Semantic based knowledge representation and adaptive mission planning for MCM missions using AUVs

Abstract

Mine Countermeasures (MCM) are a substantial challenge in the domain of underwater operations especially when using Autonomous Underwater Vehicles (AUVs). The work presented in this paper focuses on the semantic representation of knowledge and its utilization for mission planning and plan adaptation in a simulated MCM environment using the Nessie AUV. With respect to semantic knowledge representation this work builds upon the KnowRob system. Various ontologies model the environment, the AUV components and capabilities as well as the planning domain. For planning and plan adaptation we use the POPF Planning Domain Definition Language (PDDL) planner. Plan adaptation reuses previous plans when calculating a new plan thus saving computational resources. The main contribution of this work is an approach that relies on semantic information to represent knowledge in a MCM context and its usage for planning MCM missions in an energy efficient manner.