Matches in SemOpenAlex for { <https://semopenalex.org/work/W3188523627> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W3188523627 abstract "Learning new tasks has always been a challenging problem in robotics. Even though several approaches have been proposed, from manual programming to learning from demonstrations, the field has directions which require further research and development. This thesis focuses on one of these relatively unexplored areas: observational learning. We present O2A, a novel method for learning to perform robotic manipulation tasks from a single (one-shot) third-person demonstration video. The key novelty lies in pre-training a feature extractor for creating an abstract feature representation for actions that we call ‘action vectors’. The action vectors are extracted using a 3D-CNN network pre-trained for action recognition on a generic action dataset. The distance between the action vectors from the observed third-person demonstration and trial robot executions are used as a reward/cost for learning of the demonstrated task. We report on experiments in simulation and on a real robot, with changes in viewpoint of observation, properties of the objects involved, scene background and morphology of the manipulator between the demonstration and the learning domains. O2A outperforms baseline approaches under different domain shifts and has comparable performance with an oracle (that uses an ideal reward function). We also plot visualisation of trajectories and show that our method has high reward for desired trajectories. Finally, we present a framework for extending observational learning with multi modal observations. We report our initial experiments and results in the future works." @default.
- W3188523627 created "2021-08-16" @default.
- W3188523627 creator A5014095557 @default.
- W3188523627 date "2021-03-01" @default.
- W3188523627 modified "2023-09-22" @default.
- W3188523627 title "Seeing to learn: Observational learning of robotic manipulation tasks" @default.
- W3188523627 hasPublicationYear "2021" @default.
- W3188523627 type Work @default.
- W3188523627 sameAs 3188523627 @default.
- W3188523627 citedByCount "0" @default.
- W3188523627 crossrefType "dissertation" @default.
- W3188523627 hasAuthorship W3188523627A5014095557 @default.
- W3188523627 hasConcept C107457646 @default.
- W3188523627 hasConcept C119857082 @default.
- W3188523627 hasConcept C121332964 @default.
- W3188523627 hasConcept C138885662 @default.
- W3188523627 hasConcept C154945302 @default.
- W3188523627 hasConcept C27206212 @default.
- W3188523627 hasConcept C2776401178 @default.
- W3188523627 hasConcept C2778738651 @default.
- W3188523627 hasConcept C2778924833 @default.
- W3188523627 hasConcept C2780791683 @default.
- W3188523627 hasConcept C34413123 @default.
- W3188523627 hasConcept C41008148 @default.
- W3188523627 hasConcept C41895202 @default.
- W3188523627 hasConcept C62520636 @default.
- W3188523627 hasConcept C90509273 @default.
- W3188523627 hasConceptScore W3188523627C107457646 @default.
- W3188523627 hasConceptScore W3188523627C119857082 @default.
- W3188523627 hasConceptScore W3188523627C121332964 @default.
- W3188523627 hasConceptScore W3188523627C138885662 @default.
- W3188523627 hasConceptScore W3188523627C154945302 @default.
- W3188523627 hasConceptScore W3188523627C27206212 @default.
- W3188523627 hasConceptScore W3188523627C2776401178 @default.
- W3188523627 hasConceptScore W3188523627C2778738651 @default.
- W3188523627 hasConceptScore W3188523627C2778924833 @default.
- W3188523627 hasConceptScore W3188523627C2780791683 @default.
- W3188523627 hasConceptScore W3188523627C34413123 @default.
- W3188523627 hasConceptScore W3188523627C41008148 @default.
- W3188523627 hasConceptScore W3188523627C41895202 @default.
- W3188523627 hasConceptScore W3188523627C62520636 @default.
- W3188523627 hasConceptScore W3188523627C90509273 @default.
- W3188523627 hasLocation W31885236271 @default.
- W3188523627 hasOpenAccess W3188523627 @default.
- W3188523627 hasPrimaryLocation W31885236271 @default.
- W3188523627 hasRelatedWork W1164749991 @default.
- W3188523627 hasRelatedWork W2108689239 @default.
- W3188523627 hasRelatedWork W2108970313 @default.
- W3188523627 hasRelatedWork W2157527365 @default.
- W3188523627 hasRelatedWork W2583137229 @default.
- W3188523627 hasRelatedWork W2743553019 @default.
- W3188523627 hasRelatedWork W2887503931 @default.
- W3188523627 hasRelatedWork W2889878992 @default.
- W3188523627 hasRelatedWork W2963823230 @default.
- W3188523627 hasRelatedWork W2968227116 @default.
- W3188523627 hasRelatedWork W2995078345 @default.
- W3188523627 hasRelatedWork W3003653070 @default.
- W3188523627 hasRelatedWork W3012384939 @default.
- W3188523627 hasRelatedWork W3044694928 @default.
- W3188523627 hasRelatedWork W3115080916 @default.
- W3188523627 hasRelatedWork W3126596751 @default.
- W3188523627 hasRelatedWork W3135512538 @default.
- W3188523627 hasRelatedWork W3198691241 @default.
- W3188523627 hasRelatedWork W3209493138 @default.
- W3188523627 hasRelatedWork W3213085571 @default.
- W3188523627 isParatext "false" @default.
- W3188523627 isRetracted "false" @default.
- W3188523627 magId "3188523627" @default.
- W3188523627 workType "dissertation" @default.