Research‎ > ‎

Path Tracking & Obstacle Avoidance of Redundant Robotic Manipulators in Non-Stationary Environments

YouTube Video



Robot manipulators, in order to interact with human, are needed to perform in environments which contain movable objects such as moving obstaclesThis research, considering nonlinear dynamic of the robot including actuators dynamic and physical constraints, presents a solution for online optimal control of redundant robot manipulators in non-stationary environments, using nonlinear model predictive control ( NMPC ). Using NMPC, the end - effector of robotic manipulator tracks a predefined geometry path in the Cartesian space in such a way that no collision with moving obstacles in the workspace and no singular configurations for robot occurs. To avoid collision with moving obstacles, the future position of the obstacles in 3D space is predicted using artificial neural network. Using online neural network, no knowledge about obstacles motion is needed. Moreover, the end-effector of robotic manipulator, using this method, 
can capture a moving target.