Laser‐based corridor detection for reactive navigation

Abstract

For mobile robots operating in real-world environments, reactive navigation is a useful complement (or even replacement) to pure plan-based metric navigation. Reactive navigation is performed with respect to local perceived features, rather than a global metric reference frame, and can provide reduced installation costs, increased flexibility, and robustness to changes in the environment. To be effective, however, reactive navigation requires fast and reliable perception of the relevant features in the environment. Corridor-like structures are one of the most common features that are used for this purpose. In this paper, we propose a new method for corridor detection from laser data, based on the Hough transform, which is fast, reliable, and noise tolerant. We describe the algorithm, report an extensive experimental evaluation of its performance, and motivate the research with a real application involving the autonomous operation of a loader vehicle in an underground mine.

Online Tracking Control of Autonomous Mobile Robot Utilizing Optimal Formulation

“…Since the major objective is to put obstacles avoidance and autonomous movement into practice in this study, a simple curve fitting suffices for defining functions of obstacles' shapes, and the functions are defined as gatherings of line segments. Therefore, the Hough transform (7) (8) , which can recognize obstacles' shapes as gatherings of line segments, is used as a method for defining functions. The major procedures of the Hough transform are as follows.…”

“…In this thesis, in order to successfully realize the autonomous wheeled movement, the following methods are described. A range sensor (5) (6) is used for measuring the shapes and forms of obstacles, the Hough transformation used for making functions out of shapes (7) (8) , robot localization (9) , and the optimal track design involving convergent calculations for online control algorithms (10) . As arithmetic processing improves over the years, it is now possible to carry out image processing's calculations and optimization problem (11) with converging calculations, by utilizing the calculation ability developed for onboard computers.…”

Design of a Mobile Robot for Air Ducts Exploration

“…While [11] analyzes recent advances in both domains, [12] presents a localization approach based on a strap-down Inertial Measurement Unit (IMU). In terms of navigation challenges, [13] provides a method to detect the walls in a corridor to enable an efficient navigation of a mobile robot, and [14] focuses on the mapping of large-scale underground environments. The present work focuses instead on ventilation ducts, which typically have a relatively small scale.…”

Flexible infrastructure free navigation for vehicles in underground mines

“…The feature detection algorithms that operate on data from a laser scanner to extract features such as tunnel center line and intersections have been described previously [2] [3] and will therefore not get any further attention here. Instead we focus on the overall architecture of the system and report on experiments performed to assess the performance of the full navigation system.…”

“…We also present the results of experiments that have been performed on two different mobile robots, one research robot and one LHD vehicle, to verify the functionality of the system. Different parts of the autonomous navigation system presented here have previously been described in [1], [2] and [3]. Despite previous efforts by several parties to automate the tramming function of underground machines, widespread adoption of such technologies has yet to occur in the minerals industry.…”