Obstacle avoidance path planning of a manipulator
Kaichen Xia, S. Jiang, Li-Tung Lu · 2003
This basic robot planning system chooses a motion path to avoid collision with obstacles in workspace. With a camera above the workspace the computer vision can give a simple description of the world model. The presented algorithm transfers a Cartesian description of obstacles into the coordinate of the first three joints of a manipulator. The freespace is described hierarchically by a two-level representation, and a two-level optimization is used for the path planning. Experiments show the whole system can be realized by an IBM-PC with very small memory. The average computation time for one obstacle is 10 s.>