The problem of action selection for an autonomous creature implies resolving conflicts between competing behavioral alternatives. These conflicts can be resolved either via competition, following a "winner-take-all" approach, or via cooperation in a "voting-based" approach. In this paper we present two robotic architectures implementing these approaches, and report on experiments we have performed to compare their underlying optimization policies. We have framed this study within the context of the "two-resource problem," as it provides a widely used standard that favors systematic experimentation, analysis, and comparison of results.
展开▼
