Efficient search and hierarchical motion planning using dynamic single-source shortest paths trees

All previous robot motion planners based on approximate cell decomposition exhibit redundancy between successive searchers for a sequence of empty cells. A search method that eliminates this redundancy is presented. It is founded on the ability to efficiently maintain a single-source shortest paths tree embedded in the connectivity graph that is subject to the dynamic modifications that result from incremental subdivision of cells. The convergence of the algorithm is controlled by the vertex cost function, which relies on an estimate for the proportion of free space in a cell. The planner is fully implemented, and empirical results are given to illustrate the performance improvements of the dynamic algorithm compared to Dijkstra's algorithm.<
>