CN115495540A - Intelligent route identification method, system and medium for robot inspection - Google Patents
Intelligent route identification method, system and medium for robot inspection Download PDFInfo
- Publication number
- CN115495540A CN115495540A CN202211453343.4A CN202211453343A CN115495540A CN 115495540 A CN115495540 A CN 115495540A CN 202211453343 A CN202211453343 A CN 202211453343A CN 115495540 A CN115495540 A CN 115495540A
- Authority
- CN
- China
- Prior art keywords
- identification information
- inspection
- information
- robot
- working 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to a method, a system and a medium for intelligently identifying a route for robot inspection, which belong to the technical field of robot inspection, wherein the method comprises the steps of obtaining identification information of an abnormal working area, obtaining a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure schematic diagram, and obtaining the position point where the identification information of the current inspection robot is located; and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map. By the method, undetected nodes of the inspection robot can be quickly found, and the phenomenon of missed inspection caused by the condition that the positioning marks are unclear due to the fact that the RFID labels are covered by dirt for a long time is avoided.
Description
Technical Field
The invention relates to the technical field of robot inspection, in particular to a method, a system and a medium for intelligently identifying a route for robot inspection.
Background
The positioning and navigation technology is also a core technology in the intelligent inspection robot, and under the assistance of the technology, the whole inspection work is carried out, so that the positioning is more accurate. At present, along with the continuous development of modern intelligent technologies, a great deal of research is carried out in the positioning and navigation technologies of the intelligent inspection robot, platform support is provided for the positioning and navigation technologies of the intelligent inspection robot, and some researchers put forward a magnetic track guiding theory. In this way, the autonomous identification of the guide mark can be recorded in an image acquisition mode, and the routing inspection path, the parking position and the like can be determined autonomously on the basis, but in this navigation mode, once the ground guide mark is unclear, the navigation positioning precision is not high. Not enough and lead to ground to berth the sign and can't be swept yard rifle discernment and RFID label long-term use and covered by the filth and lead to the location sign unclear when appearing in the light of patrolling and examining the environment, patrol and examine the robot and appear partial position easily and not berth to produce and missed the detection phenomenon. Nowadays, the inspection robot under the mode is not accurate enough for identifying the navigation road belt, so that the inspection robot runs along the road belt.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a method, a system and a medium for intelligently identifying a route for robot routing inspection.
In order to achieve the purpose, the invention adopts the technical scheme that:
the invention provides a route intelligent identification method for robot inspection, which comprises the following steps:
the method comprises the steps that a navigation road belt is arranged in an area to be inspected in advance, identification information is arranged on the navigation road belt, and pre-trained multi-source data information is led into the identification information to generate trained identification information;
generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information;
acquiring identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure diagram, and acquiring a position point where the identification information of the current inspection robot is located;
and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map.
Further, in a preferred embodiment of the present invention, the acquiring work information of the current inspection robot within a preset time, and determining whether the work information is greater than the preset work information includes the following steps:
dividing the navigation road belt plane structure schematic diagram into a plurality of working areas, and acquiring identification information in each working area;
calculating a distance value between the identification information in each working area, and generating a distance set according to the distance value between the identification information;
acquiring a traveling distance value of a working area where the current inspection robot is located within a preset time, importing the traveling distance value into the distance set for comparison and matching, and generating a matching result;
and judging whether a preset matching result exists in the matching result, and if not, taking the working area as an abnormal area.
Further, in a preferred embodiment of the present invention, the obtaining of the identification information of the abnormal working area, and the obtaining of the position point of the identification information of the abnormal working area according to the identification information of the abnormal working area and the navigation road band planar structure diagram specifically include the following steps:
acquiring identification information of the abnormal working area, and obtaining a distance value between the identification information according to the identification information of the abnormal working area;
obtaining abnormal working area segments based on the traveling distance value of the current working area where the inspection robot is located within the preset time and the distance values among all the identification information;
obtaining identification information of one or more abnormal working areas according to the abnormal working area section and a preset working area section of the current working area;
and importing the identification information of the abnormal working area into the navigation road belt plane structure schematic diagram to obtain the position point of the identification information of the abnormal working area.
Further, in a preferred embodiment of the present invention, a corrected navigation route map is generated based on the location point of the identification information of the abnormal working area and the location point of the identification information of the current inspection robot, and the initial inspection route map is corrected according to the corrected navigation route map to obtain a final navigation route map, which specifically includes the following steps:
generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot;
acquiring an initial routing inspection route map of the routing inspection robot and a routing inspection route map passed by the routing inspection robot within preset time;
obtaining an inspection route map to be inspected according to the initial inspection route map of the inspection robot and the inspection route map passed by the inspection robot within preset time;
and generating a final navigation route map based on the route map to be patrolled and the corrected navigation route map.
