Joint Age-of-Latent and Resource Minimization for Wireless Multi-Camera Perception With Temporal Window Selection
2026-08-10 • Information Theory
Information Theory
AI summaryⓘ
The authors studied how to keep information from many cameras fresh and useful for a central station, even when network resources are limited. They created a new measure called Age-of-Latent (AoL) that tracks how up-to-date the decoded camera data is, not just when updates arrive. Their method, CoLA, smartly decides when and how cameras send updates by predicting camera views based on overlap and using resources efficiently. Tests showed CoLA works well, especially when some cameras stop working for a while, by balancing freshness, reliability, and cost.
Age-of-InformationAge-of-Latentmulti-camera perceptionuplink resourcestemporal window of integrationNOMA power allocationLyapunov optimizationproximal policy optimizationlatent representationmulti-camera prediction
Authors
Chih-Yu Lin, Wanjiun Liao, Sumudu Samarakoon, Mehdi Bennis
Abstract
Multi-camera wireless perception requires a base station (BS) to maintain timely and reliable latent beliefs from distributed cameras under limited uplink resources. Conventional Age-of-Information (AoI) measures the age of the latest received update but not task-relevant latent content. We introduce Age-of-Latent (AoL) to quantify the freshness of each camera's latest decoded latent representation. A finite temporal window of integration (TWI) determines the task-commitment time and available uplink slots, creating a tradeoff among update opportunities, prediction duration, commit-time AoL, prediction reliability, and accumulated resource cost. Within this horizon, redundant or overlapping views enable correlated prediction, reducing reliance on the highest-cost communication and encoding configuration to maintain BS-side latent beliefs. We formulate a joint AoL-resource minimization problem coupling task-level TWI selection with slot-level encoder selection, scheduling, and NOMA power allocation under prediction-reliability constraints. We propose correlation-aware latent prediction for AoL minimization (CoLA), which uses Lyapunov optimization for task-level TWI selection based on AoL-resource cost and prediction uncertainty, and proximal policy optimization for slot-level resource control. Results on a warehouse multi-camera RF dataset show that CoLA adapts the TWI to camera-update availability and achieves the most favorable AoL-resource tradeoff among the benchmarks while maintaining prediction reliability, particularly under prolonged and severe camera outages.