Exploiting capability constraints to solve global two-dimensional path planning problems

Mobile autonomous vehicles require the capability of planning routes over ranges that are too great to be characterized by local sensor systems. Completion of this task requires some form of map data. Much work has been done concerning planning paths through local areas, those which can be scanned by on-board sensor systems. However, planning paths based on long range map data is a very different problem. Extant solution techniques require the search of discrete, node and link representations which characterize continuous, two dimensional problem environments. We assume the availability of topographic data organized into regions of homogeneous traversal cost. Given this, we present a solution technique for the long range planning problem which relies on a Snell´s Law heuristic to limit a graph search for the optimal solution.