Fuzzy logic based control system implementation in ROS middleware

Autonomous mobile vehicles are used in many areas. These vehicles are supposed to realize correct robotic behaviors in respect of the application type. Classical robot control/decision mechanisms can give imperfect results due to sensor compensation errors or calculation costs. Fuzzy logic, in some cases, can be used to overcome these problems. In this study, we have designed a robot control system which consists of two fuzzy inference systems to realize goal reaching and obstacle avoidance behaviors. The system has been implemented on Robot Operating System (ROS) which runs on Ubuntu 12.04 OS. We have tested the system under Gazebo simulation platform on the Akıllı Tekerlekli Sandalye (ATEKS) model and obtained satisfactory results.