ShapeStacks: Learning vision-based physical intuition for generalised object stacking
Physical intuition is pivotal for intelligent agents to perform complex tasks. In this paper we investigate the passive acquisition of an intuitive understanding of physical principles as well as the active utilisation of this intuition in the context of generalised object stacking. To this end, we...
Auteurs principaux: | Groth, O, Fuchs, F, Posner, H, Vedaldi, A |
---|---|
Format: | Conference item |
Publié: |
Springer
2018
|
Documents similaires
-
Scrutinizing and de-biasing intuitive physics with neural stethoscopes
par: Fuchs, FB, et autres
Publié: (2019) -
SimStack: An Intuitive Workflow Framework
par: Celso R. C. Rêgo, et autres
Publié: (2022-05-01) -
Learning physical intuition for robotic manipulation
par: Groth, OM
Publié: (2021) -
A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap
par: Goh, Kai Leong
Publié: (2022) -
Generalised stacking fault energies of copper alloys - density functional theory calculations
par: Muzyk M., et autres
Publié: (2019-01-01)