用验证门控机制确保多机器人系统长期任务执行安全可靠。
Verification-Gated Agentic Mission-State Governance for Intelligent Industrial Multi-Robot Systems
- 构建任务森林与受控黑板双状态模型，实现任务依赖与资源锁定的动态管理。
- 在工厂场景测试中，无效承诺减少，锁冲突、重复分配等问题显著降低。
- 适合需要高安全性与可追溯性的工业自动化系统开发者使用。
代理式人工智能被广泛用于分解工业任务、生成机器人动作并适应动态网络物理环境中的执行计划。然而，仅靠自主提案无法保证多机器人系统在长时序执行中维持任务依赖、资源所有权、安全约束或修复边界。本文提出一种验证门控的智能工业多机器人系统任务状态治理框架。该框架维护两个同步状态对象：一个演化任务森林，用于保持任务层次结构、延迟落地和可修复子结构；一个受控黑板，用于在线执行状态、机器人轨迹、资源锁、世界信念、提案、验证记录及场景临时约束。从每次森林-黑板快照中推导出执行耦合拓扑，揭示跨分支依赖关系，用于提案验证、并行提交资格判断和有界修复。候选任务分配、修复、延期或约束更新可由启发式、优化或代理推理模块生成，但仅在确定性验证和原子提交后才能更新已承诺任务状态。我们在室内工厂多机器人场景下进行评估，涵盖30次种子远程建设压力测试、结构消融实验与可扩展性探测。结果表明，在预设任务谓词下，任务状态进展的验证率与安全审计率更高，无效承诺、锁冲突、重复分配、废弃节点和破坏性修复均显著减少。研究将代理式AI定位为可检视任务状态验证的提案生成层，而非无监督的执行主体。
原文摘要 · Abstract (English)
Agentic artificial intelligence is increasingly used to decompose industrial tasks, propose robot actions, and adapt execution plans in dynamic cyber-physical environments. However, autonomous proposal generation alone does not guarantee that multi-robot industrial systems preserve task dependencies, resource ownership, safety holds, or repair boundaries during long-horizon execution. This paper introduces a verification-gated agentic mission-state governance framework for intelligent industrial multi-robot systems. The framework maintains two synchronized state objects: an evolving task forest for persistent hierarchy, delayed grounding, and repairable substructures; and a governed blackboard for online execution state, robot traces, resource locks, world beliefs, proposals, verification records, and scene-temporary constraints. From each forest--blackboard snapshot, a derived execution coupling topology exposes cross-branch dependencies for proposal verification, parallel-commit eligibility, and bounded repair. Candidate assignments, repairs, deferrals, and constraint updates may be generated by heuristic, optimization, or agentic reasoning modules, but they can update the committed mission state only after deterministic verification and atomic commit. We evaluate the framework in an indoor factory multi-robot scenario, 30-seed remote-construction stress benchmarks, structural ablations, and scalability probes. The results show improved verified and safety-audited mission-state progress with fewer invalid commitments, lock conflicts, duplicate assignments, abandoned nodes, and disruptive repairs under modeled mission predicates. The study positions agentic AI as a proposal-generating layer governed by inspectable mission-state verification rather than as an unchecked execution authority.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。