CN116380935A - High-speed railway box girder damage detection robot car and damage detection method - Google Patents
High-speed railway box girder damage detection robot car and damage detection method Download PDFInfo
- Publication number
- CN116380935A CN116380935A CN202310647285.7A CN202310647285A CN116380935A CN 116380935 A CN116380935 A CN 116380935A CN 202310647285 A CN202310647285 A CN 202310647285A CN 116380935 A CN116380935 A CN 116380935A
- Authority
- CN
- China
- Prior art keywords
- information
- box girder
- damage
- pose
- crack
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 97
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 49
- 230000007547 defect Effects 0.000 claims abstract description 44
- 230000000007 visual effect Effects 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000003384 imaging method Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 26
- 230000011218 segmentation Effects 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 9
- 230000015556 catabolic process Effects 0.000 claims description 8
- 238000006731 degradation reaction Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 230000008878 coupling Effects 0.000 claims description 5
- 238000010168 coupling process Methods 0.000 claims description 5
- 238000005859 coupling reaction Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- XEEYBQQBJWHFJM-UHFFFAOYSA-N iron Substances [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 229910052742 iron Inorganic materials 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 239000011150 reinforced concrete Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004567 concrete Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005293 physical law Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D55/00—Endless track vehicles
- B62D55/06—Endless track vehicles with tracks without ground wheels
- B62D55/065—Multi-track vehicles, i.e. more than two tracks
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01D—CONSTRUCTION OF BRIDGES, ELEVATED ROADWAYS OR VIADUCTS; ASSEMBLY OF BRIDGES
- E01D19/00—Structural or constructional details of bridges
- E01D19/10—Railings; Protectors against smoke or gases, e.g. of locomotives; Maintenance travellers; Fastening of pipes or cables to bridges
- E01D19/106—Movable inspection or maintenance platforms, e.g. travelling scaffolding or vehicles specially designed to provide access to the undersides of bridges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/06—Visualisation of the interior, e.g. acoustic microscopy
- G01N29/0654—Imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4454—Signal recognition, e.g. specific values or portions, signal events, signatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
- G01N2021/9518—Objects of complex shape, e.g. examined with use of a surface follower device using a surface follower, e.g. robot
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
- G01N2291/0234—Metals, e.g. steel
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/028—Material parameters
- G01N2291/0289—Internal structure, e.g. defects, grain size, texture
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a high-speed railway box girder damage detection machine vehicle and a damage detection method, wherein the machine vehicle comprises: the device comprises a bearing and running module, a detection module, a control module and a data processing module; the bearing and running module is provided with a bearing trolley; the detection module is arranged on the bearing trolley and used for detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder; the control module is used for controlling the bearing trolley to realize self-walking and damage detection in the beam body according to the laser signals and the pose information; the data processing module is used for recognizing the crack image of the inner surface of the beam body based on a crack intelligent detection algorithm according to the panoramic image of the inner part of the box beam to obtain crack information; performing defect identification in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information; and obtaining visual damage evaluation information according to the crack information and the defect information. Thereby realizing the visual damage detection and evaluation of the high-speed railway box girder.
Description
Technical Field
The invention belongs to the technical field of robots, and particularly relates to a high-speed railway box girder damage detection robot car and a damage detection method.
Background
In recent years, high-speed railways rapidly develop, and the high-speed railway bridge has the advantages of large number of structures, large scale and clear characteristics; because of the construction mode of 'replacing road with bridge', the proportion of the box girder bridge in the line is high, and the service performance of the box girder bridge is ensured to be critical to the normal operation of the line; the daily maintenance operation and maintenance of the bridge and the real-time concern of the health condition of the bridge are the bases of the safety operation of the bridge.
At present, the detection modes of the high-speed railway box girder are mainly divided into two types: the first is to drill into the box girder and stand near the fence at the pier top for inspection by the inspector; the mode is limited by space, the inspection coverage is incomplete, the omission is easy to cause, and the subjectivity of the result is strong; meanwhile, the working intensity of the inspector is high, and the inspector is hard to work under the condition of being bitter and cold in the highland; the second type is to use the working platform that the bridge inspection car of the high-speed railway provides to patrol and examine; the method needs to work in a high-iron air window period, has low working efficiency, and cannot observe the structural condition under the high-iron running condition.
With the rapid development of robot control, machine vision and artificial intelligence technologies, how to improve the traditional detection technology by the technologies has become a new research field, and has good engineering application prospect; therefore, in the prior art, a high-speed railway box girder inspection robot is adopted to carry out inspection work, but as the box body is formed by reinforced concrete, various electric facilities running on high-speed railway are arranged on the upper part of the bridge, so that electromagnetic shielding exists in the box body, and absolute positioning information is difficult to acquire through GPS and the like; the real-time map modeling and self-positioning work can be carried out only by using the sensors carried by the sensor; moreover, the high-speed railway box girder is a typical degradation environment, accurate drawing construction and self-positioning cannot be realized from the principle level by only using a laser radar, a serious positioning drift phenomenon can occur, and normal use is seriously affected; the prior art needs to determine absolute positioning based on the marking information in the box girders, but the actual situation is that not all the box girders have obvious marking information, so that the working range of the prior art is small and the applicability is low; in the prior art, the position relation is calculated based on the movement quantity of the travelling component, and the method cannot adapt to a severe working environment (the situation that internal ponding, icing and the like exist in an actual working environment), and the position calculated by calculating the movement quantity based on the travelling component is extremely easy to cause position drift caused by slipping of the travelling component); and the idle running phenomenon also exists when the travelling assembly passes through a manhole and other large holes, so that displacement calculation drift is not in line with the actual situation.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a high-speed railway box girder damage detection machine vehicle and a damage detection method.
