AutoBio+：基于真实实验室中动态实验现象的灵巧操作基准测试
AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories
AI总结：
本文推出AutoBio+灵巧操作基准测试框架，含14项任务与可控动态实验现象，构建混合渲染与并行仿真框架，评估显示策略性能有差异，且仿真到真实差距缩小，可用于真实操作评估。
摘要：
自动化生物实验室需要机器人在真实视觉条件下执行灵巧的工具交互，同时处理动态实验现象，这对机器人操作提出了重大挑战。为了在这些条件下实现系统评估，我们推出了AutoBio+，这是一个用于真实生物实验室环境中灵巧操作的仿真基准测试与框架。AutoBio+包含4种机器人形态的14项任务，涵盖功能性工具使用、精密操作、语言条件下的视觉定位以及仪器操作。我们引入了可控的动态实验现象，包括火焰、蒸汽和气泡，以捕捉实验室流程中不断变化的视觉条件。为进一步提升环境真实感，我们开发了混合渲染管线，将交互式仿真前景对象与从6个真实实验室场景重建的高斯溅射（Gaussian-splatting）背景相集成。为实现高效的大规模数据生成与评估，我们在mjlab之上构建了并行仿真框架，提出了并行有限状态机（Parallel Finite-State Machine, PFSM），并集成了批量渲染与解耦轨迹回放，用于演示生成及与模型无关的闭环策略评估。我们的评估显示，不同任务间的策略性能存在显著差异，暴露了当前操作策略的不同优势与劣势。真实世界实验进一步证明了缩小的仿真到真实（sim-to-real）差距，支持AutoBio+用于真实操作评估的有效性。补充材料可访问此https URL。
英文摘要：
Automating biological laboratories requires robots to perform dexterous tool interactions under realistic visual conditions while handling dynamic experimental phenomena, presenting significant challenges for robotic manipulation. To enable systematic evaluation under these conditions, we introduce AutoBio+, a simulation benchmark and framework for dexterous manipulation in realistic biological laboratory environments. AutoBio+ comprises 14 tasks across 4 robot embodiments, spanning functional tool use, precision manipulation, language-conditioned visual grounding, and instrument operation. We introduce controllable dynamic experimental phenomena, including flames, vapor, and bubbles, to capture the evolving visual conditions of laboratory procedures. To further enhance environmental realism, we develop a hybrid rendering pipeline that integrates interactive simulated foreground objects with Gaussian-splatting backgrounds reconstructed from 6 real laboratory scenes. For efficient large-scale data generation and evaluation, we further build a parallel simulation framework on top of mjlab, proposing Parallel Finite-State Machine (PFSM) and integrating batched rendering with decoupled trajectory replay for demonstration generation and model-independent closed-loop policy evaluation. Our evaluation reveals substantial variation in policy performance across tasks, exposing distinct strengths and weaknesses of current manipulation policies. Real-world experiments further demonstrate a reduced sim-to-real gap, supporting the validity of AutoBio+ for realistic manipulation evaluation. Supplementary materials are available at https://autobio-plus.github.io/AutoBioPlus.
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。