Further, in a preferred embodiment of the present invention, the method for intelligently identifying a route for robot inspection further includes the following steps:
acquiring real-time navigation road belt image information through a camera arranged on the inspection robot;
preprocessing the real-time navigation road belt image information to obtain preprocessed image information, and obtaining outer contour information of the navigation road belt according to the preprocessed image information;
correcting the outer contour information of the navigation road belt by a characteristic decomposition method to obtain corrected information;
and adjusting the moving pose of the current inspection robot according to the correction information.
Further, in a preferred embodiment of the present invention, the method for correcting the outer contour information of the navigation road band by a feature decomposition method to obtain correction information specifically includes the following steps:
establishing a characteristic vector decomposition model, and introducing the outer contour information of the navigation road belt into the characteristic vector decomposition model for decomposition to obtain an orthogonal matrix and a diagonal matrix;
establishing a new coordinate system according to a coordinate zero point by taking a limit vector in the orthogonal matrix and the diagonal matrix as the coordinate zero point;
importing the orthogonal matrix and the diagonal matrix into the new coordinate system to generate a new coordinate number set;
and acquiring a limit coordinate point set in a new coordinate number set, importing the limit coordinate point set in the new coordinate number set into a world coordinate system, recombining the limit coordinate point set to obtain a processed navigation road belt graph, and outputting the navigation road belt graph as correction information.
Further, in a preferred embodiment of the present invention, the method for intelligently identifying a route for robot inspection includes the following steps:
acquiring obstacle information of the inspection robot in the inspection process through a radar detector arranged on the inspection robot;
judging whether the barrier is within a preset range of the navigation road belt or not, and if so, obtaining an initial position node and a final position node of the current barrier according to the barrier information;
leading the starting position node and the ending position node into a navigation road belt plane structure schematic diagram to determine a current starting obstacle node and a current ending obstacle node;
and determining an obstacle avoidance driving route map according to the current starting obstacle node and the ending obstacle node, and transmitting the obstacle avoidance driving route map to a control terminal of the inspection robot.
The invention provides a route intelligent identification system for robot inspection, which comprises a memory and a processor, wherein the memory comprises a route intelligent identification method program for robot inspection, and when the route intelligent identification method program for robot inspection is executed by the processor, the following steps are realized:
the method comprises the steps that a navigation road belt is arranged in an area to be inspected in advance, identification information is arranged on the navigation road belt, and pre-trained multi-source data information is led into the identification information to generate trained identification information;
generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information;
acquiring identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure diagram, and acquiring a position point where the identification information of the current inspection robot is located;
and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map.
Further, in a preferred embodiment of the present invention, the route intelligent recognition system for robot inspection further includes the following steps:
acquiring real-time navigation road belt image information through a camera arranged on the inspection robot;
preprocessing the real-time navigation road belt image information to obtain preprocessed image information, and obtaining outer contour information of the navigation road belt according to the preprocessed image information;
correcting the outer contour information of the navigation road belt by a characteristic decomposition method to obtain corrected information;
and adjusting the moving pose of the current inspection robot according to the correction information.
A third aspect of the present invention provides a computer-readable storage medium containing a program of a method for intelligently identifying a route for robot inspection, which when executed by a processor, implements any one of the steps of the method for intelligently identifying a route for robot inspection.
The invention solves the defects in the background technology, and has the following beneficial effects:
the method comprises the steps that a navigation road belt is arranged in an area to be inspected in advance, identification information is arranged on the navigation road belt, pre-trained multi-source data information is led into the identification information, and trained identification information is generated; generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information; acquiring identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure diagram, and acquiring a position point where the identification information of the current inspection robot is located; and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map. The phenomenon of missed detection caused by the fact that the ground parking mark cannot be identified by the code scanning gun due to insufficient light rays appearing in the routing inspection environment and the situation that the positioning mark is not clear due to the fact that the RFID label is covered by dirt in long-term use is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that drawings of other embodiments can be obtained according to the drawings without creative efforts.
