Perception and remembrance of the environment during real-time navigation of a mobile robot

This paper deals with the advantages of incorporating cognition and remembr ance capabilities in a sensor-based real-time navigation algorithm. The spe cific features of the algorithm apart from real-time collision avoidance in clude spatial comprehension of the local scenario of the robot, remembrance and recollection of such comprehended scenarios and temporal correlation o f similar scenarios witnessed during different instants of navigation. Thes e features enhance the robot's performance by providing for a memory-based reasoning whereby the robot's forthcoming decisions are also affected by it s previous experiences during the navigation apart from the current range i nputs. The environment of the robot is modeled by classifying temporal sequ ences of spatial sensory patterns. A fuzzy classification scheme coupled to Kohonen's self-organizing map and fuzzy ART network determines this classi fication. A detailed comparison of the present method with other recent app roaches in the specific case of local minimum detection and avoidance is al so presented. As for escaping the local minimum barrier is concerned this p aper divulges a new system of rules that lead to shorter paths than the oth er methods. The method has been tested in concave, maze-like, unstructured and altered environments and its efficacy established. (C) 2001 Elsevier Sc ience B.V. All rights reserved.