"Active Scene Understanding with Robot Interaction," Shuran Song (Columbia University, Computer Science)
Tuesday, December 03, 2019, 01:00pm - 02:30pm
Busch Campus, Psych 105
Abstract: Most computer vision algorithms are built with the goal to understand the physical world. Yet, as reflected in standard vision benchmarks and datasets, these algorithms continue to assume the role of a passive observer -- only watching static images or videos, without the ability to interact with the environment. This assumption becomes a fundamental limitation for applications in robotics, where systems are intrinsically built to actively engage with the physical world.
In this talk, I will present some recent work from my group that demonstrates how we can enable robots to leverage their ability to interact with the environment in order to better understand what they see: from discovering physical properties of novel objects through different dynamic interactions, to learning generalizable shape priors for assembly through self-supervised disassembly. We will demonstrate how the learned knowledge can be used to facilitate downstream manipulation tasks. Finally, I will discuss a few open research directions in the area of active scene understanding.
DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions. Zhenjia Xu, Jiajun Wu, Andy Zeng, Joshua B. Tenenbaum, and Shuran Song
TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
Andy Zeng, Shuran Song, Johnny Lee, Alberto Rodriguez, Thomas Funkhouser
Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly