CN115903797A - Autonomous routing inspection method for multi-floor modeling of transformer substation - Google Patents
Autonomous routing inspection method for multi-floor modeling of transformer substation Download PDFInfo
- Publication number
- CN115903797A CN115903797A CN202211399661.7A CN202211399661A CN115903797A CN 115903797 A CN115903797 A CN 115903797A CN 202211399661 A CN202211399661 A CN 202211399661A CN 115903797 A CN115903797 A CN 115903797A
- Authority
- CN
- China
- Prior art keywords
- quadruped robot
- transformer substation
- grid
- coordinate system
- map
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000006243 chemical reaction Methods 0.000 claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008447 perception Effects 0.000 abstract 2
- 238000005516 engineering process Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000014616 translation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A method for automatically inspecting multi-floor modeling of a transformer substation adopts a four-foot robot to inspect the transformer substation with multiple floors, and comprises four calculation processes of laser radar and depth camera coordinate system conversion, multi-floor modeling of the transformer substation, path planning and autonomous navigation, obstacle avoidance and map planning updating, acquired data are stored in control system software of the four-foot robot, and the control system controls inspection work of the four-foot robot by combining the acquired data. The invention can make the software of the control system of the quadruped robot more clearly position the quadruped robot in the inspection process and identify the environment, the control software combines each sensor to model the multi-floor of the transformer substation, and can complete the perception of the surrounding environment according to the perception system of the control software, obtain the accurate positioning of the quadruped robot in the environment, plan out an optimal or near optimal collision-free path from the current pose to the target inspection pose, and control the quadruped robot to safely inspect according to the planned path, thereby improving the inspection effect.
Description
Technical Field
The invention relates to the technical field of inspection of transformer substation application, in particular to an autonomous inspection method for multi-floor modeling of a transformer substation.
Background
In the electric power field, in order to guarantee the normal operation of power equipment and the like, areas such as transformer substations and the like need to be patrolled and examined to find hidden dangers and timely handle the hidden dangers, and the probability of power supply accidents is reduced. At present, the inspection of a transformer substation in a power system still mainly adopts manual inspection, and due to high inspection working strength and severe operating environment, the working efficiency is insufficient, and certain potential safety hazards also exist. Moreover, different routing inspection personnel are influenced by objective factors such as own skills, responsibility and the like, different problems can be found in the routing inspection process, and the routing inspection result is lack of objectivity.
With the progress of science and technology, equipment inspection technologies such as replacing manual autonomous mobile robots are also greatly developed (an unmanned aerial vehicle inspection mode is limited due to the fact that collision damage of the unmanned aerial vehicle and equipment is easy to happen due to the influence of indoor equipment of a transformer substation), the existing inspection robots (the autonomous mobile robots) are mainly divided into crawler-type robots and track-type robots, the crawler-type robots are limited to be used in flat terrain and cannot go up and down stairs, and therefore inspection of multiple floors of the transformer substation cannot be conducted; the rail-mounted robot has the disadvantages of large workload and capital investment in rail construction and installation and limited inspection range, so that the application limitation exists. The quadruped robot can climb stairs and the like to patrol a target area, so that the quadruped robot is applied to transformer substation patrol. In fact, any robot (including a quadruped robot) inspects areas such as a transformer substation, particularly multi-floor inspection of the transformer substation, and control software thereof needs to be combined with various sensors to overcome indoor complex environments, model the software per se and control the robot to inspect and inspect stairs; the premise of autonomous walking of the autonomous mobile robot in the environment is that the self control software senses the environment through the sensor and further controls the patrol route mode of the autonomous mobile robot (namely the patrol route mode of the autonomous mobile robot is controlled by the corresponding navigation technology). In the prior art, the navigation technology adopted by the quadruped robot mainly comprises visual navigation, sensor navigation, visual and inertial navigation. The visual navigation calculates navigation parameters by a multi-view geometric principle by perceiving the environmental image characteristics, and although the information is rich and the utilization rate is high, the defects of large calculated amount and influence of illumination exist; the vision and inertial navigation acquire data through an inertial sensor, the robot calculates attitude angles and displacements in real time, the initial precision is high and easy to fuse, but the precision is reduced along with accumulated errors; the sensor navigation refers to that passive sensors such as infrared sensors, ultrasonic sensors, laser sensors and the like are used, data are generated after the emitted light of the passive sensors acts with the environment, the accuracy is high, and the passive sensors are easily influenced by the surrounding environment. In summary, it is necessary to provide a method for inspecting a multi-floor substation based on a quadruped robot, which can overcome the disadvantages of the navigation technologies.
