Tuyere scene autonomous navigation system and method based on point cloud fusion

Through the air vent scene autonomous navigation system based on point cloud fusion, 16-line lidar, IMU inertial measuring instrument and other sensors are used to realize high-precision positioning and autonomous navigation of the air vent site, solving the environmental damage problem of traditional manual temperature measurement work, and realizing the High frequency and high accuracy temperature monitoring at the air outlet site.

CN118999544AActive Publication Date: 2024-11-22МААНЬШАНЬ АЙРОН ЭНД СТИЛ КО ЛТД
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411113548.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-22
Estimated Expiration
2044-08-14

AI Technical Summary

Technical Problem

Traditional air outlet temperature measurement methods rely on manual handheld thermometers, which cause great damage to the human body in the on-site environment and reduce the feasibility of temperature measurement.

Method used

The air vent scene autonomous navigation system based on point cloud fusion is adopted, and the air vent and obstacle information is obtained through sensors such as 16-line lidar, IMU inertial measuring instrument, depth camera, etc., and combined with the odometer fusion algorithm and particle set to express confidence, realizing the robot car's High-precision positioning and autonomous navigation ensure accurate temperature measurement in high-temperature and high-pressure environments.

Benefits of technology

High frequency and high-precision temperature measurement at the air vent site is realized, ensuring multiple inspections every day, instead of manual inspections, significantly improving the efficiency and safety of air vent temperature data monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118999544A_ABST
    Figure CN118999544A_ABST
Patent Text Reader

Abstract

The invention discloses a tuyere scene autonomous navigation system and method based on point cloud fusion, and belongs to the technical field of blast furnace production process control. The system comprises a robot trolley, and a 16-line laser radar, an IMU inertial measurement instrument, a depth camera, a holder, a temperature and humidity sensor, a gas sensor, a sound intensity sensor and a database server are sequentially arranged on the robot trolley. According to the invention, the problem that the environment greatly damages the human body due to the fact that a temperature measuring gun is manually held to measure the temperature at the tuyere in the prior art is solved, the tuyere and obstacle information is better obtained by adopting a point cloud fusion technology, and more accurate coarse positioning is provided for the robot trolley by adopting an odometer fusion algorithm; the IMU inertial measurement instrument is used for collecting information of a rotation angle and a horizontal angle of the robot trolley, high-precision positioning work is completed, and accurate temperature measurement of a temperature measurement point position is ensured; a positioning autonomous navigation scheme is adopted to ensure that the robot trolley accurately walks to a temperature measurement point in a high-temperature and high-pressure environment, and high-frequency work every day is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace production process control, and in particular to an autonomous navigation system and method for a tuyere scene based on point cloud fusion. Background Art

[0002] The blast furnace tuyere is on the blast furnace of the iron-making plant. The high-temperature hot air blown into the blast furnace tuyere and the coke at the bottom of the furnace are oxidized and burned to generate CO. CO reduces the iron that originally existed in the form of oxides at high temperature. It is the most important part of steelmaking and ironmaking. The material of the blast furnace tuyere is mainly high-purity copper. Considering the strength, rigidity and crack resistance of the tuyere, the material state includes forging, copper plate rolling and casting. The copper plate rolling tuyere has low weight and low cost, but if the wall thickness is too thin and the rigidity is insufficient, it is easy to deform. Because the blast furnace tuyere is cooled by water to keep the tuyere body running at a low temperature to maintain strength and rigidity, the purity of copper is very important.

[0003] The traditional method of checking air vents is to measure the temperature of the air vents on site using a manual handheld temperature measuring gun. The on-site environment is also very harmful to the human body, thus reducing the feasibility of existing on-site air vent temperature measurement work.

