[论文] RAPID: Robot Agentic Programming from Demonstrations
研究领域: CV 作者: Yuyao Liu, Jiayuan Mao, David Hsu, Leslie Pack Kaelbling, Tomás Lozano-Pérez 发布时间: 2026-09-24 arXiv: 2609.30249
论文概要
研究领域: CV 作者: Yuyao Liu, Jiayuan Mao, David Hsu, Leslie Pack Kaelbling, Tomás Lozano-Pérez 发布时间: 2026-09-24 arXiv: 2609.30249
中文摘要
代码智能体在解决复杂编程问题上已取得巨大成功。为将其潜力引入机器人系统,本工作提出机器人智能体演示编程(RAPID),仅需单张视觉人工演示,即可自动生成、验证并迭代优化机器人程序。代码优化的智能体循环需要几个关键要素:(i)可测试的任务规范,(ii)供机器人执行的动作基元,以及(iii)用于程序执行与验证的交互环境。RAPID 能从演示中自动推断出这三者。为使生成的程序在演示场景之外可复用,RAPID 采用以物体为中心的关系化程序表示,聚焦于演示策略的底层结构而非具体的运动本身:它将动作基元表达为实现物体级运动效果的轨迹优化程序,并通过捕捉运行时场景特定几何关系的关系约束进行组合。我们在仿真中的八个具有挑战性的富接触非抓取操作任务以及 LIBERO-Pro 基准的通用抓取操作任务上评估了 RAPID。我们还成功将其部署到真实的 Franka 机械臂上,并在全部八个非抓取任务上进行了评估。在所有实验中,RAPID 均展现出强劲性能,并在物体位姿、形状、材质和环境方面实现了泛化。项目网站:https://yuyaoliu.me/projects/rapid。
原文摘要
Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically generates, verifies, and refines robot programs, given a single visual human demonstration. The iterative agentic loop of code refinement requires several key ingredients: (i) a testable task specification, (ii) action primitives for robot execution, and (iii) an interactive environment for program execution and verification. RAPID infers all three from the demonstration automatically. To make the resulting program reusable beyond the demonstration setting, RAPID uses an object-centric relational program representation that focuses on the underlying structure o...
*自动采集于 2026-09-28*
#论文 #arXiv #CV #小凯