Disclosure of Invention
In order to overcome the defects of the prior quadruped robot applied to the inspection of the transformer substation with multiple floors, due to the limited technical limit, the invention provides the autonomous modeling method for the transformer substation for the multiple floors, which can enable the control software of the quadruped robot to position the quadruped robot and identify the environment more clearly under the combined action of the related calculation processes, can combine each sensor to effectively model the multiple floors of the transformer substation, can complete the sensing of the surrounding environment according to the sensing system of the control software, obtain the accurate positioning of the quadruped robot in the environment, plan an optimal or approximately optimal collision-free path from the current position to the target inspection position, and control the quadruped robot to safely inspect according to the planned path, thereby improving the inspection effect.
The technical scheme adopted by the invention for solving the technical problem is as follows:
a multi-floor modeling autonomous inspection method for a transformer substation adopts a quadruped robot to inspect the transformer substation with multiple floors, and is characterized by comprising four calculation processes of laser radar and depth camera coordinate system conversion, transformer substation multi-floor modeling, path planning and autonomous navigation, obstacle avoidance and map planning updating, wherein data obtained by the four processes are stored in control system software of the quadruped robot, and the control system controls the inspection work of the quadruped robot by combining the data obtained by the four processes; the coordinate systems of the laser radar and the depth camera are converted, and the data coordinate systems obtained by the laser radar and the depth camera carried by the quadruped robot are converted to obtain the information of the same target object under different sensors, so that the positioning of the quadruped robot and the identification of the environment are clearer; data obtained by the conversion of the coordinate systems of the laser radar and the depth camera are used for modeling multiple floors of the transformer substation; the path planning and autonomous navigation can control the quadruped robot to combine the laser radar and the depth camera coordinate system for conversion to establish a well-established grid map, and autonomously plan a path going to a target inspection place; the obstacle avoidance and map planning updating and control quadruped robot updates the surrounding grid map in real time in the autonomous inspection process so as to realize obstacle avoidance, and the specific updating content of the grid map is mainly some moving objects; the method comprises the following steps of setting a target object P detected by a coordinate system, calculating the coordinate of a point P under the camera coordinate system, calculating the conversion relation between the point P and the camera pixel coordinate system, calculating the conversion relation between the projection point coordinate of the point P under the image plane coordinate system and the laser radar coordinate system, and calculating the relation between the coordinate of the point P and the polar coordinate.
Further, the coordinate formula of the calculation P point in the camera coordinate system is as follows,
the formula for calculating the conversion relation between the P point and the camera pixel coordinate system is as follows>
The formula for calculating the conversion relation between the projection point coordinate of the P point in the image plane coordinate system and the laser radar coordinate system is as follows, z L ＝rcosα，x L ＝rsinα、
Furthermore, the multi-floor modeling of the transformer substation adopts a grid map model, the quadruped robot graph occupies the grid map, the environment where the quadruped robot graph is located is divided into a plurality of grid units with equal scales, the external environment corresponding to the quadruped robot graph is described by means of the grid units in combination with data obtained by converting a laser radar and a depth camera coordinate system, and meanwhile whether the grid has obstacles or not is recorded, namely the grid unit state is occupied, idle or unavailable.
Furthermore, in the multi-floor modeling of the transformer substation, in the occupied grid map, the probability value 0 is used for representing the grid idle state, 1 is used for representing that the grid is occupied at the moment, and 0.5 is used for representing that the state cannot be acquired.
