Vision Based Cable Assembly in Constrained Environment

In this paper, we proposed a vision based method for automatic cable assembly conducted in constrained environment. The primary difficult issue involved in such tasks is to avoid the possible contact between the cable and the surrounding environment. The solution to this problem is combination of cable deformation control and obstacle avoidance control based on artificial potential field method. Both of the control utilize the vision feedback. The cable deformation control does not require a precise model of the cable. The obstacle avoidance method ensures that the cable will not contact with the surrounding obstacles. The effectiveness of the proposed method is verified by a cable assembly experiment conducted by using a URS robot manipulator.