[0004] After searching, the publication number is CN217687263U, which discloses a robot identification and positioning navigation system based on the ROS system. The solution runs the ROS operating system on an industrial computer, and simultaneously connects to a variety of sensors such as image recognition, UWB positioning, laser radar, infrared detection, and ultrasonic detection, and then the industrial computer controls the movement of the robot chassis. The target recognition, autonomous obstacle avoidance, autonomous positioning, mapping, and path planning related software design are implemented on ROS to achieve robot identification and autonomous positioning navigation; however, the radar and sensor fusion methods used in the present invention are different, making it more intelligent to conduct autonomous patrol and temperature detection work on the vent platform. Summary of the invention

[0005] The purpose of the present invention is to provide an autonomous navigation system and method for air vent scenes based on point cloud fusion, which adopts point cloud fusion technology to better obtain air vent and obstacle information, and adopts odometer fusion algorithm to give a robot car more accurate coarse positioning; collects the rotation angle and horizontal angle information of the robot car through the IMU inertial measurement instrument to complete high-precision positioning work, ensuring accurate temperature measurement of temperature measurement points; adopts positioning autonomous navigation scheme to ensure that the robot car accurately walks to the temperature measurement point in a high temperature and high pressure environment, ensuring high-frequency operation every day, and solving the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An autonomous navigation system for vent scenes based on point cloud fusion includes: a robot car, characterized in that: the robot car is used to autonomously navigate to the temperature measurement point of the vent scene, and the robot car is sequentially provided with a 16-line laser radar, an IMU inertial measurement unit, a depth camera, a pan-tilt head, a temperature and humidity sensor, a gas sensor, a sound intensity sensor and a database server, and the database server is loaded with programming software, screen editing software and a database, and the programming software includes point cloud fusion software and autonomous navigation software.

[0008] Furthermore, the point cloud fusion software includes:

[0009] The point cloud fusion module is used to fuse the information obtained by the 16-line laser radar and the depth camera to obtain multi-dimensional fused point cloud data of the wind outlet scene;

[0010] Point cloud optimization module, used to optimize the multi-dimensional fusion point cloud data of the vent scene into point cloud information suitable for environmental matching;

[0011] Point cloud matching module is used to match the matched point cloud information with the established map point cloud information to determine the correct temperature measurement point;

[0012] The path planning module is used to plan the local path of the robot car according to the established temperature measurement points and the three-dimensional reality of the vent scene. The autonomous navigation software controls the robot car in real time according to the local path, and controls the robot car to avoid obstacles according to the point cloud data of the obstacle protrusions that do not match.

[0013] Furthermore, the multi-dimensional fusion point cloud data of the vent scene is optimized, specifically:

[0014] Delete the point cloud data on the ground, the point cloud data that is too far away, the useless point cloud data at the rear 90° intersection, and the point cloud data with too much overlap, and re-compress the simplified point cloud into 2D data.

[0015] Furthermore, after matching the matched point cloud information with the recorded map point cloud information, a set of M particles is used to represent the confidence, and the set expression formula is as follows:

[0016]

[0017] X t is the confidence level, M is the total number of particles;

[0018] The initial confidence is obtained by distributing M randomly generated particles, and the motion model is used for sampling. The particles are used with the current confidence as the starting point, and the importance weights of the particles are determined using the measurement model. Then, the positioning accuracy of the temperature measurement point is determined by increasing the total number of particles M. After determining the temperature measurement point, the pan-tilt head autonomously rotates to the preset point for infrared temperature measurement. After the temperature measurement is completed, the autonomous navigation software navigates the robot car to the next point.

[0019] Furthermore, the 16-line laser radar is used to collect multi-dimensional 3D image information of the vent scene to obtain a multi-dimensional 3D model of the vent scene, and the depth camera is used to collect spatial distance information of the vent scene.

[0020] Furthermore, the IMU inertial measurement unit is used to collect the rotation angle and horizontal angle information of the robot car in real time, and the gimbal is used to issue control instructions to the temperature and humidity sensor, gas sensor and sound intensity sensor.

[0021] Furthermore, the temperature and humidity sensor, gas sensor and sound intensity sensor are used to collect temperature and humidity data, gas concentration data and on-site sound wave data in the vent scene.

[0022] Furthermore, the 16-line laser radar, IMU inertial measurement unit, depth camera, gimbal, temperature and humidity sensor, gas sensor, sound intensity sensor and database server are all electrically connected to the industrial control machine through wireless transmission technology.

[0023] An autonomous navigation method for a vent scene based on point cloud fusion includes the following steps:

[0024] Step 1: Connect each sensor through a wireless communication network, and connect each sensor to an industrial computer;

[0025] Integrate each sensor into the industrial computer and publish topics to publish the real-time frequency of sensor data.