Furthermore, in the path planning and autonomous navigation, the control system firstly plans a global path for the quadruped robot in real navigation, the quadruped robot detects a local path in real motion according to a sensor of the quadruped robot in real time, when no obstacle exists on the path, the quadruped robot continues to move forward according to the original path, when the obstacle is detected, whether the global path and the obstacle interfere with each other is judged, if the obstacle does not interfere with each other, the quadruped robot normally moves forward, if the obstacle does interfere with each other, the current speed and the current pose are adjusted through the local path planning, and meanwhile, the global path is continuously updated.
Furthermore, in the obstacle avoidance and map planning updating, the global map can be incrementally updated according to the pose of the robot and a local map constructed by a laser radar scanning data structure; by the formula
Whether the grid is occupied by the obstacle or not is judged, the situation that the grid in the global map is occupied by the obstacle is further judged, and information in the global map can be updated in real time.
The invention has the beneficial effects that: the invention is based on the four-footed robot as the substation polling work with floors, the data obtained by four calculation processes of laser radar and depth camera coordinate system conversion, substation multi-floor modeling, path planning and autonomous navigation, obstacle avoidance and map planning updating can enable the control system software of the four-footed robot to more clearly identify the location and environment in the polling process of the four-footed robot, the control software can combine each sensor to model the multiple floors of the substation, can complete the sensing of the surrounding environment according to the sensing system of the control software, obtain the accurate location of the four-footed robot in the environment, plan an optimal or approximately optimal collision-free path from the current position to the target polling position, and control the four-footed robot to safely poll according to the planned path, thereby improving the polling effect, reducing the probability of damage of the four-footed robot when colliding with other objects and playing a favorable promoting role for the intelligent polling of the substation. In conclusion, the invention has good application prospect.
Drawings
FIG. 1 is a schematic diagram of the laser radar and depth camera coordinate system transformation of the present invention.
Fig. 2 is a flow chart of the path planning and autonomous navigation of the present invention.
Fig. 3 is a flow chart of obstacle avoidance and map planning update according to the present invention.
Detailed Description
As shown in fig. 1, 2 and 3, an autonomous inspection method for modeling multiple floors of a transformer substation is characterized in that a quadruped robot is adopted to inspect the transformer substation with multiple floors, the method comprises four calculation processes of coordinate system conversion of a laser radar and a depth camera, modeling of multiple floors of the transformer substation, path planning and autonomous navigation, obstacle avoidance and map planning and updating, data obtained by the four processes are stored in control system software of the quadruped robot, and the control system controls inspection work of the quadruped robot by combining the data obtained by the four processes; the coordinate system of the laser radar and the depth camera is converted, and the coordinate system of data obtained by the laser radar and the depth camera carried by the quadruped robot is converted to obtain information of the same target object under different sensors, so that the positioning of the quadruped robot and the identification of the environment are clearer; the data obtained by the conversion of the laser radar and the depth camera coordinate system is used for modeling multiple floors of the transformer substation; the path planning and autonomous navigation can control the quadruped robot to combine the laser radar and the depth camera coordinate system for conversion to establish a well-established grid map, and autonomously plan a path going to a target inspection place; the obstacle avoidance and map planning updating and control quadruped robot updates the surrounding grid map in real time in the autonomous inspection process so as to realize obstacle avoidance, and the specific updating content of the grid map is mainly some moving objects; the method comprises the following steps of setting a target object P detected by a coordinate system, calculating the coordinate of a point P under the camera coordinate system, calculating the conversion relation between the point P and the camera pixel coordinate system, calculating the conversion relation between the projection point coordinate of the point P under the image plane coordinate system and the laser radar coordinate system, and calculating the relation between the coordinate of the point P and the polar coordinate.
