Dynamic Urban Air Mobility Ride-Sharing Trajectory Planning Using Radio Maps and Multi-Source Hybrid Attention Reinforcement Learning

Urban Air Mobility (UAM) systems are emerging as promising solutions to alleviate urban congestion, with path planning becoming a key focus area. Unlike ground transportation, UAM trajectory planning has to prioritize communication quality for accurate location tracking in constantly changing environments to ensure safety. Meanwhile, the UAM system, serving as an air taxi, requires adaptive planning to respond to real-time passenger requests, especially in ride-sharing scenarios. However, conventional trajectory planning strategies based on predefined routes lack the flexibility to meet unpredictable passenger ride demands. To address these challenges, this work first proposes constructing a radio map to evaluate communication quality. Building on this, we introduce a novel Multi-Source Hybrid Attention Reinforcement Learning (MSHA-RL) framework that integrates diverse data sources, balancing global and local insights for responsive, realtime path planning. Experimental results demonstrate that our approach enables communication-compliant trajectory planning, reducing travel time and enhancing operational efficiency.