Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203018838> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3203018838 abstract "In this paper we present the first safe system for full control of self-driving vehicles trained from human demonstrations and deployed in challenging, real-world, urban environments. Current industry-standard solutions use rule-based systems for planning. Although they perform reasonably well in common scenarios, the engineering complexity renders this approach incompatible with human-level performance. On the other hand, the performance of machine-learned (ML) planning solutions can be improved by simply adding more exemplar data. However, ML methods cannot offer safety guarantees and sometimes behave unpredictably. To combat this, our approach uses a simple yet effective rule-based fallback layer that performs sanity checks on an ML planner's decisions (e.g. avoiding collision, assuring physical feasibility). This allows us to leverage ML to handle complex situations while still assuring the safety, reducing ML planner-only collisions by 95%. We train our ML planner on 300 hours of expert driving demonstrations using imitation learning and deploy it along with the fallback layer in downtown San Francisco, where it takes complete control of a real vehicle and navigates a wide variety of challenging urban driving scenarios." @default.
- W3203018838 created "2021-10-11" @default.
- W3203018838 creator A5009893506 @default.
- W3203018838 creator A5011461720 @default.
- W3203018838 creator A5021285235 @default.
- W3203018838 creator A5025503042 @default.
- W3203018838 creator A5027150082 @default.
- W3203018838 creator A5027640416 @default.
- W3203018838 creator A5054632305 @default.
- W3203018838 creator A5055852137 @default.
- W3203018838 creator A5056457613 @default.
- W3203018838 creator A5090610298 @default.
- W3203018838 date "2022-05-23" @default.
- W3203018838 modified "2023-10-11" @default.
- W3203018838 title "SafetyNet: Safe Planning for Real-World Self-Driving Vehicles Using Machine-Learned Policies" @default.
- W3203018838 cites W155097506 @default.
- W3203018838 cites W1971086298 @default.
- W3203018838 cites W1983948265 @default.
- W3203018838 cites W2021667711 @default.
- W3203018838 cites W2144304287 @default.
- W3203018838 cites W2152422164 @default.
- W3203018838 cites W2219970372 @default.
- W3203018838 cites W2343568200 @default.
- W3203018838 cites W2394607849 @default.
- W3203018838 cites W2505763307 @default.
- W3203018838 cites W2905173465 @default.
- W3203018838 cites W2963645756 @default.
- W3203018838 cites W2967969632 @default.
- W3203018838 cites W2968008415 @default.
- W3203018838 cites W2968983352 @default.
- W3203018838 cites W3034722190 @default.
- W3203018838 cites W3090153548 @default.
- W3203018838 cites W3090202852 @default.
- W3203018838 cites W3105834261 @default.
- W3203018838 cites W3172477795 @default.
- W3203018838 cites W3207915602 @default.
- W3203018838 doi "https://doi.org/10.1109/icra46639.2022.9811576" @default.
- W3203018838 hasPublicationYear "2022" @default.
- W3203018838 type Work @default.
- W3203018838 sameAs 3203018838 @default.
- W3203018838 citedByCount "6" @default.
- W3203018838 countsByYear W32030188382022 @default.
- W3203018838 countsByYear W32030188382023 @default.
- W3203018838 crossrefType "proceedings-article" @default.
- W3203018838 hasAuthorship W3203018838A5009893506 @default.
- W3203018838 hasAuthorship W3203018838A5011461720 @default.
- W3203018838 hasAuthorship W3203018838A5021285235 @default.
- W3203018838 hasAuthorship W3203018838A5025503042 @default.
- W3203018838 hasAuthorship W3203018838A5027150082 @default.
- W3203018838 hasAuthorship W3203018838A5027640416 @default.
- W3203018838 hasAuthorship W3203018838A5054632305 @default.
- W3203018838 hasAuthorship W3203018838A5055852137 @default.
- W3203018838 hasAuthorship W3203018838A5056457613 @default.
- W3203018838 hasAuthorship W3203018838A5090610298 @default.
- W3203018838 hasBestOaLocation W32030188382 @default.
- W3203018838 hasConcept C119857082 @default.
- W3203018838 hasConcept C136197465 @default.
- W3203018838 hasConcept C153083717 @default.
- W3203018838 hasConcept C154945302 @default.
- W3203018838 hasConcept C2776999362 @default.
- W3203018838 hasConcept C41008148 @default.
- W3203018838 hasConcept C44154836 @default.
- W3203018838 hasConcept C81074085 @default.
- W3203018838 hasConcept C90509273 @default.
- W3203018838 hasConceptScore W3203018838C119857082 @default.
- W3203018838 hasConceptScore W3203018838C136197465 @default.
- W3203018838 hasConceptScore W3203018838C153083717 @default.
- W3203018838 hasConceptScore W3203018838C154945302 @default.
- W3203018838 hasConceptScore W3203018838C2776999362 @default.
- W3203018838 hasConceptScore W3203018838C41008148 @default.
- W3203018838 hasConceptScore W3203018838C44154836 @default.
- W3203018838 hasConceptScore W3203018838C81074085 @default.
- W3203018838 hasConceptScore W3203018838C90509273 @default.
- W3203018838 hasLocation W32030188381 @default.
- W3203018838 hasLocation W32030188382 @default.
- W3203018838 hasOpenAccess W3203018838 @default.
- W3203018838 hasPrimaryLocation W32030188381 @default.
- W3203018838 hasRelatedWork W1548568597 @default.
- W3203018838 hasRelatedWork W2002361198 @default.
- W3203018838 hasRelatedWork W2114119680 @default.
- W3203018838 hasRelatedWork W2366039691 @default.
- W3203018838 hasRelatedWork W2482749251 @default.
- W3203018838 hasRelatedWork W2897994211 @default.
- W3203018838 hasRelatedWork W4244698559 @default.
- W3203018838 hasRelatedWork W4246538999 @default.
- W3203018838 hasRelatedWork W56933075 @default.
- W3203018838 hasRelatedWork W804484174 @default.
- W3203018838 isParatext "false" @default.
- W3203018838 isRetracted "false" @default.
- W3203018838 magId "3203018838" @default.
- W3203018838 workType "article" @default.