File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICRA.2014.6907620
- Scopus: eid_2-s2.0-84929224436
- WOS: WOS:000377221105034
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Predicting initialization effectiveness for trajectory optimization
Title | Predicting initialization effectiveness for trajectory optimization |
---|---|
Authors | |
Issue Date | 2014 |
Citation | 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 31 May-7 June 2014. In Conference Proceedings, 2014, p. 5183-5190 How to Cite? |
Abstract | Trajectory optimization is a method for solving motion planning problems by formulating them as non-convex constrained optimization problems. The optimization process, however, can get stuck in local optima that are in collision. As a consequence, these methods typically require multiple initializations. This poses the problem of deciding which initializations to use when given a limited computational budget. In this paper we propose a machine learning approach to predict whether a collision-free solution will be found from a given initialization. We present a set of trajectory features that encode the obstacle distribution locally around a robot. These features are designed for generalization across different tasks. Our experiments on various planning benchmarks demonstrate the performance of our approach. |
Persistent Identifier | http://hdl.handle.net/10722/308853 |
ISSN | 2023 SCImago Journal Rankings: 1.620 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pan, Jia | - |
dc.contributor.author | Chen, Zhuo | - |
dc.contributor.author | Abbeel, Pieter | - |
dc.date.accessioned | 2021-12-08T07:50:16Z | - |
dc.date.available | 2021-12-08T07:50:16Z | - |
dc.date.issued | 2014 | - |
dc.identifier.citation | 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 31 May-7 June 2014. In Conference Proceedings, 2014, p. 5183-5190 | - |
dc.identifier.issn | 1050-4729 | - |
dc.identifier.uri | http://hdl.handle.net/10722/308853 | - |
dc.description.abstract | Trajectory optimization is a method for solving motion planning problems by formulating them as non-convex constrained optimization problems. The optimization process, however, can get stuck in local optima that are in collision. As a consequence, these methods typically require multiple initializations. This poses the problem of deciding which initializations to use when given a limited computational budget. In this paper we propose a machine learning approach to predict whether a collision-free solution will be found from a given initialization. We present a set of trajectory features that encode the obstacle distribution locally around a robot. These features are designed for generalization across different tasks. Our experiments on various planning benchmarks demonstrate the performance of our approach. | - |
dc.language | eng | - |
dc.relation.ispartof | 2014 IEEE International Conference on Robotics and Automation (ICRA) | - |
dc.title | Predicting initialization effectiveness for trajectory optimization | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICRA.2014.6907620 | - |
dc.identifier.scopus | eid_2-s2.0-84929224436 | - |
dc.identifier.spage | 5183 | - |
dc.identifier.epage | 5190 | - |
dc.identifier.isi | WOS:000377221105034 | - |