FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204607681> ?p ?o ?g. }

• W3204607681 abstract "We tackle real-world long-horizon robot manipulation tasks through skill discovery. We present a bottom-up approach to learning a library of reusable skills from unsegmented demonstrations and use these skills to synthesize prolonged robot behaviors. Our method starts with constructing a hierarchical task structure from each demonstration through agglomerative clustering. From the task structures of multi-task demonstrations, we identify skills based on the recurring patterns and train goal-conditioned sensorimotor policies with hierarchical imitation learning. Finally, we train a meta controller to compose these skills to solve long-horizon manipulation tasks. The entire model can be trained on a small set of human demonstrations collected within 30 minutes without further annotations, making it amendable to real-world deployment. We systematically evaluated our method in simulation environments and on a real robot. Our method has shown superior performance over state-of-the-art imitation learning methods in multi-stage manipulation tasks. Furthermore, skills discovered from multi-task demonstrations boost the average task success by $8%$ compared to those discovered from individual tasks." @default.
• W3204607681 created "2021-10-11" @default.
• W3204607681 creator A5001594330 @default.
• W3204607681 creator A5030826237 @default.
• W3204607681 creator A5035249197 @default.
• W3204607681 date "2021-09-28" @default.
• W3204607681 modified "2023-09-27" @default.
• W3204607681 title "Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation" @default.
• W3204607681 cites W1488730473 @default.
• W3204607681 cites W1529739011 @default.
• W3204607681 cites W1585861384 @default.
• W3204607681 cites W1837533429 @default.
• W3204607681 cites W1907587592 @default.
• W3204607681 cites W2022760091 @default.
• W3204607681 cites W2027972120 @default.
• W3204607681 cites W2039170454 @default.
• W3204607681 cites W2070683816 @default.
• W3204607681 cites W2097856935 @default.
• W3204607681 cites W2105348292 @default.
• W3204607681 cites W2108535023 @default.
• W3204607681 cites W2109910161 @default.
• W3204607681 cites W2112474089 @default.
• W3204607681 cites W2116064496 @default.
• W3204607681 cites W2132914434 @default.
• W3204607681 cites W2135639338 @default.
• W3204607681 cites W2172131460 @default.
• W3204607681 cites W2307770531 @default.
• W3204607681 cites W2397253692 @default.
• W3204607681 cites W2556477470 @default.
• W3204607681 cites W2594829461 @default.
• W3204607681 cites W2601322194 @default.
• W3204607681 cites W2605016475 @default.
• W3204607681 cites W2785342287 @default.
• W3204607681 cites W2892211305 @default.
• W3204607681 cites W2898525034 @default.
• W3204607681 cites W2899289853 @default.
• W3204607681 cites W2902592652 @default.
• W3204607681 cites W2945438069 @default.
• W3204607681 cites W2951004968 @default.
• W3204607681 cites W2963438456 @default.
• W3204607681 cites W2963669336 @default.
• W3204607681 cites W2963927307 @default.
• W3204607681 cites W2964001908 @default.
• W3204607681 cites W2964055695 @default.
• W3204607681 cites W2964250417 @default.
• W3204607681 cites W2968344028 @default.
• W3204607681 cites W2982673782 @default.
• W3204607681 cites W2995636097 @default.
• W3204607681 cites W2996086858 @default.
• W3204607681 cites W3012366945 @default.
• W3204607681 cites W3012573144 @default.
• W3204607681 cites W3027456239 @default.
• W3204607681 cites W3028830971 @default.
• W3204607681 cites W3034731205 @default.
• W3204607681 cites W3035406442 @default.
• W3204607681 cites W3039055967 @default.
• W3204607681 cites W3088304681 @default.
• W3204607681 cites W3090369311 @default.
• W3204607681 cites W3128894241 @default.
• W3204607681 cites W3150915266 @default.
• W3204607681 cites W3174700686 @default.
• W3204607681 cites W3207612633 @default.
• W3204607681 cites W377632744 @default.
• W3204607681 cites W567721252 @default.
• W3204607681 cites W2962799400 @default.
• W3204607681 doi "https://doi.org/10.48550/arxiv.2109.13841" @default.
• W3204607681 hasPublicationYear "2021" @default.
• W3204607681 type Work @default.
• W3204607681 sameAs 3204607681 @default.
• W3204607681 citedByCount "0" @default.
• W3204607681 crossrefType "posted-content" @default.
• W3204607681 hasAuthorship W3204607681A5001594330 @default.
• W3204607681 hasAuthorship W3204607681A5030826237 @default.
• W3204607681 hasAuthorship W3204607681A5035249197 @default.
• W3204607681 hasBestOaLocation W32046076811 @default.
• W3204607681 hasConcept C105339364 @default.
• W3204607681 hasConcept C107457646 @default.
• W3204607681 hasConcept C111919701 @default.
• W3204607681 hasConcept C119857082 @default.
• W3204607681 hasConcept C121332964 @default.
• W3204607681 hasConcept C126388530 @default.
• W3204607681 hasConcept C127413603 @default.
• W3204607681 hasConcept C1276947 @default.
• W3204607681 hasConcept C132758656 @default.
• W3204607681 hasConcept C154945302 @default.
• W3204607681 hasConcept C15744967 @default.
• W3204607681 hasConcept C159176650 @default.
• W3204607681 hasConcept C162324750 @default.
• W3204607681 hasConcept C177264268 @default.
• W3204607681 hasConcept C199360897 @default.
• W3204607681 hasConcept C201995342 @default.
• W3204607681 hasConcept C2780451532 @default.
• W3204607681 hasConcept C41008148 @default.
• W3204607681 hasConcept C50522688 @default.
• W3204607681 hasConcept C73555534 @default.
• W3204607681 hasConcept C77805123 @default.
• W3204607681 hasConcept C90509273 @default.
• W3204607681 hasConceptScore W3204607681C105339364 @default.
• W3204607681 hasConceptScore W3204607681C107457646 @default.
• W3204607681 hasConceptScore W3204607681C111919701 @default.

• next