Optimization of parallel manipulator trajectory for obstacle and singularity avoidances based on neural network

This paper presents a novel method for singularity-free path planning and obstacle avoidance of parallel manipulators. A modified 3-4-5 interpolating polynomial is used to plan a trajectory for a planar 3-DOF parallel manipulator. The polynomial function which is smooth and continuous in displacement, velocity, and acceleration is used to find a smooth path avoiding the obstacles and singularities. An artificial neural network is implemented to solve forward kinematics of the manipulator to estimate the distance between gripper and singularity or obstacle. The simulating results demonstrate the efficiency of the proposed algorithm.