CN116166016A - Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device - Google Patents

Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device Download PDF

Info

Publication number
CN116166016A
CN116166016A CN202310143301.9A CN202310143301A CN116166016A CN 116166016 A CN116166016 A CN 116166016A CN 202310143301 A CN202310143301 A CN 202310143301A CN 116166016 A CN116166016 A CN 116166016A
Authority
CN
China
Prior art keywords
real
vehicle
detection device
time
tunnel lining
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
Application number
CN202310143301.9A
Other languages
Chinese (zh)
Inventor
雷洋
江波
田甜
齐法琳
瞿起明
贾飞宇
王兆宁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Academy of Railway Sciences Corp Ltd CARS
Infrastructure Inspection Institute of CARS
Beijing IMAP Technology Co Ltd
Original Assignee
China Academy of Railway Sciences Corp Ltd CARS
Infrastructure Inspection Institute of CARS
Beijing IMAP Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Academy of Railway Sciences Corp Ltd CARS, Infrastructure Inspection Institute of CARS, Beijing IMAP Technology Co Ltd filed Critical China Academy of Railway Sciences Corp Ltd CARS
Priority to CN202310143301.9A priority Critical patent/CN116166016A/en
Publication of CN116166016A publication Critical patent/CN116166016A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a real-time obstacle avoidance method and device of a vehicle-mounted tunnel lining detection device, and relates to the technical field of automatic tunnel lining detection, wherein the method comprises the following steps: when the vehicle-mounted tunnel lining detection device performs operation, acquiring three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of the vehicle-mounted tunnel lining detection device; carrying out real-time mapping on the data by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information; according to the real-time point cloud map information, interference path information between an enveloping path of the vehicle-mounted tunnel lining detection device and the position of an obstacle in the tunnel is determined; and determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, and controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the real-time obstacle avoidance strategy. The invention can improve the accuracy of obstacle detection and the generation efficiency of obstacle avoidance strategies when the vehicle-mounted tunnel lining detection device works, and realize real-time obstacle avoidance.