In order to solve the technical problems, the invention adopts the following technical scheme:
in a first aspect, a high-speed railway case roof beam damage detection robot is provided, includes:
the device comprises a bearing and running module, a detection module, a control module and a data processing module;
the bearing and travelling module is provided with a bearing trolley, and the bearing trolley is placed in the box body through a box girder manhole of the high-speed railway box girder;
the detection module is arranged on the bearing trolley and used for detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder;
the control module is used for controlling the bearing trolley to realize self-walking and damage detection in the beam body according to the laser signals and the pose information;
the data processing module is used for recognizing the crack image of the inner surface of the beam body based on a crack intelligent detection algorithm according to the panoramic image of the inner part of the box beam to obtain crack information; performing defect identification in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information; and obtaining visual damage evaluation information according to the crack information and the defect information.
Further, the carrying trolley comprises a trolley body, a track assembly and a cantilever assembly;
the vehicle body is placed in the box body through a box girder manhole of the high-speed railway box girder;
the cantilever component is a telescopic component, the tail end of the cantilever component is connected with the vehicle body, and the front end of the cantilever component can be contacted with the inner surface of the box girder through adjustment.
Further, the detection module comprises a monocular camera, a laser radar, an IMU (inertial measurement unit) and an ultrasonic detector;
the laser radar and the pose sensor IMU are fixedly arranged on the vehicle body;
the monocular camera is arranged on the cantilever assembly, and the ultrasonic detector is arranged at the front end of the cantilever assembly.
Further, the control module includes:
the bearing trolley obstacle avoidance control unit and the cantilever component control unit;
the bearing trolley obstacle avoidance control unit is used for realizing real-time map building and self-positioning in the box girder by utilizing a LIO-based synchronous positioning and map drawing SLAM algorithm according to the laser signals and the pose information to obtain map information and self-positioning information, and formulating obstacle avoidance shape-moving information based on an automatic obstacle avoidance algorithm so as to control the bearing trolley to realize self-walking in the girder;
and the cantilever component control unit is used for controlling the cantilever component to move according to the map information, the self-positioning information and the obstacle avoidance shape shifting information, so that the monocular camera and the ultrasonic detector can detect damage.
Further, according to the laser signal and the pose information, real-time mapping and self-positioning of the interior of the box girder are realized by utilizing an LIO-based synchronous positioning and mapping SLAM algorithm, so as to obtain map information and self-positioning information, which comprises the following steps:
performing time alignment on the laser radar and the IMU by using a time stamp distribution mechanism of a robot operating system ROS, determining relative coordinates of the laser radar and the IMU by a hand-eye calibration method, and realizing the calibration of the space pose;
performing point cloud segmentation and feature extraction on the laser signals, performing initial estimation on the pose state of the laser radar, adding pose information of an IMU (inertial measurement unit) of a pose sensor for motion distortion correction, obtaining a point cloud map of a current frame, and adding the point cloud map of the current frame into state update of the pose information of the IMU of the pose sensor;
pre-integrating pose information of an IMU (inertial measurement unit) of a pose sensor to obtain pose estimation and error covariance of the IMU of the pose sensor, mutually correcting the pose estimation of the IMU of the pose sensor and the pose state of a laser radar, performing iterative coupling, performing degradation judgment by combining known box girder characteristics, and performing back-end extended Kalman filtering optimization to obtain real-time map information;
judging whether the position of the beam end is reached or not by utilizing the idea of graph optimization, carrying out loop detection after a round trip in a single-section beam, and completing calibration of pose information and map information by utilizing the loop detection.
Further, the crack intelligent detection algorithm comprises a YOLOv3 target detection algorithm and a deep labv3 semantic segmentation algorithm, and the data processing module comprises:
the crack identification unit is used for processing the panoramic image in the box girder through a YOLOv3 target detection algorithm and a DeepLabV3 semantic segmentation algorithm, carrying out pixel level identification on cracks on the inner surface of the girder to obtain crack classification and crack positioning, generating a crack region and realizing crack segmentation; and counting to obtain the lengths, widths and areas of all the cracks, and obtaining the crack information.
Further, the data processing module further includes:
and the internal defect identification unit is used for processing ultrasonic information by utilizing an acoustic wave physical equation of ultrasonic detection and combining a physical information network PINN, and identifying and obtaining the defect position, the defect size and the defect outline in the beam body to obtain defect information.
