A reconfigurable hybrid intelligent system for robot navigation

Abstract

Soft computing has come of age to o er us a wide array of powerful and e cient algorithms
\nthat independently matured and in
\nuenced our approach to solving problems in robotics,
\nsearch and optimisation. The steady progress of technology, however, induced a 
\nux of new
\nreal-world applications that demand for more robust and adaptive computational paradigms,
\ntailored speci cally for the problem domain. This gave rise to hybrid intelligent systems, and
\nto name a few of the successful ones, we have the integration of fuzzy logic, genetic algorithms
\nand neural networks. As noted in the literature, they are signi cantly more powerful than
\nindividual algorithms, and therefore have been the subject of research activities in the past
\ndecades. There are problems, however, that have not succumbed to traditional hybridisation
\napproaches, pushing the limits of current intelligent systems design, questioning their solutions
\nof a guarantee of optimality, real-time execution and self-calibration. This work presents an
\nimproved hybrid solution to the problem of integrated dynamic target pursuit and obstacle
\navoidance, comprising of a cascade of fuzzy logic systems, genetic algorithm, the A* search
\nalgorithm and the Voronoi diagram generation algorithm.