Shreeya Jain

Hi there! I am a second year Master’s student studying Computer Science at Columbia University. I work as a research assistant, advised by Professor Shuran Song at the Columbia Artificial Intelligence and Robotics Lab. I also actively collaborate with Professor Steven Feiner at the Computer Graphics and User Interfaces Lab.

My current research interests lie at the intersection of Robotic Learning, Computer Vision, and Computer Graphics. I am broadly interested in developing algorithms that enable intelligent systems to learn from their interactions with the physical world and subsequently, acquire novel & complex skills that can assist humans.

Before joining Columbia, I obtained my integrated B.E. in Computer Science and M.Sc. in Economics from Birla Institute of Technology and Science, Pilani.

news

Jan 5, 2023	I will be TAing COMS 4733 Computational Aspects of Robotics for Professor Song
Sep 1, 2022	I will be TAing COMS 6998 Topics in Robotic Learning for Professor Song
Mar 16, 2022	I started working at the Computer Graphics and User Interfaces Lab
Nov 29, 2021	I started working at the Columbia Artificial Intelligence and Robotics Lab
Sep 9, 2021	I joined the MS in Computer Science program at Columbia
Jul 19, 2021	I graduated from BITS Pilani
May 12, 2020	I started working on the DARPA-funded project ToMCAT at IVILAB

selected publications

Built to Order: A Virtual Reality Testbed for Assigning High-Level Assembly Goals to Remote Robots

Portia Wang*, Shreeya Jain*, Manxueying Li*, Shuran Song, Jen-Shuo Liu, and Steven Feiner

In Submission 2023
Bag All You Need: Learning a Generalizable Bagging Strategy for Heterogeneous Objects

Arpit Bahety*, Shreeya Jain*, Huy Ha, Nathalie Hager, Benjamin Burchfiel, Eric Cousineau, Siyuan Feng, and Shuran Song

In Submission 2022

Abs arXiv HTML

We introduce a practical robotics solution for the task of heterogeneous bagging, requiring the placement of multiple rigid and deformable objects into a deformable bag. This is a difficult task as it features complex interactions between multiple highly deformable objects under limited observability. To tackle these challenges, we propose a robotic system consisting of two learned policies: a rearrangement policy that learns to place multiple rigid objects and fold deformable objects in order to achieve desirable pre-bagging conditions, and a lifting policy to infer suitable grasp points for bi-manual bag lifting. We evaluate these learned policies on a real-world three-arm robot platform that achieves a 70% heterogeneous bagging success rate with novel objects. To facilitate future research and comparison, we also develop a novel heterogeneous bagging simulation benchmark that will be made publicly available.