arXiv cs.AI· Billy Yan, Isaac Tu, Kelly Lee, Blake Chang, Kenny Ma, Kanad Patel, Dhawal Kabra, Neer Patel, Kevin Wu, Lerrel Pinto, Irmak Guzey·· 3 天前AI 评分62
Steertuning：用 5 段人类视频让机器人学会新任务
Steertuning Policies from a Few Human Videos
AI 导读
研究者提出 Steertuning 系统，让机器人在新环境中仅凭 5 段人类演示学习新任务，整个流程从数据采集到策略部署不到 5 分钟。该系统先在 100 小时带密集标注的第一人称人类交互数据上预训练一个 400M 参数的扩散策略，再针对新任务微调 2 分钟（2000 次训练更新），并在反向采样时用与部署环境观测最接近的演示来引导动作。
正文 · 原文
Authors:Billy Yan, Isaac Tu, Kelly Lee, Blake Chang, Kenny Ma, Kanad Patel, Dhawal Kabra, Neer Patel, Kevin Wu, Lerrel Pinto, Irmak Guzey
Abstract:Current recipes for robot learning require massive amounts of robot demonstrations to obtain robust and adaptive policies. In this work, we introduce Steertuning, a system that enables robots to learn new tasks in new environments from 5 human demonstrations in under 5
Steertuning consists of two parts. (1) We pretrain a 400M-parameter diffusion policy on our egocentric human dataset, which consists of 100 hours of densely annotated random interactions. This pretraining makes Steertuning robust to background differences and enables spatial and object generalization when deployed on new tasks. (2) Given 5 demonstrations of a new task, we finetune our model for only 2 minutes (2000 training updates) and steer the policy's actions during reverse sampling using the demonstration whose observation is closest to that of the deployment environment. Together with a carefully designed data processing pipeline for embodiment transfer, this enables Steertuning to achieve a 71% success rate across 12 tasks in 12 new environments, ranging from lab settings to kitchens in new homes. The entire process, from data collection for a new task to robot policy deployment, takes less than 5 minutes. Our full dataset, model weights, codebase, and robot videos will be made available at our website: this https URL.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18711 [cs.RO] |
| (or arXiv:2610.18711v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18711 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Irmak Guzey [view email]
[v1]
Tue, 13 Oct 2026 16:55:32 UTC (3,606 KB)
来源：arXiv cs.AI · arxiv.org