Operationally meaningful representations of physical systems in neural networks
To make progress in science, we often build abstract representations of physical systems
that meaningfully encode information about the systems. Such representations ignore …
that meaningfully encode information about the systems. Such representations ignore …
Predicting the physical dynamics of unseen 3d objects
Abstract Machines that can predict the effect of physical interactions on the dynamics of
previously unseen object instances are important for creating better robots and interactive …
previously unseen object instances are important for creating better robots and interactive …
[PDF][PDF] Predicting the physical dynamics of unseen 3d objects
SS Davis Rempe - IEEE Winter Conference on Applications of Computer …, 2020 - par.nsf.gov
Abstract Machines that can predict the effect of physical interactions on the dynamics of
previously unseen object instances are important for creating better robots and interactive …
previously unseen object instances are important for creating better robots and interactive …
Combining learning and structure for robotic manipulation
A Kloss - 2021 - tobias-lib.ub.uni-tuebingen.de
Household robots have been a long standing promise of robotics. But despite of decades of
robotic research and progress in the field, we still do not encounter many robots in our …
robotic research and progress in the field, we still do not encounter many robots in our …