Fig. 1 shows a first method flowchart of a route intelligent identification method for robot inspection;
fig. 2 shows a second method flowchart of a method for intelligent route identification for robot routing inspection;
fig. 3 shows a third method flowchart of a route intelligent recognition method for robot inspection;
fig. 4 shows a system block diagram of a route intelligent recognition system for robot inspection.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
The invention provides a route intelligent identification method for robot inspection, which comprises the following steps:
s102, generating training finished identification information by setting a navigation road belt in an area to be inspected in advance, setting identification information on the navigation road belt and importing pre-trained multi-source data information into the identification information;
s104, generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information;
s106, acquiring the identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and the navigation road belt plane structure schematic diagram, and acquiring the position point where the identification information of the current inspection robot is located;
and S108, generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection path map according to the corrected navigation path map to obtain a final navigation path map.
It should be noted that the identification information may be an RFID electronic tag, a barcode tag, and the like, where the multi-source data information includes information such as positioning information of each inspection area, travel information of the inspection robot, target object information of the inspection area, and charging information, and the target object information may be a virtual scene of the inspection area, such as an instrument model diagram of the area to be inspected. And establishing a navigation road belt plane structure schematic diagram through three-dimensional modeling software (such as SkechUp software, rhino software, maya software, 3Ds Max software, revit and the like), wherein the navigation road belt plane structure schematic diagram comprises a planning road belt of the navigation road belt and a position node of the identification information in the area to be inspected. The inspection robot control terminal stores identification information of each working area.
It should be noted that when the light in the inspection environment is insufficient, the ground parking mark cannot be recognized by the code scanning gun and the RFID label is covered by dirt for a long time, so that the positioning mark is not clear, the code scanning gun arranged on the inspection robot cannot acquire the identification information, the inspection area where the identification information which cannot be recognized is located by the inspection robot is subjected to missed inspection, and the undetected node of the inspection robot can be quickly found out by the method, so that the missed inspection phenomenon caused by the condition that the ground parking mark cannot be recognized by the code scanning gun and the RFID label is covered by the dirt for a long time due to the insufficient light in the inspection environment is avoided.
Further, in a preferred embodiment of the present invention, the acquiring work information of the current inspection robot within a preset time, and determining whether the work information is greater than the preset work information includes the following steps:
dividing the navigation road belt plane structure schematic diagram into a plurality of working areas, and acquiring identification information in each working area;
calculating a distance value between the identification information in each working area, and generating a distance set according to the distance value between the identification information;
acquiring a traveling distance value of a working area where the current inspection robot is located within a preset time, importing the traveling distance value into the distance set for comparison and matching, and generating a matching result;
and judging whether a preset matching result exists in the matching result, and if not, taking the working area as an abnormal area.
Further, in a preferred embodiment of the present invention, the obtaining of the identification information of the abnormal working area, and the obtaining of the position point of the identification information of the abnormal working area according to the identification information of the abnormal working area and the navigation road band planar structure diagram specifically include the following steps:
acquiring identification information of the abnormal working area, and obtaining a distance value between the identification information according to the identification information of the abnormal working area;
obtaining abnormal working area segments based on the traveling distance value of the current working area where the inspection robot is located within the preset time and the distance values among all the identification information;
obtaining identification information of one or more abnormal working areas according to the abnormal working area section and a preset working area section of the current working area;
and importing the identification information of the abnormal working area into the navigation road belt plane structure schematic diagram to obtain the position point of the identification information of the abnormal working area.
It should be noted that, in an actual application scenario, the distance information between each identification information may be equal or may not be equal, and each identification information is a stop point of the inspection robot, that is, a certain distance value exists between adjacent stop points, when a certain distance value does not match a distance value in a distance set in the working area, that is, one or more RFID tag positions are not stopped, which results in missed inspection of the cruise robot, the method can quickly detect the position point where the identification information of the abnormal working area is located.
Further, in a preferred embodiment of the present invention, a corrected navigation path map is generated based on the location point of the identification information of the abnormal working area and the location point of the identification information of the current inspection robot, and the initial inspection path map is corrected according to the corrected navigation path map to obtain a final navigation path map, which specifically includes the following steps:
generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot;
acquiring an initial routing inspection route map of the routing inspection robot and a routing inspection route map passed by the routing inspection robot within preset time;
obtaining an inspection route map to be inspected according to the initial inspection route map of the inspection robot and the inspection route map passed by the inspection robot within preset time;
and generating a final navigation route map based on the route map to be patrolled and the corrected navigation route map.
It should be noted that when the missing detection phenomenon occurs, the final navigation route map can be re-formulated by the method, so that the cruise robot re-checks the missing detection position node, and the integrity of the inspection is ensured.
