Publication | Closed Access
Using a PRM planner to compare centralized and decoupled planning for multi-robot systems
193
Citations
18
References
2003
Year
Unknown Venue
Artificial IntelligenceEngineeringPrm PlannerField RoboticsIntelligent SystemsOperations ResearchDescribes ExperimentsSystems EngineeringRobot LearningComputational GeometryMulti-agent PlanningMultirobot SystemCentralized PlanningPath PlanningDesignDistributed RoboticsMulti-robot SystemsProbabilistic Roadmap PlannerComputer ScienceMulti-robot TeamAi PlanningAutomationPlanningRobotics
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.
| Year | Citations | |
|---|---|---|
Page 1
Page 1