Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320029090> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4320029090 abstract "Grasping objects of different shapes and sizes-a foundational, effortless skill for humans-remains a challenging task in robotics. Although model-based approaches can predict stable grasp configurations for known object models, they struggle to generalize to novel objects and often operate in a non-interactive open-loop manner. In this work, we present a reinforcement learning framework that learns the interactive grasping of various geometrically distinct real-world objects by continuously controlling an anthropomorphic robotic hand. We explore several explicit representations of object geometry as input to the policy. Moreover, we propose to inform the policy implicitly through signed distances and show that this is naturally suited to guide the search through a shaped reward component. Finally, we demonstrate that the proposed framework is able to learn even in more challenging conditions, such as targeted grasping from a cluttered bin. Necessary pre-grasping behaviors such as object reorientation and utilization of environmental constraints emerge in this case. Videos of learned interactive policies are available at https://maltemosbach.github.io/geometry_aware_grasping policies." @default.
- W4320029090 created "2023-02-12" @default.
- W4320029090 creator A5034530070 @default.
- W4320029090 creator A5081692888 @default.
- W4320029090 date "2022-12-01" @default.
- W4320029090 modified "2023-10-03" @default.
- W4320029090 title "Efficient Representations of Object Geometry for Reinforcement Learning of Interactive Grasping Policies" @default.
- W4320029090 cites W1505952289 @default.
- W4320029090 cites W2023751161 @default.
- W4320029090 cites W2073408938 @default.
- W4320029090 cites W2415026371 @default.
- W4320029090 cites W2736737714 @default.
- W4320029090 cites W2962759351 @default.
- W4320029090 cites W2963411833 @default.
- W4320029090 cites W2981010689 @default.
- W4320029090 cites W3004091482 @default.
- W4320029090 cites W3088158297 @default.
- W4320029090 cites W3090299930 @default.
- W4320029090 cites W3092037789 @default.
- W4320029090 cites W4226166070 @default.
- W4320029090 cites W4283787029 @default.
- W4320029090 cites W4283788634 @default.
- W4320029090 doi "https://doi.org/10.1109/irc55401.2022.00034" @default.
- W4320029090 hasPublicationYear "2022" @default.
- W4320029090 type Work @default.
- W4320029090 citedByCount "3" @default.
- W4320029090 countsByYear W43200290902023 @default.
- W4320029090 crossrefType "proceedings-article" @default.
- W4320029090 hasAuthorship W4320029090A5034530070 @default.
- W4320029090 hasAuthorship W4320029090A5081692888 @default.
- W4320029090 hasConcept C107457646 @default.
- W4320029090 hasConcept C121332964 @default.
- W4320029090 hasConcept C127413603 @default.
- W4320029090 hasConcept C154945302 @default.
- W4320029090 hasConcept C168167062 @default.
- W4320029090 hasConcept C171268870 @default.
- W4320029090 hasConcept C194995250 @default.
- W4320029090 hasConcept C199360897 @default.
- W4320029090 hasConcept C201995342 @default.
- W4320029090 hasConcept C2775960376 @default.
- W4320029090 hasConcept C2776716048 @default.
- W4320029090 hasConcept C2780451532 @default.
- W4320029090 hasConcept C2781238097 @default.
- W4320029090 hasConcept C31972630 @default.
- W4320029090 hasConcept C34413123 @default.
- W4320029090 hasConcept C41008148 @default.
- W4320029090 hasConcept C49774154 @default.
- W4320029090 hasConcept C78519656 @default.
- W4320029090 hasConcept C90509273 @default.
- W4320029090 hasConcept C97355855 @default.
- W4320029090 hasConcept C97541855 @default.
- W4320029090 hasConceptScore W4320029090C107457646 @default.
- W4320029090 hasConceptScore W4320029090C121332964 @default.
- W4320029090 hasConceptScore W4320029090C127413603 @default.
- W4320029090 hasConceptScore W4320029090C154945302 @default.
- W4320029090 hasConceptScore W4320029090C168167062 @default.
- W4320029090 hasConceptScore W4320029090C171268870 @default.
- W4320029090 hasConceptScore W4320029090C194995250 @default.
- W4320029090 hasConceptScore W4320029090C199360897 @default.
- W4320029090 hasConceptScore W4320029090C201995342 @default.
- W4320029090 hasConceptScore W4320029090C2775960376 @default.
- W4320029090 hasConceptScore W4320029090C2776716048 @default.
- W4320029090 hasConceptScore W4320029090C2780451532 @default.
- W4320029090 hasConceptScore W4320029090C2781238097 @default.
- W4320029090 hasConceptScore W4320029090C31972630 @default.
- W4320029090 hasConceptScore W4320029090C34413123 @default.
- W4320029090 hasConceptScore W4320029090C41008148 @default.
- W4320029090 hasConceptScore W4320029090C49774154 @default.
- W4320029090 hasConceptScore W4320029090C78519656 @default.
- W4320029090 hasConceptScore W4320029090C90509273 @default.
- W4320029090 hasConceptScore W4320029090C97355855 @default.
- W4320029090 hasConceptScore W4320029090C97541855 @default.
- W4320029090 hasFunder F4320311687 @default.
- W4320029090 hasLocation W43200290901 @default.
- W4320029090 hasOpenAccess W4320029090 @default.
- W4320029090 hasPrimaryLocation W43200290901 @default.
- W4320029090 hasRelatedWork W1636820063 @default.
- W4320029090 hasRelatedWork W2100239260 @default.
- W4320029090 hasRelatedWork W2163529784 @default.
- W4320029090 hasRelatedWork W2597594640 @default.
- W4320029090 hasRelatedWork W3004284873 @default.
- W4320029090 hasRelatedWork W3014080459 @default.
- W4320029090 hasRelatedWork W3185561939 @default.
- W4320029090 hasRelatedWork W4249963983 @default.
- W4320029090 hasRelatedWork W4320029090 @default.
- W4320029090 hasRelatedWork W4360993698 @default.
- W4320029090 isParatext "false" @default.
- W4320029090 isRetracted "false" @default.
- W4320029090 workType "article" @default.