Further, in a preferred embodiment of the present invention, the method for intelligently identifying a route for robot inspection further includes the following steps:
s202, acquiring real-time navigation road belt image information through a camera arranged on the inspection robot;
s204, preprocessing the real-time navigation road belt image information to obtain preprocessed image information, and obtaining outer contour information of the navigation road belt according to the preprocessed image information;
s206, correcting the outer contour information of the navigation road belt by a characteristic decomposition method to obtain correction information;
and S208, adjusting the moving pose of the current inspection robot according to the correction information.
Further, in a preferred embodiment of the present invention, the method for correcting the outer contour information of the navigation road band by a feature decomposition method to obtain correction information specifically includes the following steps:
establishing a characteristic vector decomposition model, and introducing the outer contour information of the navigation road belt into the characteristic vector decomposition model for decomposition to obtain an orthogonal matrix and a diagonal matrix;
establishing a new coordinate system according to a coordinate zero point by taking a limit vector in the orthogonal matrix and the diagonal matrix as the coordinate zero point;
importing the orthogonal matrix and the diagonal matrix into the new coordinate system to generate a new coordinate number set;
and acquiring a limit coordinate point set in a new coordinate number set, importing the limit coordinate point set in the new coordinate number set into a world coordinate system, recombining the limit coordinate point set to obtain a processed navigation road belt graph, and outputting the navigation road belt graph as correction information.
It should be noted that the image may be processed by denoising and filtering using methods such as a nonlinear filter, a median filter, and a morphological filter, where the preprocessed image information includes a feature vector matrix, and the matrix represents a matrix map of the area range of the navigation road band. Furthermore, the singular value characteristic decomposition mode is used for decomposing the area range matrix diagram of the navigation road belt to obtain an orthogonal matrix and a diagonal matrix, the characteristic vector of one limit position in the orthogonal matrix and the diagonal matrix is selected as a construction reference point, the reference point is used as a coordinate origin to establish a new coordinate system, and the characteristic vector of one limit position in the orthogonal matrix and the diagonal matrix after decomposition is introduced into the new coordinate system to form a new coordinate matrix. The method can effectively eliminate the redundancy problem caused by the shooting angle problem of the camera system on the navigation road belt inspection robot, and can effectively process the original image to obtain the navigation road belt which is more in line with the actual range, so that the cruise robot can move along the navigation road belt more accurately to finish the inspection purpose.
Further, in a preferred embodiment of the present invention, the method for intelligently identifying a route for robot inspection includes the following steps:
s302, acquiring obstacle information of the inspection robot in the inspection process through a radar detector arranged on the inspection robot;
s304, judging whether the barrier is in a preset range of the navigation road belt, and if so, obtaining a starting position node and an ending position node of the current barrier according to the barrier information;
s306, leading the starting position node and the ending position node into a navigation road belt plane structure schematic diagram to determine a current starting obstacle node and a current ending obstacle node;
and S308, leading the starting position node and the ending position node into the navigation road belt plane structure schematic diagram to determine the current starting obstacle node and ending obstacle node.
It should be noted that, by the method, the inspection robot can effectively avoid the obstacle when the navigation road belt has the obstacle, and the intelligence in the inspection process is provided. The obstacle information comprises information such as volume information of obstacles and position information in the patrol inspection area.
In addition, the method can also comprise the following steps:
acquiring a temperature value of a current working environment of the inspection robot, and establishing an operation consumption model of the inspection robot based on a neural network;
acquiring energy consumption characteristics of a historical inspection robot under each temperature value, inputting the energy consumption characteristics into an operation consumption model of the inspection robot, adjusting parameters of the operation consumption model, and storing optimal model parameters;
generating the energy consumption value change of the inspection robot under the current temperature according to the temperature value of the current inspection robot working environment and the inspection robot battery operation consumption model, and generating the inspection robot consumed power according to the energy consumption value change;
and acquiring a residual energy consumption value of the current inspection robot, calculating to obtain the time capable of continuing inspection according to the power consumption of the inspection robot and the residual energy consumption value of the inspection robot, calculating whether the time is less than preset time, and if so, retrieving a charging node from the working area and transmitting the charging node to the inspection robot control terminal.
It should be noted that, according to the actual situation, the battery consumption under different temperatures is inconsistent, and if the energy consumption of the inspection robot is in an increased state in high-temperature weather, the method can simulate the energy consumption change of the inspection robot according to the actual working environment temperature, so that the robot in inspection adjusts the charging time node according to the environment change, and the inspection robot extracts the energy consumption in the actual temperature application scene to obtain the time node for supplementing in advance, thereby supplementing the energy.
