Adaptive mission plan diagnosis and repair for fault recovery in autonomous underwater vehicles

This paper proposes a novel approach for autonomous mission diagnosis and repair for maintaining operability of unmanned underwater vehicles. It combines the benefits of knowledge-based ontology representation, autonomous partial ordering plan repair and robust mission execution. The approach uses the potential of ontology reasoning in order to orient the planning algorithms adapting the mission plan of the vehicle. It can handle uncertainty and action scheduling in order to maximize mission efficiency and minimise mission failures due to external or unexpected factors. Its performance is presented in a set of simulated scenarios. The paper concludes by showing the results of a trial demonstration. Observations of different environmental and internal parameters are simulated in a REMUS 100 AUV while performing a mission. These trigger a knowledge exchange between the diagnosis monitor agent and the adaptive mission planner embedded agent. Based on the observed data and the original knowledge, the experiment shows how the adaptive planner system is able to identify the gaps in the mission and adapt the platform´s mission plan accordingly.