Description

Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device
Technical Field
The invention relates to the technical field of automatic tunnel lining detection, in particular to a real-time obstacle avoidance method and device of a vehicle-mounted tunnel lining detection device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The large detection vehicle for detecting the defects in the tunnel carries out detection operation through the ground penetrating radar, and the ground penetrating radar needs to be carried with the large mechanical arm on the vehicle to reach a lining test line station, so that the distance between the large mechanical arm and the surface of the tunnel lining is kept about 10 cm. The abnormal protrusions, cables, staggered platforms, anchor-falling sections and other structures on the surface of the tunnel lining can generate physical interference with ground penetrating radars and mechanical arms in the operation process, if continuous running detection is carried out without timely obstacle avoidance, serious operation accidents can occur, and serious loss of people and objects is caused.
In the prior art, a single-line obstacle scanner is arranged on the working surface of a vehicle-mounted tunnel lining detection device (a vehicle-mounted mechanical arm and a bottom detection radar) to perform collision risk early warning, but the single-line section risk detection can be performed, the detection of abnormal protrusions such as spikes and cables is easy to leak, and the accuracy of obstacle detection is low; moreover, the obstacle avoidance strategy still needs to be manually decided during actual operation, the obstacle avoidance cannot be performed in real time, and the generation efficiency of the obstacle avoidance strategy is low, so that the safety risk cannot be avoided during operation of the vehicle-mounted tunnel lining detection device.
Disclosure of Invention
The embodiment of the invention provides a real-time obstacle avoidance method of a vehicle-mounted tunnel lining detection device, which is used for improving the accuracy of obstacle detection and the generation efficiency of an obstacle avoidance strategy when the vehicle-mounted tunnel lining detection device works, realizing real-time obstacle avoidance and effectively avoiding safety risks, and comprises the following steps:
when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed, acquiring three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device;
real-time mapping is carried out on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that real-time point cloud map information is obtained; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device;
According to the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle information in the tunnel and the real-time tunnel section information and the enveloping path information of the vehicle-mounted tunnel lining detection device, the enveloping path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the obstacle position in the tunnel is determined;
determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device;
and controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
The embodiment of the invention also provides a real-time obstacle avoidance device of the vehicle-mounted tunnel lining detection device, which is used for improving the accuracy of obstacle detection and the generation efficiency of an obstacle avoidance strategy when the vehicle-mounted tunnel lining detection device works, realizing real-time obstacle avoidance and effectively avoiding safety risks, and comprises the following components:
the data acquisition module is used for acquiring three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device;
The positioning and mapping module is used for carrying out real-time mapping on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device;
the interference information determining module is used for determining interference path information between an envelope path of the vehicle-mounted tunnel lining detecting device and the position of the obstacle in the tunnel according to the relative position relation information among the vehicle-mounted tunnel lining detecting device, the obstacle information in the tunnel and the real-time tunnel section information and the envelope path information of the vehicle-mounted tunnel lining detecting device;
the strategy generation module is used for determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device;
the execution module is used for controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium which stores a computer program, and the computer program realizes the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the computer program realizes the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device when being executed by a processor.
In the embodiment of the invention, when a vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed, three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device are acquired; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device; real-time mapping is carried out on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that real-time point cloud map information is obtained; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device; according to the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle information in the tunnel and the real-time tunnel section information and the enveloping path information of the vehicle-mounted tunnel lining detection device, the enveloping path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the obstacle position in the tunnel is determined; determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device; and controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device. In this way, three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of the vehicle-mounted tunnel lining detection device are collected when the vehicle-mounted tunnel lining detection device performs operation, and real-time mapping is performed on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that obstacle information in a tunnel can be accurately presented, and the accuracy of obstacle detection is improved; and the interference path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel is determined through the obtained real-time point cloud map information, so that the real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device is determined, manual decision is not needed, the generation efficiency of the obstacle avoidance strategy can be improved, real-time obstacle avoidance is realized, and the safety risk is effectively avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flow chart of a real-time obstacle avoidance method of a vehicle-mounted tunnel lining detection device provided in an embodiment of the invention;
FIG. 2 is a flowchart of real-time mapping using a synchronous positioning and mapping SLAM algorithm according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a real-time obstacle avoidance device of a vehicle-mounted tunnel lining detection device according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a real-time obstacle avoidance device of yet another vehicle-mounted tunnel lining inspection device provided in an embodiment of the present invention;
fig. 5 is a schematic diagram of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are open-ended terms, meaning including, but not limited to. Reference to the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is used to schematically illustrate the practice of the present application, and is not limited thereto and may be appropriately adjusted as desired.
According to research, in the prior art, a single-line obstacle scanner is arranged on the working surface of a vehicle-mounted tunnel lining detection device (a vehicle-mounted mechanical arm and a bottom detection radar) to perform collision risk early warning, but the method can only perform single-line tangent plane risk detection, is easy to leak through detection of abnormal protrusions such as spikes and cables, and has low obstacle detection accuracy; moreover, the obstacle avoidance strategy still needs to be manually decided during actual operation, the obstacle avoidance cannot be performed in real time, and the generation efficiency of the obstacle avoidance strategy is low, so that the safety risk cannot be avoided during operation of the vehicle-mounted tunnel lining detection device.
