Motion coordination algorithm for distributed agents in the cellular warehouse problem

A distributed approach is shown to coordinate the motions of transport tables for the cellular warehouse problem. In this approach, the tables are considered to be autonomous agents, and a built-in behavior function given by artificial neural networks (ANNs) and the evolved problem-oriented connection weights navigate the agents to their specified goals. To determine the agent to be moved, a measure of the priority to move is introduced. We show that distributed agents with the learned behavior function and the negotiation value perform a similar strategy to a “serializable” solution forN-puzzle problems, which provides a good heuristic strategy for large-scale problems. This work was presented, in part, at the Sixth International Symposium on Artificial Life and Robotics, Tokyo, Japan, January 15–17, 2001