Behavior coordination and selection using situation context-dependent method for behavior based robot navigation using AI techniques for real world environments

Behavior coordination and action selection mechanism of the mobile robot navigation involves considerable design effort and parameter tuning. This work considers some of the different approaches and methods employed, which are motivated by the approaches used by Saffiotti and Tunstel et al. In this paper, we briefly present the design, coordination and fusion of the three elementary behaviors using fuzzy logic expert system. In this work the design of the behavior is based on regulatory control using fuzzy logic and the coordination and behavior selection is defined by fuzzy rules, which define the situation context of applicability for each behavior. Also, in this paper the decision making process of a few behaviors is illustrated specifically for active media pioneer robot. Fuzzy logic decision mechanism, used here simplifies the design of the robotic controller and reduces the number of rules to be determined. Decision making process uses fuzzy logic for coordination and action selection provides a smooth transition between behaviors with a consequent smooth output response. In addition, the new behavior can be added or modified easily. Some of the experimental results are also shown for the obstacle avoidance, wall following and seek-goal behaviors.