Aiming at the research, the embodiment of the invention provides a real-time obstacle avoidance mode of the vehicle-mounted tunnel lining detection device, which can accurately analyze the interference between the enveloping path of the advancing direction of the vehicle-mounted tunnel lining detection device and the obstacle in real time, and autonomously formulate an obstacle avoidance strategy, so that the accuracy of obstacle detection and the generation efficiency of the obstacle avoidance strategy are greatly improved, and an important technical protection guarantee is provided for unattended operation with safe redundancy.
As shown in fig. 1, a flowchart of a real-time obstacle avoidance method of a vehicle-mounted tunnel lining detection device provided by an embodiment of the present invention may include the following steps:
step 101, acquiring three-dimensional real-time point cloud data acquired by a sensor arranged on a vehicle-mounted tunnel lining detection device when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device;
102, carrying out real-time mapping on three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of a vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device;
Step 103, determining interference path information between an envelope path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel according to the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle information in the tunnel and the real-time tunnel section information and the envelope path information of the vehicle-mounted tunnel lining detection device;
104, determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device;
step 105, controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
In the embodiment of the invention, when a vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed, three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device are acquired; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device; real-time mapping is carried out on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that real-time point cloud map information is obtained; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device; according to the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle information in the tunnel and the real-time tunnel section information and the enveloping path information of the vehicle-mounted tunnel lining detection device, the enveloping path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the obstacle position in the tunnel is determined; determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device; and controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device. In this way, three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of the vehicle-mounted tunnel lining detection device are collected when the vehicle-mounted tunnel lining detection device performs operation, and real-time mapping is performed on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that obstacle information in a tunnel can be accurately presented, and the accuracy of obstacle detection is improved; in addition, interference path information between an enveloping path of the vehicle-mounted tunnel lining detection device and the position of an obstacle in the tunnel is determined through the obtained real-time point cloud map information, so that a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device is determined, manual decision is not needed, the generation efficiency of the obstacle avoidance strategy can be improved, real-time obstacle avoidance is realized, and the safety risk is effectively avoided
In the embodiment of the invention, the sensor and the camera can be respectively arranged on the main telescopic arm and the arc bent arm at the upper end of the vehicle-mounted tunnel lining detection device to realize forward and reverse bidirectional detection so as to adapt to the bidirectional running of the detection vehicle. Wherein the sensor may be a 3D lidar, which may output a relatively dense point cloud; the camera may be a 2D camera.
The following describes in detail the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device shown in fig. 1.
In the step 101, when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed, three-dimensional real-time point cloud data acquired by a sensor mounted on the vehicle-mounted tunnel lining detection device can be acquired; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; and acquiring real-time coordinate data of the vehicle-mounted tunnel lining detection device.
In specific implementation, when the detection is started, the vehicle-mounted tunnel detection device performs running operation at a preferable speed of 5km/h, at this time, three-dimensional real-time point cloud data in the advancing direction of the 3D laser radar acquisition detection device mounted on the vehicle-mounted tunnel lining detection device can be specifically adjusted according to different tunnel section contours, the scanning threshold of the vehicle-mounted tunnel lining detection device can be adjusted, a tunnel section with a speed level of 300km/h is taken as an example, the area scanning can be preferably performed in a range of 80 DEG x 25 DEG forward, and scanning sampling is performed by preset frequency (high frequency, such as 300 HZ) and densely repeated twice according to the vehicle speed control requirement, so that three-dimensional real-time point cloud data not lower than 240000 points can be acquired every second, the resolution is doubled, and the point cloud density of the acquired three-dimensional real-time point cloud data can be increased by more than 10 times.
When the method is implemented, the vehicle-mounted tunnel detection device performs running operation at a preferable speed of 5km/h during detection opening, and at the moment, the 2D camera installed on the vehicle-mounted tunnel lining detection device is used for collecting real-time tunnel section information in the advancing direction of the detection device; the real-time tunnel section information may include two-dimensional section profile coordinate data and two-dimensional section image information.
When the detection is started, the vehicle-mounted tunnel detection device runs at a preferable speed of 5km/h, and at the moment, real-time coordinate data of the vehicle-mounted tunnel lining detection device can be obtained through the sensor.
In the step 102, a synchronous positioning and mapping SLAM algorithm may be used to map three-dimensional real-time point cloud data, real-time tunnel section information, and real-time coordinate data of the vehicle-mounted tunnel lining detection device in real time, so as to obtain real-time point cloud map information.
In the specific implementation, the synchronous positioning and mapping (Simultaneous Localization and Mapping, SLAM) refers to the process of constructing an environment map while calculating the position of a moving object according to the information of a sensor. The real-time mapping is performed through the SLAM algorithm, and forward point clouds can be accumulated, so that three-dimensional point cloud data can be presented on a small-size object in a middle-long-distance and three-dimensional space. Specifically, the spatial position information of any object in the tunnel can be presented in the real-time point cloud map information, so that the real-time point cloud map information can present the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information. In addition, the real-time point cloud map information also comprises envelope path information of the vehicle-mounted tunnel lining detection device.
In the embodiment of the present invention, in order to improve the accuracy of real-time mapping, before the step 102, the method may further include:
