aiqbench analysis
This research introduces MemoGuard, a runtime system that mitigates "memory traps" in communication-limited robots by validating episodic memories against safety constraints before reuse. By leveraging local small language models like Llama 3.2 for fallback reasoning only when necessary, the approach significantly reduces battery violations and computational overhead compared to naive similarity-based or always-reasoning strategies.
MemoGuard: An Adaptive Runtime for Guarding Against Memory Traps in Communication-Limited Robot Navigation
arXiv:2607.15589v1 Announce Type: cross Abstract: 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.
Abstract: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 this https URL.
Paper accepted at IEEE/ACM ESWEEK (CODES) 2026. Authors' version posted for personal use and not for redistribution. The definitive version of the paper will appear in IEEE Embedded Systems Letters
Robotics (cs.RO); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI); Systems and Control (eess.SY)
arXiv:2607.15589 [cs.RO]
(or arXiv:2607.15589v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.15589 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 245 words
