Hierarchical Vision-motion Planning With Uncertainty: Local Path Planning And Global Route Selection

A new framework of a hierarchical vision-motion planning for a mobile robot iiridcr uncertainty is proposed. An optimal plan is gcmer- ated by two-level planning: global roiitc. selection arid local path planning. In global roiite sc4ec- tion, a sequence of' observation points to acquire sufficient information to reach a destination is clc- ternlined. Both the cost and the uncrrtainty of vi- sion are considered in this planning. In local path planning, given two successive observation points, trajectories, moving speeds, and reference points for robot localization are deteriiiined so that a robot can reach the second point safely with a minimum cost. Both tlic error in localization and that in niotion control are considered in this plan- ning. A local path planner is repcatedly invoked in global route selection to tlrterinine an actual path between observation points. Oiir hierarchi- cal planner can generate an optimal plan for a miobile robot planning problcm.