carrying out two-dimensional coordinate registration on the two-dimensional section contour coordinate data by taking the real-time coordinate data of the vehicle-mounted tunnel lining detection device as a reference system to obtain real-time tunnel section information after the two-dimensional coordinate registration;
step 102 may specifically include:
and carrying out real-time mapping on the real-time coordinate data of the vehicle-mounted tunnel lining detection device, the real-time tunnel section information after two-dimensional coordinate registration and the three-dimensional real-time point cloud data by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information.
In specific implementation, the real-time tunnel section information can be subjected to data preprocessing, the real-time coordinate data of the vehicle-mounted tunnel lining detection device can be used as a reference frame for data preprocessing, and the two-dimensional section profile coordinate data is adjusted, namely, the external reference coordinate is transformed, so that a foundation can be provided for realizing the registration of 2D and 3D coordinates in the subsequent real-time map building.
In the embodiment of the present invention, real-time mapping is performed on real-time coordinate data of an on-vehicle tunnel lining detection device, real-time tunnel section information after two-dimensional coordinate registration, and three-dimensional real-time point cloud data by using a synchronous positioning and mapping SLAM algorithm, so as to obtain real-time point cloud map information, as shown in fig. 2, the method specifically may include:
Step 201, carrying out coordinate fusion registration on real-time tunnel section information after registering real-time coordinate data and two-dimensional coordinates of a vehicle-mounted tunnel lining detection device and three-dimensional real-time point cloud data, and determining position information of an obstacle in a tunnel and relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information;
step 202, combining the barrier position information in the tunnel with the two-dimensional section image information in the real-time tunnel section information after the two-dimensional coordinate registration to perform barrier feature recognition, so as to obtain barrier feature information in the tunnel;
step 203, analyzing the gesture of the vehicle-mounted tunnel lining detection device according to real-time coordinate data of the vehicle-mounted tunnel lining detection device, and predicting envelope path information of the vehicle-mounted tunnel lining detection device;
and 204, carrying out real-time mapping according to the position information of the obstacle in the tunnel, the characteristic information of the obstacle in the tunnel, the enveloping path information of the vehicle-mounted tunnel lining detection device and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information to obtain real-time point cloud map information.
In the implementation, before the real-time mapping is performed, the three-dimensional real-time point cloud data is further required to be preprocessed, and specifically, the three-dimensional real-time point cloud data is decoded and the running speed is matched, namely, the motion compensation is performed, so that the data accords with objective reality; in order to prevent the three-dimensional real-time point cloud data from being distorted due to the misalignment of the speed information, it is necessary to check the distortion of the calibration image, and to prevent the data image from overlapping and uneven distribution which cannot be practically associated with the longitudinal running direction. After data preprocessing, real-time mapping can be carried out on real-time coordinate data of the vehicle-mounted tunnel lining detection device, real-time tunnel section information after two-dimensional coordinate registration and three-dimensional real-time point cloud data by utilizing a synchronous positioning and mapping SLAM algorithm.
Specifically, in step 201, coordinate fusion registration is performed between the real-time tunnel section information after the real-time coordinate data and the two-dimensional coordinate registration of the vehicle-mounted tunnel lining detection device and the three-dimensional real-time point cloud data, so that the position information of the obstacle in the tunnel and the relative position relationship information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information can be determined.
Then, in step 202, in order to enhance the accuracy of obstacle recognition and avoid partial misjudgment, qualitative judgment analysis can be assisted by the cooperation of machine vision images. Specifically, the two-dimensional section image information in the real-time tunnel section information is a real-time image in the acquired tunnel, and the real-time image includes image characteristic information of the obstacle in the tunnel, such as the color of the obstacle, so that the characteristic of the obstacle information can be analyzed through the characteristic value of the image obtained after learning and accumulating in the classical sample library. In the embodiment of the invention, the barrier characteristic identification is carried out by combining the barrier position information in the tunnel and the two-dimensional section image information in the real-time tunnel section information after the two-dimensional coordinate registration, so that the barrier characteristic information in the tunnel can be determined, and the barrier characteristic information in the tunnel can comprise at least one of the following items: size information, color information, type information, location information. Thus, the initial state of the point cloud data after the mapping can be intuitively reflected.
In step 203, the gesture of the vehicle-mounted tunnel lining detection device may be resolved according to the real-time coordinate data of the vehicle-mounted tunnel lining detection device, and envelope path information of the vehicle-mounted tunnel lining detection device may be predicted.
Specifically, envelope path information of the vehicle-mounted tunnel lining detection device means: the space moving path formed by the vehicle-mounted tunnel lining detection device in the running and advancing detection process is called a safe enveloping path, and any obstacle position information detected during the moving path is considered to generate potential collision risks if the obstacle position information is in cross interference with the enveloping path surface. Therefore, in order to improve the accuracy of collision detection, the attitude of the vehicle-mounted tunnel lining detection device can be analyzed according to the real-time coordinate data of the vehicle-mounted tunnel lining detection device, and the envelope path information of the vehicle-mounted tunnel lining detection device can be predicted.
In the specific implementation, in step 203, the real-time image of the vehicle-mounted tunnel lining detection device may be combined to perform image analysis on the posture states of the mechanical arm, the electric push rod, etc. of the vehicle-mounted tunnel lining detection device, so as to facilitate visual verification of the accuracy of the real-time initial state of the map building, and finally accurately realize the segmentation of the safety limits of the vehicle-mounted tunnel lining detection device.
In step 204, real-time mapping may be performed according to the position information of the obstacle in the tunnel, the characteristic information of the obstacle in the tunnel, the enveloping path information of the on-vehicle tunnel lining detection device, and the relative position relationship information among the on-vehicle tunnel lining detection device, the obstacle in the tunnel, and the real-time tunnel section information, so as to obtain real-time point cloud map information.
In the embodiment of the invention, in order to restore the tunnel live-action with high precision, nonlinear curve interpolation enhancement processing can be performed on the real-time point cloud map information after the real-time point cloud map information is obtained; the method can be used for apparent comprehensive integrated display and is associated with camera picture results so as to achieve the effect of multi-dimensional application of the homologous sensor.
