A neuro-fuzzy approach for the motion planning of redundant manipulators

This paper outlines a Neuro-Fuzzy Inference Systems approach to efficient path planning in the work envelope of a redundant robot manipulator. The proposed methodology is two tier; i.e. it deals with continuous obstacle avoidance along with singularities avoidance in the task space. Obstacle avoidance is achieved based on the calculation of an appropriate null space vector and a proper pseudo inverse perturbation helps avoid singularities effectively. The computation of the inverse kinematics is accomplished with the help of dully trained Adaptive Neuro-Fuzzy Inference Systems, thus enabling the methodology to be applicable to all redundant robots operating in a sensor based real time environment. The methodology has been successfully tested on the simulation of a planar redundant manipulator performing some benchmark tasks.