Learning Hierarchical Control For Multi-Agent Capacity-Constrained Systems

This paper introduces a data-driven hierarchical control scheme for a fleet of nonlinear, capacity-constrained autonomous agents in an iterative environment. The proposed control framework consists of a high-level dynamic task assignment and routing layer and low-level motion planning and tracking layer. Each layer uses a data-driven Model Predictive Control (MPC) policy for efficient calculation of new task assignments and actuation. We use collected data to iteratively refine estimates of agent capacity usage, and update MPC policy parameters accordingly. We leverage tools from iterative learning control to integrate learning at both hierarchy levels, and coordinate learning between levels to maintain closed-loop feasibility and performance improvement at each iteration.