According to this embodiment, the present invention may further include the steps of:
acquiring estimated supplement time of the inspection robot which is supplementing energy at present, and calculating a time node for completing supplement according to the current time point and the estimated supplement time of the inspection robot;
judging whether the supplemented time node is within a preset working time node or not, if not, acquiring the remaining working task time of the inspection robot closest to the current inspection robot and the inspection robot which is supplementing energy;
acquiring a residual target task of the inspection robot closest to the current inspection robot, and acquiring the finishing working time of the inspection robot closest to the current inspection robot according to the residual target task;
and judging whether the sum of the remaining work task time and the finishing work time of the inspection robot closest to the current inspection robot is not more than a preset work time node, if not, transmitting the remaining work task of the inspection robot which is currently replenishing energy to the inspection robot closest to the current inspection robot, and finishing the current work task by the inspection robot closest to the current inspection robot.
It should be noted that, according to the actual usage scenario, an inspection robot needs to inspect one or more work cycles of the current work area, and it can be understood that an inspection robot completes inspection for a preset number of times within a preset work time. And the preset working time node is a working period ending node.
In addition, the method can also comprise the following steps:
if the sum of the remaining work task time and the finishing work time of the inspection robot closest to the current inspection robot is greater than a preset work time node, acquiring a position node of the idle state inspection robot within a preset range;
establishing a distance sorting table, and acquiring a position starting node and a position ending node of the rest work tasks of the inspection robot which is supplementing energy;
calculating distance values according to the position nodes of the rest work tasks of the inspection robot which is replenishing energy, the termination position nodes and the position nodes of the idle state inspection robot, and introducing the distance values into the distance sorting table for sorting;
and extracting the minimum distance value from the distance sorting table, acquiring the position node corresponding to the minimum distance value, and regenerating the routing inspection path according to the position node corresponding to the minimum distance value.
It should be noted that the polling robots in idle states can be retrieved through the method, so that polling tasks can be completed quickly, the coordination capacity among the polling robots is improved, and the polling process is more reasonable.
The second aspect of the present invention provides a route intelligent identification system for robot inspection, the system includes a memory 41 and a processor 62, the memory 41 includes a route intelligent identification method program for robot inspection, when the route intelligent identification method program for robot inspection is executed by the processor 62, the following steps are realized:
the method comprises the steps that a navigation road band is arranged in an area to be inspected in advance, identification information is arranged on the navigation road band, and pre-trained multi-source data information is led into the identification information to generate trained identification information;
generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information;
acquiring identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure diagram, and acquiring a position point where the identification information of the current inspection robot is located;
and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map.
It should be noted that the identification information may be an RFID electronic tag, a barcode tag, and the like, where the multi-source data information includes information such as positioning information of each inspection area, travel information of the inspection robot, target object information of the inspection area, and charging information, and the target object information may be a virtual scene of the inspection area, such as an instrument model diagram of the area to be inspected. And establishing a navigation road belt plane structure schematic diagram through three-dimensional modeling software (such as SkechUp software, rhino software, maya software, 3Ds Max software, revit and the like), wherein the navigation road belt plane structure schematic diagram comprises a planning road belt of the navigation road belt and a position node of the identification information in the area to be inspected. The inspection robot control terminal stores identification information of each working area.
It should be noted that when insufficient light occurs in the inspection environment and the ground parking mark cannot be recognized by the code scanning gun and the RFID label is covered by dirt for a long time and the positioning mark is unclear, the code scanning gun arranged on the inspection robot cannot acquire the identification information, the inspection robot leaks the inspection region where the identification information which cannot be recognized is located, the undetected nodes of the inspection robot can be quickly found through the method, and the phenomenon of missed inspection is avoided when insufficient light occurs in the inspection environment and the ground parking mark cannot be recognized by the code scanning gun and the RFID label is covered by dirt for a long time and the positioning mark is unclear.
Further, in a preferred embodiment of the present invention, the route intelligent recognition system for robot inspection further includes the following steps:
acquiring real-time navigation road belt image information through a camera arranged on the inspection robot;
preprocessing the real-time navigation road belt image information to obtain preprocessed image information, and obtaining outer contour information of the navigation road belt according to the preprocessed image information;
correcting the outer contour information of the navigation road belt by a characteristic decomposition method to obtain correction information;
and adjusting the moving pose of the current inspection robot according to the correction information.
