MaCoPlanner：面向机器人工业面板操作的、结合主动安全验证的大语言模型辅助人工编译任务规划

中文摘要 AI 辅助

机器人工业面板操作不仅需要精准的控制定位，还需遵守分散在各类手册中的操作流程、安全规则及设备状态约束。本研究提出MaCoPlanner，这是一个基于设备手册编译知识构建的任务规划框架，它将设备手册转换为类型化中间表示，检索与任务及状态相关的证据，并以此支持规划生成。执行前，候选规划会被符号化展开，对照流程及状态转移约束进行检查；检测到的违规会被定位并返回以进行针对性修复，而未解决的规划则会被拒绝。独立的执行接口会将已验证的符号动作映射到物理控制并更新设备状态。在独立评估 oracle 下，MaCoPlanner 的最终违规率为2.7%，修复分析中26.3%的运行在耗尽优化预算后被拒绝。与 Raw-Manual 相比，Level-2 任务的任务成功率从62.8%提升至84.4%，Level-3 任务从25.9%提升至43.2%。在无附加工业负载的控制器面板模拟器上的实验进一步证明，其在代表性交互条件下具备集成执行可行性，但未宣称已具备工业部署就绪性。

英文摘要

Robotic industrial panel operation requires not only accurate control localization but also compliance with operating procedures, safety rules, and device-state constraints distributed across heterogeneous manuals. This study presents MaCoPlanner, a task-planning framework built on knowledge compiled from equipment manuals that converts equipment manuals into a typed intermediate representation, retrieves task- and state-relevant evidence, and uses it to support plan generation. Before actuation, candidate plans are symbolically rolled out and checked against procedural and state-transition constraints; detected violations are localized and returned for targeted repair, while unresolved plans are rejected. A separate execution interface grounds verified symbolic actions to physical controls and updates the device state. Under an independent evaluation oracle, MaCoPlanner achieves a final violation rate of 2.7%, and 26.3% of the runs in the repair analysis are rejected after exhausting the refinement budget. Compared with Raw-Manual, task success increases from 62.8% to 84.4% on Level-2 tasks and from 25.9% to 43.2% on Level-3 tasks. Experiments on a controller-panel simulator without an attached industrial load further demonstrate integrated execution feasibility under representative interaction conditions, without claiming industrial deployment readiness.

发表机构

• Huazhong University of Science and Technology（华中科技大学）
• University of New South Wales（新南威尔士大学）

机构由 AI 辅助整理，请以论文原文为准。