This award is to support a postdoctoral associate to work in experimental computer science. The associate, Marcos Salganicoff, will work with Dr. Ruzena Bajcsy on problems involving robot control and planning. The research will blend learning, data structures, and parallelism. Planning information will be stored in binary trees (such a k-D-trees or quadtrees). This information, usually massive amounts of it, is then used in learning algorithms. A hybrid approach using distributed workstations for some of the computation and a MIMD computer for some of the rest will be employed to implement these learning algorithms in a cost effective manner.