Further, the data processing module further includes:
the visual damage assessment unit is used for classifying the identified crack information and defect information based on the real-time display characteristic of BIM-REVIT visual software, creating a corresponding damage group, and forming damage visual modeling by inputting the geometric dimension and position information of the damage group to obtain damage visual information.
Further, the visual damage assessment unit is further configured to determine size and coordinate information of the entity units through a BIM model known by the high-speed railway box girder, convert the visual damage information to the entity units in the BIM, use the damage boundary as a grid division boundary, re-grid-divide the entity units by using the damage analysis model to obtain a new BIM model, respond to the new BIM model by inputting an operation load, obtain structural deformation and dynamic characteristics of the box girder structure, and obtain visual damage assessment information according to the structural deformation and the dynamic characteristics.
In a second aspect, a method for detecting damage to a high-speed railway box girder is provided, which is applied to the high-speed railway box girder damage detection robot in the first aspect, and the method includes:
detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder;
according to the laser signals and the pose information, controlling the bearing trolley to realize self-walking and damage detection in the beam body;
carrying out crack image identification on the inner surface of the beam body based on a crack intelligent detection algorithm of data driving and deep learning according to the panoramic image in the box beam, so as to obtain crack information;
performing defect identification in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information;
and obtaining visual damage evaluation information according to the crack information and the defect information.
The invention has the beneficial effects that:
aiming at the problems of complex internal structure and numerous obstacles of the box girder, the high-speed railway box girder damage detection robot vehicle finishes self-walking of the robot vehicle by utilizing a laser radar and an IMU; aiming at the beam damage detection problem, an intelligent detection algorithm based on physical constraint and data driving is used, and the multi-quality element detection of the high-speed railway bridge is realized by utilizing a machine vision and ultrasonic detection technology;
because the box body of the high-speed railway box girder is formed by reinforced concrete, various electric facilities and the like for running high-speed railway are arranged at the upper part of the bridge, so that electromagnetic shielding exists in the box body of the high-speed railway box girder, and absolute positioning information is difficult to obtain through GPS and the like; only the self-carried laser radar and IMU sensor can be used for carrying out real-time map modeling and self-positioning work; the self-positioning and pose resolving are completed completely depending on the self-sensor and algorithm; the high-speed railway box girder is a typical degradation environment, accurate drawing construction and self-positioning cannot be realized from the principle level by only using a laser radar, a serious positioning drift phenomenon can occur, and normal use is seriously affected; the method comprises the steps of utilizing a tight coupling algorithm of LiDAR and IMU sensors, matching with algorithms such as loop detection and the like, completing accurate positioning of a degradation environment inside a high-speed railway box girder on a map construction, and displaying the environment inside the box girder;
the prior art needs to determine absolute positioning based on the marking information in the high-speed railway box girders, and in the actual situation, not all the high-speed railway box girders have obvious marking information, so that the working range of the prior art is small, and the applicability is low; according to the method, the constructed laser point cloud map and the pose track are utilized to calculate, a full-bridge health detection range map can be generated, and the detection position is automatically marked without depending on external information;
in the prior art, the position relation is calculated based on the movement quantity of the travelling component, so that the device cannot adapt to a severe working environment (for example, the situation of internal ponding, icing and the like exists in an actual working environment, the position calculated based on the movement quantity of the travelling component is extremely easy to have position drift caused by slipping of the travelling component), and idle running phenomenon exists when the device passes through a large hole such as a manhole and the like, so that the displacement calculation drift does not accord with the actual situation; the LiDAR-IMU combined scheme adopted by the application eliminates the phenomenon in principle;
the damage detection precision is low, the recognition rate is poor, the damage recognition variety is few, and the neural network is applied to the beam body crack recognition of the machine vision, so that the operation states of other facilities outside the beam body at the positions of the drain pipe, the vent hole, the expansion joint and the like cannot be recognized; the method adopts deep learning based on the neural network, locks various cracks in the beam body by utilizing machine vision, classifies and judges the cracks, and simultaneously distinguishes the working operation conditions of auxiliary facilities such as a drain pipe, an expansion joint and the like;
the existing instrument is difficult to fully detect the internal damage condition of the iron box girder, the phased array ultrasonic equipment in the existing mode is far away from the detected object, is greatly influenced by the work of the machine, can only judge whether an internal hole exists or not, and can not judge key problems such as damage condition, reinforcement corrosion and the like; the phased array ultrasonic algorithm based on the physical neural network PINN is adopted, and the ultrasonic detector can be close to the surface of the object to be detected by utilizing the folded mechanical assembly, so that the damage condition of the beam body can be judged more fully and strictly.
Drawings
FIG. 1 is a block diagram of a high-speed railway box girder damage detection robot;
FIG. 2 is a block diagram of the load-bearing cart of the present invention;
FIG. 3 is a flow chart of the mapping and self-positioning process of the present invention;
fig. 4 is a flowchart of the method for detecting damage to a high-speed railway box girder according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a high-speed railway box girder damage detection robot, including:
a carrying and running module 101, a detection module 102, a control module 103 and a data processing module 104;
the bearing and travelling module 101 is provided with a bearing trolley, and the bearing trolley is placed in the box body through a box girder manhole of the high-speed railway box girder;
the detection module 102 is arranged on the carrying trolley and is used for detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder;
the control module 103 is used for controlling the bearing trolley to realize self-walking and damage detection in the beam body according to the laser signals and the pose information;
the data processing module 104 is used for carrying out crack image recognition on the inner surface of the beam body based on a crack intelligent detection algorithm according to the panoramic image of the inner part of the box beam to obtain crack information; performing defect identification in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information; and obtaining visual damage evaluation information according to the crack information and the defect information.
