Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383108450> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4383108450 abstract "Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches lack safety guarantees; and learned navigation systems may not generalize well to unseen environments. Despite a variety of recent learning techniques to tackle these challenges in general, a lack of an open-source benchmark and reproducible learning methods specifically for autonomous navigation makes it difficult for roboticists to choose what learning methods to use for their mobile robots and for learning researchers to identify current shortcomings of general learning methods for autonomous navigation. In this paper, we identify four major desiderata of applying deep RL approaches for autonomous navigation: (D1) reasoning under uncertainty, (D2) safety, (D3) learning from limited trial-and-error data, and (D4) generalization to diverse and novel environments. Then, we explore four major classes of learning techniques with the purpose of achieving one or more of the four desiderata: memory-based neural network architectures (D1), safe RL (D2), model-based RL (D2, D3), and domain randomization (D4). By deploying these learning techniques in a new open-source large-scale navigation benchmark and real-world environments, we perform a comprehensive study aimed at establishing to what extent can these techniques achieve these desiderata for RL-based navigation systems." @default.
- W4383108450 created "2023-07-05" @default.
- W4383108450 creator A5001594330 @default.
- W4383108450 creator A5002854000 @default.
- W4383108450 creator A5013037940 @default.
- W4383108450 creator A5017662025 @default.
- W4383108450 creator A5081564295 @default.
- W4383108450 date "2023-05-29" @default.
- W4383108450 modified "2023-10-16" @default.
- W4383108450 title "Benchmarking Reinforcement Learning Techniques for Autonomous Navigation" @default.
- W4383108450 cites W1662842982 @default.
- W4383108450 cites W1980035368 @default.
- W4383108450 cites W1995938954 @default.
- W4383108450 cites W2117211893 @default.
- W4383108450 cites W2152536965 @default.
- W4383108450 cites W2158782408 @default.
- W4383108450 cites W2167340365 @default.
- W4383108450 cites W2605102758 @default.
- W4383108450 cites W2912063360 @default.
- W4383108450 cites W2962872206 @default.
- W4383108450 cites W2962887844 @default.
- W4383108450 cites W2976046470 @default.
- W4383108450 cites W3004375689 @default.
- W4383108450 cites W3036170014 @default.
- W4383108450 cites W3103780890 @default.
- W4383108450 cites W3163454111 @default.
- W4383108450 cites W3190038566 @default.
- W4383108450 cites W3192162805 @default.
- W4383108450 cites W3206314692 @default.
- W4383108450 cites W3207060053 @default.
- W4383108450 cites W4220840735 @default.
- W4383108450 doi "https://doi.org/10.1109/icra48891.2023.10160583" @default.
- W4383108450 hasPublicationYear "2023" @default.
- W4383108450 type Work @default.
- W4383108450 citedByCount "0" @default.
- W4383108450 crossrefType "proceedings-article" @default.
- W4383108450 hasAuthorship W4383108450A5001594330 @default.
- W4383108450 hasAuthorship W4383108450A5002854000 @default.
- W4383108450 hasAuthorship W4383108450A5013037940 @default.
- W4383108450 hasAuthorship W4383108450A5017662025 @default.
- W4383108450 hasAuthorship W4383108450A5081564295 @default.
- W4383108450 hasBestOaLocation W43831084502 @default.
- W4383108450 hasConcept C108583219 @default.
- W4383108450 hasConcept C119857082 @default.
- W4383108450 hasConcept C13280743 @default.
- W4383108450 hasConcept C134306372 @default.
- W4383108450 hasConcept C136197465 @default.
- W4383108450 hasConcept C144133560 @default.
- W4383108450 hasConcept C154945302 @default.
- W4383108450 hasConcept C162853370 @default.
- W4383108450 hasConcept C177148314 @default.
- W4383108450 hasConcept C185798385 @default.
- W4383108450 hasConcept C188888258 @default.
- W4383108450 hasConcept C19966478 @default.
- W4383108450 hasConcept C205649164 @default.
- W4383108450 hasConcept C33923547 @default.
- W4383108450 hasConcept C41008148 @default.
- W4383108450 hasConcept C86251818 @default.
- W4383108450 hasConcept C90509273 @default.
- W4383108450 hasConcept C97541855 @default.
- W4383108450 hasConceptScore W4383108450C108583219 @default.
- W4383108450 hasConceptScore W4383108450C119857082 @default.
- W4383108450 hasConceptScore W4383108450C13280743 @default.
- W4383108450 hasConceptScore W4383108450C134306372 @default.
- W4383108450 hasConceptScore W4383108450C136197465 @default.
- W4383108450 hasConceptScore W4383108450C144133560 @default.
- W4383108450 hasConceptScore W4383108450C154945302 @default.
- W4383108450 hasConceptScore W4383108450C162853370 @default.
- W4383108450 hasConceptScore W4383108450C177148314 @default.
- W4383108450 hasConceptScore W4383108450C185798385 @default.
- W4383108450 hasConceptScore W4383108450C188888258 @default.
- W4383108450 hasConceptScore W4383108450C19966478 @default.
- W4383108450 hasConceptScore W4383108450C205649164 @default.
- W4383108450 hasConceptScore W4383108450C33923547 @default.
- W4383108450 hasConceptScore W4383108450C41008148 @default.
- W4383108450 hasConceptScore W4383108450C86251818 @default.
- W4383108450 hasConceptScore W4383108450C90509273 @default.
- W4383108450 hasConceptScore W4383108450C97541855 @default.
- W4383108450 hasFunder F4320306076 @default.
- W4383108450 hasLocation W43831084501 @default.
- W4383108450 hasLocation W43831084502 @default.
- W4383108450 hasOpenAccess W4383108450 @default.
- W4383108450 hasPrimaryLocation W43831084501 @default.
- W4383108450 hasRelatedWork W1534851618 @default.
- W4383108450 hasRelatedWork W2115138863 @default.
- W4383108450 hasRelatedWork W2907103250 @default.
- W4383108450 hasRelatedWork W2947217676 @default.
- W4383108450 hasRelatedWork W3022038857 @default.
- W4383108450 hasRelatedWork W3041867744 @default.
- W4383108450 hasRelatedWork W3047894882 @default.
- W4383108450 hasRelatedWork W3208584567 @default.
- W4383108450 hasRelatedWork W4282981148 @default.
- W4383108450 hasRelatedWork W4321365483 @default.
- W4383108450 isParatext "false" @default.
- W4383108450 isRetracted "false" @default.
- W4383108450 workType "article" @default.