Towards an ASP-Based Architecture for Autonomous UAVs in Dynamic Environments (Extended Abstract)

摘要: Traditional AI reasoning techniques have been used successfully in many domains, including logistics, scheduling and game playing. This paper is part of a project aimed at investigating how such can be extended to coordinate teams unmanned aerial vehicles (UAVs) dynamic environments. Specifically challenging are real-world environments where UAVs other network-enabled devices must communicate -- communication actions neither reliable nor free. Such network-centric common military, public safety commercial applications, yet most research (even multi-agent planning) usually takes communications among distributed agents as given. We address this challenge by developing an agent architecture algorithms based on Answer Set Programming (ASP). Although ASP has number the best our knowledge first practical application complete ASP-based architecture. It also involving combination centralized reasoning, decentralized execution monitoring, about network communications.