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...
Hlavní autoři: | Groth, O, Fuchs, F, Posner, H, Vedaldi, A |
---|---|
Médium: | Conference item |
Vydáno: |
Springer
2018
|
Podobné jednotky
-
Scrutinizing and de-biasing intuitive physics with neural stethoscopes
Autor: Fuchs, FB, a další
Vydáno: (2019) -
SimStack: An Intuitive Workflow Framework
Autor: Celso R. C. Rêgo, a další
Vydáno: (2022-05-01) -
Learning physical intuition for robotic manipulation
Autor: Groth, OM
Vydáno: (2021) -
A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap
Autor: Goh, Kai Leong
Vydáno: (2022) -
Generalised stacking fault energies of copper alloys - density functional theory calculations
Autor: Muzyk M., a další
Vydáno: (2019-01-01)