NEURO-FUZZY AND •FPGA BASED CONTROL OF ROBOT MANIPULATOR

Abstract

The field of Robotics is continually evolving. During the last decade, -there has been significant improvement in the area of robot control. Many soft computing and reconfigurable computing algorithms have been found In the present thesis an attempt is made, to explore in to different methods pertained to control of robot manipulator. Broadly the dissertation work is divided in to two main areas. o Adaptive Neuro-Fuzzy Inference System (ANFIS) based control of robot Manipulator. o Robot control using Reconfigurable computing (FPGAs). Initially ANFIS is used for Point to point control of a planar manipulator. The superiority of ANFIS compared to conventional method of control, is outlined. The entire Modeling and simulation is carried out in MATLAB6. 1. using Simulink. The subsequent part of the dissertation emphasizes the usefulness of reconfigurable computing in robot control. The coding is done in VHDL (Very High Speed Hardware Description Language) and simulation work is carried out in Model-Sim SE 5.7 . The proposed scheme is synthesized using Xilinx webpack7.1 on VirtexE chip. The simulation and synthesis results demonstrate the usefulness of this method.