Robust vehicle routing policies using local communications & sensing

This paper analyzes the dynamic traveling repairman problem (DTRP) considering desired properties for unmanned multi-agent systems. We analyze solutions for the DTRP contemplating three desired properties; systems using local sensing and communications, systems operable through disrupted communications, and systems robust to single-agent failures. This paper presents a collaboration framework with specifications on the information transmitted between agents and constraints on the communications range. Two policies are presented using local communications and sensing which by design are operable through disrupted communications and robust to single-agent failures. An asymptotic bound is derived for the maximum wait time of targets under the two policies when targets are generated from a uniform distribution. The bound is shown to be pessimistic through simulations.