Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994157070> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2994157070 endingPage "25" @default.
- W2994157070 startingPage "1" @default.
- W2994157070 abstract "Learning from demonstration (LfD) enables a robot to emulate natural human movement instead of merely executing preprogrammed behaviors. This article presents a hierarchical LfD structure of task-parameterized models for object movement tasks, which are ubiquitous in everyday life and could benefit from robotic support. Our approach uses the task-parameterized Gaussian mixture model (TP-GMM) algorithm to encode sets of demonstrations in separate models that each correspond to a different task situation. The robot then maximizes its expected performance in a new situation by either selecting a good existing model or requesting new demonstrations. Compared to a standard implementation that encodes all demonstrations together for all test situations, the proposed approach offers four advantages. First, a simply defined distance function can be used to estimate test performance by calculating the similarity between a test situation and the existing models. Second, the proposed approach can improve generalization, e.g., better satisfying the demonstrated task constraints and speeding up task execution. Third, because the hierarchical structure encodes each demonstrated situation individually, a wider range of task situations can be modeled in the same framework without deteriorating performance. Last, adding or removing demonstrations incurs low computational load, and thus, the robot’s skill library can be built incrementally. We first instantiate the proposed approach in a simulated task to validate these advantages. We then show that the advantages transfer to real hardware for a task where naive participants collaborated with a Willow Garage PR2 robot to move a handheld object. For most tested scenarios, our hierarchical method achieved significantly better task performance and subjective ratings than both a passive model with only gravity compensation and a single TP-GMM encoding all demonstrations." @default.
- W2994157070 created "2019-12-13" @default.
- W2994157070 creator A5033050402 @default.
- W2994157070 creator A5080962480 @default.
- W2994157070 date "2019-12-02" @default.
- W2994157070 modified "2023-09-30" @default.
- W2994157070 title "Hierarchical Task-Parameterized Learning from Demonstration for Collaborative Object Movement" @default.
- W2994157070 cites W1986014385 @default.
- W2994157070 cites W2024076758 @default.
- W2994157070 cites W2057069782 @default.
- W2994157070 cites W2063182199 @default.
- W2994157070 cites W2076618452 @default.
- W2994157070 cites W2100993276 @default.
- W2994157070 cites W2115166552 @default.
- W2994157070 cites W2154018708 @default.
- W2994157070 cites W2157289187 @default.
- W2994157070 cites W2162130878 @default.
- W2994157070 cites W2168175751 @default.
- W2994157070 cites W2243880070 @default.
- W2994157070 cites W2331138946 @default.
- W2994157070 cites W2471216432 @default.
- W2994157070 cites W2593216298 @default.
- W2994157070 cites W2609992816 @default.
- W2994157070 cites W2738231311 @default.
- W2994157070 doi "https://doi.org/10.1155/2019/9765383" @default.
- W2994157070 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6914968" @default.
- W2994157070 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31885690" @default.
- W2994157070 hasPublicationYear "2019" @default.
- W2994157070 type Work @default.
- W2994157070 sameAs 2994157070 @default.
- W2994157070 citedByCount "4" @default.
- W2994157070 countsByYear W29941570702021 @default.
- W2994157070 countsByYear W29941570702022 @default.
- W2994157070 countsByYear W29941570702023 @default.
- W2994157070 crossrefType "journal-article" @default.
- W2994157070 hasAuthorship W2994157070A5033050402 @default.
- W2994157070 hasAuthorship W2994157070A5080962480 @default.
- W2994157070 hasBestOaLocation W29941570701 @default.
- W2994157070 hasConcept C103278499 @default.
- W2994157070 hasConcept C107457646 @default.
- W2994157070 hasConcept C11413529 @default.
- W2994157070 hasConcept C115961682 @default.
- W2994157070 hasConcept C119857082 @default.
- W2994157070 hasConcept C127413603 @default.
- W2994157070 hasConcept C134306372 @default.
- W2994157070 hasConcept C154945302 @default.
- W2994157070 hasConcept C165464430 @default.
- W2994157070 hasConcept C177148314 @default.
- W2994157070 hasConcept C201995342 @default.
- W2994157070 hasConcept C2779038628 @default.
- W2994157070 hasConcept C2780451532 @default.
- W2994157070 hasConcept C2781238097 @default.
- W2994157070 hasConcept C33923547 @default.
- W2994157070 hasConcept C41008148 @default.
- W2994157070 hasConcept C90509273 @default.
- W2994157070 hasConceptScore W2994157070C103278499 @default.
- W2994157070 hasConceptScore W2994157070C107457646 @default.
- W2994157070 hasConceptScore W2994157070C11413529 @default.
- W2994157070 hasConceptScore W2994157070C115961682 @default.
- W2994157070 hasConceptScore W2994157070C119857082 @default.
- W2994157070 hasConceptScore W2994157070C127413603 @default.
- W2994157070 hasConceptScore W2994157070C134306372 @default.
- W2994157070 hasConceptScore W2994157070C154945302 @default.
- W2994157070 hasConceptScore W2994157070C165464430 @default.
- W2994157070 hasConceptScore W2994157070C177148314 @default.
- W2994157070 hasConceptScore W2994157070C201995342 @default.
- W2994157070 hasConceptScore W2994157070C2779038628 @default.
- W2994157070 hasConceptScore W2994157070C2780451532 @default.
- W2994157070 hasConceptScore W2994157070C2781238097 @default.
- W2994157070 hasConceptScore W2994157070C33923547 @default.
- W2994157070 hasConceptScore W2994157070C41008148 @default.
- W2994157070 hasConceptScore W2994157070C90509273 @default.
- W2994157070 hasFunder F4320306076 @default.
- W2994157070 hasLocation W29941570701 @default.
- W2994157070 hasLocation W29941570702 @default.
- W2994157070 hasLocation W29941570703 @default.
- W2994157070 hasLocation W29941570704 @default.
- W2994157070 hasOpenAccess W2994157070 @default.
- W2994157070 hasPrimaryLocation W29941570701 @default.
- W2994157070 hasRelatedWork W1636820063 @default.
- W2994157070 hasRelatedWork W2007722085 @default.
- W2994157070 hasRelatedWork W2057210460 @default.
- W2994157070 hasRelatedWork W2132787716 @default.
- W2994157070 hasRelatedWork W3168256553 @default.
- W2994157070 hasRelatedWork W3186584605 @default.
- W2994157070 hasRelatedWork W4211240529 @default.
- W2994157070 hasRelatedWork W4221153218 @default.
- W2994157070 hasRelatedWork W4229726131 @default.
- W2994157070 hasRelatedWork W4287124629 @default.
- W2994157070 hasVolume "2019" @default.
- W2994157070 isParatext "false" @default.
- W2994157070 isRetracted "false" @default.
- W2994157070 magId "2994157070" @default.
- W2994157070 workType "article" @default.