Joint Age-of-Latent and Resource Minimization for Wireless Multi-Camera Perception With Temporal Window Selection

2026-08-10

AI Summary

This work addresses the limitation of conventional Age of Information (AoI) in capturing the freshness of task-relevant latent representations in wireless multi-camera perception systems. To this end, the paper introduces a novel metric termed Age of Latent (AoL) and proposes the CoLA framework, which jointly optimizes task-level temporal window selection, slot-level encoder scheduling, and NOMA power allocation to minimize AoL and resource overhead while ensuring prediction reliability. CoLA leverages view redundancy for correlation-aware prediction, employs Lyapunov optimization for adaptive temporal window adjustment, and utilizes a Proximal Policy Optimization (PPO) algorithm for fine-grained resource control. Experimental results demonstrate that CoLA maintains high prediction reliability even under severe camera outages and achieves an optimal trade-off between AoL and resource consumption.

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.

Problem

• Age-of-Latent
• multi-camera perception
• temporal window selection
• resource minimization
• wireless communication

Innovation

• Age-of-Latent
• Temporal Window Selection
• Correlation-aware Prediction
• Lyapunov Optimization
• Multi-Camera Wireless Perception