Machine Learning for Visual Navigation of Unmanned Ground Vehicles

TL;DR

This paper reviews recent advances in using visual texture information for autonomous ground vehicle navigation, compares machine learning algorithms for texture classification, and discusses their effectiveness in cross-country environments.

Contribution

It provides a comparative analysis of three machine learning algorithms for high-dimensional texture classification in visual navigation tasks.

Findings

Machine learning algorithms differ in classification accuracy

Texture features are less effective than color or laser data

Experimental results highlight strengths and weaknesses of each method

Abstract

The use of visual information for the navigation of unmanned ground vehicles in a cross-country environment recently received great attention. However, until now, the use of textural information has been somewhat less effective than color or laser range information. This manuscript reviews the recent achievements in cross-country scene segmentation and addresses their shortcomings. It then describes a problem related to classification of high dimensional texture features. Finally, it compares three machine learning algorithms aimed at resolving this problem. The experimental results for each machine learning algorithm with the discussion of comparisons are given at the end of the manuscript.