面向无人机自主性的选择性代理恢复与持久任务运行时
Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime
AI总结：
提出持久任务运行时（PMR）框架，通过选择性调用外部代理推理器实现无人机恢复，引入学习型调用认知价值（learned-CVI）门控机制，在Gazebo/PX4基准测试中将硬/模糊场景成功率从5.0%提升至95.0%，同时减少16.7%的远程调用和29.2%的令牌消耗。
摘要：
代理AI可以通过在基于航点或设定点的局部执行遇到阻塞路径、重复无进展行为或任务级模糊时提供高层恢复推理来支持无人机自主性。然而，在物理无人机上，远程推理只有在选择性调用时最有用，因为每次调用都会引入延迟、资源成本、后端不确定性以及验证返回决策的需求。本文提出持久任务运行时（PMR），一种无人机恢复框架，它保持任务循环和安全关键执行在本地，同时仅将外部代理推理器用作按需恢复模块。推理器从预定义的恢复技能中选择，每个返回的决策在影响飞行之前经过解析、验证、安全过滤并映射到本地执行器动作。PMR引入了学习型调用认知价值（learned-CVI），一种紧凑的准入门控，用于估计远程代理推理何时可能改善近期任务进展以证明其操作成本合理。在包含八个场景的固定400次运行Gazebo/PX4基准测试中，learned-CVI将硬/模糊场景成功率从仅本地的5.0%提升至95.0%，优于一次性推理和周期性推理基线分别20.0和32.5个百分点，并且相对于手动调整的基于规则的调用基线，减少了16.7%的远程代理调用和29.2%的日志令牌。
英文摘要：
Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passages, repeated no-progress behavior, or mission-level ambiguity. On physical UAVs, however, remote reasoning is most useful when it is invoked selectively, since each call introduces latency, resource cost, backend uncertainty, and a need to validate the returned decision. This paper presents Persistent Mission Runtime (PMR), a UAV recovery framework that keeps the mission loop and safety-critical execution local while using an external agentic reasoner only as an on-demand recovery module. The reasoner selects from predefined recovery skills, and each returned decision is parsed, verified, safety-filtered, and mapped to local executor actions before it can affect flight. PMR introduces learned Cognitive Value of Invocation (learned-CVI), a compact admission gate that estimates when remote agentic reasoning is likely to improve near-term mission progress enough to justify its operational cost. Across a fixed 400-run Gazebo/PX4 benchmark with eight scenarios, learned-CVI raises hard/ambiguous-regime success from 5.0% under local-only autonomy to 95.0%, outperforms one-shot and periodic reasoning baselines by 20.0 and 32.5 percentage points, and reduces remote-agent calls by 16.7% and logged tokens by 29.2% relative to a manually tuned rule-based invocation baseline.
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。