Further, in a preferred embodiment of the present invention, the method for correcting the outer contour information of the navigation road band by a feature decomposition method to obtain correction information specifically includes the following steps:
establishing a characteristic vector decomposition model, and introducing the outer contour information of the navigation road belt into the characteristic vector decomposition model for decomposition to obtain an orthogonal matrix and a diagonal matrix;
establishing a new coordinate system according to a coordinate zero point by taking a limit vector in the orthogonal matrix and the diagonal matrix as the coordinate zero point;
importing the orthogonal matrix and the diagonal matrix into the new coordinate system to generate a new coordinate number set;
and acquiring a limit coordinate point set in a new coordinate number set, importing the limit coordinate point set in the new coordinate number set into a world coordinate system, recombining the limit coordinate point set to obtain a processed navigation road belt graph, and outputting the navigation road belt graph as correction information.
It should be noted that the image may be processed by denoising and filtering using methods such as a nonlinear filter, a median filter, and a morphological filter, where the image information after the preprocessing includes a feature vector matrix, and the matrix represents a matrix map of the area range of the navigation road band. Furthermore, the singular value characteristic decomposition mode is used for decomposing the area range matrix diagram of the navigation road belt to obtain an orthogonal matrix and a diagonal matrix, the characteristic vector of one limit position in the orthogonal matrix and the diagonal matrix is selected as a construction reference point, the reference point is used as a coordinate origin to establish a new coordinate system, and the characteristic vector of one limit position in the orthogonal matrix and the diagonal matrix after decomposition is introduced into the new coordinate system to form a new coordinate matrix. The method can effectively eliminate the redundancy problem caused by the shooting angle problem of the camera system on the navigation road belt inspection robot, and can effectively process the original image to obtain the navigation road belt which is more in line with the actual range, so that the cruise robot can move along the navigation road belt more accurately to finish the inspection purpose.
A third aspect of the present invention provides a computer-readable storage medium including a route smart recognition method program for robot inspection, which, when executed by a processor, implements any one of the steps of the route smart recognition method for robot inspection.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media capable of storing program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present invention, and shall cover the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent route identification method for robot inspection is characterized by comprising the following steps:
the method comprises the steps that a navigation road belt is arranged in an area to be inspected in advance, identification information is arranged on the navigation road belt, and pre-trained multi-source data information is led into the identification information to generate trained identification information;
generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information;
acquiring identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure diagram, and acquiring a position point where the identification information of the current inspection robot is located;
and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map.
2. The intelligent route identification method for robot inspection according to claim 1, wherein the method comprises the steps of obtaining work information of the current inspection robot within a preset time, and judging whether the work information is larger than the preset work information, wherein the method comprises the following steps:
dividing the navigation road belt plane structure schematic diagram into a plurality of working areas, and acquiring identification information in each working area;
calculating a distance value between the identification information in each working area, and generating a distance set according to the distance value between the identification information;
acquiring a traveling distance value of a working area where the current inspection robot is located within a preset time, importing the traveling distance value into the distance set for comparison and matching, and generating a matching result;
and judging whether a preset matching result exists in the matching result, and if not, taking the working area as an abnormal area.
3. The method for intelligently identifying the route for robot inspection according to claim 1, wherein the identification information of the abnormal working area is obtained, and the position point where the identification information of the abnormal working area is located is obtained according to the identification information of the abnormal working area and the navigation road band plane structure diagram, specifically comprising the following steps:
acquiring identification information of the abnormal working area, and obtaining a distance value between the identification information according to the identification information of the abnormal working area;
obtaining abnormal working area segments based on the traveling distance value of the current working area where the inspection robot is located within the preset time and the distance values among all the identification information;
obtaining identification information of one or more abnormal working areas according to the abnormal working area section and a preset working area section of the current working area;
and importing the identification information of the abnormal working area into the navigation road belt plane structure schematic diagram to obtain the position point of the identification information of the abnormal working area.
4. The intelligent route identification method for robot inspection according to claim 1, wherein a modified navigation path map is generated based on the location point of the identification information of the abnormal working area and the location point of the identification information of the current inspection robot, and the initial inspection route map is modified according to the modified navigation path map to obtain a final navigation route map, specifically comprising the following steps:
generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot;
acquiring an initial routing inspection route map of the routing inspection robot and a routing inspection route map passed by the routing inspection robot within preset time;
obtaining a route map to be patrolled according to the initial patrolling route map of the patrolling robot and the patrolling route map passed by the patrolling robot within preset time;
and generating a final navigation route map based on the route map to be patrolled and the corrected navigation route map.
