Combining Hierarchical MILP-MPC and Artificial Potential Fields for Multi-robot Priority-Based Sanitization of Railway Stations

We propose a distributed framework, driving a team of robots for the sanitization of very large dynamic indoor environment, as the railway station. A centralized server uses the Hierarchical Mixed Integer Linear Programming to coordinate the robots assigning different zones where the cleaning is a priority; thanks to the Model Predictive Control approach we use historical data about the distribution of people and the knowledge about the transportation service of the station, to predict the future dynamic evolution of the position of people in the environment and the spreading of the contaminants. Each robot navigates the large environment represented as a gridmap, exploiting the Artificial Potential Fields technique in order to reach and clean the assigned areas. We tested our solution considering real data collected by the WiFi network of the main Italian railway station, Roma Termini. We compared our results with a Decentralized Multirobot Deep Reinforcement Learning approach.