In the coordinate system conversion of the laser radar and the depth camera, a point P in a space (the space refers to the surrounding environment where the quadruped robot is located) is assumed to represent a target object (namely, an object in a transformer substation) detected by the laser radar and the depth camera in the inspection of the quadruped robot, and the point is in a coordinate system O of the control system software of the laser radar quadruped robot L -X L -Y L -Z L The coordinate system of (x) below L ,y L ,z L ) Specifically, the data information acquired by the lidar sensor is the distance and angle of the target. Point-in-depth camera coordinate system O K -X K -Y K -Z K The coordinates of (x) below K ,y K ,z K ) P point in the image plane coordinate system O P -X P -Y P The projected point P' coordinates below are (u, v); specifically, the data acquired by the depth camera is information on the coordinate position of the projected point of the target P and the depth thereof (depth data of the target P with respect to the quadruped robot acquired by the depth camera). Target point P in laser radar coordinate system O L -X L -Y L -Z L The coordinates of (x) below L ,y L ,z L ) Obtaining the P point in a camera coordinate system O according to the geometric position relation between a depth camera coordinate system and a laser radar coordinate system K -X K -Y K -Z K Coordinates of lower (x) K ,y K ,z K ) As shown in the following formula,
wherein R represents a rotation matrix and T represents a vector of translations; the coordinate of the P' point on the pixel plane coordinate system o-u-v is [ u, v] T The conversion relationship between the P' point and the pixel coordinate system is expressed as follows>
The projected point P' coordinates (u, v) and the laser radar coordinates (x) of the point P in the image plane coordinate system can be obtained by combining the two formulas L ,y L ,z L ) Is expressed as follows>
The scanning plane of the laser radar is a coordinate system O L XL-ZL, the center of the lidar being located at an origin OL, r representing the distance of OL to the target, and α representing the angle to the ZL axis, so that the coordinates (xL, yL, zL) of point P and (r, α) in polar coordinates are related as follows, z L ＝rcosα，x L = rsin α, the distance between the plane OL-XL-ZL and the plane OK-XK-ZK being h, the following formula can be found, = live->
For a target point P in space, the depth camera can get ZK and (u, v), and the lidar can acquire (r, α). The step combines and uses an open source calibration function packet in the quadruped robot control system software, can acquire needed pixel points as many as possible, obtains a matrix R and a vector T by a least square method in the data formula of the camera parameter and the laser radar measurement, and finally completes the calibration of external parameters (in order to unify the information of the depth camera and the laser radar under different sensors for the same target object, the positioning of the quadruped robot and the identification of the environment are clearer). The inventionA grid map model is adopted for multi-floor modeling of a transformer substation, a grid map is occupied, the environment where the quadruped robot is located is divided into a plurality of grid units with equal scales, the external environment corresponding to the quadruped robot is described by means of the grid units, and whether obstacles exist in the grid is recorded, namely the state of the grid unit is occupied, idle or unavailable. In the occupied grid map, the probability value 0 represents the grid idle state, 1 represents that the grid is occupied at this time, and 0.5 represents that the state cannot be acquired.
As shown in fig. 2, in route planning and autonomous navigation, a navigation system for moving a four-footed robot is designed based on a move _ base navigation function package in a four-footed robot control system. In order to ensure that the quadruped robot completes autonomous navigation in an unfamiliar environment, a global map is firstly constructed, and then a global path is planned based on a specific global path planning algorithm. In the follow-up routing inspection real navigation of the quadruped robot, a global path is planned firstly, the quadruped robot detects a local path in real time according to a sensor of the quadruped robot in the real motion process, when no obstacle exists on the path, the quadruped robot continues to move forward according to the original path, when the obstacle is detected, whether the global path and the obstacle interfere with each other or not is judged, if the obstacle does not interfere with each other, the quadruped robot normally moves forward, if the obstacle interferes with each other, the current speed and the pose are adjusted through the planning of the local path, and meanwhile, the global path is continuously updated.
