MetaCom improves vehicle network communication under poor signals

MetaCom: Meta Codebook Learning for Robust V2X Semantic Communications

Information Theory

Summary

Vehicles that share information with each other and the environment often struggle with limited communication bandwidth and noisy channels, which can lead to errors. The authors created MetaCom, a new system that learns flexible codebooks to keep the shared information accurate even when conditions change quickly. It uses advanced training techniques to adapt on the fly and works well even when signal quality is low. Tests show MetaCom can better balance data needs and accuracy than previous methods.

What this means in practice

  • For automotive communication engineers: Design more reliable vehicle communication systems that maintain perception accuracy under poor wireless conditions by adapting codebooks dynamically.
  • For wireless network developers: Develop robust data encoding schemes for networks with rapidly changing environments, improving semantic data transfer efficiency.

Authors

Muge Yu, Danlan Huang, Xinyi Zhou, Shuqi Chai, Zhiyong Feng

Abstract

Collaborative perception in Vehicle-to-Everything (V2X) networks faces dual challenges: strictly limited bandwidth and channel impairments. Existing static quantization schemes often suffer from feature manifold drift caused by highly non-stationary traffic environments. To address this, we propose MetaCom, a robust digital semantic communication framework featuring a Meta-Codebook Learning paradigm. First, we introduce a Differentiable Quantized Semantic Communications (DQSemCom) module trained with perturbations induced by the simulated digital modulation and channel via Gumbel-Softmax relaxation. Building on this, we design a Bi-Level Meta-Evolution Mechanism (Bi-MEM) that treats manifold drift as a sequence of rapid adaptation tasks, aligning the codebook via data-level smoothing and parameter-level meta-updates. Furthermore, we validate MetaCom under AWGN, Rayleigh, and Rician fading channels. Experimental results demonstrate that MetaCom achieves superior trade-offs between perception precision and communication overhead, outperforming state-of-the-art methods by a significant margin under low-SNR conditions.