Therefore, based on the 2D image and the real-time map construction of SLAM technology, accurate positioning of the vehicle-mounted tunnel lining detection device and safety limit segmentation on the map can be realized, and further the accuracy of collision detection is improved.
In step 103, if any obstacle position information is found to intersect the envelope path of the in-vehicle tunnel lining detection device, it is considered that a potential collision risk is generated. Therefore, the interference path information between the envelope path of the in-vehicle tunnel lining detection device and the position of the obstacle in the tunnel can be determined from the relative positional relationship information between the in-tunnel obstacle and the real-time tunnel cross-section information, and the envelope path information of the in-vehicle tunnel lining detection device.
In the embodiment of the invention, the interference path information can be three-dimensional coordinate difference information between an envelope path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel.
In step 104, a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device may be determined according to the interference path information.
The real-time obstacle avoidance strategy can comprise the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
In the embodiment of the present invention, step 104 may specifically include:
decomposing three-dimensional coordinate difference information between an enveloping path of the vehicle-mounted tunnel lining detection device and the position of an obstacle in the tunnel to obtain longitudinal distance between the vehicle-mounted tunnel lining detection device and the position of the obstacle and two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining obstacle avoidance actions of the vehicle-mounted tunnel lining detection device and action amplitudes corresponding to the obstacle avoidance actions according to two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining the running speed of the vehicle-mounted tunnel lining detection device according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position;
and determining the traveling speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device as a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device.
In specific implementation, the three-dimensional coordinate difference information between the enveloping path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel can be decomposed to obtain two components, wherein one of the components is the longitudinal (i.e. advancing direction) distance between the vehicle-mounted tunnel lining detection device and the position of the obstacle; and the second component is two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information.
In specific implementation, the two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in the real-time tunnel section information can be used for determining the obstacle avoidance action of the vehicle-mounted tunnel lining detection device and the action amplitude corresponding to the obstacle avoidance action, for example, full-stroke recovery of the electric push rod of the ground penetrating radar antenna is executed, and double-freedom-degree combined reverse recovery of the vehicle-mounted tunnel lining detection device (main arm stretching and swinging and arc-shaped arm) is synchronously waited to be executed.
In the specific implementation, according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position, the advancing speed of the vehicle-mounted tunnel lining detection device, namely the running speed, is adjusted, and the running speed of the vehicle-mounted tunnel lining detection device, the action amplitude corresponding to the obstacle avoidance action and the obstacle avoidance action are determined to be a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device.
For example, when the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position is 15 meters, the travelling speed needs to be slowly reduced to 3km/h, and meanwhile, the obstacle avoidance action is executed according to the action amplitude corresponding to the obstacle avoidance action; if the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position is 10 meters before implementing, the running speed needs to be slowly reduced to 1.5km/h, and the obstacle avoidance action is continuously executed according to the action amplitude corresponding to the obstacle avoidance action; if the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position is 5 meters before implementation, emergency stop braking is carried out.
In the embodiment of the invention, the method can further comprise the following steps:
and sending collision risk prompt information according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position.
In the implementation, the real-time point cloud map information can be displayed in an equi-axis projection mode according to the forward view angle of the sensor. And marking the safe driving limit of the detection device on the real-time point cloud map information view, and marking the risk area and the distance when the risk occurs.
In the embodiment of the invention, in order to eliminate non-abnormal false alarms generated by some lens interference and the like, real-time filtering processing can be performed on the three-dimensional real-time point cloud data; in order to better combine with the assistance of machine vision to restore more realistic barrier appearances in tunnels, point cloud clustering can be performed during later demonstration; meanwhile, if a bug or an error prompt occurs, the bug can be intervened manually.
In step 105, when interference between the enveloping path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel is detected, the vehicle-mounted tunnel lining detection device may be controlled to perform real-time obstacle avoidance according to the generated real-time obstacle avoidance strategy, that is, the traveling speed, the obstacle avoidance action, and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
In summary, the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device provided by the embodiment of the invention can solve the interference risk problem existing in the running process of the vehicle-mounted tunnel lining detection device, and can realize the measurement of the position, the size and the relative speed of small-size obstacles (nails, cables and the like); the safety limit of the vehicle-mounted tunnel lining detection device is extended in real time on the basis of real-time movement direction and speed measurement, and then possible collision risks are early warned from the aspects of relative position, size, relative speed and the like of the obstacle; and the quantitative measurement and evaluation of the collision risk are realized.
The embodiment of the invention also provides a real-time obstacle avoidance device of the vehicle-mounted tunnel lining detection device, as described in the following embodiment. Because the principle of solving the problem of the real-time obstacle avoidance device is similar to that of the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device, the implementation of the real-time obstacle avoidance device can be referred to the implementation of the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device, and repeated parts are omitted.
As shown in fig. 3, a schematic diagram of a real-time obstacle avoidance device of a vehicle-mounted tunnel lining detection device according to an embodiment of the present invention may include:
the data acquisition module 301 is configured to acquire three-dimensional real-time point cloud data acquired by a sensor installed on the vehicle-mounted tunnel lining detection device when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device;