As shown in fig. 2, in some embodiments of the invention, the load-bearing cart preferably includes a body 201, a track assembly 202, and a boom assembly 203;
the vehicle body 201 is placed in the box body through a box girder manhole of the high-speed railway box girder;
the cantilever assembly 203 is a telescoping assembly, the distal end of which is attached to the vehicle body and the front end of which is adjustable to contact the interior surface of the box girder.
Preferably, in some embodiments of the present invention, the detection module includes a monocular camera, a lidar, an pose sensor IMU, and an ultrasound detector;
the laser radar and the pose sensor IMU are fixedly arranged on the vehicle body;
the monocular camera is arranged on the cantilever assembly, and the ultrasonic detector is arranged at the front end of the cantilever assembly.
In the embodiments shown in fig. 1 and 2 above, the control module is illustrated as being provided on a carriage that can travel by way of a track assembly, the boom assembly being telescopic. According to the ultrasonic detector, the ultrasonic detector is arranged at the front end of the telescopic cantilever assembly, the cantilever assembly is controlled to move and stretch out, the ultrasonic detector can be detected close to the inner wall of the box body, and the damage condition of the beam body can be judged fully and strictly. While the carrying trolley walks in the box Liang Renkong, the inside of the box girder may be in the form of an obstacle, so that the obstacle needs to be avoided during the walking process. The cantilever assembly can be retracted in time when encountering an obstacle, so that the running of the robot car is prevented from being blocked or equipment is prevented from being damaged.
Preferably, in some embodiments of the present invention, the control module includes:
the bearing trolley obstacle avoidance control unit and the cantilever component control unit;
the bearing trolley obstacle avoidance control unit is used for realizing real-time map building and self-positioning in the box girder by utilizing a LIO-based synchronous positioning and map drawing SLAM algorithm according to the laser signals and the pose information to obtain map information and self-positioning information, and formulating obstacle avoidance shape-moving information based on an automatic obstacle avoidance algorithm so as to control the bearing trolley to realize self-walking in the girder;
and the cantilever component control unit is used for controlling the cantilever component to move according to the map information, the self-positioning information and the obstacle avoidance shape shifting information, so that the monocular camera and the ultrasonic detector can detect damage.
The laser radar inertial odometer (Lidar Inertial Odometry, LIO) is combined with a synchronous positioning and mapping (Simultaneous Localization and Mapping, SLAM) algorithm, so that real-time mapping and self-positioning of the inside of the box girder can be realized, and a self-walking path of the bearing trolley in the girder can be made based on an automatic obstacle avoidance algorithm, and the specific process is shown in fig. 3:
301, performing time alignment on a laser radar and an IMU by using a time stamp distribution mechanism of a robot operating system (Robot Operating System, ROS), so that no time error exists between the laser radar and the IMU, positioning accuracy is improved, and relative coordinates of the laser radar and the IMU are determined by a hand-eye calibration method, so that calibration of a space pose is realized, and the relative coordinates are realized by a manual hand-eye calibration method when the laser radar and the IMU are installed;
302, performing point cloud segmentation and feature extraction on a laser signal, performing initial estimation on the pose state of a laser radar, adding pose information of an IMU (inertial measurement unit) of a pose sensor for motion distortion correction, obtaining a point cloud map of a current frame, and adding the point cloud map of the current frame into state update of the pose information of the IMU of the pose sensor;
303, pre-integrating pose information of the pose sensor IMU to obtain pose estimation and error covariance of the pose sensor IMU, performing mutual correction on the pose estimation of the pose sensor IMU and the pose state of the laser radar, performing iterative coupling, performing degradation judgment by combining the known box girder characteristics, and performing back-end extended Kalman filtering optimization to obtain real-time map information;
304, judging whether the position of the beam end is reached by using the thought of graph optimization, carrying out loop detection after a round trip in the single-section beam, and completing calibration of pose information and map information by using the loop detection, wherein the calibration step improves the precision degree of self-positioning and maps.
Preferably, in some embodiments of the present invention, the crack intelligent detection algorithm includes a YOLOv3 target detection algorithm and a deep labv3 semantic segmentation algorithm, and the data processing module includes:
the crack identification unit is used for processing the panoramic image in the box girder through a YOLOv3 target detection algorithm and a DeepLabV3 semantic segmentation algorithm, carrying out pixel level identification on cracks on the inner surface of the girder to obtain crack classification and crack positioning, generating a crack region and realizing crack segmentation; and counting to obtain the lengths, widths and areas of all the cracks, and obtaining the crack information.
