Dynamic route planning with uncertain information

摘要

Navigating an autonomous vehicle through a threatening zone whose characteristics may change in an unpredictable manner is an important problem that has received much attention in the recent past. The paper describes the design of a route planning system, called RUTA-100, that works with incomplete information obtained from many unreliable knowledge sources and plans an optimal route by minimizing both danger and distance. The operation of the route planner has two main phases: the initial route planning phase and the dynamic plan execution. Once a point of origin and a point of destination have been identified, the route planner determines the optimal route based on the information available at that time. Should conditions change during plan execution, the route is accordingly recalculated. This is repeated until the destination point is reached. The Dempster -Shafer theory of belief is used as the underlying formalism to pool and represent uncertain information and reason with it.