5. The intelligent route identification method for robot inspection according to claim 1, further comprising the steps of:
acquiring real-time navigation road belt image information through a camera arranged on the inspection robot;
preprocessing the real-time navigation road belt image information to obtain preprocessed image information, and obtaining outer contour information of the navigation road belt according to the preprocessed image information;
correcting the outer contour information of the navigation road belt by a characteristic decomposition method to obtain correction information;
and adjusting the moving pose of the current inspection robot according to the correction information.
6. The intelligent route identification method for robot inspection according to claim 5, wherein the outer contour information of the navigation road belt is corrected by a feature decomposition method to obtain correction information, and the method specifically comprises the following steps:
establishing a characteristic vector decomposition model, and introducing the outer contour information of the navigation road belt into the characteristic vector decomposition model for decomposition to obtain an orthogonal matrix and a diagonal matrix;
establishing a new coordinate system according to a coordinate zero point by taking a limit vector in the orthogonal matrix and the diagonal matrix as the coordinate zero point;
importing the orthogonal matrix and the diagonal matrix into the new coordinate system to generate a new coordinate number set;
and acquiring a limit coordinate point set in a new coordinate number set, importing the limit coordinate point set in the new coordinate number set into a world coordinate system, recombining the limit coordinate point set to obtain a processed navigation road belt graph, and outputting the navigation road belt graph as correction information.
7. The intelligent route identification method for robot inspection according to claim 1, further comprising the steps of:
acquiring obstacle information of the inspection robot in the inspection process through a radar detector arranged on the inspection robot;
judging whether the barrier is within a preset range of the navigation road belt or not, and if so, obtaining an initial position node and a final position node of the current barrier according to the barrier information;
leading the starting position node and the ending position node into a navigation road belt plane structure schematic diagram to determine a current starting obstacle node and a current ending obstacle node;
and determining an obstacle avoidance driving route map according to the current starting obstacle node and the ending obstacle node, and transmitting the obstacle avoidance driving route map to a patrol inspection robot control terminal.
8. An intelligent route identification system for robot inspection, which is characterized in that the system comprises a memory and a processor, wherein the memory comprises an intelligent route identification method program for robot inspection, and when the processor executes the intelligent route identification method program for robot inspection, the following steps are realized:
the method comprises the steps that a navigation road band is arranged in an area to be inspected in advance, identification information is arranged on the navigation road band, and pre-trained multi-source data information is led into the identification information to generate trained identification information;
generating a navigation road band plane structure schematic diagram based on the navigation road band and the identification information, acquiring the working information of the current inspection robot within preset time, and acquiring an abnormal working area of the inspection robot based on the working information;
acquiring identification information of the abnormal working area, acquiring a position point where the identification information of the abnormal working area is located according to the identification information of the abnormal working area and a navigation road belt plane structure diagram, and acquiring a position point where the identification information of the current inspection robot is located;
and generating a corrected navigation path map based on the position point of the identification information of the abnormal working area and the position point of the identification information of the current inspection robot, and correcting the initial inspection route map according to the corrected navigation path map to obtain a final navigation route map.
9. The intelligent route recognition system for robot routing inspection according to claim 8, further comprising:
acquiring real-time navigation road belt image information through a camera arranged on the inspection robot;
preprocessing the real-time navigation road belt image information to obtain preprocessed image information, and obtaining outer contour information of the navigation road belt according to the preprocessed image information;
correcting the outer contour information of the navigation road belt by a characteristic decomposition method to obtain correction information;
and adjusting the moving pose of the current inspection robot according to the correction information.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium includes a program of a method for intelligently recognizing a route for robot inspection, which when executed by a processor, implements the steps of the method for intelligently recognizing a route for robot inspection according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211453343.4A CN115495540B (en) | 2022-11-21 | 2022-11-21 | Intelligent route identification method, system and medium for robot inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211453343.4A CN115495540B (en) | 2022-11-21 | 2022-11-21 | Intelligent route identification method, system and medium for robot inspection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115495540A true CN115495540A (en) | 2022-12-20 |
