Trajectory Optimization of Spherical Parallel Robots Using Artificial Neural Network

Abstract

This article addresses an efficient and novel method for singularity-free path planning and obstacle avoidance of parallel manipulator based on neural networks. A modified 4-5-6-7 interpolating polynomial is used to plan a trajectory for a spherical parallel manipulator. The polynomial function which is smooth and continuous in displacement, velocity, acceleration and jerk is used to find a path avoiding obstacles and singularities. The polynomial is further modified to plan a trajectory with minimum passing length through the obstacle and singularity, and the best kinematics conditioning index, as well. An artificial neural network is implemented to solve forward kinematics of the manipulator to estimate the distance between gripper and singularity or obstacle in Euler coordinate. Moreover, the simulation results prove the efficiency of the proposed algorithm.