Active Learning-based Model Predictive Coverage Control

The problem of coverage control, i.e., of coordinating multiple agents to optimally cover an area, arises in various applications. However, existing coverage algorithms face two major challenges: (1) dealing with nonlinear dynamics while respecting system and safety critical constraints, and (2) performing the task in an initially unknown environment. We solve the coverage problem by using a hierarchical framework, where references are calculated at a central server and passed to the agents' local model predictive control (MPC) tracking schemes. Furthermore, a probabilistic exploration-exploitation trade-off is deployed to ensure that the environment is actively explored by the agents. In addition, we derive a control framework that avoids the hierarchical structure by integrating the reference optimization in the MPC formulation. Active learning is then performed drawing inspiration from Upper Confidence Bound (UCB) approaches. We guarantee recursive feasibility and convergence to an optimal configuration for all developed control architectures. Furthermore, all methods are tested and compared on hardware using a miniature car platform.