AI 中文总结
研究针对湿实验室协议难转化为机器人动作的问题，提出ProtoAct框架，结合ProtoRAG、RefineChecker、ActSchema处理协议，引入BioP2E数据集，经多模型评估与消融实验验证，可实现仿真及真实机器人的协议执行。
AI 中文摘要
生物湿实验室协议是为训练有素的研究人员编写的，常将常规操作、依赖状态的条件及上下文参数隐含，难以转化为机器人可执行的动作。我们提出ProtoAct，这是一种结构化的协议落地框架，可将自由形式的生物程序转化为感知状态、适配具身的动作序列。ProtoAct使用ProtoRAG检索手动标注的示例以进行上下文敏感解析，采用RefineChecker检测并修正缺失或不一致的步骤，应用ActSchema将优化后的程序映射为受约束的JSON函数序列。我们还引入BioP2E，已手动为其标注22个细胞培养协议，涵盖258个监控条件、910个可执行子任务及962个落地动作调用。对7种大型语言模型的评估表明，ProtoAct可通过不同主干有效实例化；消融实验证实，检索、后验检查及模式约束各有互补贡献。解析后的子任务还支持演示收集与VLA模型训练，可在仿真和真实机器人环境中成功执行。因此，ProtoAct为生物协议理解与具身机器人执行提供了实用接口。
英文摘要
Biological wet-lab protocols are written for trained researchers and often leave routine operations, state-dependent conditions, and contextual parameters implicit, making them difficult to translate into robot-executable actions. We present ProtoAct, a structured protocol-grounding framework that converts free-form biological procedures into state-aware, embodiment-ready action sequences. ProtoAct uses ProtoRAG to retrieve manually annotated examples for context-sensitive parsing, employs RefineChecker to detect and revise missing or inconsistent steps, and applies ActSchema to map the refined procedure into constrained JSON function sequences. We further introduce BioP2E, for which we manually annotate 22 cell-culture protocols into 258 monitoring conditions, 910 executable subtasks, and 962 grounded action calls. Evaluation across seven large language models demonstrates that ProtoAct can be effectively instantiated with different backbones. Ablations confirm that retrieval, posterior checking, and schema constraints make complementary contributions. The parsed subtasks further support demonstration collection and VLA model training, enabling successful execution in both simulation and real-robot settings. ProtoAct thus provides a practical interface between biological protocol understanding and embodied robotic execution.
Comments15 pages, 13 figures
