Research
My research goal is to develop generalist robotics that can do everyday tasks in complex unstructured
real-world environments. To this end, my current research focuses on scaling data collection and finding
efficient ways of using this data to train generalist robots, especially via imitation. I believe that expanding
both expert and autonomous datasets in real-world, supplemented by simulation, is crucial for creating
robust generalist robots and kick-start the robot data ’flywheel’.
|
|
Learning to Look: Seeking Information for Decision Making via Policy Factorization
Shivin Dass,
Jiaheng Hu,
Ben Abbatematteo,
Peter Stone,
Roberto Martín-Martín
Conference on Robot Learning (CoRL), 2024
project page
/
arXiv
/
code
Intelligent agents such as humans know how to look for important information in their surroundings
and take relevant actions based on the context. To that end, we propose DISaM, an active vision framework,
where one policy seeks information and the other exploits it for manipulation tasks.
|
|
TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation
Shivin Dass,
Wensi Ai,
Yuqian Jiang,
Samik Singh,
Jiaheng Hu,
Ruohan Zhang,
Peter Stone,
Ben Abbatematteo,
Roberto Martín-Martín
ICRA MoMa Workshop & RSS DGR Workshop, 2024
project page
/
arXiv
/
code
TeleMoMa is a teleoperation toolkit that enables intuitive teleoperation of high-DoF mobile manipulators. TeleMoMa
supports several teleoperation interfaces such as vision, VR, mobile phones and more. TeleMoMa is not only versatile,
allowing easy plug-and-play teleoperation of any mobile manipulator in general, but is also modular, enabling
mixing-and-matching various teleoperation interfaces to provide the most effective teleoperation experience.
|
|
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Robotics: Science and Systems (RSS), 2024
project page
/
arXiv
/
data visualizer
We introduce DROID, the most diverse robot manipulation dataset to date. It contains 76k demonstration trajectories or
350 hours of interaction data, collected across 564 scenes and 84 tasks by 50 data collectors in North America, Asia,
and Europe over the course of 12 months. We demonstrate that training with DROID leads to policies with higher performance
and improved generalization ability. We open source the full dataset, policy learning code, and a detailed guide for
reproducing our robot hardware setup.
|
|
Model-Based Runtime Monitoring with Interactive Imitation Learning
Huihan Liu,
Shivin Dass,
Roberto Martín-Martín,
Yuke Zhu
IEEE International Conference on Robotics and Automation (ICRA), 2024
project page
/
arXiv
/
code
We introduce a runtime monitoring system that utilizes human interventions from on-the-job data to learn to classify
dangerous states. Our model-based design enables us to rollout the future and preemptively ask for help from the human
supervisor. Our method outperforms the baselines, with 23% and 40% higher success rates in simulation and on physical
hardware, respectively.
|
|
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment Collaboration
IEEE International Conference on Robotics and Automation (ICRA), 2024
Best Conferance Paper Award
project page
/
arXiv
/
code
Introducing Open X-Embodiment Dataset, the largest robot learning dataset to date, with 1M+ real robot trajectories.
By training large transformer based policies (RT-1-X, RT-2-X) on this dataset, we find that co-training over multiple
embodiments substantially improves performance of the policies.
Role: As an early collaborator, I contributed the USC Jaco Play dataset and conducted evaluations, that led to useful insights about large scale co-training.
|
|
PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection
Shivin Dass*,
Karl Pertsch*,
Hejia Zhang,
Youngwoon Lee,
Joseph J. Lim,
Stefanos Nikolaidis
Robotics: Science and Systems (RSS), 2023
project page
/
arXiv
/
code
We enable scalable robot data collection by assisting human teleoperators with a learned policy. Our approach
estimates its uncertainty over future actions to determine when to request user input. In real world user studies
we demonstrate that our system enables more efficient teleoperation with reduced mental load and up to four robots
in parallel.
|
The website template was inspired from here.
|
|