Accelerating Self-Modeling in Cooperative Robot Teams
Bongard, J.C.
Dept. of Comput. Sci., Univ. of Vermont, Burlington, VT;
This paper appears in: Evolutionary Computation, IEEE Transactions on Accepted for future publication
First Published:
2008-09-26
ISSN: 1089-778X
Digital Object Identifier: 10.1109/TEVC.2008.927236
Abstract
One of the major obstacles to achieving robots capable of operating in real-world environments is enabling them to cope with a continuous stream of unanticipated situations. In previous work, it was demonstrated that a robot can autonomously generate self-models, and use those self-models to diagnose unanticipated morphological change such as damage. In this paper, it is shown that multiple physical quadrupedal robots with similar morphologies can share self-models in order to accelerate modeling. Further, it is demonstrated that quadrupedal robots which maintain separate self-modeling algorithms but swap self-models perform better than quadrupedal robots that rely on a shared self-modeling algorithm. This finding points the way toward more robust robot teams: a robot can diagnose and recover from unanticipated situations faster by drawing on the previous experiences of the other robots.
Index Terms
Available to subscribers and IEEE members.
Cart
