Path planning for manipulators
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
Similar Records
General techniques for constrained motion planning
SANDROS: A motion planner with performance proportional to task difficulty