As shown in FIG. 3, in the obstacle avoidance and map planning updating, the poses s1: t-1 of the quadruped robot from all the time 1 to the time t-1 are set first, and after the pose st of the quadruped robot at the time mt-1 and the time t is obtained according to the particle filter estimation under the determined condition, the global map can be updated incrementally according to the poses of the robot and the local map constructed by the laser radar scanning data structure. Specifically, according to the determined pose of the robot and the known scanning range of the laser radar, because the multi-layer scale of the transformer substation is very large, the grid state in the scanning coverage range of the laser radar is updated, the updating speed of the global map can be greatly improved, and the efficiency of the whole SLAM algorithm (the algorithm is adopted in all four steps of the invention) is improved. By the formula
Determining whether the grid is occupied by an obstacle, n k Indicating that at all times the grid k lidar is directly illuminated (the laser illuminates obstacles, etc. and produces reflections), n k,beam Indicating that at all times grid k is traversed directly by the laser beam (the laser illumination does not strike an obstacle to cause reflection) if p k Above a specified threshold, grid k is considered occupied by an obstacle. The situation that the grid in the global map is occupied by the obstacle is judged through the formula, the information in the global map can be updated in real time, and the method has important significance for representing the dynamic environment where the quadruped robot is located. For example, in the global map, some obstacles may be removed from the original map, when the robot passes through these places, the values of nk and beam become larger as the scanning times of the laser radar in the current area increase, and n is larger k Will remain unchanged. When p is k When the grid occupied by the obstacle is smaller than the set threshold value, the grid occupied by the obstacle can be considered to be changed into the non-obstacle grid again.
As shown in the figures 1, 2 and 3, the invention is based on the fact that the quadruped robot is used as a transformer substation inspection working carrier with floors, data obtained by four calculation processes of coordinate system conversion of a laser radar and a depth camera, multi-floor modeling of the transformer substation, path planning and autonomous navigation, obstacle avoidance and map planning are updated, positioning and environment identification of the quadruped robot in inspection can be clearer by control system software of the quadruped robot, the control software can be combined with modeling of various sensors on multiple floors of the transformer substation, sensing of the surrounding environment can be completed according to a sensing system of the control software, accurate positioning of the quadruped robot in the environment is obtained, an optimal or approximately optimal collision-free path from the current position to the target position is planned, and the quadruped robot is controlled to safely inspect according to the planned path, so that the inspection effect is improved, the damage probability of the quadruped robot when colliding with other objects is reduced, and a beneficial promotion effect is achieved for intelligent inspection of the transformer substation.
It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should take the description as a whole, and the technical solutions in the embodiments may be appropriately combined to form other embodiments understood by those skilled in the art.
Claims (6)
1. A multi-floor modeling autonomous inspection method for a transformer substation adopts a quadruped robot to inspect the transformer substation with multiple floors, and is characterized by comprising four calculation processes of coordinate system conversion of a laser radar and a depth camera, multi-floor modeling of the transformer substation, path planning and autonomous navigation, obstacle avoidance and map planning updating, wherein data obtained by the four processes are stored in control system software of the quadruped robot, and the control system controls inspection work of the quadruped robot by combining the data obtained by the four processes; the coordinate systems of the laser radar and the depth camera are converted, and the data coordinate systems obtained by the laser radar and the depth camera carried by the quadruped robot are converted to obtain the information of the same target object under different sensors, so that the positioning of the quadruped robot and the identification of the environment are clearer; data obtained by the conversion of the coordinate systems of the laser radar and the depth camera are used for modeling multiple floors of the transformer substation; the path planning and autonomous navigation can control the quadruped robot to combine the laser radar and the depth camera coordinate system for conversion to establish a well-established grid map, and autonomously plan a path going to a target inspection place; the obstacle avoidance and map planning updating and control quadruped robot updates the surrounding grid map in real time in the autonomous inspection process so as to realize obstacle avoidance, and the specific updating content of the grid map is mainly some moving objects; the method comprises the following steps of setting a target object P detected by a coordinate system, calculating the coordinate of a point P under the camera coordinate system, calculating the conversion relation between the point P and the camera pixel coordinate system, calculating the conversion relation between the projection point coordinate of the point P under the image plane coordinate system and the laser radar coordinate system, and calculating the relation between the coordinate of the point P and the polar coordinate.
