用人类操作数据训练机器人，无需昂贵遥控操作。
EMMA: Scaling Mobile Manipulation via Egocentric Human Data
- 结合人类全身动作与静态机器人数据联合训练
- 在三项真实任务中性能接近遥控训练模型
- 数据越多效果越好，适合大规模机器人学习
移动端操作模仿学习受限于昂贵的移动机器人遥控成本。我们提出端到端框架EMMA，利用人类移动操作数据与静态机器人数据训练移动操作策略，避免了移动遥控。通过协同训练人类全身运动数据与静态机器人数据，在三个真实任务中，EMMA表现与基于遥控数据训练的基线模型（Mobile ALOHA）相当，全任务成功率更高或相当。实验表明，EMMA能泛化到新的空间配置和场景，且随着人类数据时长增加，性能持续提升，为真实环境中的可扩展机器人学习开辟新路径。项目详情见 https://ego-moma.github.io/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。