Abstract:
An efficient algorithm for manipulator path planning is presented in this paper. Because of the complexity of the problem nature, it frequently takes a long time for the planner to find an optimal path. This drawback may hinder a robotic manipulator system from many real-time applications. In this research work, the concept of anytime algorithm is integrated into a novel swarm intelligence method, the Ant System with Negative Feedback (ASNF). With the proposed Anytime Ant System (AAS), a planner is able to find a suboptimal solution quickly, then improve the quality of this solution while time allows. Simulations based on a two-link manipulator have been carried out to demonstrate the feasibility and effectiveness of the proposed approach.
