Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

2026-08-17

AI Summary

This study addresses the high latency in UAV video transmission that hinders ground-assisted efficiency by proposing an edge visual optimization framework integrating Graph Convolutional Networks (GCN) with A2C reinforcement learning. The proposed method leverages GCN to exploit pixel-level feature correlations, enabling selective sub-region transmission as a superior alternative to conventional full-frame approaches, while employing Lagrangian duality for policy optimization under latency constraints. Experimental results demonstrate that this model significantly reduces both video transmission latency and false detection rates, outperforming existing deep reinforcement learning methods and state-of-the-art models. Consequently, the framework effectively achieves low-latency, high-efficiency edge intelligent perception for UAV applications.

Abstract

UAV on-board vision systems are widely used for different activities, including monitoring in no-fly zones. In this case, the vision-equipped UAV streams a video to a ground server where an operator assists its activities. The latency of video transmission has a profound impact on the effectiveness of the operator assistance. However, most techniques available for video transmission still incur significant latency costs. In this paper, we propose a graph convolutional neural network-assisted (GCN-Assisted A2C) deep reinforcement learning (DRL) system model to find the optimal pixel-correlated area of a suspicious object. We combine the Lagrangian dual form with gradient descent to prevent lack of convergence and over- and under-penalization constraint violation during latency optimization. The proposed system model sends a sub-group pixel-correlated area of the frame from the UAV to the server rather than the transmission of the whole video frame. The proposed framework utilizes the GCN model to explore hidden representations of feature-correlated groups of pixels. Moreover, the GCN supervises the A2C model, which selects a subgroup to enhance transmission latency, thus supervising the training of UAV actions in A2C. Experimental results show that GCN-assisted A2C reduces video frame transmission latency together with false detection rate in UAV vision systems over other DRL and state-of-the-art models.

Problem

• UAV vision system
• video transmission latency
• edge computing
• operator assistance

Innovation

• Graph Convolutional Network
• Deep Reinforcement Learning
• Lagrangian Dual Optimization
• Edge Vision System
• Latency Reduction