An Intelligent System for Learning Environment Models and Guidance Strategies for Visio -Based Indoor Autonomous Land Vehicle Navigation

Abstract

An intelligent system for learning environment models and guidance strategies for vision-based autonomous land vehicle (ALV) navigation in indoor environments is proposed. In the learning process, the ALV is firstly driven manually by an operator through the navigation environment. Then, a navigation model, which consists of the locations of environment features, refined sub-paths, and their corresponding guidance strategies, is generated automatically by the learning system. The selection of the guidance strategy depends on the availability of stable environment features. An intelligent navigation scheme by integrating three guidance strategies is proposed for safe ALV navigation through environments consisting of various conditions. The learned model can be used to guide the ALV through the explored environment by the proposed navigation scheme. When the tested environment changes, the new environment can be re -learned, and the proposed navigation scheme still can work in the new environment without any manual adaptation. The proposed approach has been tested on a prototype ALV and many successful navigation sessions have been per-formed, which confirm the feasibility of the proposed approach.