arXiv cs.AI· Zihan Zhang, Zeyu Wu, Xin Zhang, Mingyu Luo, Haohui Que, Tong Zhu·· 13 小时前AI 评分31
让自驱动实验室可审计：统一混合动作、测量与安全执行的框架
Making Self-Driving Laboratories Auditable:A Unified Framework for Hybrid Actions,Measurements, and Safe Execution
AI 导读
研究提出可追溯框架，包含 LAM、OpenSDL、Safe-SDL 和 L3-Bench 四个组件。LAM 是测量条件化的策略架构，将视觉-语言-动作范式扩展为同时生成连续机器人轨迹和类型化仪器 API 调用；OpenSDL 负责将角色级操作映射到异构设备并记录带时间戳的因果事件。
正文 · 原文
Abstract:Self-driving laboratories (SDLs) are laboratory systems that couple experimental planning, automated execution, and measurement feedback in a closed loop. Integrating flexible robot control with the typed application programming interfaces (APIs) and continuous measurements exposed by laboratory instruments remains an execution-interface challenge. To address this challenge, we propose a traceable framework comprising four components: LAM (Lab Action Model), OpenSDL, Safe-SDL, and L3-Bench. LAM is a proposed measurement-conditioned policy architecture that extends vision-language-action paradigms to generate both continuous robot trajectories and typed instrument API calls. OpenSDL is an execution substrate with an initial control implementation, designed to map role-level operations to heterogeneous devices, coordinate execution, and record timestamped causal events. The proposed Safe-SDL runtime gate combines pre-dispatch schema and resource checks with signal temporal logic monitoring during execution, including extended waiting periods. L3-Bench (Level-3 Laboratory Benchmark) specifies an episode-level evaluation protocol covering physical outcomes, timing, reproducibility, safety violations, and fault recovery. Together, these components provide an end-to-end design for linking hybrid action generation, monitored device execution, measurement feedback, and experimental evaluation, addressing coordination and traceability challenges in SDL workflows.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36761 [cs.RO] |
| (or arXiv:2610.36761v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36761 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zihan Zhang [view email]
[v1]
Tue, 27 Oct 2026 07:17:24 UTC (2,402 KB)
来源：arXiv cs.AI · arxiv.org