the positioning and mapping module 302 is configured to perform real-time mapping on three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of the vehicle-mounted tunnel lining detection device by using a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device;
an interference information determining module 303, configured to determine interference path information between an envelope path of the vehicle-mounted tunnel lining detecting device and a position of an obstacle in the tunnel according to relative positional relationship information among the vehicle-mounted tunnel lining detecting device, the in-tunnel obstacle information and the real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detecting device;
The strategy generation module 304 is configured to determine a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, where the real-time obstacle avoidance strategy includes a travelling speed, an obstacle avoidance action, and an action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device;
the execution module 305 is configured to control the on-vehicle tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action, and the action amplitude corresponding to the obstacle avoidance action of the on-vehicle tunnel lining detection device.
In the embodiment of the invention, the real-time tunnel section information can comprise two-dimensional section profile coordinate data and two-dimensional section image information.
In the embodiment of the present invention, as shown in fig. 4, the system may further include a coordinate registration module 401, configured to perform real-time mapping on three-dimensional real-time point cloud data, real-time tunnel section information, and real-time coordinate data of the vehicle-mounted tunnel lining detection device by using a synchronous positioning and mapping SLAM algorithm, so as to obtain real-time point cloud map information before:
carrying out two-dimensional coordinate registration on the two-dimensional section contour coordinate data by taking the real-time coordinate data of the vehicle-mounted tunnel lining detection device as a reference system to obtain real-time tunnel section information after the two-dimensional coordinate registration;
The positioning and mapping module can be specifically used for:
and carrying out real-time mapping on the real-time coordinate data of the vehicle-mounted tunnel lining detection device, the real-time tunnel section information after two-dimensional coordinate registration and the three-dimensional real-time point cloud data by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information.
In the embodiment of the invention, the positioning and mapping module can be specifically used for:
carrying out coordinate fusion registration on the real-time tunnel section information after the real-time coordinate data and the two-dimensional coordinate registration of the vehicle-mounted tunnel lining detection device and the three-dimensional real-time point cloud data, and determining the position information of the obstacle in the tunnel and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information;
combining the barrier position information in the tunnel with the two-dimensional section image information in the real-time tunnel section information after the two-dimensional coordinate registration to perform barrier feature recognition, so as to obtain barrier feature information in the tunnel;
analyzing the gesture of the vehicle-mounted tunnel lining detection device according to the real-time coordinate data of the vehicle-mounted tunnel lining detection device, and predicting envelope path information of the vehicle-mounted tunnel lining detection device;
And carrying out real-time mapping according to the position information of the obstacle in the tunnel, the characteristic information of the obstacle in the tunnel, the enveloping path information of the vehicle-mounted tunnel lining detection device and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information to obtain real-time point cloud map information.
In the embodiment of the invention, the interference path information can be three-dimensional coordinate difference information between an envelope path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel.
In the embodiment of the invention, the interference information determining module may be specifically configured to:
decomposing three-dimensional coordinate difference information between an enveloping path of the vehicle-mounted tunnel lining detection device and the position of an obstacle in the tunnel to obtain longitudinal distance between the vehicle-mounted tunnel lining detection device and the position of the obstacle and two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining obstacle avoidance actions of the vehicle-mounted tunnel lining detection device and action amplitudes corresponding to the obstacle avoidance actions according to two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining the running speed of the vehicle-mounted tunnel lining detection device according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position;
And determining the traveling speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device as a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device.
In the embodiment of the invention, a risk prompting module is also included and is used for:
and sending collision risk prompt information according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position.
The embodiment of the present invention further provides a computer device, as shown in fig. 5, which is a schematic diagram of the computer device in the embodiment of the present invention, where the computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and capable of running on the processor 520, and when the processor 520 executes the computer program 530, the real-time obstacle avoidance method of the on-vehicle tunnel lining detection device is implemented.
The embodiment of the invention also provides a computer readable storage medium which stores a computer program, and the computer program realizes the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the computer program realizes the real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device when being executed by a processor.
In the embodiment of the invention, when a vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed, three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device are acquired; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device; real-time mapping is carried out on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that real-time point cloud map information is obtained; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device; according to the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle information in the tunnel and the real-time tunnel section information and the enveloping path information of the vehicle-mounted tunnel lining detection device, the enveloping path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the obstacle position in the tunnel is determined; determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device; and controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device. In this way, three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of the vehicle-mounted tunnel lining detection device are collected when the vehicle-mounted tunnel lining detection device performs operation, and real-time mapping is performed on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that obstacle information in a tunnel can be accurately presented, and the accuracy of obstacle detection is improved; and the interference path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the position of the obstacle in the tunnel is determined through the obtained real-time point cloud map information, so that the real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device is determined, manual decision is not needed, the generation efficiency of the obstacle avoidance strategy can be improved, real-time obstacle avoidance is realized, and the safety risk is effectively avoided.
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 description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (17)