| CN115495540B CN115495540B (en) | 2023-03-24 |
Family
ID=85114718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211453343.4A Active CN115495540B (en) | 2022-11-21 | 2022-11-21 | Intelligent route identification method, system and medium for robot inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115495540B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115802013A (en) * | 2023-02-09 | 2023-03-14 | 北京熙捷科技有限公司 | Video monitoring method, device and equipment based on intelligent illumination and storage medium |
| CN116029323A (en) * | 2023-03-24 | 2023-04-28 | 亿云智慧(北京)信息技术发展有限公司 | Equipment inspection management method and system based on identification code scanning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523650A (en) * | 2018-11-27 | 2019-03-26 | 武汉瑞莱保能源技术有限公司 | A kind of method for inspecting and device of equipment working condition |
| CN109599945A (en) * | 2018-11-30 | 2019-04-09 | 武汉大学 | A kind of autonomous crusing robot cruising inspection system of wisdom power plant and method |
| CN111508097A (en) * | 2020-04-26 | 2020-08-07 | 深圳市阡丘越科技有限公司 | Site inspection method, device, equipment and storage medium |
| US20210174370A1 (en) * | 2019-12-09 | 2021-06-10 | Lg Electronics Inc. | Method and system of providing service by controlling robot in service area, and robot implementing thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114526724B (en) * | 2022-02-18 | 2023-11-24 | 山东新一代信息产业技术研究院有限公司 | Positioning method and equipment for inspection robot |
-
2022
- 2022-11-21 CN CN202211453343.4A patent/CN115495540B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523650A (en) * | 2018-11-27 | 2019-03-26 | 武汉瑞莱保能源技术有限公司 | A kind of method for inspecting and device of equipment working condition |
| CN109599945A (en) * | 2018-11-30 | 2019-04-09 | 武汉大学 | A kind of autonomous crusing robot cruising inspection system of wisdom power plant and method |
| US20210174370A1 (en) * | 2019-12-09 | 2021-06-10 | Lg Electronics Inc. | Method and system of providing service by controlling robot in service area, and robot implementing thereof |
| CN111508097A (en) * | 2020-04-26 | 2020-08-07 | 深圳市阡丘越科技有限公司 | Site inspection method, device, equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115802013A (en) * | 2023-02-09 | 2023-03-14 | 北京熙捷科技有限公司 | Video monitoring method, device and equipment based on intelligent illumination and storage medium |
| CN115802013B (en) * | 2023-02-09 | 2023-04-18 | 北京熙捷科技有限公司 | Video monitoring method, device and equipment based on intelligent illumination and storage medium |
| CN116029323A (en) * | 2023-03-24 | 2023-04-28 | 亿云智慧(北京)信息技术发展有限公司 | Equipment inspection management method and system based on identification code scanning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115495540B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115495540B (en) | Intelligent route identification method, system and medium for robot inspection | |
| CN110688992B (en) | Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle | |
| CN108764187A (en) | Extract method, apparatus, equipment, storage medium and the acquisition entity of lane line | |
| CN113911129B (en) | Traffic vehicle intention identification method based on driving behavior generation mechanism | |
| CN110765922A (en) | AGV is with two mesh vision object detection barrier systems | |
| CN112434566B (en) | Passenger flow statistics method and device, electronic equipment and storage medium | |
| CN111699410A (en) | Point cloud processing method, device and computer readable storage medium | |
| CN114782626A (en) | Transformer substation scene mapping and positioning optimization method based on laser and vision fusion | |
| CN114937083A (en) | Laser SLAM system and method applied to dynamic environment | |
| CN114355907A (en) | Cloud-based intelligent garbage recognition and cleaning method and system | |
| CN109583312A (en) | Lane detection method, apparatus, equipment and storage medium | |
| CN115909092A (en) | Light-weight power transmission channel hidden danger distance measuring method and hidden danger early warning device | |
| CN112697134A (en) | Environment sensing method, system and equipment of indoor inspection robot and computer readable storage medium thereof | |
| CN113674355A (en) | Target identification and positioning method based on camera and laser radar | |
| CN111855667A (en) | Novel intelligent train inspection system and detection method suitable for metro vehicle | |
| Liu et al. | Dloam: Real-time and robust lidar slam system based on cnn in dynamic urban environments | |
| Wen et al. | A robust sidewalk navigation method for mobile robots based on sparse semantic point cloud | |
| Muffert et al. | Stix-fusion: A probabilistic stixel integration technique | |
| CN109977884A (en) | Target follower method and device | |
| CN115661966A (en) | Inspection system and method based on augmented reality | |
| CN112884814B (en) | Anti-shielding action tracking method and device and storage medium | |
| CN115421486A (en) | Return control method and device, computer readable medium and self-moving equipment | |
| CN116109047A (en) | Intelligent scheduling method based on three-dimensional intelligent detection | |
| CN115861186A (en) | Electric power tower detection method and device based on deep learning and unmanned aerial vehicle equipment | |
| CN113469045B (en) | Visual positioning method and system for unmanned integrated card, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |