Adaptive-Resolution Map Building Approach for Robot Navigation in Dynamic Environments*

Abstract

Map building is an essential component to enable mobile robots autonomous navigation. This paper introduces a new method for learning multiresolution maps for navigation in unknown dynamic worlds. It extends a previous navigation architecture(1) that integrates a multiresolution grid world model and fuzzy ART based world model. The fuzzy ART world model is composed of a set of rectangular geometric primitives. A new method for updating the fuzzy ART model in dynamic worlds was proposed in(2). In this paper we propose a new navigation architecture that, by integrating that new map building method for dynamic worlds, is able to dynamically not only increase but also decrease local resolution according to variations in the local clutter and complexity of the world. With the new architecture the mobile robot is able to navigate in changing worlds, and a degree of optimality is maintained associated to a planning approach implemented in real-time. The paper presents experimental results obtained with a Nomad 200 mobile robot that demonstrate the efiectiveness of the proposed methods.