File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Efficient nearest-neighbor computation for GPU-based motion planning

TitleEfficient nearest-neighbor computation for GPU-based motion planning
Authors
Issue Date2010
Citation
IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings, 2010, p. 2243-2248 How to Cite?
AbstractWe present a novel k-nearest neighbor search algorithm (KNNS) for proximity computation in motion planning algorithm that exploits the computational capabilities of many-core GPUs. Our approach uses locality sensitive hashing and cuckoo hashing to construct an efficient KNNS algorithm that has linear space and time complexity and exploits the multiple cores and data parallelism effectively. In practice, we see magnitude improvement in speed and scalability over prior GPU-based KNNS algorithm. On some benchmarks, our KNNS algorithm improves the performance of overall planner by 20-40 times for CPU-based planner and up to 2 times for GPU-based planner. ©2010 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/206249

 

DC FieldValueLanguage
dc.contributor.authorPan, Jia-
dc.contributor.authorLauterbach, Christian-
dc.contributor.authorManocha, Dinesh-
dc.date.accessioned2014-10-22T01:25:31Z-
dc.date.available2014-10-22T01:25:31Z-
dc.date.issued2010-
dc.identifier.citationIEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings, 2010, p. 2243-2248-
dc.identifier.urihttp://hdl.handle.net/10722/206249-
dc.description.abstractWe present a novel k-nearest neighbor search algorithm (KNNS) for proximity computation in motion planning algorithm that exploits the computational capabilities of many-core GPUs. Our approach uses locality sensitive hashing and cuckoo hashing to construct an efficient KNNS algorithm that has linear space and time complexity and exploits the multiple cores and data parallelism effectively. In practice, we see magnitude improvement in speed and scalability over prior GPU-based KNNS algorithm. On some benchmarks, our KNNS algorithm improves the performance of overall planner by 20-40 times for CPU-based planner and up to 2 times for GPU-based planner. ©2010 IEEE.-
dc.languageeng-
dc.relation.ispartofIEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings-
dc.titleEfficient nearest-neighbor computation for GPU-based motion planning-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/IROS.2010.5651449-
dc.identifier.scopuseid_2-s2.0-78651473585-
dc.identifier.spage2243-
dc.identifier.epage2248-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats