Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201854920> ?p ?o ?g. }
- W3201854920 abstract "Visual prediction models are a promising solution for visual-based robotic grasping of cluttered, unknown soft objects. Previous models from the literature are computationally greedy, which limits reproducibility; although some consider stochasticity in the prediction model, it is often too weak to catch the reality of robotics experiments involving grasping such objects. Furthermore, previous work focused on elementary movements that are not efficient to reason in terms of more complex semantic actions. To address these limitations, we propose VP-GO, a ``light'' stochastic action-conditioned visual prediction model. We propose a hierarchical decomposition of semantic grasping and manipulation actions into elementary end-effector movements, to ensure compatibility with existing models and datasets for visual prediction of robotic actions such as RoboNet. We also record and release a new open dataset for visual prediction of object grasping, called PandaGrasp. Our model can be pre-trained on RoboNet and fine-tuned on PandaGrasp, and performs similarly to more complex models in terms of signal prediction metrics. Qualitatively, it outperforms when predicting the outcome of complex grasps performed by our robot." @default.
- W3201854920 created "2021-10-11" @default.
- W3201854920 creator A5022711233 @default.
- W3201854920 creator A5032227198 @default.
- W3201854920 creator A5042342752 @default.
- W3201854920 creator A5071730207 @default.
- W3201854920 date "2021-09-26" @default.
- W3201854920 modified "2023-10-14" @default.
- W3201854920 title "VP-GO: a light action-conditioned visual prediction model" @default.
- W3201854920 cites W1560270123 @default.
- W3201854920 cites W1686810756 @default.
- W3201854920 cites W1974652642 @default.
- W3201854920 cites W1989021449 @default.
- W3201854920 cites W2057299504 @default.
- W3201854920 cites W2058702345 @default.
- W3201854920 cites W2070681743 @default.
- W3201854920 cites W2097579122 @default.
- W3201854920 cites W2108598243 @default.
- W3201854920 cites W2114770744 @default.
- W3201854920 cites W2126496149 @default.
- W3201854920 cites W2127374659 @default.
- W3201854920 cites W2132602743 @default.
- W3201854920 cites W2133665775 @default.
- W3201854920 cites W2142401694 @default.
- W3201854920 cites W2290564286 @default.
- W3201854920 cites W2400532028 @default.
- W3201854920 cites W2405660904 @default.
- W3201854920 cites W2470475590 @default.
- W3201854920 cites W2528489519 @default.
- W3201854920 cites W2557283755 @default.
- W3201854920 cites W2580909119 @default.
- W3201854920 cites W2583901669 @default.
- W3201854920 cites W2626778328 @default.
- W3201854920 cites W2749658623 @default.
- W3201854920 cites W2765363933 @default.
- W3201854920 cites W2796303840 @default.
- W3201854920 cites W2889347284 @default.
- W3201854920 cites W2902125520 @default.
- W3201854920 cites W2949098821 @default.
- W3201854920 cites W2950061832 @default.
- W3201854920 cites W2950813077 @default.
- W3201854920 cites W2950988471 @default.
- W3201854920 cites W2951004968 @default.
- W3201854920 cites W2951383673 @default.
- W3201854920 cites W2953249127 @default.
- W3201854920 cites W2953318193 @default.
- W3201854920 cites W2962696750 @default.
- W3201854920 cites W2962785568 @default.
- W3201854920 cites W2962793652 @default.
- W3201854920 cites W2963678509 @default.
- W3201854920 cites W2964303162 @default.
- W3201854920 cites W2964327849 @default.
- W3201854920 cites W2965813579 @default.
- W3201854920 cites W2989705138 @default.
- W3201854920 cites W2991019415 @default.
- W3201854920 cites W2994760783 @default.
- W3201854920 cites W3028676366 @default.
- W3201854920 cites W3149531584 @default.
- W3201854920 cites W3174902251 @default.
- W3201854920 doi "https://doi.org/10.48550/arxiv.2109.12694" @default.
- W3201854920 hasPublicationYear "2021" @default.
- W3201854920 type Work @default.
- W3201854920 sameAs 3201854920 @default.
- W3201854920 citedByCount "0" @default.
- W3201854920 crossrefType "posted-content" @default.
- W3201854920 hasAuthorship W3201854920A5022711233 @default.
- W3201854920 hasAuthorship W3201854920A5032227198 @default.
- W3201854920 hasAuthorship W3201854920A5042342752 @default.
- W3201854920 hasAuthorship W3201854920A5071730207 @default.
- W3201854920 hasBestOaLocation W32018549201 @default.
- W3201854920 hasConcept C119857082 @default.
- W3201854920 hasConcept C121332964 @default.
- W3201854920 hasConcept C154945302 @default.
- W3201854920 hasConcept C2780791683 @default.
- W3201854920 hasConcept C34413123 @default.
- W3201854920 hasConcept C41008148 @default.
- W3201854920 hasConcept C62520636 @default.
- W3201854920 hasConcept C90509273 @default.
- W3201854920 hasConceptScore W3201854920C119857082 @default.
- W3201854920 hasConceptScore W3201854920C121332964 @default.
- W3201854920 hasConceptScore W3201854920C154945302 @default.
- W3201854920 hasConceptScore W3201854920C2780791683 @default.
- W3201854920 hasConceptScore W3201854920C34413123 @default.
- W3201854920 hasConceptScore W3201854920C41008148 @default.
- W3201854920 hasConceptScore W3201854920C62520636 @default.
- W3201854920 hasConceptScore W3201854920C90509273 @default.
- W3201854920 hasLocation W32018549201 @default.
- W3201854920 hasOpenAccess W3201854920 @default.
- W3201854920 hasPrimaryLocation W32018549201 @default.
- W3201854920 hasRelatedWork W2002867377 @default.
- W3201854920 hasRelatedWork W2045758229 @default.
- W3201854920 hasRelatedWork W2065963568 @default.
- W3201854920 hasRelatedWork W2089011450 @default.
- W3201854920 hasRelatedWork W2398963826 @default.
- W3201854920 hasRelatedWork W2540676782 @default.
- W3201854920 hasRelatedWork W2961085424 @default.
- W3201854920 hasRelatedWork W2962829499 @default.
- W3201854920 hasRelatedWork W405964254 @default.
- W3201854920 hasRelatedWork W4250956039 @default.
- W3201854920 isParatext "false" @default.