Acquiring Mechanical Knowledge from 3D Point Clouds
Zijia Li,Kei Okada,Masayuki Inaba,Zijia Li,Kei Okada,Masayuki Inaba
We consider the problem of acquiring mechanical knowledge through visual cues to help robots use objects in new situations. In this work, we propose a novel deep learning approach that allows a robot to acquire mechanical knowledge from 3D point clouds. This presents two main challenges. The first challenge is that a robot needs to infer novel objects' functions from its experience. Secondly, the ...
