Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models

November 21, 2022 ยท Declared Dead ยท ๐Ÿ› Robotics: Science and Systems

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Ted Xiao, Harris Chan, Pierre Sermanet, Ayzaan Wahid, Anthony Brohan, Karol Hausman, Sergey Levine, Jonathan Tompson arXiv ID 2211.11736 Category cs.RO: Robotics Cross-listed cs.AI, cs.LG Citations 77 Venue Robotics: Science and Systems Last Checked 3 months ago
Abstract
In recent years, much progress has been made in learning robotic manipulation policies that follow natural language instructions. Such methods typically learn from corpora of robot-language data that was either collected with specific tasks in mind or expensively re-labelled by humans with rich language descriptions in hindsight. Recently, large-scale pretrained vision-language models (VLMs) like CLIP or ViLD have been applied to robotics for learning representations and scene descriptors. Can these pretrained models serve as automatic labelers for robot data, effectively importing Internet-scale knowledge into existing datasets to make them useful even for tasks that are not reflected in their ground truth annotations? To accomplish this, we introduce Data-driven Instruction Augmentation for Language-conditioned control (DIAL): we utilize semi-supervised language labels leveraging the semantic understanding of CLIP to propagate knowledge onto large datasets of unlabelled demonstration data and then train language-conditioned policies on the augmented datasets. This method enables cheaper acquisition of useful language descriptions compared to expensive human labels, allowing for more efficient label coverage of large-scale datasets. We apply DIAL to a challenging real-world robotic manipulation domain where 96.5% of the 80,000 demonstrations do not contain crowd-sourced language annotations. DIAL enables imitation learning policies to acquire new capabilities and generalize to 60 novel instructions unseen in the original dataset.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Robotics

Died the same way โ€” ๐Ÿ‘ป Ghosted