Finding Narrow Passages with Probabilistic Roadmaps: The SmallStep Retraction Method - PowerPoint PPT Presentation

About This Presentation
Title:

Finding Narrow Passages with Probabilistic Roadmaps: The SmallStep Retraction Method

Description:

free samples. colliding samples. colliding local path. narrow passage. low density of ... free samples. high density. of free samples. The efficiency of PRM ... – PowerPoint PPT presentation

Number of Views:92
Avg rating:3.0/5.0
Slides: 17
Provided by: timothy8
Learn more at: http://ai.stanford.edu
Category:

less

Transcript and Presenter's Notes

Title: Finding Narrow Passages with Probabilistic Roadmaps: The SmallStep Retraction Method


1
Finding Narrow Passages withProbabilistic
Roadmaps The Small-Step Retraction Method
Mitul Saha and Jean-Claude Latombe
Research supported by NSF, ABB and GM
Artificial Intelligence Lab Stanford University
2
Probabilistic Roadmaps (PRM)
goal configuration
start configuration
free-space
c-obstacle
Configuration-space components
Kavraki, Svetska, Latombe, Overmars, 1996
3
PRM planners solve complicated problems
Complex geometries obstacles 43530
polygons Robot 4053 polygons
High dimensional
4
Main Issue Narrow Passages
narrow passage
free samples
colliding local path
colliding samples
The efficiency of PRM planners drops
dramatically in spaces with narrow passages
5
Main Issue Narrow Passages
  • Problems with narrow passages are commonly
    encountered

6
Main Issue Narrow Passages
  • Proposed strategies
  • Filtering strategies,
  • e.g., Gaussian sampling Boor et al. 99
  • and bridge test Hsu et al. 03
  • ? rely heavily on rejection sampling
  • Retraction strategies,
  • e.g., Wilmart et al. 99Lien et al. 03
  • ? waste time moving many
    configurations out of collision

7
Motivating Observation
planning time
decreasing width of the narrow passage
8
Small-Step Retraction Method
Roadmap construction and repair
(2 3)
(1)
  • Slightly fatten the robots free space
  • Construct a roadmap in fattened free space
  • Repair the roadmap into original free space

9
Small-Step Retraction Method
Roadmap construction and repair
Fattening
widened passage
fattened free space
  • Free space can be indirectly fattened by
  • reducing the scale of the geometries (usually of
  • the robot) in the 3D workcell with respect to
  • their medial axis
  • -This can be pushed into the pre-processing
  • phase

10
Small-Step Retraction Method
Roadmap construction and repair
Fattening
start
Repair during construction
Pessimist Strategy
Optimist Strategy
Repair after construction
goal
fattened free space
11
Small-Step Retraction Method
Roadmap construction and repair
Fattening
start
Repair during construction
Pessimist Strategy
Optimist Strategy
Repair after construction
goal
fattened free space
12
Small-Step Retraction Method
Roadmap construction and repair
Fattening
start
Pessimist Strategy
Repair during construction
?Integrated planner 1. Try Optimist for N
time. 2. If Optimist fails, then run
Pessimist
Optimist Strategy
Repair after construction
goal
fattened free space
13
Quantitative Results
  • Fattening preserves topology/ connectivity of
    the free space
  • Fattening alters the topology/ connectivity of
    the free space

(c)
(a)
(b)
Alpha 1.1
(g)
Alpha 1.0
(f)
(d)
(e)
Upto 3 orders of magnitude improvement in the
planning time was observed
14
Quantitative Results
  • Test environments without narrow passages
  • SSRP and SBL have similar performance

(i)
(j)
15
Conclusion
  • SSRP is very efficient at finding narrow passages
    and still works well when there is none
  • The main drawback is that there is an additional
    pre-computation step

16
Finding Narrow Passages withProbabilistic
Roadmaps The Small-Step Retraction Method
Write a Comment
User Comments (0)
About PowerShow.com