MemoGuard: An Adaptive Runtime for Guarding Against Memory Traps in Communication-Limited Robot Navigation
RoboticsArtificial IntelligenceNetworking and Internet Architecture
Summary
The authors study robots that have to make decisions on their own when they can't communicate with humans. They focus on using past experiences (episodic memory) to help robots decide quickly, but sometimes these memories aren't safe to use because conditions have changed. Their solution, MemoGuard, checks past memories against current robot conditions before using them, which helps prevent unsafe decisions without always needing time-consuming thinking. In tests, MemoGuard improved safety and used less energy compared to other methods.
Authors
Rajat Bhattacharjya, Hyeonjong Ju, Sing-Yao Wu, Eli Bozorgzadeh, Nikil Dutt
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.