Connectivity Management in Satellite-Aided Vehicular Networks With Multi-Head Attention-Based State Estimation

Managing connectivity in integrated satellite-terrestrial vehicular networks is critical for 6G, yet is challenged by dynamic conditions and partial observability. This letter introduces the Multi-Agent Actor-Critic with Satellite-Aided Multi-head self-attention (MAAC-SAM), a novel multi-agent reinforcement learning framework that enables vehicles to autonomously manage connectivity across Vehicle-to-Satellite (V2S), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Vehicle (V2V) links. Our key innovation is the integration of a multi-head attention mechanism, which allows for robust state estimation even with fluctuating and limited information sharing among vehicles. It leverages self-imitation learning (SIL) and fingerprinting to enhance learning efficiency. Simulation results, based on realistic SUMO traffic models and 3GPP-compliant configurations, demonstrate that MAAC-SAM outperforms satellite-aided baselines by about 8% and terrestrial-only baselines by up to 14% in transmission utility and maintains high estimation accuracy across varying vehicle densities and sharing levels.