Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313148857> ?p ?o ?g. }
- W4313148857 endingPage "69" @default.
- W4313148857 startingPage "51" @default.
- W4313148857 abstract "Pushing back the frontiers of collaborative robots in industrial environments, we propose a new Separable-Sparse Graph Convolutional Network (SeS-GCN) for pose forecasting. For the first time, SeS-GCN bottlenecks the interaction of the spatial, temporal and channel-wise dimensions in GCNs, and it learns sparse adjacency matrices by a teacher-student framework. Compared to the state-of-the-art, it only uses 1.72% of the parameters and it is $$sim $$ 4 times faster, while still performing comparably in forecasting accuracy on Human3.6M at 1 s in the future, which enables cobots to be aware of human operators. As a second contribution, we present a new benchmark of Cobots and Humans in Industrial COllaboration (CHICO ). CHICO includes multi-view videos, 3D poses and trajectories of 20 human operators and cobots, engaging in 7 realistic industrial actions. Additionally, it reports 226 genuine collisions, taking place during the human-cobot interaction. We test SeS-GCN on CHICO for two important perception tasks in robotics: human pose forecasting, where it reaches an average error of 85.3 mm (MPJPE) at 1 sec in the future with a run time of 2.3 ms, and collision detection, by comparing the forecasted human motion with the known cobot motion, obtaining an F1-score of 0.64." @default.
- W4313148857 created "2023-01-06" @default.
- W4313148857 creator A5001003105 @default.
- W4313148857 creator A5024576844 @default.
- W4313148857 creator A5033120247 @default.
- W4313148857 creator A5033671063 @default.
- W4313148857 creator A5060453305 @default.
- W4313148857 creator A5082670871 @default.
- W4313148857 creator A5083001091 @default.
- W4313148857 creator A5034845651 @default.
- W4313148857 date "2022-01-01" @default.
- W4313148857 modified "2023-10-13" @default.
- W4313148857 title "Pose Forecasting in Industrial Human-Robot Collaboration" @default.
- W4313148857 cites W1735317348 @default.
- W4313148857 cites W1846144685 @default.
- W4313148857 cites W1849277567 @default.
- W4313148857 cites W2004669996 @default.
- W4313148857 cites W2023597997 @default.
- W4313148857 cites W2070935310 @default.
- W4313148857 cites W2101032778 @default.
- W4313148857 cites W2194775991 @default.
- W4313148857 cites W2300242332 @default.
- W4313148857 cites W2417429787 @default.
- W4313148857 cites W2531409750 @default.
- W4313148857 cites W2549139847 @default.
- W4313148857 cites W2891091472 @default.
- W4313148857 cites W2892124085 @default.
- W4313148857 cites W2895748257 @default.
- W4313148857 cites W2921119892 @default.
- W4313148857 cites W2948218505 @default.
- W4313148857 cites W2962896489 @default.
- W4313148857 cites W2963165299 @default.
- W4313148857 cites W2963548793 @default.
- W4313148857 cites W2964203186 @default.
- W4313148857 cites W2966649515 @default.
- W4313148857 cites W2971856312 @default.
- W4313148857 cites W2982573856 @default.
- W4313148857 cites W2983925976 @default.
- W4313148857 cites W2993797559 @default.
- W4313148857 cites W2997343295 @default.
- W4313148857 cites W2998644037 @default.
- W4313148857 cites W3003298897 @default.
- W4313148857 cites W3026295510 @default.
- W4313148857 cites W3027351386 @default.
- W4313148857 cites W3034696014 @default.
- W4313148857 cites W3034902964 @default.
- W4313148857 cites W3035204081 @default.
- W4313148857 cites W3035545045 @default.
- W4313148857 cites W3090204015 @default.
- W4313148857 cites W3097237405 @default.
- W4313148857 cites W3099484381 @default.
- W4313148857 cites W3101151469 @default.
- W4313148857 cites W3101560663 @default.
- W4313148857 cites W3109717189 @default.
- W4313148857 cites W3130825927 @default.
- W4313148857 cites W3133064118 @default.
- W4313148857 cites W3150051753 @default.
- W4313148857 cites W3162121377 @default.
- W4313148857 cites W3175335528 @default.
- W4313148857 cites W3177437499 @default.
- W4313148857 cites W3177765762 @default.
- W4313148857 cites W3179837392 @default.
- W4313148857 cites W3184557462 @default.
- W4313148857 cites W3188486176 @default.
- W4313148857 cites W3195123155 @default.
- W4313148857 cites W3203785074 @default.
- W4313148857 cites W3215117597 @default.
- W4313148857 cites W3215686035 @default.
- W4313148857 cites W4230178929 @default.
- W4313148857 doi "https://doi.org/10.1007/978-3-031-19839-7_4" @default.
- W4313148857 hasPublicationYear "2022" @default.
- W4313148857 type Work @default.
- W4313148857 citedByCount "5" @default.
- W4313148857 countsByYear W43131488572023 @default.
- W4313148857 crossrefType "book-chapter" @default.
- W4313148857 hasAuthorship W4313148857A5001003105 @default.
- W4313148857 hasAuthorship W4313148857A5024576844 @default.
- W4313148857 hasAuthorship W4313148857A5033120247 @default.
- W4313148857 hasAuthorship W4313148857A5033671063 @default.
- W4313148857 hasAuthorship W4313148857A5034845651 @default.
- W4313148857 hasAuthorship W4313148857A5060453305 @default.
- W4313148857 hasAuthorship W4313148857A5082670871 @default.
- W4313148857 hasAuthorship W4313148857A5083001091 @default.
- W4313148857 hasBestOaLocation W43131488572 @default.
- W4313148857 hasConcept C119857082 @default.
- W4313148857 hasConcept C132525143 @default.
- W4313148857 hasConcept C13280743 @default.
- W4313148857 hasConcept C145460709 @default.
- W4313148857 hasConcept C154945302 @default.
- W4313148857 hasConcept C185798385 @default.
- W4313148857 hasConcept C205649164 @default.
- W4313148857 hasConcept C34413123 @default.
- W4313148857 hasConcept C41008148 @default.
- W4313148857 hasConcept C80444323 @default.
- W4313148857 hasConcept C90509273 @default.
- W4313148857 hasConceptScore W4313148857C119857082 @default.
- W4313148857 hasConceptScore W4313148857C132525143 @default.
- W4313148857 hasConceptScore W4313148857C13280743 @default.