2. The autonomous routing inspection method for the modeling of the multiple floors of the transformer substation according to claim 1, wherein the coordinate formula of the P point under the camera coordinate system is calculated as follows,
the formula for calculating the conversion relation between the P point and the camera pixel coordinate system is as follows>
The conversion relation formula for calculating the projection point coordinate of the P point in the image plane coordinate system and the laser radar coordinate system is as follows, z L ＝rcosα，x L ＝rsinα、/>
3. The automatic inspection method for the multi-floor modeling of the transformer substation according to claim 1, characterized in that the multi-floor modeling of the transformer substation adopts a grid map model, a quadruped robot graph occupies the grid map, divides the environment where the quadruped robot graph is located into a plurality of grid units with equal dimensions, describes the external environment corresponding to the quadruped robot graph by means of the grid units in combination with data obtained by conversion of coordinate systems of a laser radar and a depth camera, and simultaneously records whether the grid unit has obstacles, namely whether the grid unit state is occupied, idle or unavailable.
4. The autonomous inspection method for the multi-floor modeling of the transformer substation according to claim 3, characterized in that in the multi-floor modeling of the transformer substation, a probability value of 0 is used for representing a grid idle state, a value of 1 is used for representing that the grid is occupied at the moment, and a value of 0.5 is used for representing that the state cannot be acquired.
5. The method for the autonomous routing inspection of the multi-floor modeling of the transformer substation according to claim 1, wherein in path planning and autonomous navigation, a control system firstly plans a global path for a quadruped robot in real navigation, the quadruped robot detects a local path in real motion according to a sensor of the quadruped robot in real time, when no obstacle exists in the path, the quadruped robot continues to move forward according to the original path, when the obstacle is detected, whether the global path and the obstacle interfere with each other is judged, if the obstacle does not interfere with each other, the quadruped robot normally moves forward, if the obstacle interferes with each other, the current speed and the pose are adjusted through local path planning, and meanwhile, the global path is continuously updated.
6. The autonomous inspection method for modeling of the multiple floors of the transformer substation according to claim 1, wherein in obstacle avoidance and map planning updating, incremental updating of a global map can be performed according to a pose of a robot and a local map constructed by a laser radar scanning data structure; by the formula
Whether the grid is occupied by the obstacle or not is judged, the situation that the grid in the global map is occupied by the obstacle is further judged, and information in the global map can be updated in real time. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211399661.7A CN115903797A (en) | 2022-11-09 | 2022-11-09 | Autonomous routing inspection method for multi-floor modeling of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211399661.7A CN115903797A (en) | 2022-11-09 | 2022-11-09 | Autonomous routing inspection method for multi-floor modeling of transformer substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115903797A true CN115903797A (en) | 2023-04-04 |
Family
ID=86472079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211399661.7A Pending CN115903797A (en) | 2022-11-09 | 2022-11-09 | Autonomous routing inspection method for multi-floor modeling of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115903797A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189412A (en) * | 2019-05-13 | 2019-08-30 | 武汉大学 | More floor doors structure three-dimensional modeling methods and system based on laser point cloud |
| CN111045017A (en) * | 2019-12-20 | 2020-04-21 | 成都理工大学 | Method for constructing transformer substation map of inspection robot by fusing laser and vision |
| CN211022482U (en) * | 2019-06-12 | 2020-07-17 | 深圳飞科机器人有限公司 | Cleaning robot |
