Robustness via run-time adaptation of contingent plans

In this paper, we discuss our approach to making the behavior of planetary rovers more robust for the purpose of increased productivity. Due to the inherent uncertainty in rover exploration, the traditional approach to rover control is conservative, limiting the autonomous operation of the rover and sacri cing performance for safety. Our objective is to increase the science productivity possible within a single uplink by allowing the rover's behavior to be speci ed with exible, contingent plans and by employing dynamic plan adaptation during execution. We have deployed a system exhibiting exible, contingent execution; this paper concentrates on our ongoing e orts on plan adaptation. Plans can be revised in two ways: plan steps may be deleted, with execution continuing with the plan su x; and the current plan may be merged with an \alternate plan" from an on-board library. The planrevision action is chosen to maximize the expected utility of the plan. Plan merging and action deletion constitute a more conservative general-purpose planning system; in return, our approach is more e cient and more easily veri ed, two important criteria for deployed rovers.