Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287639300> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4287639300 abstract "Navigating fluently around pedestrians is a necessary capability for mobile robots deployed in human environments, such as buildings and homes. While research on social navigation has focused mainly on the scalability with the number of pedestrians in open spaces, typical indoor environments present the additional challenge of constrained spaces such as corridors and doorways that limit maneuverability and influence patterns of pedestrian interaction. We present an approach based on reinforcement learning (RL) to learn policies capable of dynamic adaptation to the presence of moving pedestrians while navigating between desired locations in constrained environments. The policy network receives guidance from a motion planner that provides waypoints to follow a globally planned trajectory, whereas RL handles the local interactions. We explore a compositional principle for multi-layout training and find that policies trained in a small set of geometrically simple layouts successfully generalize to more complex unseen layouts that exhibit composition of the structural elements available during training. Going beyond walls-world like domains, we show transfer of the learned policy to unseen 3D reconstructions of two real environments. These results support the applicability of the compositional principle to navigation in real-world buildings and indicate promising usage of multi-agent simulation within reconstructed environments for tasks that involve interaction." @default.
- W4287639300 created "2022-07-25" @default.
- W4287639300 creator A5005763357 @default.
- W4287639300 creator A5042646536 @default.
- W4287639300 creator A5046758466 @default.
- W4287639300 creator A5065277392 @default.
- W4287639300 creator A5081165104 @default.
- W4287639300 date "2020-10-16" @default.
- W4287639300 modified "2023-09-27" @default.
- W4287639300 title "Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning" @default.
- W4287639300 doi "https://doi.org/10.48550/arxiv.2010.08600" @default.
- W4287639300 hasPublicationYear "2020" @default.
- W4287639300 type Work @default.
- W4287639300 citedByCount "0" @default.
- W4287639300 crossrefType "posted-content" @default.
- W4287639300 hasAuthorship W4287639300A5005763357 @default.
- W4287639300 hasAuthorship W4287639300A5042646536 @default.
- W4287639300 hasAuthorship W4287639300A5046758466 @default.
- W4287639300 hasAuthorship W4287639300A5065277392 @default.
- W4287639300 hasAuthorship W4287639300A5081165104 @default.
- W4287639300 hasBestOaLocation W42876393001 @default.
- W4287639300 hasConcept C104114177 @default.
- W4287639300 hasConcept C107457646 @default.
- W4287639300 hasConcept C111472728 @default.
- W4287639300 hasConcept C120665830 @default.
- W4287639300 hasConcept C121332964 @default.
- W4287639300 hasConcept C127413603 @default.
- W4287639300 hasConcept C1276947 @default.
- W4287639300 hasConcept C13662910 @default.
- W4287639300 hasConcept C138885662 @default.
- W4287639300 hasConcept C139807058 @default.
- W4287639300 hasConcept C154945302 @default.
- W4287639300 hasConcept C177264268 @default.
- W4287639300 hasConcept C199360897 @default.
- W4287639300 hasConcept C19966478 @default.
- W4287639300 hasConcept C22212356 @default.
- W4287639300 hasConcept C2776999362 @default.
- W4287639300 hasConcept C2777113093 @default.
- W4287639300 hasConcept C2780586882 @default.
- W4287639300 hasConcept C41008148 @default.
- W4287639300 hasConcept C48044578 @default.
- W4287639300 hasConcept C77088390 @default.
- W4287639300 hasConcept C90509273 @default.
- W4287639300 hasConcept C97541855 @default.
- W4287639300 hasConceptScore W4287639300C104114177 @default.
- W4287639300 hasConceptScore W4287639300C107457646 @default.
- W4287639300 hasConceptScore W4287639300C111472728 @default.
- W4287639300 hasConceptScore W4287639300C120665830 @default.
- W4287639300 hasConceptScore W4287639300C121332964 @default.
- W4287639300 hasConceptScore W4287639300C127413603 @default.
- W4287639300 hasConceptScore W4287639300C1276947 @default.
- W4287639300 hasConceptScore W4287639300C13662910 @default.
- W4287639300 hasConceptScore W4287639300C138885662 @default.
- W4287639300 hasConceptScore W4287639300C139807058 @default.
- W4287639300 hasConceptScore W4287639300C154945302 @default.
- W4287639300 hasConceptScore W4287639300C177264268 @default.
- W4287639300 hasConceptScore W4287639300C199360897 @default.
- W4287639300 hasConceptScore W4287639300C19966478 @default.
- W4287639300 hasConceptScore W4287639300C22212356 @default.
- W4287639300 hasConceptScore W4287639300C2776999362 @default.
- W4287639300 hasConceptScore W4287639300C2777113093 @default.
- W4287639300 hasConceptScore W4287639300C2780586882 @default.
- W4287639300 hasConceptScore W4287639300C41008148 @default.
- W4287639300 hasConceptScore W4287639300C48044578 @default.
- W4287639300 hasConceptScore W4287639300C77088390 @default.
- W4287639300 hasConceptScore W4287639300C90509273 @default.
- W4287639300 hasConceptScore W4287639300C97541855 @default.
- W4287639300 hasLocation W42876393001 @default.
- W4287639300 hasOpenAccess W4287639300 @default.
- W4287639300 hasPrimaryLocation W42876393001 @default.
- W4287639300 hasRelatedWork W1240780431 @default.
- W4287639300 hasRelatedWork W1576801573 @default.
- W4287639300 hasRelatedWork W2907103250 @default.
- W4287639300 hasRelatedWork W3113555494 @default.
- W4287639300 hasRelatedWork W3181420625 @default.
- W4287639300 hasRelatedWork W3211480525 @default.
- W4287639300 hasRelatedWork W3212504492 @default.
- W4287639300 hasRelatedWork W4200570312 @default.
- W4287639300 hasRelatedWork W4308427659 @default.
- W4287639300 hasRelatedWork W4312941588 @default.
- W4287639300 isParatext "false" @default.
- W4287639300 isRetracted "false" @default.
- W4287639300 workType "article" @default.