1. The real-time obstacle avoidance method of the vehicle-mounted tunnel lining detection device is characterized by comprising the following steps of:
when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed, acquiring three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device;
real-time mapping is carried out on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm, so that real-time point cloud map information is obtained; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device;
according to the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle information in the tunnel and the real-time tunnel section information and the enveloping path information of the vehicle-mounted tunnel lining detection device, the enveloping path information between the enveloping path of the vehicle-mounted tunnel lining detection device and the obstacle position in the tunnel is determined;
Determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device;
and controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
2. The method of claim 1, wherein the real-time tunnel section information comprises two-dimensional section profile coordinate data and two-dimensional section image information.
3. The method of claim 2, wherein real-time mapping is performed on three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of the vehicle-mounted tunnel lining detection device by using a synchronous positioning and mapping SLAM algorithm, and further comprising, before obtaining the real-time point cloud map information:
carrying out two-dimensional coordinate registration on the two-dimensional section contour coordinate data by taking the real-time coordinate data of the vehicle-mounted tunnel lining detection device as a reference system to obtain real-time tunnel section information after the two-dimensional coordinate registration;
real-time mapping is carried out on three-dimensional real-time point cloud data, real-time tunnel section information and real-time coordinate data of a vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information, and the method comprises the following steps:
And carrying out real-time mapping on the real-time coordinate data of the vehicle-mounted tunnel lining detection device, the real-time tunnel section information after two-dimensional coordinate registration and the three-dimensional real-time point cloud data by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information.
4. The method of claim 3, wherein real-time mapping is performed on real-time coordinate data of the vehicle-mounted tunnel lining detection device, real-time tunnel section information after two-dimensional coordinate registration, and three-dimensional real-time point cloud data by using a synchronous positioning and mapping SLAM algorithm, to obtain real-time point cloud map information, comprising:
carrying out coordinate fusion registration on the real-time tunnel section information after the real-time coordinate data and the two-dimensional coordinate registration of the vehicle-mounted tunnel lining detection device and the three-dimensional real-time point cloud data, and determining the position information of the obstacle in the tunnel and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information;
combining the barrier position information in the tunnel with the two-dimensional section image information in the real-time tunnel section information after the two-dimensional coordinate registration to perform barrier feature recognition, so as to obtain barrier feature information in the tunnel;
Analyzing the gesture of the vehicle-mounted tunnel lining detection device according to the real-time coordinate data of the vehicle-mounted tunnel lining detection device, and predicting envelope path information of the vehicle-mounted tunnel lining detection device;
and carrying out real-time mapping according to the position information of the obstacle in the tunnel, the characteristic information of the obstacle in the tunnel, the enveloping path information of the vehicle-mounted tunnel lining detection device and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information to obtain real-time point cloud map information.
5. The method of claim 1, wherein the interference path information is three-dimensional coordinate difference information between an envelope path of the in-vehicle tunnel lining detection device and a position of an obstacle in the tunnel.
6. The method of claim 5, wherein determining a real-time obstacle avoidance strategy for the in-vehicle tunnel lining inspection device based on the interference path information comprises:
decomposing three-dimensional coordinate difference information between an enveloping path of the vehicle-mounted tunnel lining detection device and the position of an obstacle in the tunnel to obtain longitudinal distance between the vehicle-mounted tunnel lining detection device and the position of the obstacle and two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
Determining obstacle avoidance actions of the vehicle-mounted tunnel lining detection device and action amplitudes corresponding to the obstacle avoidance actions according to two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining the running speed of the vehicle-mounted tunnel lining detection device according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position;
and determining the traveling speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device as a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device.
7. The method as recited in claim 6, further comprising:
and sending collision risk prompt information according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position.
8. The utility model provides a real-time obstacle avoidance device of on-vehicle tunnel lining detection device which characterized in that includes:
the data acquisition module is used for acquiring three-dimensional real-time point cloud data acquired by a sensor arranged on the vehicle-mounted tunnel lining detection device when the vehicle-mounted tunnel lining detection device performs operation on a tunnel at a preset speed; acquiring real-time tunnel section information acquired by a camera arranged on a vehicle-mounted tunnel lining detection device; acquiring real-time coordinate data of a vehicle-mounted tunnel lining detection device;
The positioning and mapping module is used for carrying out real-time mapping on the three-dimensional real-time point cloud data, the real-time tunnel section information and the real-time coordinate data of the vehicle-mounted tunnel lining detection device by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information; the real-time point cloud map information comprises a vehicle-mounted tunnel lining detection device, relative position relation information between an obstacle in a tunnel and real-time tunnel section information, and envelope path information of the vehicle-mounted tunnel lining detection device;
the interference information determining module is used for determining interference path information between an envelope path of the vehicle-mounted tunnel lining detecting device and the position of the obstacle in the tunnel according to the relative position relation information among the vehicle-mounted tunnel lining detecting device, the obstacle information in the tunnel and the real-time tunnel section information and the envelope path information of the vehicle-mounted tunnel lining detecting device;
the strategy generation module is used for determining a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device according to the interference path information, wherein the real-time obstacle avoidance strategy comprises the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device;
the execution module is used for controlling the vehicle-mounted tunnel lining detection device to avoid the obstacle in real time according to the running speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device.
9. The apparatus of claim 8, wherein the real-time tunnel section information comprises two-dimensional section profile coordinate data and two-dimensional section image information.
10. The apparatus of claim 9, further comprising a coordinate registration module for real-time mapping the three-dimensional real-time point cloud data, the real-time tunnel section information, and the real-time coordinate data of the on-vehicle tunnel lining detection apparatus using a synchronous positioning and mapping SLAM algorithm before the positioning and mapping module obtains the real-time point cloud map information:
carrying out two-dimensional coordinate registration on the two-dimensional section contour coordinate data by taking the real-time coordinate data of the vehicle-mounted tunnel lining detection device as a reference system to obtain real-time tunnel section information after the two-dimensional coordinate registration;
the positioning and mapping module is specifically used for:
and carrying out real-time mapping on the real-time coordinate data of the vehicle-mounted tunnel lining detection device, the real-time tunnel section information after two-dimensional coordinate registration and the three-dimensional real-time point cloud data by utilizing a synchronous positioning and mapping SLAM algorithm to obtain real-time point cloud map information.
11. The apparatus of claim 10, wherein the positioning and mapping module is configured to:
Carrying out coordinate fusion registration on the real-time tunnel section information after the real-time coordinate data and the two-dimensional coordinate registration of the vehicle-mounted tunnel lining detection device and the three-dimensional real-time point cloud data, and determining the position information of the obstacle in the tunnel and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information;
combining the barrier position information in the tunnel with the two-dimensional section image information in the real-time tunnel section information after the two-dimensional coordinate registration to perform barrier feature recognition, so as to obtain barrier feature information in the tunnel;
analyzing the gesture of the vehicle-mounted tunnel lining detection device according to the real-time coordinate data of the vehicle-mounted tunnel lining detection device, and predicting envelope path information of the vehicle-mounted tunnel lining detection device;
and carrying out real-time mapping according to the position information of the obstacle in the tunnel, the characteristic information of the obstacle in the tunnel, the enveloping path information of the vehicle-mounted tunnel lining detection device and the relative position relation information among the vehicle-mounted tunnel lining detection device, the obstacle in the tunnel and the real-time tunnel section information to obtain real-time point cloud map information.
12. The apparatus of claim 8, wherein the interference path information is three-dimensional coordinate difference information between an envelope path of the in-vehicle tunnel lining detection apparatus and a position of an obstacle in the tunnel.
13. The apparatus of claim 12, wherein the interference information determining module is specifically configured to:
decomposing three-dimensional coordinate difference information between an enveloping path of the vehicle-mounted tunnel lining detection device and the position of an obstacle in the tunnel to obtain longitudinal distance between the vehicle-mounted tunnel lining detection device and the position of the obstacle and two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining obstacle avoidance actions of the vehicle-mounted tunnel lining detection device and action amplitudes corresponding to the obstacle avoidance actions according to two-dimensional projection image information of the vehicle-mounted tunnel lining detection device in real-time tunnel section information;
determining the running speed of the vehicle-mounted tunnel lining detection device according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position;
and determining the traveling speed, the obstacle avoidance action and the action amplitude corresponding to the obstacle avoidance action of the vehicle-mounted tunnel lining detection device as a real-time obstacle avoidance strategy of the vehicle-mounted tunnel lining detection device.
14. The apparatus of claim 13, further comprising a risk prompting module to:
and sending collision risk prompt information according to the longitudinal distance between the vehicle-mounted tunnel lining detection device and the obstacle position.
15. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 7 when executing the computer program.
16. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 7.
17. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any of claims 1 to 7.
CN202310143301.9A 2023-02-10 2023-02-10 Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device Pending CN116166016A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310143301.9A CN116166016A (en) 2023-02-10 2023-02-10 Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310143301.9A CN116166016A (en) 2023-02-10 2023-02-10 Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device

