Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Path planning for manipulators

Conference ·
OSTI ID:10109629

To facilitate robot programming, we present three different path planners with complementary capabilities. The first planner uses SANDROS, a new search strategy that combines hierarchical, nonuniform-multi-resolution, and best-first search to find a near-optimal solution in the configuration space. It is an efficient and resolution-complete algorithm that has performance commensurate with task difficulty. The second planner uses a simpler path planning algorithm based on a series of plausible task restrictions. It is designed to solve ``realistic`` problems very quickly, at the expense of not being able to solve every problem. Finally, the third planner uses a learning algorithm designed to improve path planning. The learning algorithm not only reduces the time cost of existing planners, but also increases their capability in solving difficult tasks.

Research Organization:
Sandia National Labs., Albuquerque, NM (United States)
Sponsoring Organization:
USDOE, Washington, DC (United States)
DOE Contract Number:
AC04-76DP00789
OSTI ID:
10109629
Report Number(s):
SAND--92-1437C; CONF-930403--6; ON: DE93004050
Country of Publication:
United States
Language:
English