Topic: Intelligent Optimization and Decision-Making for Complex Low-Altitude Transportation Systems

Low-altitude transportation systems comprise interacting aircraft, airspace management systems, communication networks, and ground infrastructure that jointly support cargo delivery, passenger mobility, and emergency transport. Their operation involves coupled decisions across vehicle, fleet, and network levels, subject to airspace capacity limits, vehicle dynamics, environmental uncertainty, and communication and energy constraints. Heterogeneous vehicle capabilities, dynamic traffic demand, and competing objectives further complicate system modeling, planning, and control. Reliable operation therefore requires optimization and decision-making methods that explicitly account for these interdependencies and constraints. Integrating predictive modeling, constrained optimization, and adaptive control provides a basis for addressing these challenges, while world models, digital twins, and causal learning offer approaches to improving environmental prediction, policy evaluation, and generalization across operating conditions.

This Special Issue aims to bring together advances in intelligent optimization and decision-making for complex low-altitude transportation systems. It focuses on methods for autonomous navigation, coordinated fleet operations, and system-level resource allocation, with particular attention to feasibility, safety, robustness, and computational efficiency. Contributions addressing predictive world models, digital twins, constrained multi-objective optimization, multi-agent coordination, communication-aware decision-making, causal learning, and integrated system design are welcome. The Special Issue invites original theoretical and methodological research, as well as application studies supported by simulation, experiments, or operational data.

Potential topics include but are not limited to the following:

1. Autonomous navigation, trajectory planning, obstacle avoidance, and conflict detection and resolution for unmanned aerial vehicles (UAVs) in low-altitude airspace;

2. World models for environment representation, action-conditioned dynamics prediction, and model-based planning in low-altitude transportation;

3. Digital twins for system modeling, simulation-based policy evaluation, simulation-to-reality transfer, and closed-loop model and policy adaptation;

4. Constrained multi-objective optimization for trajectory planning, fleet scheduling, and resource allocation in dynamic and uncertain environments;

5. Multi-agent planning and control, adaptive UAV grouping, coordination topology optimization, and cooperative task allocation in heterogeneous air–ground systems;

6. Aerial communication network optimization, communication-aware planning and control, and joint allocation of communication and computing resources;

7. Causal representation learning and causal inference for policy generalization, transfer, and robust decision-making across operating environments;

8. Task-oriented automated co-design of UAV configurations, sensing systems, and control policies under payload, energy, and computational constraints;

9. Safe reinforcement learning, risk-aware planning, and online decision-making subject to collision avoidance, vehicle dynamics, and operational constraints.