Search results

Recently there has been a strong trend towards automation in the mine industry. This paper seeks to describe and analyse an algorithm that can be used as a part of an infrastructure‐free reactive navigation system for autonomous vehicles in underground mines.

The idea presented here to enable infrastructure‐free autonomous navigation is to combine reactive behaviours for tunnel following, with topological localization. To assess the reliability and precision of the corridor detection algorithm real data recorded in both indoor and mine environments have been used.

In the research it was found that the algorithm is able to reliably detect corridors even in difficult environments such as office corridors where a large part of the walls are made of glass or in mine tunnels with a high intensity of intersections. It was also concluded that the algorithm provides good enough precision and robustness to noise in the data to enable reactive tunnel following.

This paper presents an algorithm for corridor detection, intended to be used in combination with reactive behaviours for tunnel following in underground mines. To enable fully autonomous navigation, functionality to detect and turn at intersections also needs to be developed.

This research shows that corridor detection can be used for reactive tunnel following in certain underground mine types, and that the concept of using reactive tunnel following in combination with topological localization is worthy of continued development.

This paper has presented a new algorithm for corridor detection based on the Hough transform. The algorithm is robust to noise in the data and can reliably detect corridors even where the surfaces of the walls are uneven and slightly curved.