| CN112650244A (en) * | 2020-12-22 | 2021-04-13 | 哈尔滨工业大学（深圳） | Multi-floor automatic mapping method for mobile robot in building based on feature point matching |
| CN114005021A (en) * | 2021-12-27 | 2022-02-01 | 中国农业大学 | Laser vision fusion based unmanned inspection system and method for aquaculture workshop |
| CN114237225A (en) * | 2021-11-19 | 2022-03-25 | 武汉华中思能科技有限公司 | Quadruped robot and intelligent inspection management platform thereof |
| CN114638909A (en) * | 2022-03-24 | 2022-06-17 | 杭州电子科技大学 | Substation semantic map construction method based on laser SLAM and visual fusion |
-
2022
- 2022-11-09 CN CN202211399661.7A patent/CN115903797A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110189412A (en) * | 2019-05-13 | 2019-08-30 | 武汉大学 | More floor doors structure three-dimensional modeling methods and system based on laser point cloud |
| CN211022482U (en) * | 2019-06-12 | 2020-07-17 | 深圳飞科机器人有限公司 | Cleaning robot |
| CN111045017A (en) * | 2019-12-20 | 2020-04-21 | 成都理工大学 | Method for constructing transformer substation map of inspection robot by fusing laser and vision |
| CN112650244A (en) * | 2020-12-22 | 2021-04-13 | 哈尔滨工业大学（深圳） | Multi-floor automatic mapping method for mobile robot in building based on feature point matching |
| CN114237225A (en) * | 2021-11-19 | 2022-03-25 | 武汉华中思能科技有限公司 | Quadruped robot and intelligent inspection management platform thereof |
| CN114005021A (en) * | 2021-12-27 | 2022-02-01 | 中国农业大学 | Laser vision fusion based unmanned inspection system and method for aquaculture workshop |
| CN114638909A (en) * | 2022-03-24 | 2022-06-17 | 杭州电子科技大学 | Substation semantic map construction method based on laser SLAM and visual fusion |
Non-Patent Citations (2)
| Title |
|---|
| 熊光明，龚建伟，陈慧岩主编: "《无人驾驶车辆理论与设计：慕课版》", 北京：北京理工大学出版社, pages: 119 - 127 * |
| 肖宇峰，等: "Kinect与二维激光雷达结合的机器人障碍检测", 《电子科技大学学报》, vol. 47, no. 3, pages 337 - 342 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3612906B1 (en) | Method and system for environment map generation and alignment | |
| WO2020192000A1 (en) | Livestock and poultry information perception robot based on autonomous navigation, and map building method | |
| CN113189977B (en) | Intelligent navigation path planning system and method for robot | |
| CN103064416B (en) | Crusing robot indoor and outdoor autonomous navigation system | |
| US20200264616A1 (en) | Location estimation system and mobile body comprising location estimation system | |
| Harapanahalli et al. | Autonomous Navigation of mobile robots in factory environment | |
| CN112882053B (en) | Method for actively calibrating external parameters of laser radar and encoder | |
| CN113110457A (en) | Autonomous coverage inspection method for intelligent robot in indoor complex dynamic environment | |
| CN112518739A (en) | Intelligent self-navigation method for reconnaissance of tracked chassis robot | |
| US20200363212A1 (en) | Mobile body, location estimation device, and computer program | |
| Beinschob et al. | Advances in 3d data acquisition, mapping and localization in modern large-scale warehouses | |
| US11537140B2 (en) | Mobile body, location estimation device, and computer program | |
| CN113566808A (en) | Navigation path planning method, device, equipment and readable storage medium | |
| CN114413909A (en) | Indoor mobile robot positioning method and system | |
| Li et al. | Hybrid filtering framework based robust localization for industrial vehicles | |
| CN114200945A (en) | Safety control method of mobile robot | |
| Choi et al. | Improved CNN-based path planning for stairs climbing in autonomous UAV with LiDAR sensor | |
| Wulf et al. | Robust self-localization in industrial environments based on 3D ceiling structures | |
| CN112611374A (en) | Path planning and obstacle avoidance method and system based on laser radar and depth camera | |
| CN116466712A (en) | Autonomous cruising method and system based on CML-AVG laser radar trolley | |
| CN115903797A (en) | Autonomous routing inspection method for multi-floor modeling of transformer substation | |
| CN115877853A (en) | Intelligent storage flow path planning system and method | |
| CN113776515B (en) | Robot navigation method and device, computer equipment and storage medium | |
| Takahashi et al. | Performance evaluation of robot localization using 2d and 3d point clouds | |
| Li et al. | Comparison and evaluation of SLAM algorithms for AGV navigation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230404 |