The YOLO algorithm is a one-stage target detection algorithm, a picture is divided into a plurality of grids, a priori frame is generated based on an anchor mechanism, a detection frame is generated only by one step, and YOLOv3 is an improved algorithm for the YOLO algorithm. And (3) selecting a photo training neural network containing false crack diseases (such as a template mark and deep black linear water stains) by using a YOLOv3 target detection algorithm through field shooting so as to distinguish an actual crack image from a 'false crack' image.
Preferably, in some embodiments of the present invention, the data processing module further includes:
and the internal defect identification unit is used for processing ultrasonic information by utilizing an acoustic wave physical equation of ultrasonic detection and combining a physical information network PINN, and identifying and obtaining the defect position, the defect size and the defect outline in the beam body to obtain defect information.
Physical information-based neural networks (PINNs) are a class of neural networks used to solve supervised learning tasks, which are capable of learning not only the distribution rules of training data samples like conventional neural networks, but also the physical laws described by mathematical equations. Compared with pure data-driven neural network learning, the PINN imposes physical information constraint in the training process, so that a model with more generalization capability can be learned by using fewer data samples. The ultrasonic detector carried at the front end of the cantilever component of the machine vehicle is utilized to delay and emit sound beams through different array elements, an incident wave front is formed in the beam body concrete, a multichannel receiving signal is utilized to analyze an internal scattering sound field, the identification of defects (such as cracks and holes) in the beam body is completed through an ultrasonic imaging technology, the convergence speed of a neural network is accelerated by utilizing a sound wave physical equation of phased array ultrasonic and combining with PINN, the training optimization of a sound wave damage identification algorithm is completed, and the information of defect positions, defect sizes, defect contours and the like is judged.
Preferably, in some embodiments of the present invention, the data processing module further includes:
the visual damage assessment unit is used for classifying the identified crack information and defect information based on the real-time display characteristic of BIM-REVIT visual software, creating a corresponding damage group, and forming damage visual modeling by inputting the geometric dimension and position information of the damage group to obtain damage visual information.
The visual damage evaluation unit is further used for determining the size and coordinate information of the entity units through a BIM model known by the high-speed railway box girder, converting the visual damage information into the entity units in the BIM, taking the damage boundary as a grid division boundary, re-conducting the grid division of the entity units by using the damage analysis model to obtain a new BIM model, responding to the new BIM model through input operation load, obtaining the structural deformation and dynamic characteristics of the box girder structure, and obtaining the visual damage evaluation information according to the structural deformation and the dynamic characteristics.
The embodiment principle of the embodiment of the invention is as follows:
aiming at the problems of complex internal structure and numerous obstacles of the box girder, the high-speed railway box girder damage detection robot vehicle finishes self-walking of the robot vehicle by utilizing a laser radar and an IMU; aiming at the beam damage detection problem, an intelligent detection algorithm based on physical constraint and data driving is used, and the multi-quality element detection of the high-speed railway bridge is realized by utilizing a machine vision and ultrasonic detection technology;
1. because the box body of the high-speed railway box girder is formed by reinforced concrete, various electric facilities and the like for running high-speed railway are arranged at the upper part of the bridge, so that electromagnetic shielding exists in the box body of the high-speed railway box girder, and absolute positioning information is difficult to obtain through GPS and the like; only the self-carried laser radar and IMU sensor can be used for carrying out real-time map modeling and self-positioning work; the self-positioning and pose resolving are completed completely depending on the self-sensor and algorithm; the high-speed railway box girder is a typical degradation environment, accurate drawing construction and self-positioning cannot be realized from the principle level by only using a laser radar, a serious positioning drift phenomenon can occur, and normal use is seriously affected; the method comprises the steps of utilizing a tight coupling algorithm of LiDAR and IMU sensors, matching with algorithms such as loop detection and the like, completing accurate positioning of a degradation environment inside a high-speed railway box girder on a map construction, and displaying the environment inside the box girder;
2. the prior art needs to determine absolute positioning based on the marking information in the high-speed railway box girders, and in the actual situation, not all the box girders have obvious marking information, so that the working range of the prior art is small, and the applicability is low; according to the method, the constructed laser point cloud map and the pose track are utilized to calculate, a full-bridge health detection range map can be generated, and the detection position is automatically marked without depending on external information;
3. in the prior art, the position relation is calculated based on the movement quantity of the travelling component, so that the device cannot adapt to a severe working environment (for example, the situation of internal ponding, icing and the like exists in an actual working environment, the position calculated based on the movement quantity of the travelling component is extremely easy to have position drift caused by slipping of the travelling component), and idle running phenomenon exists when the device passes through a large hole such as a manhole and the like, so that the displacement calculation drift does not accord with the actual situation; the LiDAR-IMU combined scheme adopted by the application eliminates the phenomenon in principle;
4. the damage detection precision is low, the recognition rate is poor, the damage recognition variety is few, and the neural network is applied to the beam body crack recognition of the machine vision, so that the operation states of other facilities outside the beam body at the positions of the drain pipe, the vent hole, the expansion joint and the like cannot be recognized; the method adopts deep learning based on the neural network, locks various cracks in the beam body by utilizing machine vision, classifies and judges the cracks, and simultaneously distinguishes the working operation conditions of auxiliary facilities such as a drain pipe, an expansion joint and the like;
5. the existing instrument is difficult to fully detect the internal damage condition of the iron box girder, the phased array ultrasonic equipment in the existing mode is far away from the detected object, is greatly influenced by the work of the machine, can only judge whether an internal hole exists or not, and can not judge key problems such as damage condition, reinforcement corrosion and the like; the phased array ultrasonic algorithm based on the physical neural network PINN is adopted, and the ultrasonic detector can be close to the surface of the object to be detected by utilizing the folded mechanical assembly, so that the damage condition of the beam body can be judged more fully and strictly.
