Semi-Unknown Environments Exploration Inspired by Swarm Robotics using Fuzzy Cognitive Maps

摘要

This paper aims to present a fuzzy cognitive map (FCM) controller on multiple autonomous mobile robots (multirobot system) in order to complete a foraging task in semiunknown environments, and to compare the FCM results with a fuzzy logic controller (FLC). In this work, the limits of the searching area are known. However, everything within it (goals, obstacles and position of other robots during navigation) is unknown. The foraging task simulates a real-life application of robots on rescue missions, where the main objective is rescuing the victims of a tragedy, or lost in a forest, or even victims of a major accident in an industry. Although it is a simulated environment, we tested the autonomy and cooperation among all robots for this kind of operation in different simulated scenarios. We used a reactive (real-time) architecture to enhance the robots' global robustness on dealing with unpredictable situations. The results imply that the FCM approach presented, in general, less simulation processing time and distance traveled, without significant prejudice in the explored area. In this way, we expect to collaborate and serve as inspiration for future works on this research area.