[0026] Step 2: Integrate and calculate to publish new odometer odom information;

[0027] The motion data of the robot chassis and the data of the IMU are integrated to correct the odometer information, where odom_trans.transform.translation.x = x + (vx*cos(th)-vy*sin(th))*dt;

[0028] odom_trans.transform.translation.y=y+(vx*sin(th)+vy*cos(th))*dt;

[0029] odom_trans.transform.rotation=tf::createQuaternionMsgFromYaw(th).

[0030] Step 3: Integrate the point cloud data of the depth camera and the point cloud data of the 16-line lidar;

[0031] According to the positions of the 16-line laser radar and the depth camera, the TF transformation relationship of the two sensors is added to the base_link coordinate system, and the two parts of the point cloud data are fused to reduce the overlapped point cloud data in the front.

[0032] Step 4: Optimize the integrated point cloud data;

[0033] The integrated point cloud data is further optimized by deleting point cloud data on the ground, point cloud data that is too far away, useless point cloud data at 90° in the back, and point cloud data with too much overlap, and then the simplified point cloud is recompressed into 2D data.

[0034] Step 5: Compare with the established map;

[0035] The integrated point cloud data obtained in step 4 is matched and compared with the 2D data and the pre-established map, and the possible location of the robot is provided according to the location weight information, and the location with poor matching is deleted; various existing positioning information is then integrated to obtain a more accurate positioning location; and a local path planning algorithm is performed based on the location, and the autonomous navigation software controls the robot car to move in real time along the path; if there is an obstacle protrusion that does not match the point cloud data, the autonomous navigation software controls the robot car to perform obstacle avoidance actions

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention collects multi-dimensional 3D image information and spatial distance information at the vent site, and fuses the two into point clouds to obtain multi-dimensional point cloud data of the vent site, so as to better obtain information about the vent and obstacles; and adopts an odometer odom fusion algorithm to obtain a more accurate odometer, giving the robot car a more accurate rough positioning; through the IMU inertial measurement instrument to perform point cloud data fusion, the rotation angle and horizontal angle information of the robot car can be collected, which can have a better effect on point cloud data processing, thereby completing a more high-precision positioning work and ensuring accurate temperature measurement of the temperature measurement point; adopting a positioning autonomous navigation solution to ensure that the robot car accurately walks to the temperature measurement point under a high temperature and high pressure environment, can ensure the high-frequency work of multiple inspections at the vent site environment every day. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram of matching the initially fused point cloud information of the present invention with a map;

[0039] Figure 2 A schematic diagram of matching the processed point cloud information of the present invention with a map;

[0040] Figure 3 It is a schematic diagram of the working principle of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In order to solve the problem that the traditional method of checking the air outlet is to measure the temperature of the air outlet on site by manually holding a temperature measuring gun, the on-site environment is also very harmful to the human body, thus reducing the technical problem of the feasibility of the existing on-site air outlet temperature measurement work, please refer to Figure 1-Figure 3 , this embodiment provides the following technical solutions:

[0043] An autonomous navigation system for vent scenes based on point cloud fusion includes: a robot car, characterized in that: the robot car is used to autonomously navigate to the temperature measurement point of the vent scene, and a 16-line laser radar is sequentially arranged on the robot car, and the 16-line laser radar is used to collect multi-dimensional 3D image information of the vent scene, so as to obtain a multi-dimensional 3D model of the vent scene; an IMU inertial measurement instrument, which is used to collect the rotation angle and horizontal angle information of the robot car in real time, and can play a better effect on point cloud data processing, and can complete more high-precision positioning work to ensure accurate temperature measurement of the temperature measurement point; a depth camera, which is used to collect spatial distance information of the vent scene, and can accurately know the distance of each point in the vent scene image from the camera, and then match it with the x, y coordinates in the 2D image, so as to obtain the three-dimensional spatial coordinates of each point in the vent scene; the three-dimensional actual situation of the vent scene can be restored through the three-dimensional coordinates, so as to Subsequently, it will be point cloud fused with the information obtained by the 16-line laser radar; the gimbal, the gimbal is used to issue control instructions to the temperature and humidity sensor, gas sensor and sound intensity sensor; the temperature and humidity sensor, gas sensor, sound intensity sensor and database server, the temperature and humidity sensor, gas sensor and sound intensity sensor are used to collect temperature and humidity data, gas concentration data and on-site sound wave data in the vent scene, the database server is loaded with programming software, screen editing software and database, the programming software includes point cloud fusion software and autonomous navigation software, and the 16-line laser radar, IMU inertial measurement instrument, depth camera, gimbal, temperature and humidity sensor, gas sensor, sound intensity sensor and database server are electrically connected to the industrial control machine through wireless transmission technology, each sensor is integrated into the industrial control machine, and the real-time frequency of the sensor data is published by publishing topics, so that the client can grasp the temperature and humidity information of the vent scene and the driving progress of the robot car in real time through the industrial control machine.

