Massive Autonomous UAV Path Planning: A Neural Network Based Mean-Field Game Theoretic Approach
This addresses the challenge of autonomous path planning for large-scale UAV fleets in mission-critical applications like firefighting, offering a solution that balances communication and computation energy, though it is incremental as it builds on existing MFG methods with ML enhancements.
The paper tackles the problem of controlling massive UAVs for fast, energy-efficient travel without collisions under wind, by proposing a neural network-based mean-field game approach that reduces communication energy by exchanging states only initially and approximates PDE solutions with low computational complexity, achieving effective collision avoidance with low communication and acceptable computation energy.
This paper investigates the autonomous control of massive unmanned aerial vehicles (UAVs) for mission-critical applications (e.g., dispatching many UAVs from a source to a destination for firefighting). Achieving their fast travel and low motion energy without inter-UAV collision under wind perturbation is a daunting control task, which incurs huge communication energy for exchanging UAV states in real time. We tackle this problem by exploiting a mean-field game (MFG) theoretic control method that requires the UAV state exchanges only once at the initial source. Afterwards, each UAV can control its acceleration by locally solving two partial differential equations (PDEs), known as the Hamilton-Jacobi-Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations. This approach, however, brings about huge computation energy for solving the PDEs, particularly under multi-dimensional UAV states. We address this issue by utilizing a machine learning (ML) method where two separate ML models approximate the solutions of the HJB and FPK equations. These ML models are trained and exploited using an online gradient descent method with low computational complexity. Numerical evaluations validate that the proposed ML aided MFG theoretic algorithm, referred to as MFG learning control, is effective in collision avoidance with low communication energy and acceptable computation energy.