Neuro-Fuzzy Dynamic Obstacle Avoidance for Autonomous Robot Manipulators

This paper presents an integration of fuzzy local planner and modified Elman neural networks (MENN) approximation-based computed-torque controller for motion control of autonomous manipulators in dynamic and partially known environments containing moving obstacles. The navigation is based on fuzzy technique for the idea of artificial potential fields (APF) using analytic harmonic functions. Unlike fuzzy technique, the development of APF is computationally intensive operation. The MENN controller can deal with unmodeled bounded disturbances and/or unstructured unmodeled dynamics of the robot arm. The MENN weights are tuned on-line, with no off-line learning phase required. The stability of the closed-loop system is guaranteed by the Lyapunov theory. The purpose of the controller, which is designed as a Neuro-fuzzy controller, is to generate the commands for the servo-systems of the robot so it may choose its way to its goal autonomously, while reacting in real-time to unexpected events. The proposed scheme has been successfully tested. The controller also demonstrates remarkable performance in adaptation to changes in manipulator dynamics. Sensor-based motion control is an essential feature for dealing with model uncertainties and unexpected obstacles in real-time world systems.