An incremental constraint-based framework for task and motion planning

Simple item page
dc.citation.journalTitleThe International Journal of Robotics Researchen_US
dc.contributor.authorDantam, Neil T.en_US
dc.contributor.authorKingston, Zachary K.en_US
dc.contributor.authorChaudhuri, Swaraten_US
dc.contributor.authorKavraki, Lydia E.en_US
dc.date.accessioned2018-06-27T13:50:15Zen_US
dc.date.available2018-06-27T13:50:15Zen_US
dc.date.issued2018en_US
dc.description.abstractWe present a new constraint-based framework for task and motion planning (TMP). Our approach is extensible, probabilistically complete, and offers improved performance and generality compared with a similar, state-of-the-art planner. The key idea is to leverage incremental constraint solving to efficiently incorporate geometric information at the task level. Using motion feasibility information to guide task planning improves scalability of the overall planner. Our key abstractions address the requirements of manipulation and object rearrangement. We validate our approach on a physical manipulator and evaluate scalability on scenarios with many objects and long plans, showing order-of-magnitude gains compared with the benchmark planner and improved scalability from additional geometric guidance. Finally, in addition to describing a new method for TMP and its implementation on a physical robot, we also put forward requirements and abstractions for the development of similar planners in the future.en_US
dc.identifier.citationDantam, Neil T., Kingston, Zachary K., Chaudhuri, Swarat, et al.. "An incremental constraint-based framework for task and motion planning." <i>The International Journal of Robotics Research,</i> (2018) Sage: https://doi.org/10.1177/0278364918761570.en_US
dc.identifier.doihttps://doi.org/10.1177/0278364918761570en_US
dc.identifier.urihttps://hdl.handle.net/1911/102293en_US
dc.language.isoengen_US
dc.publisherSageen_US
dc.rightsThis is an author's peer-reviewed final manuscript, as accepted by the publisher. The published article is copyrighted by the authors.en_US
dc.subject.keywordAI reasoning methodsen_US
dc.subject.keywordmanipulation planningen_US
dc.subject.keywordpath planning for manipulatorsen_US
dc.subject.keywordtask and motion planningen_US
dc.titleAn incremental constraint-based framework for task and motion planningen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpost-printen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dantam2018incremental-tmp.pdf
Size:
5.57 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Faculty Publications
Computer Science Publications