EMMA: Scaling Mobile Manipulation via Egocentric Human Data
Scaling mobile manipulation imitation learning is bottlenecked by expensive mobile robot teleoperation. We present Egocentric Mobile MAnipulation (EMMA), an end-to-end framework training mobile manipulation policies from human mobile manipulation data with static robot data, sidestepping mobile teleoperation. To accomplish this, we co-train human full-body motion data with static robot data. In our experiments across three real-world tasks, EMMA demonstrates comparable performance to baselines trained on teleoperated mobile robot data (Mobile ALOHA), achieving higher or equivalent task performance in full task success. We find that EMMA is able to generalize to new spatial configurations and scenes, and we observe positive performance scaling as we increase the hours of human data, opening new avenues for scalable robotic learning in real-world environments. Details of this project can be found at https://ego-moma.github.io/.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulation directly from robot-free human demonstrations. We augment UMI interf…
In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does no…
Few-Shot LearningDomain AdaptationEgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
Human behavior is among the most scalable sources of data for learning physical intelligence, yet how to effectively leverage it for dexterous manipulation remains unclear. While prior work demonstrates human to robot tr…
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Vision-language-action (VLA) models are promising for diverse robotic tasks, but their performance heavily depends on large-scale high-quality training data, whose collection on real robots is costly and time-consuming. …
Robot NavigationWh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
Scaling dexterous manipulation requires generalization across objects, scenes, and tasks, yet existing data sources face a trade-off between scale and scene/embodiment alignment: teleoperation data is well aligned with r…