Evolving the Multiagent Navigation System

As we have already mentioned previously, our Navigation system is decomposed into a set of different agents that are responsible for different tasks. Each of these agents has certain parameters that affect its bidding behavior. Trying to manually find the best values for the parameters of the bidding functions is an extremely difficult task. In this section we describe the application of an evolutionary approach to do this optimization.



Subsections

© 2003 Dídac Busquets