A mobility-aware 6G-enabled V2X communications using multi-user MC-CDMA-OTFS and car-following Markov mobility model with multi-agent deep Q-learning

Engineering notes

Simulation results show that the proposed MC-CDMA–OTFS system with DQL tracking achieves up to a 2.5 dB SNR gain at BER = 10⁻³ and improves throughput compared to a conventional OFTS baseline.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

This paper presents a novel 6G-Enabled vehicle-to-everything (V2X) communication framework designed for the Intelligent Internet of Vehicles (IoV). The proposed system integrates the multi-user access and interference suppression capabilities of multi-carrier code division multiple access (MC-CDMA) with the delay–Doppler domain robustness of orthogonal time frequency space (OTFS) modulation. This hybrid design ensures reliable transmission in high-mobility and dense vehicular environments. Vehicle mobility is modeled using a combination of car-following dynamics and Markov chain-based lane-changing behavior, capturing both longitudinal and lateral motion patterns. The communication system further employs minimum mean square error (MMSE) and zero-forcing (ZF) techniques for multi-user detection at the receiver. To cope with rapid channel variations caused by mobility, we introduce a Multi-Agent Deep Q-learning (DQL) framework for mobility-aware channel tracking. Each agent learns adaptive channel update strategies based on historical channel estimates and mobility context. Simulation results show that the proposed MC-CDMA–OTFS system with DQL tracking achieves up to a 2.5 dB SNR gain at BER = 10⁻³ and improves throughput compared to a conventional OFTS baseline. These findings highlight the potential of the proposed hybrid design as a robust physical-layer foundation for next-generation 6G V2X networks.

Links and sources

• PDF from original source

Comments