Interactive Language: Talking to Robots in Real Time
We present a framework for building interactive, real-time, naturallanguage-instructable robots in the real world, and we open source related assets (dataset, environment, benchmark, and policies).
Trained with behavioralcloning on a dataset of hundreds of thousands of language-annotated trajectories, a produced policy can proficiently execute an order of magnitude more commands than previous works : specifically we estimate a 93.5% success rate on a set of 87,000 unique natural language strings specifying raw end-to-end visuo-linguo-motor skills in the real world.
We find that the same policy is capable of being guided by a human via real-time language to address a wide range of precise long-horizon rearrangement goals, e.g.
Corey Lynch, Ayzaan Wahid, Jonathan Tompson, Tianli Ding, James Betker, Robert Baruch, Travis Armstrong, Pete Florence