The structure of the high-speed railway box girder damage detection robot and the operation principle thereof are described in detail in the above embodiments, and a method for detecting the damage of the high-speed railway box girder applied to the robot is described below by way of embodiments, as shown in fig. 4, including:
401, detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder;
402, controlling the bearing trolley to realize self-walking and damage detection in the beam body according to the laser signals and the pose information;
403, carrying out crack image identification on the inner surface of the beam body based on a crack intelligent detection algorithm according to the panoramic image in the box beam to obtain crack information;
404, identifying defects in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information;
and 405, obtaining visual damage assessment information according to the crack information and the defect information.
The specific content of each step in the implementation process of the embodiment of the invention refers to the description of the high-speed railway box girder damage detection robot car, and the laser radar and the IMU are utilized to complete the self-walking of the robot car; aiming at the beam damage detection problem, an intelligent detection algorithm based on physical constraint and data driving is used, and the multi-quality element detection of the high-speed railway bridge is realized by utilizing a machine vision and ultrasonic detection technology.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof, but rather as providing for the use of additional embodiments and advantages of all such modifications, equivalents, improvements and similar to the present invention are intended to be included within the scope of the present invention as defined by the appended claims.
Claims (10)
1. High-speed railway case roof beam damage detection machine car, its characterized in that includes:
the device comprises a bearing and running module, a detection module, a control module and a data processing module;
the bearing and travelling module is provided with a bearing trolley, and the bearing trolley is placed in the box body through a box girder manhole of the high-speed railway box girder;
the detection module is arranged on the bearing trolley and used for detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder;
the control module is used for controlling the bearing trolley to realize self-walking and damage detection in the beam body according to the laser signals and the pose information;
the data processing module is used for carrying out crack image identification on the inner surface of the beam body based on a crack intelligent detection algorithm according to the panoramic image of the inner part of the box beam to obtain crack information; performing defect identification in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information; and obtaining visual damage evaluation information according to the crack information and the defect information.
2. The high-speed railway box girder damage detection machine vehicle according to claim 1, wherein,
the bearing trolley comprises a trolley body, a crawler belt assembly and a cantilever assembly;
the vehicle body is placed in the box body through a box girder manhole of the high-speed railway box girder;
the cantilever component is a telescopic component, the tail end of the cantilever component is connected with the vehicle body, and the front end of the cantilever component can be in contact with the inner surface of the box girder through adjustment.
3. The high-speed railway box girder damage detection machine vehicle according to claim 2, wherein,
the detection module comprises a monocular camera, a laser radar, an IMU (inertial measurement unit) and an ultrasonic detector;
the laser radar and the pose sensor IMU are fixedly arranged on the vehicle body;
the monocular camera is arranged on the cantilever assembly, and the ultrasonic detector is arranged at the front end of the cantilever assembly.
4. A high-speed railway box girder damage detection machine car according to claim 3, wherein the control module comprises:
the bearing trolley obstacle avoidance control unit and the cantilever component control unit;
the carrying trolley obstacle avoidance control unit is used for realizing real-time image construction and self-positioning of the inside of the box girder by utilizing an LIO-based synchronous positioning and map drawing SLAM algorithm according to the laser signals and the pose information to obtain map information and self-positioning information, and formulating obstacle avoidance shape-moving information based on an automatic obstacle avoidance algorithm so as to control the carrying trolley to realize self-walking in the girder;
and the cantilever assembly control unit is used for controlling the cantilever assembly to move according to the map information, the self-positioning information and the obstacle avoidance shape shifting information so that the monocular camera and the ultrasonic detector perform damage detection.
5. The machine vehicle for detecting damage to a high-speed railway box girder according to claim 4, wherein the method for realizing real-time mapping and self-positioning of the interior of the box girder by utilizing a LIO-based synchronous positioning and mapping SLAM algorithm according to the laser signal and the pose information to obtain map information and self-positioning information comprises the following steps:
performing time alignment on the laser radar and the pose sensor IMU by using a time stamp distribution mechanism of a robot operating system ROS, and determining relative coordinates of the laser radar and the pose sensor IMU by a hand-eye calibration method to realize the calibration of a space pose;
performing point cloud segmentation and feature extraction on the laser signals, performing initial estimation on the pose state of the laser radar, adding pose information of the pose sensor IMU to perform motion distortion correction, obtaining a current frame point cloud map, and adding the obtained current frame point cloud map to state update of the pose information of the pose sensor IMU;
pre-integrating pose information of the pose sensor IMU to obtain pose estimation and error covariance of the pose sensor IMU, mutually correcting the pose estimation of the pose sensor IMU and the pose state of the laser radar, performing iterative coupling, performing degradation judgment by combining known box girder characteristics, and performing back-end extended Kalman filtering optimization to obtain real-time map information;
judging whether the position of the beam end is reached or not by utilizing the idea of graph optimization, carrying out loop detection after a round trip in a single-section beam, and completing calibration of pose information and map information by utilizing the loop detection.
