<title>Path planning is no substitute for intelligent behavior</title>

This paper describes our experience implementing navigation behavior for two different autonomous multi-robot systems using two very different approaches. We describe the problems encountered and their solutions and the extensions necessary to support planning for multiple robots in our application domains. We conclude that there are many applications of path-planning that would be well served by the introduction of a little domain specific intelligent behavior as a substitute for brute force path planning over unnecessarily large configuration spaces. * (A-Star) 1 to search for a path through discrete states representing regions of physical space. The second approach, which we'll call behavior planning, also searches over discrete states, but the states represent both behavioral states and regions of space. We encountered a number of problems during implementation and we describe how they were overcome. The two approaches are compared and we discuss the application characteristics for which we believe each approach is best suited. We argue the case that there are many applications in which planning over large configurations spaces is often utilized, that would be better served by the introduction of some domain specific 'intelligent' behavior.