inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010029541.2A CN111239768A (en) | 2020-01-13 | 2020-01-13 | Method for automatically constructing map and searching inspection target by electric power inspection robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111239768A true CN111239768A (en) | 2020-06-05 |
Family
ID=70868374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010029541.2A Pending CN111239768A (en) | 2020-01-13 | 2020-01-13 | Method for automatically constructing map and searching inspection target by electric power inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111239768A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111752305A (en) * | 2020-06-30 | 2020-10-09 | 国电南瑞科技股份有限公司 | Mountain land type distributed photovoltaic power station unmanned aerial vehicle inspection obstacle avoidance method and system |
| CN112332541A (en) * | 2020-10-29 | 2021-02-05 | 国网山西省电力公司检修分公司 | Monitoring system and method for transformer substation |
| CN112461227A (en) * | 2020-10-22 | 2021-03-09 | 新兴际华集团有限公司 | Intelligent autonomous navigation method for polling wheel type chassis robot |
| CN112506178A (en) * | 2020-08-25 | 2021-03-16 | 深圳市银星智能科技股份有限公司 | Robot control method, device, terminal and medium |
| CN113311861A (en) * | 2021-05-14 | 2021-08-27 | 国家电投集团青海光伏产业创新中心有限公司 | Automatic detection method and system for photovoltaic module subfissure characteristics |
| WO2022110928A1 (en) * | 2020-11-24 | 2022-06-02 | 追觅创新科技(苏州)有限公司 | Robot mapping method, robot, storage medium and electronic apparatus |
| CN115146879A (en) * | 2022-09-05 | 2022-10-04 | 国网山西省电力公司超高压变电分公司 | Optimization method for safety measure arrangement path of transformer substation relay protection room |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN107966150A (en) * | 2017-11-21 | 2018-04-27 | 武汉中元华电软件有限公司 | Substation's Work robot path planning and navigation locating method based on crossing point and section |
| CN108227753A (en) * | 2017-12-08 | 2018-06-29 | 国网浙江省电力公司温州供电公司 | For the not parking method for inspecting of power equipment |
| JP2018112830A (en) * | 2017-01-10 | 2018-07-19 | 株式会社東芝 | Self position estimation device and self position estimation method |
| CN109141430A (en) * | 2018-09-04 | 2019-01-04 | 南京理工大学 | Electric inspection process robot path planning method based on simulated annealing ant group algorithm |
| CN110026978A (en) * | 2019-02-28 | 2019-07-19 | 上海宇航***工程研究所 | A kind of control system and working method of electric inspection process robot |
| CN110531760A (en) * | 2019-08-16 | 2019-12-03 | 广东工业大学 | It is explored based on the boundary that curve matching and target vertex neighborhood are planned and independently builds drawing method |
-
2020
- 2020-01-13 CN CN202010029541.2A patent/CN111239768A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018112830A (en) * | 2017-01-10 | 2018-07-19 | 株式会社東芝 | Self position estimation device and self position estimation method |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN107966150A (en) * | 2017-11-21 | 2018-04-27 | 武汉中元华电软件有限公司 | Substation's Work robot path planning and navigation locating method based on crossing point and section |
| CN108227753A (en) * | 2017-12-08 | 2018-06-29 | 国网浙江省电力公司温州供电公司 | For the not parking method for inspecting of power equipment |
| CN109141430A (en) * | 2018-09-04 | 2019-01-04 | 南京理工大学 | Electric inspection process robot path planning method based on simulated annealing ant group algorithm |
| CN110026978A (en) * | 2019-02-28 | 2019-07-19 | 上海宇航***工程研究所 | A kind of control system and working method of electric inspection process robot |
| CN110531760A (en) * | 2019-08-16 | 2019-12-03 | 广东工业大学 | It is explored based on the boundary that curve matching and target vertex neighborhood are planned and independently builds drawing method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111752305A (en) * | 2020-06-30 | 2020-10-09 | 国电南瑞科技股份有限公司 | Mountain land type distributed photovoltaic power station unmanned aerial vehicle inspection obstacle avoidance method and system |