[0044] Point cloud fusion software, including:

[0045] The point cloud fusion module is used to integrate the information obtained by the 16-line laser radar and the depth camera into point cloud data to obtain multi-dimensional fused point cloud data of the wind outlet scene. It is mainly used to better obtain information about the wind outlet scene and obstacles, make detailed plans for the robot car's travel path, mark obstacles, and effectively control the robot car to avoid obstacles autonomously.

[0046] The point cloud optimization module is used to optimize the multi-dimensional fused point cloud data of the vent scene into point cloud information suitable for environmental matching; specifically: delete the point cloud data on the ground, the point cloud data that is too far away, the useless point cloud data at the rear 90° intersection, and the point cloud data with too much overlap, and re-compress the simplified point cloud into 2D data; it is mainly used to optimize the authenticity of the image information of the vent scene, highlight the important local paths, and provide more accurate path information and positioning information for the robot car.

[0047] The point cloud matching module is used to match the matched point cloud information with the established map point cloud information. The confidence is expressed by a set of M particles. The set expression formula is as follows:

[0048]

[0049] X t is the confidence level, M is the total number of particles;

[0050] The initial confidence is obtained by distributing M randomly generated particles, and the motion model is used for sampling. The particles are used with the current confidence as the starting point, and the importance weight of the particles is determined by the measurement model. Then, the positioning accuracy of the temperature measurement point is determined by increasing the total number of particles M. After the temperature measurement point is determined, the pan-tilt head autonomously rotates to the preset point for infrared temperature measurement. After the temperature measurement work is completed, the autonomous navigation software navigates the robot car to the next point.

[0051] The path planning module is used to plan the local path of the robot car according to the established temperature measurement points and the three-dimensional reality of the vent scene. The autonomous navigation software controls the robot car in real time according to the local path, and controls the robot car to avoid obstacles according to the point cloud data of the obstacle protrusions that do not match.

[0052] Specifically, by collecting multi-dimensional 3D image information and spatial distance information at the vent site, the two are fused into point cloud to obtain multi-dimensional point cloud data of the vent site; and the odometer odom fusion algorithm is used, combined with the rotation angle and horizontal angle information of the robot car collected by the IMU inertial measurement device, through the processing of point cloud data, it can achieve a better vent scene restoration effect, give the robot car a more accurate coarse positioning, and enable the robot car to complete more high-precision positioning work, ensuring accurate temperature measurement of temperature measurement points; the positioning autonomous navigation solution is used to ensure that the robot car accurately walks to the temperature measurement point under high temperature and high pressure environment, and the autonomous navigation and autonomous obstacle avoidance functions of the fused information can ensure the high-frequency work of multiple inspections of the vent site environment every day; through 12 temperature measurement inspections per day, the temperature data changes of all vents on the vent platform can be monitored in real time, and the number of inspections greatly exceeds the number of manual inspections, which can replace manual inspections.

[0053] In this embodiment, an autonomous navigation method for a vent scene based on point cloud fusion is provided, and the specific operation steps are as follows:

[0054] Step 1: Connect each sensor through a wireless communication network, and connect each sensor to an industrial computer;

[0055] Integrate each sensor into the industrial computer and publish topics to publish the real-time frequency of sensor data.

[0056] Step 2: Integrate and calculate to publish new odometer odom information;

[0057] The motion data of the robot chassis and the data of the IMU are integrated to correct the odometer information, where odom_trans.transform.translation.x = x + (vx*cos(th)-vy*sin(th))*dt;

[0058] odom_trans.transform.translation.y=y+(vx*sin(th)+vy*cos(th))*dt;

[0059] odom_trans.transform.rotation=tf::createQuaternionMsgFromYaw(th).

