arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01110cs.RO
收藏

紧凑的任务对齐模仿学习用于实验室自动化

Compact Task-Aligned Imitation Learning for Laboratory Automation

Spatial Robotics Research Center, Fujitsu Limited.(富士通株式会社空间机器人研究中心);Faculty of Science and Engineering, Waseda University(早稻田大学理工学部);National Institute of Advanced Industrial Science and Technology(国家工业科学与技术研究院)

Kanata Suzuki, Hanon Nakamura, Kana Miyamoto, Tetsuya Ogata

AI总结:

本文提出了一种紧凑的模仿学习框架,通过小基础模型和扩散变换器专家实现高效实验室自动化,实验显示其在三个任务中的高成功率。

摘要:

机器人实验室自动化传统上依赖于精心设计的运动管道和任务特定的硬件接口,导致设计成本高且灵活性有限。尽管最近的模仿学习技术可以生成通用的机器人行为,但其大模型大小通常需要高性能计算资源,限制了在实际实验室环境中的应用。在本研究中,我们提出了一种用于实验室自动化的紧凑模仿学习框架,使用小基础模型。所提出的方法TVF-DiT通过紧凑的适配器将自监督视觉基础模型与视觉-语言模型对齐,并将其与基于扩散变换器的动作专家集成。整个模型参数少于5亿,能够在低VRAM GPU上进行推断。在三个现实世界实验室任务——试管清洁、试管排列和粉末转移——上的实验显示,平均成功率为86.6%,显著优于替代的轻量级基线。此外,详细的任务提示提高了视觉-语言对齐和任务性能。这些结果表明,当适当对齐并集成扩散基政策学习时,小基础模型可以有效支持有限计算资源的实用实验室自动化。

英文摘要:

Robotic laboratory automation has traditionally relied on carefully engineered motion pipelines and task-specific hardware interfaces, resulting in high design cost and limited flexibility. While recent imitation learning techniques can generate general robot behaviors, their large model sizes often require high-performance computational resources, limiting applicability in practical laboratory environments. In this study, we propose a compact imitation learning framework for laboratory automation using small foundation models. The proposed method, TVF-DiT, aligns a self-supervised vision foundation model with a vision-language model through a compact adapter, and integrates them with a Diffusion Transformer-based action expert. The entire model consists of fewer than 500M parameters, enabling inference on low-VRAM GPUs. Experiments on three real-world laboratory tasks - test tube cleaning, test tube arrangement, and powder transfer - demonstrate an average success rate of 86.6%, significantly outperforming alternative lightweight baselines. Furthermore, detailed task prompts improve vision-language alignment and task performance. These results indicate that small foundation models, when properly aligned and integrated with diffusion-based policy learning, can effectively support practical laboratory automation with limited computational resources.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