There is a growing interest in using data-driven methods to scale up manipulation capabilities of robots for handling a large variety of objects. Many of these methods are oblivious to the notion of objects and they learn monolithic policies from the whole scene in image space. As a result, they don’t generalize well to different scenes, viewpoints, and lighting changes. In addition, these models cannot be combined with other components and constraints without re-training. In this talk, Arsalan Mousavian will present our approach for learning object centric models trained on 3D depth data. He will show how these approaches are combined with each other to accomplish tasks on unseen objects and environments. In particular, he will cover our works on grasping and segmenting unknown objects, obstacle avoidance, and task planning for unknown object rearrangement task.
Wednesday, December 22, 2021
5:00 PM – 6:15 PM UTC
5:00 PM | Welcome |
5:05 PM | Speaker Session with Arsalan Mousavian |
5:55 PM | Q&A |
6:05 PM | Wrap-up |
NVIDIA
Senior Research Scientist
ETH Zurich
GDSC Lead
ETH Zürich
GDSC Lead
ETH Zürich
GDSC Lead
Core Team Member
ETH Zurich
Core Team Member
ETH Zurich
Core Team Member
Core Team Member
Core Team Member
Core Team Member
ETH
Core Team Member
Core Team Member
Core Team Member
Core Team Member
Core Team Member
ETH Zürich
Core Team Member
Core Team Member