A VAE-Driven Multi-Task Satellite-Aided Semantic Communication Framework for 6G-Enabled Connected Autonomous Vehicles

2026-07-15

AI Summary

This work addresses the inefficiency of conventional satellite communications in 6G vehicular networks, where transmitting redundant raw data wastes bandwidth and fails to meet the stringent requirements of low-latency, high-reliability semantic transmission. To overcome this, the paper proposes a variational autoencoder (VAE)-based multi-task semantic communication framework that extracts probabilistic latent representations capturing semantics relevant to both traffic sign reconstruction and classification. The framework enables end-to-end joint optimization and, to the best of the authors’ knowledge, represents the first application of VAEs in satellite-aided multi-task semantic communication. It enhances the robustness and compression efficiency of semantic features under noisy channel conditions, maintains stable performance across varying signal-to-noise ratios, and achieves substantial bandwidth savings ranging from 87.23% to 98.17%.

Abstract

The development of smart transportation systems and the introduction of 6G wireless communication technologies have significantly changed vehicle network topologies. Future connected autonomous vehicle (CAV) networks require bandwidth-efficient, reliable, and low-latency communication for safety-critical applications such as traffic sign recognition and decision-making. Conventional communication systems transmit raw data regardless of task relevance, which is inefficient in resource-constrained satellite channels where uplink bandwidth is scarce and propagation losses are large. Semantic communication addresses this limitation by transmitting task-relevant information instead of full signal representations. It extracts and conveys essential semantic features and leverages deep learning to optimize task performance at the receiver. Therefore, we present a Variational Autoencoder (VAE)-based multi-task semantic communication framework for satellite-assisted autonomous driving. Unlike deterministic autoencoder-based methods, the proposed model uses probabilistic latent representations for more robust and efficient encoding. The learned features are transmitted over noisy wireless channels to perform traffic sign reconstruction and classification. The framework is trained end-to-end to jointly optimize both tasks. Results show that the proposed approach achieves significant bandwidth reduction of up to 87.23\% to 98.17\% while maintaining stable performance across varying signal-to-noise ratio conditions.

Problem

• semantic communication
• connected autonomous vehicles
• satellite-aided communication
• bandwidth efficiency
• 6G

Innovation

• Variational Autoencoder
• Semantic Communication
• Multi-Task Learning
• Satellite-Aided Communication
• Connected Autonomous Vehicles