| CN112506178A (en) * | 2020-08-25 | 2021-03-16 | 深圳市银星智能科技股份有限公司 | Robot control method, device, terminal and medium |
| CN112506178B (en) * | 2020-08-25 | 2023-02-28 | 深圳银星智能集团股份有限公司 | Robot control method, device, terminal and medium |
| CN112461227A (en) * | 2020-10-22 | 2021-03-09 | 新兴际华集团有限公司 | Intelligent autonomous navigation method for polling wheel type chassis robot |
| CN112461227B (en) * | 2020-10-22 | 2023-07-21 | 新兴际华集团有限公司 | Wheel type chassis robot inspection intelligent autonomous navigation method |
| CN112332541A (en) * | 2020-10-29 | 2021-02-05 | 国网山西省电力公司检修分公司 | Monitoring system and method for transformer substation |
| WO2022110928A1 (en) * | 2020-11-24 | 2022-06-02 | 追觅创新科技(苏州)有限公司 | Robot mapping method, robot, storage medium and electronic apparatus |
| CN113311861A (en) * | 2021-05-14 | 2021-08-27 | 国家电投集团青海光伏产业创新中心有限公司 | Automatic detection method and system for photovoltaic module subfissure characteristics |
| CN115146879A (en) * | 2022-09-05 | 2022-10-04 | 国网山西省电力公司超高压变电分公司 | Optimization method for safety measure arrangement path of transformer substation relay protection room |
| CN115146879B (en) * | 2022-09-05 | 2022-12-06 | 国网山西省电力公司超高压变电分公司 | Optimization method for safety measure arrangement path of relay protection room of transformer substation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111239768A (en) | Method for automatically constructing map and searching inspection target by electric power inspection robot | |
| Borrmann et al. | A mobile robot based system for fully automated thermal 3D mapping | |
| CN109977813B (en) | Inspection robot target positioning method based on deep learning framework | |
| CN108297115B (en) | Autonomous repositioning method for robot | |
| US9761015B2 (en) | Method for determining dimensions in an indoor scene from a single depth image | |
| CN110928301A (en) | Method, device and medium for detecting tiny obstacles | |
| Holz et al. | Towards semantic scene analysis with time-of-flight cameras | |
| CN111709988B (en) | Method and device for determining characteristic information of object, electronic equipment and storage medium | |
| Lamon et al. | Environmental modeling with fingerprint sequences for topological global localization | |
| CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
| CN113936198A (en) | Low-beam laser radar and camera fusion method, storage medium and device | |
| CN112001298B (en) | Pedestrian detection method, device, electronic equipment and storage medium | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| Kim et al. | Robotic sensing and object recognition from thermal-mapped point clouds | |
| Yuan et al. | An automated 3D scanning algorithm using depth cameras for door detection | |
| Alidoost et al. | Y-shaped convolutional neural network for 3d roof elements extraction to reconstruct building models from a single aerial image | |
| CN115546116A (en) | Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass | |
| CN113496163B (en) | Obstacle recognition method and device | |
| Nagarajan et al. | Obstacle detection and avoidance for mobile robots using monocular vision | |
| Li et al. | Feature point extraction and tracking based on a local adaptive threshold | |
| CN116700228A (en) | Robot path planning method, electronic device and readable storage medium | |
| Kong et al. | Toward the automatic detection of access holes in disaster rubble | |
| Dong et al. | Semantic lidar odometry and mapping for mobile robots using rangeNet++ | |
| Rachman et al. | End-to-End Lidar-Camera Self-Calibration for Autonomous Vehicles | |
| CN111708046A (en) | Method and device for processing plane data of obstacle, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |
|
| RJ01 | Rejection of invention patent application after publication |