Top Banner
Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004
21

Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Dec 16, 2015

Download

Documents

Tabitha Small
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Clearance Based Path Optimization for Motion Planning

Roland Geraerts and Mark OvermarsICRA 2004

Page 2: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Problem setting Low quality paths

Often long detours Discontinuity Unnecessary motions

Quality criteria Length Clearance Combination

Page 3: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Length

Post processing Path pruning Shortcut Partial shortcut

Page 4: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Length

Path pruning Fast and simple heuristic Translational dist. improves

considerably Rotation is more difficult to remove

Page 5: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Length

Shortcut More general than path pruning Simple technique Fast convergence

Page 6: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Length

Weakness of the shortcut heuristic Path can still contain many redundant

(rotational) motions Creating shortcuts on large portions

will fail Partial shortcut

Query path Shortcut Partial shortcut

Page 7: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Clearance Method

Remove redundant nodes Retract path to medial axis Remove branches

Can help improving path length

Query path Retracted path No branches

Page 8: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Clearance

Retract path to medial axis Retract sample to medial axis

d2 x d

4 x d

Page 9: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Clearance

Retract path to medial axis Maximum stepsize s between samples

Page 10: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Clearance

Retract path to medial axis Redundant branches

redundant branch

Page 11: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Clearance

Remove redundant branches

Maximum step size

Page 12: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Path Quality – Combination Technique

Retract path to medial axis Increase size of robots Create partial shortcuts

Result Reasonable short path Path has a particular minimum

amount of clearance where it is possible

Page 13: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experimental Setup – Path Length

Environment SAMPLE 3 test scenes/paths

Focus Free flying objects Post processing

Page 14: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experiments – Simple Corridor Simple scene, cylinder Many motions are redundant Redundant motions are easy to remove

Page 15: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experiments – Simple Corridor Simple scene, cylinder Many motions are redundant Redundant motions are easy to remove

0

200

400

600

Initial path Redundantnodes

Shortcut MA +Shortcut

Partialshortcut

MA+Partialshortcut

Optimal

Pat

h l

eng

th

translation

rotation400%

27% 16% 14% 1% 2% 0%

Page 16: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experiments – Corridor Elbow shaped object is forced to rotate Little clearance to corridors

Page 17: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experiments – Corridor Elbow shaped object is forced to rotate Little clearance to corridors

0

250

500

750

Initial path Redundantnodes

Shortcut MA +Shortcut

Partialshortcut

MA+Partialshortcut

Optimal

Pat

h l

eng

th

translation

rotation

256%

65%24% 24

%11% 5% 0%

Page 18: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experiments – Hole Object must rotate to get through the

hole Clearance is small inside the hole

Page 19: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Experiments – Hole Object must rotate to get through the

hole Clearance is small inside the hole

0

40

80

120

Initial path Redundantnodes

Shortcut MA + Shortcut Partial shortcut MA+Partialshortcut

Optimal

Pat

h le

ng

th

translation

rotation

41% 14% 0%

184%

112%

36%

23%

Page 20: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Future Work

Extension to other robot types

Preprocessing techniques

Page 21: Clearance Based Path Optimization for Motion Planning Roland Geraerts and Mark Overmars ICRA 2004.

Questions

Home page: www.cs.uu.nl/~roland

Mail: [email protected]