Using a PRM planner to compare centralized and decoupled planning for multi-robot systems
Gildardo Sanchez‐Ante, J.-C. Latombe
- 发表年份
- 2003
- 引用次数
- 196
摘要
Describes experiments with a probabilistic roadmap planner (PRM) on a spot-welding station with 2 to 6 robot manipulators combining 12 to 36 degrees of freedom. When performing centralized planning, the planner has proven to be reliable and fast. When performing decoupled planning, it was not significantly faster, but it was much less reliable, failing to find a solution 30 to 75% of the times in 6-robot examples. This is an important result as it invalidates the assumption that the loss of completeness in performing decoupled planning is not very substantial in practice and indicates that centralized planning is a more desirable approach-at least in applications like spot-welding, which requires rather tight robot coordination.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002