Research on Visual Positioning of a Roadheader and Construction of an Environment Map

Zhang, Wentao; Zhai, Guodong; Yue, Zhongwen; Pan, Tao; Cheng, Ran

doi:10.3390/app11114968

Cited by 11 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Karto algorithm is a typical SLAM algorithm based on graph optimization [11,12]. Highly optimized and non-iterative Cholesky matrix decompositions are used as the solver of the sparse linear system, and SPA (Sparse Pose Adjustment) is used to complete scan matching and loopback detection [13].…”

Section: Karto Slammentioning

confidence: 99%

Research and Implementation of Autonomous Navigation for Mobile Robots Based on SLAM Algorithm under ROS

Zhao

Liu

2022

Sensors

View full text Add to dashboard Cite

Aiming at the problems of low mapping accuracy, slow path planning efficiency, and high radar frequency requirements in the process of mobile robot mapping and navigation in an indoor environment, this paper proposes a four-wheel drive adaptive robot positioning and navigation system based on ROS. By comparing and analyzing the mapping effects of various 2D-SLAM algorithms (Gmapping, Karto SLAM, and Hector SLAM), the Karto SLAM algorithm is used for map building. By comparing the Dijkstra algorithm with the A* algorithm, the A* algorithm is used for heuristic searches, which improves the efficiency of path planning. The DWA algorithm is used for local path planning, and real-time path planning is carried out by combining sensor data, which have a good obstacle avoidance performance. The mathematical model of four-wheel adaptive robot sliding steering was established, and the URDF model of the mobile robot was established under a ROS system. The map environment was built in Gazebo, and the simulation experiment was carried out by integrating lidar and odometer data, so as to realize the functions of mobile robot scanning mapping and autonomous obstacle avoidance navigation. The communication between the ROS system and STM32 is realized, the packaging of the ROS chassis node is completed, and the ROS chassis node has the function of receiving speed commands and feeding back odometer data and TF transformation, and the slip rate of the four-wheel robot in situ steering is successfully measured, making the chassis pose more accurate. Simulation tests and experimental verification show that the system has a high precision in environment map building and can achieve accurate navigation tasks.

show abstract

Section: Karto Slammentioning

confidence: 99%

Research and Implementation of Autonomous Navigation for Mobile Robots Based on SLAM Algorithm under ROS

Zhao

Liu

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…is calculation method based on the recurrent neural network has been widely used in speech recognition, natural language processing, stock evaluation, and other issues [41][42][43].…”

Section: Neural Network Algorithm and Computermentioning

confidence: 99%

Computer Vision Positioning and Local Obstacle Avoidance Optimization Based on Neural Network Algorithm

Yang

Lei

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Due to the rapid development of social computerization and smart devices, there is an increasing demand for indoor positioning of mobile robots in the robotics field, so it is very important to realize the autonomous navigation of mobile robots. However, in indoor scenes, due to factors such as dark walls, the global positioning system cannot effectively locate, and the broadband and wired positioning technologies used indoors have problems such as base station laying and delay. Computer vision positioning technology has greatly improved the camera hardware due to its simple equipment and low cost. Compared with other sensor cameras, it is less affected by environmental changes, so visual positioning has received extensive attention. Image matching has become the most critical link in visual positioning. The accuracy, speed, and robustness of image matching directly determine the results of visual positioning, so image matching has become the main topic of this study. In this study, the neural network algorithm is systematically optimized, especially for the robot’s local obstacle avoidance, and an obstacle data acquisition method based on VGG16 and fast RCNN is proposed. In order to solve the problem that the semantic image segmentation algorithm based on AlexNet and ResNet is difficult to accurately obtain the information of multiple objects, and an image semantic segmentation algorithm combined with VGG16 is designed to classify the background and road in the image at the pixel level and capture the path boundary line. The collection of robot obstacle path information improves the speed and accuracy of highly automated local obstacle avoidance. This study uses neural network algorithms to systematically optimize computer vision positioning and also studies the accuracy optimization of local obstacle avoidance, aiming to promote its better development.

show abstract

“…the most difficult thing in such a working, and more precisely in the face, is to transport and install the elements of the roadway support [3] due to very little free space (fig. 1) [4,5]. this applies to all types of supports, mainly the yielding arch support type ŁP [6,7].…”

Section: Introductionmentioning

confidence: 99%

Computer-Aided Selection of the Stabilising System Parameters of the Mobile Transport and Assembly Manipulator in Mining Excavations

2023

Archives of Mining Sciences

View full text Add to dashboard Cite

Computer-Aided SeleCtion of the StAbiliSing SyStem pArAmeterS of the mobile trAnSport And ASSembly mAnipulAtor in mining exCAvAtionSShifting masses in a confined space in the company of other machines and devices, which limits the manoeuvring and transport area, poses a significant problem in every field of industry, especially with underground mining. the works involved in transporting and manoeuvring masses in underground workings are challenging and are most often performed using various auxiliary machines or manually. hence the need arose to develop a device carrying out activities related to the shifting of masses with the assumed maximum value. the device was created as a result of cooperation between fAMA sp. z o.o. and the AGh university of Science and technology in Kraków, poland. the mining modular transport and assembly unit (Mzt-M) enables assembling and transporting various masses, especially the elements of the roadway support in the face. the primary function of this device is its movement in the excavation along with the transported mass and delivering it to a specific place. therefore, an important issue is to ensure the module's stability in different phases of its operation (lifting, transport, manoeuvring, feeding, lowering) due to the limited space in the excavation. that is why an analytical model and specialised software were created to determine the design parameters of the device as a function of its operating phases, especially the counterweight's mass. As previously mentioned, an analytical model (physical, mathematical) with equations and applications written in Microsoft Visual Studio and Matlab was used for this purpose. it is beneficial at the design or construction changes stage. calculation results are documented in the form of numerical summaries and graphs.

show abstract

Research on Visual Positioning of a Roadheader and Construction of an Environment Map

Cited by 11 publications

References 39 publications

Research and Implementation of Autonomous Navigation for Mobile Robots Based on SLAM Algorithm under ROS

Research and Implementation of Autonomous Navigation for Mobile Robots Based on SLAM Algorithm under ROS

Computer Vision Positioning and Local Obstacle Avoidance Optimization Based on Neural Network Algorithm

Computer-Aided Selection of the Stabilising System Parameters of the Mobile Transport and Assembly Manipulator in Mining Excavations

Contact Info

Product

Resources

About