A Prospective Fuzzy Logic approach to Knowledge-based Navigation of Mobile LEGO-Robot Hrudaya Ku. Tripathy* 1 , B.K.Tripathy 2 and Pradip K Das 3 *1 Institute of Advanced Computer and Research, Prajukti Bihar, Rayagada-765002 (Orissa), India 2 School of Computing Sciences, VIT University, Vellore-632014, Tamil Nadu, India 3 Department of Computer Science & Engineering, Indian Institute of Technology Guwahati, North Guwahati-781039 (Assam), India hrudayakumar@hotmail.com, tripathybk@rediffmail.com, pkdas@iitg.ernet.in Abstract The development of techniques for knowledge-based navigation constitutes one of the major trends in the current research on mobile robotics. Fuzzy logic provides tools that are of potential interest to mobile robot control. Most applications of fuzzy logic in this field concern the use of fuzzy control techniques to implement individual behavior units. In this paper we discuss how fuzzy logic computation techniques have been used in the mobile Lego robot for knowledge- based navigation. Also we implemented a robot that learns how to avoid obstacle using online self- adaptation. The outputs from each behaviour’s rule base are integrated using the command fusion process and made crisp using a modified defuzzification technique. The end result is very smooth motion control of the robot. The robot was built using the Lego RCX microcomputer and was designed with the subsumption architecture. We choose to implement the robot’s brain using the Lego RCX due to the lower cost. Keywords Fuzzy Logic, Mobile Lego Robot, Navigation, Path finding, Obstacle avoidance. 1. Introduction The development of techniques for robot navigation constitutes one of the major trends in the current research on mobile robotics. The goal of autonomous mobile robotics is to build physical systems that can move purposefully and without human intervention in unmodified environments that is, in real-world environments that have not been specifically engineered for the robot. The development of techniques for autonomous robot navigation constitutes one of the major trends in the current research on robotics. This trend is motivated by the current gap between the available technology and the new application demands. On the one hand, current industrial robots lack flexibility and autonomy. In [1] typically, the robots perform pre-programmed sequences of operations in highly constrained environments, and are not able to operate in new environments or to face unexpected situations. On the other hand, there is a clear emerging market for truly autonomous robots. Possible applications include intelligent service robots for offices, hospitals, and factory floors; maintenance robots operating in hazardous or hardly accessible areas; domestic robots for cleaning or entertainment; semi autonomous vehicles for help to disabled people and so on. The problem of reliable navigation is the most pervasive in all of mobile robotics. For a robot to be truly mobile, it must be able to repeatable move from point to point while keeping track of its current location with respect to its environment and robustly recognizing when it achieves its goals. In [2] this problem has received considerable attention; it still does not have a fully satisfactory solution: existing systems often lack flexibility, reliability, or both. Computational cost is also an issue. The main problem is that of dealing with uncertainty, which refers to the statistical distribution of errors in both control and sensing. Mobile Robots currently employ a number of navigation strategies and use various sensors as navigational aids. In [3] the selection of sensors is directly dependent on the strategy the robot employs; A Prospective Fuzzy Logic approach to Knowledge-based Navigation of Mobile LEGO-Robot Hrudaya Ku. Tripathy, B.K.Tripathy and Pradip K Das 64