Adaptive autonomous navigation system for coal mine inspection robots: overcoming intersection challenges

Abstract

Purpose

In response to the navigation challenges faced by coal mine tunnel inspection robots in semistructured underground intersection environments, many current studies rely on structured map-based planning algorithms and trajectory tracking techniques. However, this approach is highly dependent on the accuracy of the global map, which can lead to deviations from the predetermined route or collisions with obstacles. To improve the environmental adaptability and navigation precision of the robot, this paper aims to propose an adaptive navigation system based on a two-dimensional (2D) LiDAR.

Design/methodology/approach

Leveraging the geometric features of coal mine tunnel environments, the clustering and fitting algorithms are used to construct a geometric model within the navigation system. This not only reduces the complexity of the navigation system but also optimizes local positioning. By constructing a local potential field, there is no need for path-fitting planning, thus enhancing the robot’s adaptability in intersection environments. The feasibility of the algorithm principles is validated through MATLAB and robot operating system simulations in this paper.

Findings

The experiments demonstrate that this method enables autonomous driving and optimized positioning capabilities in harsh environments, with high real-time performance and environmental adaptability, achieving a positioning error rate of less than 3%.

Originality/value

This paper presents an adaptive navigation system for a coal mine tunnel inspection robot using a 2D LiDAR sensor. The system improves robot attitude estimation and motion control accuracy to ensure safe and reliable navigation, especially at tunnel intersections.

Citation

Wang, H., Li, C., Liang, W., Wang, D. and Yao, L. (2024), "Adaptive autonomous navigation system for coal mine inspection robots: overcoming intersection challenges", Industrial Robot, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/IR-11-2023-0295