arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2611.06881cs.RO
收藏

VABAR:面向智能体机器人学的变异性自动化基准

VABAR: A Variational Automation Benchmark for Agentic Robotics

University of California, Berkeley(加州大学伯克利分校);Siemens(西门子);NVIDIA(英伟达)
Shuangyu Xie, Kaiyuan Chen, Uksang Yoo, Xinyue Zhu, Meadow Shen, Jaimyn Drake, Eugen Solowjow, Lionel Gulich, Alexander Millane, Rafael Cathomen, Tuur Stuyck, S… 展开作者

Shuangyu Xie, Kaiyuan Chen, Uksang Yoo, Xinyue Zhu, Meadow Shen, Jaimyn Drake, Eugen Solowjow, Lionel Gulich, Alexander Millane, Rafael Cathomen, Tuur Stuyck, Sangeeta Subramanian, Yichao Pan, Bruce McGowan, Michael Benedict, Linxi Fan, Yuke Zhu, Spencer Huang, Ken Goldberg

AI总结:

该研究提出面向智能体机器人学的变异性自动化基准VABAR,制定了智能体机器人学基准设计标准,构建含六类操作任务的仿真基准,并基于GaP和Isaac Lab Arena完成初始评估。

摘要:

为使机器人在商业和工业应用中可靠运行,它们必须持续执行特定任务,且任务中物体的形状和姿态存在已知变化,我们将这类场景称为变异性自动化(Variational Automation,VA),以区别于固定自动化场景。受近期智能体机器人学(Agentic Robotics)相关论文的启发,其中预训练的大语言模型(LLM)和视觉语言模型(VLM)编码智能体将可解释的机器人编程与无模型策略的开放世界适应性相结合,我们提出了一套通用的智能体机器人学基准设计标准,包括可访问性、可重复性、多样性、与智能体机器人学及实际应用的相关性、物理可实现性、抗基准饱和性和计算效率。我们将这些原则应用于涵盖工业、医疗和基础设施应用的六类操作任务:工具分类、工具悬挂、齿轮啮合、注射器包装、线缆插入和线缆布线。我们推出了面向智能体机器人学的变异性自动化基准(Variational Automation Benchmark for Agentic Robotics,VABAR),这是一个开放、易于复制、基于仿真的操作基准,用于系统评估智能体机器人学系统。VABAR完全基于开源工具构建,具有使用牛顿物理引擎(Newton physics engine)的详细实现、标准化任务变体、难度等级、成功指标,以及包含33种可泛化技能的库,这些技能配有人类编写的程序化参考解决方案。我们使用开源智能体操作工具Graph-as-Policy(GaP)和Isaac Lab Arena提供了初始基准评估。

英文摘要:

For robots to operate reliably in commercial and industrial applications, they must persistently perform specific tasks with known variations in object shape and pose. We call this Variational Automation (VA) to differentiate these settings from fixed automation. Inspired by recent papers on Agentic Robotics, where pretrained LLM and VLM coding agents combine interpretable robot programming with the open-world adaptability of model free policies, we propose a general set of agentic robotics benchmark design criteria that includes accessibility, repeatability, diversity, relevance to agentic robotics and practical applications, physical realizability, resistance to benchmark saturation, and computational efficiency. We instantiate these principles in six manipulation task classes spanning industrial, medical, and infrastructure applications: tool sorting, tool hanging, gear meshing, syringe packing, cable insertion, and cable routing. We introduce the Variational Automation Benchmark for Agentic Robotics (VABAR), an open, easily replicable, simulation-based manipulation benchmark to systematically evaluating agentic robotics systems. Built fully on open-source tools, VABAR features detailed implementations using the Newton physics engine, standardized task variations, difficulty tiers, success metrics, and a library of 33 generalizable skills with human-authored programmatic reference solutions. We provide initial baseline evaluations using an open agentic manipulation harness, Graph-as-Policy (GaP), and Isaac Lab Arena.

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。

↑