6. The high-speed railway box girder damage detection robot of claim 1, wherein the crack intelligent detection algorithm comprises a YOLOv3 target detection algorithm and a deep labv3 semantic segmentation algorithm, and the data processing module comprises:
the crack identification unit is used for processing the panoramic image in the box girder through a YOLOv3 target detection algorithm and a DeepLabV3 semantic segmentation algorithm, carrying out pixel level identification on cracks on the inner surface of the girder to obtain crack classification and crack positioning, generating a crack region and realizing crack segmentation; and counting to obtain the lengths, widths and areas of all the cracks, and obtaining the crack information.
7. The high-speed railway box girder damage detection robot of claim 6, wherein the data processing module further comprises:
and the internal defect identification unit is used for processing the ultrasonic information by utilizing an acoustic wave physical equation of ultrasonic detection and combining a physical information network PINN, and identifying and obtaining the defect position, the defect size and the defect outline of the beam body to obtain defect information.
8. The high-speed railway box girder damage detection robot of claim 7, wherein the data processing module further comprises:
the visual damage assessment unit is used for classifying the identified crack information and the defect information based on the real-time display characteristic of BIM-REVIT visual software, creating a corresponding damage group, and forming damage visual modeling by inputting the geometric dimension and the position information of the damage group to obtain damage visual information.
9. The high-speed railway box girder damage detection machine vehicle according to claim 8, wherein,
the visual damage evaluation unit is further used for determining the size and coordinate information of the entity units through the BIM model known by the high-speed railway box girder, converting the damage visual information into the entity units in the BIM, taking the damage boundary as a grid division boundary, re-conducting entity unit grid division by using the damage analysis model to obtain a new BIM model, responding to the new BIM model through input operation load, obtaining structural deformation and dynamic characteristics of the box girder structure, and obtaining visual damage evaluation information according to the structural deformation and the dynamic characteristics.
10. A method for detecting damage to a high-speed railway box girder, which is applied to the high-speed railway box girder damage detection robot according to any one of claims 1 to 9, and comprises the following steps:
detecting and acquiring panoramic images, ultrasonic information, laser signals and pose information in the box girder;
according to the laser signals and the pose information, controlling a bearing trolley to realize self-walking and damage detection in the beam body;
carrying out crack image identification on the inner surface of the girder body based on a crack intelligent detection algorithm according to the panoramic image of the inside of the box girder to obtain crack information;
performing defect identification in the beam body based on an ultrasonic imaging technology according to the ultrasonic information to obtain defect information;
and obtaining visual damage evaluation information according to the crack information and the defect information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310647285.7A CN116380935A (en) | 2023-06-02 | 2023-06-02 | High-speed railway box girder damage detection robot car and damage detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310647285.7A CN116380935A (en) | 2023-06-02 | 2023-06-02 | High-speed railway box girder damage detection robot car and damage detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116380935A true CN116380935A (en) | 2023-07-04 |
Family
ID=86963751
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310647285.7A Pending CN116380935A (en) | 2023-06-02 | 2023-06-02 | High-speed railway box girder damage detection robot car and damage detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116380935A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645205A (en) * | 2017-02-24 | 2017-05-10 | 武汉大学 | Unmanned aerial vehicle bridge bottom surface crack detection method and system |
| CN110578293A (en) * | 2019-09-26 | 2019-12-17 | 中铁大桥科学研究院有限公司 | Concrete box girder inspection robot |
| CN110610483A (en) * | 2019-08-12 | 2019-12-24 | 全球能源互联网研究院有限公司 | Crack image acquisition and detection method, computer equipment and readable storage medium |
| CN111597608A (en) * | 2020-04-17 | 2020-08-28 | 南京震坤物联网科技有限公司 | Bridge BIM model crack belt parameter visualization creation method based on crack contour family |
| CN112285676A (en) * | 2020-10-22 | 2021-01-29 | 知行汽车科技（苏州）有限公司 | Laser radar and IMU external reference calibration method and device |
| CN112726360A (en) * | 2020-12-24 | 2021-04-30 | 中铁建设集团基础设施建设有限公司 | Airport concrete pavement crack repairing method |
| CN113432600A (en) * | 2021-06-09 | 2021-09-24 | 北京科技大学 | Robot instant positioning and map construction method and system based on multiple information sources |
