Long-Run Multi-Robot Planning With Uncertain Task Durations

This paper presents a multi-robot long-term planning approach under uncertainty on the duration of tasks. The proposed methodology takes advantage of generalized stochastic Petri nets to model multi-robot teams. It allows for unified modeling of action selection and uncertainty on duration of action execution. Goals are specified through the use of transition rewards and rewards per time unit. Our approach exploits the semantics provided by Markov reward automata in order to synthesize policies that optimize the long-run average reward. We provide an empirical evaluation on a simulated multi-robot monitoring problem, showing that the synthesized policy outperforms a carefully hand-crafted policy.