ALOHA Lightning 论文提出学习快速精准机器人操作的系统
ALOHA Lightning: Learning Fast and Precise Manipulation
AI 导读
论文提出 ALOHA Lightning(Flash ALOHA)系统,通过动觉教学在可反向驱动的双臂平台上采集接近人类速度的示范,并用测试时动作平滑和掩码对齐视觉数据分布,实现平稳高速执行。每任务仅需 50 条示范,抛接球、叠短裤、装入电池和收拾桌面等双臂任务成功率超过 80%,速度接近人类。
正文 · 原文
Abstract:Learning from human demonstrations has enabled robots to acquire a wide range of manipulation skills, but learned policies typically execute far slower than ordinary humans. This speed gap is mainly due to lack of an interface for collecting demonstration data at high speed, and the difficulty in training policies that can robustly execute high-speed motions. In this paper, we present ALOHA Lightning (Flash ALOHA), a system for learning fast and precise robotic manipulation. Our system uses kinesthetic teaching to intuitively collect near-human-speed demonstrations on a backdrivable bimanual platform, yielding natural and fast trajectories. We also present a learning pipeline that enables smooth high-speed execution through test-time action smoothing and aligns the visual data distribution between data collection and deployment with masking. Given 50 demonstrations for each task, ALOHA Lightning autonomously completes bimanual tasks such as ball tossing and catching, folding shorts, battery insertion, and bussing tables for over 80% success rates while close to human speed. Project website: this https URL
| Comments: | Project website: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY) |
| Cite as: | arXiv:2611.21919 [cs.RO] |
| (or arXiv:2611.21919v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21919 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zipeng Fu [view email]
[v1]
Mon, 16 Nov 2026 21:31:18 UTC (4,854 KB)
来源:arXiv cs.AI · arxiv.org