| CN114964212A (en) * | 2022-06-02 | 2022-08-30 | 广东工业大学 | Multi-machine collaborative fusion positioning and mapping method oriented to unknown space exploration |
| CN115790618A (en) * | 2022-11-03 | 2023-03-14 | 中科天极(新疆)空天信息有限公司 | SLAM positioning method and system based on laser radar and storage medium |
| CN115903805A (en) * | 2022-11-15 | 2023-04-04 | 无锡八英里电子科技有限公司 | Wheeled robot monitoring method and system for pedestrian crossing area in traffic scene |
| CN116203579A (en) * | 2023-03-06 | 2023-06-02 | 上海交通大学 | Laser radar SLAM degradation detection method and system based on point cloud residual error |
-
2023
- 2023-06-02 CN CN202310647285.7A patent/CN116380935A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645205A (en) * | 2017-02-24 | 2017-05-10 | 武汉大学 | Unmanned aerial vehicle bridge bottom surface crack detection method and system |
| CN110610483A (en) * | 2019-08-12 | 2019-12-24 | 全球能源互联网研究院有限公司 | Crack image acquisition and detection method, computer equipment and readable storage medium |
| CN110578293A (en) * | 2019-09-26 | 2019-12-17 | 中铁大桥科学研究院有限公司 | Concrete box girder inspection robot |
| CN111597608A (en) * | 2020-04-17 | 2020-08-28 | 南京震坤物联网科技有限公司 | Bridge BIM model crack belt parameter visualization creation method based on crack contour family |
| CN112285676A (en) * | 2020-10-22 | 2021-01-29 | 知行汽车科技（苏州）有限公司 | Laser radar and IMU external reference calibration method and device |
| CN112726360A (en) * | 2020-12-24 | 2021-04-30 | 中铁建设集团基础设施建设有限公司 | Airport concrete pavement crack repairing method |
| CN113432600A (en) * | 2021-06-09 | 2021-09-24 | 北京科技大学 | Robot instant positioning and map construction method and system based on multiple information sources |
| CN114964212A (en) * | 2022-06-02 | 2022-08-30 | 广东工业大学 | Multi-machine collaborative fusion positioning and mapping method oriented to unknown space exploration |
| CN115790618A (en) * | 2022-11-03 | 2023-03-14 | 中科天极(新疆)空天信息有限公司 | SLAM positioning method and system based on laser radar and storage medium |
| CN115903805A (en) * | 2022-11-15 | 2023-04-04 | 无锡八英里电子科技有限公司 | Wheeled robot monitoring method and system for pedestrian crossing area in traffic scene |
| CN116203579A (en) * | 2023-03-06 | 2023-06-02 | 上海交通大学 | Laser radar SLAM degradation detection method and system based on point cloud residual error |
Non-Patent Citations (1)
| Title |
|---|
| CHAN QIN ET AL.: ""LINS:A lindar-inertial state estimator for robust and efficient navigation"", 《ROBOTICS》, pages 1 - 7 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | Real-time multiple damage mapping using autonomous UAV and deep faster region-based neural networks for GPS-denied structures | |
| Kim et al. | SLAM-driven robotic mapping and registration of 3D point clouds | |
| KR102008973B1 (en) | Apparatus and Method for Detection defect of sewer pipe based on Deep Learning | |
| Yang et al. | Deep concrete inspection using unmanned aerial vehicle towards cssc database | |
| Le et al. | Autonomous robotic system using non-destructive evaluation methods for bridge deck inspection | |
| CN101075376B (en) | Intelligent video traffic monitoring system based on multi-viewpoints and its method | |
| Protopapadakis et al. | Autonomous robotic inspection in tunnels | |
| US11790542B2 (en) | Mapping and localization system for autonomous vehicles | |
| KR102305328B1 (en) | System and method of Automatically Generating High Definition Map Based on Camera Images | |
| Han et al. | Detection and location of steel structure surface cracks based on unmanned aerial vehicle images | |
| CN112346463B (en) | Unmanned vehicle path planning method based on speed sampling | |
| CN200990147Y (en) | Intelligent video traffic monitoring system based on multi-view point | |
| CN111967360A (en) | Target vehicle attitude detection method based on wheels | |
| CN111721279A (en) | Tail end path navigation method suitable for power transmission inspection work | |
| Tavasoli et al. | Real-time autonomous indoor navigation and vision-based damage assessment of reinforced concrete structures using low-cost nano aerial vehicles | |
| CN103116743B (en) | A kind of railway obstacle detection method based on on-line study | |
| Ioli et al. | UAV photogrammetry for metric evaluation of concrete bridge cracks | |
| CN113532439B (en) | Synchronous positioning and map construction method and device for power transmission line inspection robot | |
| CN117369460A (en) | Intelligent inspection method and system for loosening faults of vehicle bolts | |
| CN112684797A (en) | Obstacle map construction method | |
| CN116380935A (en) | High-speed railway box girder damage detection robot car and damage detection method | |
| CN113848209B (en) | Dam crack detection method based on unmanned aerial vehicle and laser ranging | |
| CN115755888A (en) | AGV obstacle detection system with multi-sensor data fusion and obstacle avoidance method | |
| CN113554705B (en) | Laser radar robust positioning method under changing scene | |
| CN115205397A (en) | Vehicle space-time information identification method based on computer vision and pose estimation |
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 |