Extending a Refinement Acting Engine for Fleet Management: Concurrency and Resources

Recent years have seen an important increase in the complexity of deployed robotic systems, both in terms of the number of robots involved, and scale of the tackled problems. The key challenge in this context is to allow the design of fleet control systems that, on the one hand, allow flexible and reactive operation of individual robots and, on the other hand, enable the system to optimize the global behavior of the fleet in order to increase its effectiveness and efficiency. To approach this problem, we propose to extend the Refinement Acting Engine (RAE) that has been used to program the behavior of autonomous agents through a hierarchical decomposition of high-level tasks into primitive commands, and is the subject of active research in order to guide its decisions with planning and scheduling techniques. The core of our proposal is to provide first-hand support for concurrency in the RAE procedure, allowing a natural representation for concurrent systems by reasoning on resource allocation. The resulting acting engine exploits a custom language that is designed to ease its integration with planning engines, both through its simple and orthogonal core constructs as well as in the explicit identification of decision points in the system operation. We provide an initial validation of the system in simulation on a logistic problem involving a fleet of robots.