Abstract
A two-stage supervisory model predictive control (MPC) framework is developed for cooperative unmanned aerial vehicle (UAV) coverage during mission transit and reconfiguration after single-agent loss. A synchronized predictive supervisory layer coordinates sector responsibility and constrained motion planning through a ranked assignment–feasibility architecture: Stage 1 orders candidate sector assignments, and Stage 2 selects an assignment-consistent finite-horizon trajectory. This explicitly links combinatorial task allocation to predictive sensing-service constraints while separating mission coordination from low-level vehicle stabilization. Existence, exact-model interval-wise constraint satisfaction, and conditional post-fault solvability are characterized for the finite-dimensional analytical formulation. A fully specified, reproducible finite-control-library realization is assessed through matched-weight nominal ablations, continuous-time separation checks on executed first-order trajectories, and post-fault task-coverage histories. An additional controlled study tests assignment-conditioned trajectory candidates against frozen-task and universal-library references for five deterministic fault configurations, with matched pre-fault motion within each comparison. The experiments demonstrate a reproducible post-fault redistribution mechanism: candidate responsibilities are coupled to predictive service-feasibility tests, and the resulting motion choices are evaluated against coverage, overlap, terminal progress, and computation. Matched ablations and five paired fault configurations quantify both the sensing effects and the competing objectives of the supervisory policy. A supplementary two-phase completion experiment then switches from the monitoring task to a terminal gathering mode and shows representative nominal and post-fault arrivals to the target region under the same first-order safety model.