AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents

Michael Ahn, Debidatta Dwibedi, Chelsea Finn, Montserrat Gonzalez Arenas, Keerthana Gopalakrishnan, Karol Hausman, brian ichter, Alex Irpan, Nikhil J Joshi, Ryan Julian, Sean Kirmani, Isabel Leal, Tsang-Wei Edward Lee, Sergey Levine, Yao Lu, Sharath Maddineni, Kanishka Rao, Dorsa Sadigh, Pannag R Sanketi, Pierre Sermanet et al. (7 additional authors not shown)

Primary Area: applications to robotics, autonomy, planning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: robot learning, robotics, robot manipulation, large language models, vision language models, agent, decision making

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: large number of robots that explore novel environments, propose tasks using LLMs, and collect those tasks, run in the real world.

Abstract: Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world. In this paper, we propose AutoRT, a system that leverages existing foundation models to scale up the deployment of operational robots in completely unseen scenarios with minimal human supervision. AutoRT leverages vision-language models (VLMs) for scene understanding and grounding, and further uses large language models (LLMs) for proposing diverse and novel instructions to be performed by a fleet of robots. Guiding data collection by tapping into the knowledge of foundation models enables AutoRT to effectively reason about autonomy tradeoffs and safety while significantly scaling up data collection for robot learning. We demonstrate AutoRT proposing instructions to over 20 robots across multiple buildings and collecting 77k real robot episodes via both teleoperation and autonomous robot policies. We experimentally show that such “in-the-wild” data collected by AutoRT is significantly more diverse, and that AutoRT’s use of LLMs allows for instruction following data collection robots that are aligned with human preferences.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6606