Optimizing autonomous surveillance route solutions from minimal human-robot interaction

Resource-constrained surveillance tasks represent a promising domain for autonomous robotic systems in a variety of real-world applications. In particular, we consider tasks where the system must maximize the probability of detecting a target while traversing an environment subject to resource constraints that make full coverage infeasible. In order to perform well, accurate knowledge of the underlying distribution of the surveillance targets is essential for practical use, but this is typically not available to robots. To successfully address surveillance route planning in human-robot teams, the design and optimization of human-robot interaction is critical. Further, in human-robot teaming, the human often possesses essential knowledge of the mission, environment, or other agents. In this paper, we introduce a new approach named Human-robot Autonomous Route Planning (HARP) that explores the space of surveillance solutions to maximize task-performance using information provided through interactions with humans. Experimental results have shown that with minimal interaction, we can successfully leverage human knowledge to create more successful surveillance routes under resource constraints.