[0060] Step 3: Integrate the point cloud data of the depth camera and the point cloud data of the 16-line lidar;

[0061] According to the positions of the 16-line laser radar and the depth camera, the TF transformation relationship of the two sensors is added to the base_link coordinate system, and the two parts of the point cloud data are fused to reduce the overlapped point cloud data in the front.

[0062] Step 4: Optimize the integrated point cloud data;

[0063] The integrated point cloud data is further optimized by deleting point cloud data on the ground, point cloud data that is too far away, useless point cloud data at 90° in the back, and point cloud data with too much overlap, etc., and then the simplified point cloud is recompressed into 2D data.

[0064] Step 5: Compare with the established map;

[0065] According to the integrated point cloud data obtained in step 4, the 2D data and the map established at the beginning are matched and compared, and the possible location of the robot is provided according to the position weight information, and the location with very poor matching is deleted; then various existing positioning information is integrated to obtain a more accurate positioning position; and a local path planning algorithm is performed according to the position, and the autonomous navigation software controls the robot car to move in real time according to the path; if there is an obstacle protrusion that does not match the point cloud data, the autonomous navigation software controls the robot car to avoid the obstacle, thereby realizing the functions of autonomous navigation and autonomous obstacle avoidance of the robot car in the wind outlet scene.

[0066] The beneficial effects achieved by the above content are: by adopting point cloud fusion technology to better obtain information on vents and obstacles, and using odometer fusion algorithm to give the robot car a more accurate coarse positioning; by using the IMU inertial measurement device to collect the rotation angle and horizontal angle information of the robot car, high-precision positioning is completed to ensure accurate temperature measurement of the temperature measurement points; the positioning autonomous navigation solution is used to ensure that the robot car accurately reaches the temperature measurement point in a high temperature and high pressure environment, ensuring high-frequency work every day.

[0067] Working principle: By collecting multi-dimensional 3D image information and spatial distance information at the vent site, the two are fused into point cloud to obtain multi-dimensional point cloud data at the vent site; the odometer odom fusion algorithm is used, combined with the rotation angle and horizontal angle information of the robot car collected by the IMU inertial measurement device, so that the robot car can complete more high-precision positioning work and ensure accurate temperature measurement at the temperature measurement points; the positioning autonomous navigation solution is used to ensure that the robot car can realize autonomous navigation and autonomous obstacle avoidance functions in a high temperature and high pressure environment; through 12 temperature measurement inspections per day, the temperature data changes of all vents on the vent platform can be monitored in real time, thereby replacing manual inspections.

[0068] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusions, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0069] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An autonomous navigation system for wind outlet scenes based on point cloud fusion, comprising: A robot car, characterized in that: the robot car is used for autonomous navigation to the temperature measurement point of the vent scene, and is sequentially provided with a 16-line laser radar, an IMU inertial measurement instrument, a depth camera, a pan-tilt, a temperature and humidity sensor, a gas sensor, a sound intensity sensor and a database server. The 16-line laser radar, the IMU inertial measurement instrument, the depth camera, the temperature and humidity sensor, the gas sensor and the sound intensity sensor are all connected to the pan-tilt through wireless transmission technology, and the pan-tilt is used to control the operating status of the above-mentioned sensing equipment. The database server is loaded with programming software, screen editing software and a database, and the programming software includes point cloud fusion software and autonomous navigation software.

2. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 1 is characterized by: The point cloud fusion software includes: The point cloud fusion module is used to fuse the information obtained by the 16-line laser radar and the depth camera to obtain multi-dimensional fused point cloud data of the wind outlet scene; Point cloud optimization module, used to optimize the multi-dimensional fusion point cloud data of the vent scene into point cloud information suitable for environmental matching; Point cloud matching module is used to match the matched point cloud information with the established map point cloud information to determine the correct temperature measurement point; The path planning module is used to plan the local path of the robot car according to the established temperature measurement points and the three-dimensional reality of the vent scene. The autonomous navigation software controls the robot car in real time according to the local path, and controls the robot car to avoid obstacles according to the point cloud data of the obstacle protrusions that do not match.

3. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 2 is characterized by: The multi-dimensional fusion point cloud data of the vent scene is optimized as follows: Delete the point cloud data on the ground, the point cloud data that is too far away, the useless point cloud data at the rear 90° intersection, and the point cloud data with too much overlap, and re-compress the simplified point cloud into 2D data.

4. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 2 is characterized by: After matching the matched point cloud information with the recorded map point cloud information, a set of M particles is used to represent the confidence. The set expression formula is as follows: X t is the confidence level, M is the total number of particles; The initial confidence is obtained by distributing M randomly generated particles, and the motion model is used for sampling. The particles are used with the current confidence as the starting point, and the importance weights of the particles are determined using the measurement model. Then, the positioning accuracy of the temperature measurement point is determined by increasing the total number of particles M. After determining the temperature measurement point, the pan-tilt head autonomously rotates to the preset point for infrared temperature measurement. After the temperature measurement is completed, the autonomous navigation software navigates the robot car to the next point.

5. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 1 is characterized by: The 16-line laser radar is used to collect multi-dimensional 3D image information of the vent scene to obtain a multi-dimensional 3D model of the vent scene, and the depth camera is used to collect spatial distance information of the vent scene.

6. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 1 is characterized by: The IMU inertial measurement unit is used to collect the rotation angle and horizontal angle information of the robot car in real time, and the gimbal is used to issue control instructions to the temperature and humidity sensor, gas sensor and sound intensity sensor.

7. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 1 is characterized by: The temperature and humidity sensor, gas sensor and sound intensity sensor are used to collect temperature and humidity data, gas concentration data and on-site sound wave data in the vent scene.

8. The point cloud fusion-based autonomous navigation system for vent scenes according to claim 1 is characterized by: The 16-line laser radar, IMU inertial measurement unit, depth camera, gimbal, temperature and humidity sensor, gas sensor, sound intensity sensor and database server are all electrically connected to the industrial control machine through wireless transmission technology.

9. An autonomous navigation method for a vent scene based on point cloud fusion, implemented based on an autonomous navigation system for a vent scene based on point cloud fusion according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Connect each sensor through a wireless communication network, and connect each sensor to an industrial computer; Integrate each sensor into the industrial computer and publish topics to publish the real-time frequency of sensor data; Step 2: Integrate and calculate to publish new odometer odom information; The motion data of the robot chassis and the data of the IMU are integrated to correct the odometer information, where odom_trans.transform.translation.x = x + (vx*cos(th)-vy*sin(th))*dt; odom_trans.transform.translation.y=y+(vx*sin(th)+vy*cos(th))*dt; odom_trans.transform.rotation=tf::createQuaternionMsgFromYaw(th); Step 3: Integrate the point cloud data of the depth camera and the point cloud data of the 16-line lidar; According to the positions of the 16-line laser radar and the depth camera, the TF transformation relationship of the two sensors is added to the base_link coordinate system, and the point cloud data of the two parts are fused to reduce the overlapped point cloud data in the front. Step 4: Optimize the integrated point cloud data; The integrated point cloud data is further optimized by deleting point cloud data on the ground, point cloud data that is too far away, useless point cloud data at 90° intersection at the rear, and point cloud data that overlaps too much, and then the simplified point cloud is recompressed into 2D data; Step 5: Compare with the established map; The integrated point cloud data obtained in step 4 is matched and compared with the 2D data and the pre-established map, and the possible location of the robot is provided according to the position weight information, and the location with poor matching is deleted; various existing positioning information is then integrated to obtain a more accurate positioning location; and a local path planning algorithm is performed based on the location, and the autonomous navigation software controls the robot car to move in real time along the path; if there is an obstacle protrusion that does not match the point cloud data, the autonomous navigation software controls the robot car to perform obstacle avoidance actions.

Citation Information

Patent Citations

  • Unmanned inspection robot for spinning workshop

    CN111515918A

  • Security patrol robot system applied to smart park

    CN113110502A

  • Three-dimensional visualization method applied to intelligent operation and maintenance system of transformer substation

    CN113177086A

  • Convolutional neural network-based wheel-type inspection robot and method for substation

    CN117270545A

  • System and method for structural inspection and construction estimation using an unmanned aerial vehicle

    US20170206648A1