外观
论文arXiv 2610.1871115 天前
从少量人类视频对策略进行 Steertuning
原文链接：Steertuning Policies from a Few Human Videos（arXiv 2610.18711 · 发布日期：2026-10-13）
Steertuning Policies from a Few Human Videos
提出 Steertuning，通过人类数据预训练扩散策略并少量演示微调，在12项任务和12个新环境中验证机器人新任务学习。
核心要点
- 动机：现有机器人学习通常需要大量机器人演示，难以获得鲁棒且自适应的策略。
- 方法：在100小时密集标注的自我中心人类交互数据上预训练4亿参数扩散策略。
- 新任务仅用5个人类演示，微调2分钟，并用最相近观测的演示引导反向采样动作。
- 结果与开源：12个新环境12项任务成功率71%，将开放数据、权重、代码和机器人视频。
验证范围与局限：验证范围为12个新环境中的12项任务，场景从实验室到新家庭厨房。
英文摘要 (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: https://steertuning.github.io.
作者：Billy Yan, Isaac Tu, Kelly Lee, Blake Chang, Kenny Ma, Kanad Patel, Dhawal Kabra, Neer Patel, Kevin Wu, Lerrel Pinto
来源
本页事实对应的公开页面，以原文为准。