MemoGuard：一种用于在通信受限的机器人导航中防范内存陷阱的自适应运行时
MemoGuard: An Adaptive Runtime for Guarding Against Memory Traps in Communication-Limited Robot Navigation
- University of California, Irvine（加利福尼亚大学欧文分校）
- Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对通信受限机器人导航中的内存陷阱问题，提出MemoGuard自适应运行时，在重用情景记忆前依拓扑、资源和结果契约验证，在模拟器及特定硬件上实验，有效减少电池安全违规和备用调用，降低开销并开源。
AI中文摘要：
在灾难检查和搜索救援等关键任务场景中，通信受限的机器人必须在无法访问远程操作员或高容量推理服务的情况下做出可靠的机载决策。情景记忆重用是一种有吸引力的低成本备用方案，但检索相似性不能保证执行有效性，即检索到的动作可能与当前上下文匹配，但由于拓扑变化、电池余量不足或先前结果不可靠而不安全。我们将这种高相似性但执行无效的情节称为内存陷阱。这就创造了一个安全效率设计空间，其中仅相似性重用可将备用成本降至最低，但可能不安全，而始终调用本地推理则以高计算和能源成本提高安全性。本文提出了MemoGuard，一种轻量级自适应运行时，在重用之前根据拓扑、资源和结果契约验证情景记忆，仅在验证失败时调用备用方案。在基于图形的走廊检查模拟器中，MemoGuard比仅相似性的top-1重用减少了76.6%的电池安全违规，同时比始终推理减少了21.4%的备用调用。在配备本地llama3.2:3b备用推理的NVIDIA Jetson AGX Xavier上，每次试验可避免3.67秒和36.97焦耳的备用推理开销。我们在这个https URL上开源了MemoGuard。
英文摘要：
Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services. Episodic memory reuse is an attractive low-cost fallback, but retrieval similarity does not guarantee execution validity, i.e., a retrieved action may match the current context yet be unsafe due to changed topology, insufficient battery margin, or unreliable prior outcomes. We call such high-similarity but execution-invalid episodes memory traps. This creates a safety-efficiency design space where similarity only reuse minimizes fallback cost but can be unsafe, while always invoking local reasoning improves safety at high computational and energy cost. This paper presents MemoGuard, a lightweight adaptive runtime that validates episodic memories against topology, resource, and outcome contracts before reuse, invoking fallback only when validation fails. In a graph-based corridor-inspection simulator, MemoGuard reduces battery safety violations by 76.6% over similarity-only top-1 reuse while reducing fallback calls by 21.4% over always reasoning. On an NVIDIA Jetson AGX Xavier with local llama3.2:3b fallback reasoning, this corresponds to 3.67 s and 36.97 J of avoided fallback-reasoning overhead per trial. We open-source MemoGuard at https://github.com/hetheiin/memoguard.
