Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386981938> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4386981938 abstract "Humans can leverage physical interaction to teach robot arms. This physical interaction takes multiple forms depending on the task, the user, and what the robot has learned so far. State-of-the-art approaches focus on learning from a single modality, or combine some interaction types. Some methods do so by assuming that the robot has prior information about the features of the task and the reward structure. By contrast, in this paper we introduce an algorithmic formalism that unites learning from demonstrations, corrections, and preferences. Our approach makes no assumptions about the tasks the human wants to teach the robot; instead, we learn a reward model from scratch by comparing the human’s input to nearby alternatives, i.e., trajectories close to the human’s feedback. We first derive a loss function that trains an ensemble of reward models to match the human’s demonstrations, corrections, and preferences. The type and order of feedback is up to the human teacher: we enable the robot to collect this feedback passively or actively. We then apply constrained optimization to convert our learned reward into a desired robot trajectory. Through simulations and a user study we demonstrate that our proposed approach more accurately learns manipulation tasks from physical human interaction than existing baselines, particularly when the robot is faced with new or unexpected objectives. Videos of our user study are available at: https://youtu.be/FSUJsTYvEKU" @default.
- W4386981938 created "2023-09-24" @default.
- W4386981938 creator A5014071264 @default.
- W4386981938 creator A5063608480 @default.
- W4386981938 date "2023-09-22" @default.
- W4386981938 modified "2023-10-18" @default.
- W4386981938 title "Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot Interaction" @default.
- W4386981938 cites W1837766154 @default.
- W4386981938 cites W187005120 @default.
- W4386981938 cites W1986014385 @default.
- W4386981938 cites W2050835671 @default.
- W4386981938 cites W2050985708 @default.
- W4386981938 cites W2142224528 @default.
- W4386981938 cites W2169513627 @default.
- W4386981938 cites W2766053765 @default.
- W4386981938 cites W2784881541 @default.
- W4386981938 cites W2799280697 @default.
- W4386981938 cites W2801531857 @default.
- W4386981938 cites W2907920236 @default.
- W4386981938 cites W3014235025 @default.
- W4386981938 cites W3092948749 @default.
- W4386981938 cites W3101780148 @default.
- W4386981938 cites W3105789002 @default.
- W4386981938 cites W3106171760 @default.
- W4386981938 cites W3134935089 @default.
- W4386981938 cites W3207713159 @default.
- W4386981938 doi "https://doi.org/10.1145/3623384" @default.
- W4386981938 hasPublicationYear "2023" @default.
- W4386981938 type Work @default.
- W4386981938 citedByCount "0" @default.
- W4386981938 crossrefType "journal-article" @default.
- W4386981938 hasAuthorship W4386981938A5014071264 @default.
- W4386981938 hasAuthorship W4386981938A5063608480 @default.
- W4386981938 hasBestOaLocation W43869819381 @default.
- W4386981938 hasConcept C107457646 @default.
- W4386981938 hasConcept C111919701 @default.
- W4386981938 hasConcept C120665830 @default.
- W4386981938 hasConcept C121332964 @default.
- W4386981938 hasConcept C127413603 @default.
- W4386981938 hasConcept C145460709 @default.
- W4386981938 hasConcept C153083717 @default.
- W4386981938 hasConcept C154945302 @default.
- W4386981938 hasConcept C188888258 @default.
- W4386981938 hasConcept C192209626 @default.
- W4386981938 hasConcept C19966478 @default.
- W4386981938 hasConcept C201995342 @default.
- W4386981938 hasConcept C2780451532 @default.
- W4386981938 hasConcept C2781235140 @default.
- W4386981938 hasConcept C41008148 @default.
- W4386981938 hasConcept C90509273 @default.
- W4386981938 hasConcept C97541855 @default.
- W4386981938 hasConceptScore W4386981938C107457646 @default.
- W4386981938 hasConceptScore W4386981938C111919701 @default.
- W4386981938 hasConceptScore W4386981938C120665830 @default.
- W4386981938 hasConceptScore W4386981938C121332964 @default.
- W4386981938 hasConceptScore W4386981938C127413603 @default.
- W4386981938 hasConceptScore W4386981938C145460709 @default.
- W4386981938 hasConceptScore W4386981938C153083717 @default.
- W4386981938 hasConceptScore W4386981938C154945302 @default.
- W4386981938 hasConceptScore W4386981938C188888258 @default.
- W4386981938 hasConceptScore W4386981938C192209626 @default.
- W4386981938 hasConceptScore W4386981938C19966478 @default.
- W4386981938 hasConceptScore W4386981938C201995342 @default.
- W4386981938 hasConceptScore W4386981938C2780451532 @default.
- W4386981938 hasConceptScore W4386981938C2781235140 @default.
- W4386981938 hasConceptScore W4386981938C41008148 @default.
- W4386981938 hasConceptScore W4386981938C90509273 @default.
- W4386981938 hasConceptScore W4386981938C97541855 @default.
- W4386981938 hasLocation W43869819381 @default.
- W4386981938 hasOpenAccess W4386981938 @default.
- W4386981938 hasPrimaryLocation W43869819381 @default.
- W4386981938 hasRelatedWork W1763389228 @default.
- W4386981938 hasRelatedWork W2079554071 @default.
- W4386981938 hasRelatedWork W2211482300 @default.
- W4386981938 hasRelatedWork W2323122434 @default.
- W4386981938 hasRelatedWork W2342491023 @default.
- W4386981938 hasRelatedWork W2343019076 @default.
- W4386981938 hasRelatedWork W2568232068 @default.
- W4386981938 hasRelatedWork W2627853561 @default.
- W4386981938 hasRelatedWork W4200394088 @default.
- W4386981938 hasRelatedWork W4229726131 @default.
- W4386981938 isParatext "false" @default.
- W4386981938 isRetracted "false" @default.
- W4386981938 workType "article" @default.