Next: Case Based Reasoning Up: Future Work Previous: Genetic Algorithm
The results obtained through real experimentation confirmed that, as already seen through simulation, the bidding coordination mechanism and the mapping and navigation methods work appropriately. Nonetheless, the scenarios used in the real experiments were not very complex, and some more experimentation on more complex scenarios should be performed. These new scenarios should include some more obstacles, eventually having some cul-de-sacs, so that the robot would need to undo the path already done.
However, the big next step on our research is to move the experimentation to outdoor environments. The main difficulty of doing so is the availability of a vision system for outdoors, which we do not have at this moment. However, we think that the successful results obtained on indoor unstructured environments could be quite easily obtained outdoors, since neither the navigation method nor the control architecture are dramatically affected by the differences of indoor/outdoor environments.