Publications (1)

Publication Number Publication Date
CN116166016A true CN116166016A (en) 2023-05-26

Family

ID=86414460

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310143301.9A Pending CN116166016A (en) 2023-02-10 2023-02-10 Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device

Country Status (1)

Country Link
CN (1) CN116166016A (en)

Similar Documents

Publication Publication Date Title
CN103455144B (en) Vehicle-mounted man-machine interaction system and method
CN106257242B (en) Unit and method for adjusting road boundaries
CN112665556B (en) Generating a three-dimensional map of a scene using passive and active measurements
CN112132896B (en) Method and system for detecting states of trackside equipment
Bounini et al. Autonomous vehicle and real time road lanes detection and tracking
JP5023186B2 (en) Object motion detection system based on combination of 3D warping technique and proper object motion (POM) detection
Marín-Plaza et al. Stereo vision-based local occupancy grid map for autonomous navigation in ros
CN109085829B (en) Dynamic and static target identification method
CN101941438B (en) Intelligent detection control device and method of safe interval
EP3842751B1 (en) System and method of generating high-definition map based on camera
WO2015024407A1 (en) Power robot based binocular vision navigation system and method based on
CN110766785B (en) Real-time positioning and three-dimensional reconstruction device and method for underground pipeline
CN111680611B (en) Road trafficability detection method, system and equipment
CN110341621B (en) Obstacle detection method and device
CN110033621A (en) A kind of hazardous vehicles detection method, apparatus and system
CN112068152A (en) Method and system for simultaneous 2D localization and 2D map creation using a 3D scanner
Rato et al. LIDAR based detection of road boundaries using the density of accumulated point clouds and their gradients
JP6263453B2 (en) Momentum estimation device and program
CN115439621A (en) Three-dimensional map reconstruction and target detection method for coal mine underground inspection robot
CN112684797A (en) Obstacle map construction method
CN116166016A (en) Real-time obstacle avoidance method and device for vehicle-mounted tunnel lining detection device
CN116129669A (en) Parking space evaluation method, system, equipment and medium based on laser radar
CN116030686A (en) Human-vehicle road environment data testing method, medium and system of virtual simulation environment
CN112241717B (en) Front vehicle detection method, and training acquisition method and device of front vehicle detection model
CN115063771A (en) Error correction method, system, storage medium and device for distance detection of obstacle

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