A Study of the Influence of the Combination Method in Fuzzy Behavior Coordination

The implementation of complex behavior generation for artificial systems can be extremely difficult due to the very high level of complexity involved. This problem can be partially overcome by decomposing the global tasks into simpler well specified behaviors which are easier to design and can be tuned independently of each other. Robot behaviour can be implemented as a set of fuzzy rules which mimic expert knowledge in specific tasks in order to model expert knowledge. Two combination methods for fusing the preferences from each behaviour are experimentally studied and compared. Both methods use fuzzy metarules to fuse the actions derived from the predefined elementary behaviours which will only be activated in their own context of applicability. The performance of the combination/arbitration algorithms have been demonstrated in both simulated and real worlds. When the results of the experimentation from both methods are taken into account, the influence of the combination method appe..