Search papers, labs, and topics across Lattice.
This paper introduces KDG-SemNOMA, a novel framework that leverages knowledge distillation and generative models to enhance semantic communication in 6G robotic vehicle networks under bandwidth and energy constraints. The approach integrates a ConvNeXt-based deep joint source-channel coding architecture with a two-stage knowledge distillation strategy to reduce interference in uplink non-orthogonal multiple access (NOMA) scenarios. Experimental results show that KDG-SemNOMA achieves superior pixel-level accuracy and perceptual fidelity compared to existing methods, addressing critical challenges in high-fidelity visual perception for robotic vehicles.
KDG-SemNOMA transforms 6G robotic vehicle communications by significantly enhancing visual perception while minimizing bandwidth and energy usage.
To achieve sustainable intelligent mobility, 6G-empowered robotic vehicles (RVs) require high-fidelity visual perception under stringent bandwidth and energy constraints. Semantic communication offers a spectral-efficient solution but suffers from severe interference in uplink non-orthogonal multiple access (NOMA) RV networks. To address this, we propose a knowledge distillation-driven and generative models-enhanced NOMA framework for robust and green RV communications, named KDG-SemNOMA. First, we develop a ConvNeXt-based deep joint source-channel coding (DeepJSCC) architecture with an enhanced attention feature (AF) module for dynamic channel adaptation. Second, to mitigate interference without inference overhead, an orthogonal transmission teacher model guides the NOMA student model via a two-stage knowledge distillation strategy. Finally, to address the over-smoothing artifacts of pixel-wise optimization, we introduce a channel-conditional GAN (cGAN). By explicitly taking the Stage-I initial reconstruction and channel states as conditional inputs, this module refines coarse outputs into high-fidelity images with realistic textures. Experiments on FFHQ-256 demonstrate that KDG-SemNOMA significantly outperforms state-of-the-art methods in both pixel-level accuracy and perceptual fidelity.
