Certain investigations on mobile robot navigation for unknown and unpredictable environment

Abstract

Intelligent robots are expected to work intelligently even in the unknown/uncertain environment. It is sometimes difficult to evaluate their performance with only one evaluation function under various situations. The desired behavior sometimes depends on the circumstances while there can be contradicting objectives that have special importance in certain situations. A mobile robot to navigate purposefully from a start location to a target location, needs two basic requirements: sensing and reasoning. However, the pervasive presence of uncertainty in sensing makes the choice of a suitable tool of reasoning and decision making that can deal with incomplete information, vital to ensure a robust control system. The development of techniques for autonomous navigation in realworld environments constitutes one of the major trends in the current research on robotics. A type - 2 fuzzy interval controllers is applied to the autonomous robot in order to handle uncertainty in a better way. Ant colony optimization technique is used for an optimized path planning in traffic environment in a multi robotic environment. Fuzzy logic with Support Vector Machine is an adequate method to obtain certain and finite data in an optimal manner. This approach proves that it is enough for areas of highest danger coefficients to cause the robot to change direction, which consequently reduces the number of fuzzy rules that control the robot motion. In this work, we developed multi sensor integration using simple and inexpensive map based sensor processing, which allows a mobile robot to understand the environment and convey its belief about the environment to a remote location. The Cognitive Robotics is concerned with endowing robotic or software agents with higher level cognitive functions that involve reasoning. The ultimate purpose of this thesis is to automate a real time Cognitive Robotics using a nose and eye gesture in a relatively normal environment. newline newline newline