Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205111278> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3205111278 abstract "Learning object manipulation is a critical skill for robots to interact with their environment. Even though there has been significant progress in robotic manipulation of rigid objects, interacting with non-rigid objects remains challenging for robots. In this work, we introduce velcro peeling as a new application for robotic manipulation of non-rigid objects in complex environments. We present a method of learning force-based manipulation from noisy and incomplete sensor inputs in partially observable environments by modeling long term dependencies between measurements with a multi-step deep recurrent network. We present experiments on a real robot to show the necessity of modeling these long term dependencies and validate our approach in simulation and robot experiments. Our results show that using tactile input enables the robot to overcome geometric uncertainties present in the environment with high fidelity in ∼ 90% of all cases, outperforming the baselines by a large margin." @default.
- W3205111278 created "2021-10-25" @default.
- W3205111278 creator A5033839227 @default.
- W3205111278 creator A5046044122 @default.
- W3205111278 creator A5085052085 @default.
- W3205111278 date "2021-05-30" @default.
- W3205111278 modified "2023-09-26" @default.
- W3205111278 title "Multi-Step Recurrent Q-Learning for Robotic Velcro Peeling" @default.
- W3205111278 cites W1966487689 @default.
- W3205111278 cites W1978580730 @default.
- W3205111278 cites W1983156320 @default.
- W3205111278 cites W1988207416 @default.
- W3205111278 cites W2017801178 @default.
- W3205111278 cites W2045448547 @default.
- W3205111278 cites W2094808257 @default.
- W3205111278 cites W2120429435 @default.
- W3205111278 cites W2145339207 @default.
- W3205111278 cites W2146662771 @default.
- W3205111278 cites W2166459342 @default.
- W3205111278 cites W2201912979 @default.
- W3205111278 cites W2287992105 @default.
- W3205111278 cites W2322971354 @default.
- W3205111278 cites W2795550549 @default.
- W3205111278 cites W2808405904 @default.
- W3205111278 cites W2952866402 @default.
- W3205111278 cites W2962679776 @default.
- W3205111278 cites W2962736495 @default.
- W3205111278 cites W2962793652 @default.
- W3205111278 cites W2963033241 @default.
- W3205111278 cites W2963280659 @default.
- W3205111278 cites W2968095426 @default.
- W3205111278 cites W2979717831 @default.
- W3205111278 cites W2990032740 @default.
- W3205111278 cites W2990747716 @default.
- W3205111278 cites W3006936931 @default.
- W3205111278 cites W3106023961 @default.
- W3205111278 cites W32403112 @default.
- W3205111278 doi "https://doi.org/10.1109/icra48506.2021.9561030" @default.
- W3205111278 hasPublicationYear "2021" @default.
- W3205111278 type Work @default.
- W3205111278 sameAs 3205111278 @default.
- W3205111278 citedByCount "1" @default.
- W3205111278 countsByYear W32051112782023 @default.
- W3205111278 crossrefType "proceedings-article" @default.
- W3205111278 hasAuthorship W3205111278A5033839227 @default.
- W3205111278 hasAuthorship W3205111278A5046044122 @default.
- W3205111278 hasAuthorship W3205111278A5085052085 @default.
- W3205111278 hasBestOaLocation W32051112782 @default.
- W3205111278 hasConcept C113364801 @default.
- W3205111278 hasConcept C119599485 @default.
- W3205111278 hasConcept C119857082 @default.
- W3205111278 hasConcept C127413603 @default.
- W3205111278 hasConcept C154945302 @default.
- W3205111278 hasConcept C2776459999 @default.
- W3205111278 hasConcept C2781238097 @default.
- W3205111278 hasConcept C31972630 @default.
- W3205111278 hasConcept C41008148 @default.
- W3205111278 hasConcept C76155785 @default.
- W3205111278 hasConcept C774472 @default.
- W3205111278 hasConcept C90509273 @default.
- W3205111278 hasConceptScore W3205111278C113364801 @default.
- W3205111278 hasConceptScore W3205111278C119599485 @default.
- W3205111278 hasConceptScore W3205111278C119857082 @default.
- W3205111278 hasConceptScore W3205111278C127413603 @default.
- W3205111278 hasConceptScore W3205111278C154945302 @default.
- W3205111278 hasConceptScore W3205111278C2776459999 @default.
- W3205111278 hasConceptScore W3205111278C2781238097 @default.
- W3205111278 hasConceptScore W3205111278C31972630 @default.
- W3205111278 hasConceptScore W3205111278C41008148 @default.
- W3205111278 hasConceptScore W3205111278C76155785 @default.
- W3205111278 hasConceptScore W3205111278C774472 @default.
- W3205111278 hasConceptScore W3205111278C90509273 @default.
- W3205111278 hasLocation W32051112781 @default.
- W3205111278 hasLocation W32051112782 @default.
- W3205111278 hasOpenAccess W3205111278 @default.
- W3205111278 hasPrimaryLocation W32051112781 @default.
- W3205111278 hasRelatedWork W1837097281 @default.
- W3205111278 hasRelatedWork W1966410754 @default.
- W3205111278 hasRelatedWork W2007544051 @default.
- W3205111278 hasRelatedWork W2030539674 @default.
- W3205111278 hasRelatedWork W2095705906 @default.
- W3205111278 hasRelatedWork W2325242284 @default.
- W3205111278 hasRelatedWork W2363840281 @default.
- W3205111278 hasRelatedWork W2732308154 @default.
- W3205111278 hasRelatedWork W2789220062 @default.
- W3205111278 hasRelatedWork W2975200075 @default.
- W3205111278 isParatext "false" @default.
- W3205111278 isRetracted "false" @default.
- W3205111278 magId "3205111278" @default.
- W3205111278 workType "article" @default.