Abstract
Multiple Autonomous Underwater Vehicles (AUVs) are a potential alternative to conventional large manned vessels for mine countermeasure (MCM) operations. Online mission planning for cooperative multi-AUV network often relies or predefined contingency on reactive methods and do not deliver an optimal end-goal performance. Markov Decision Process (MDP) is a decision-making framework that allows an optimal solution, taking into account future decision estimates, rather than having a myopic view. However, most real-world problems are too complex to be represented by this framework. We deal with the complexity problem by abstracting the MCM scenario with a reduced state and action space, yet retaining the information that defines the goal and constraints coming from the application. Another critical part of the model is the ability of the vehicles to communicate and enable a cooperative mission. We use the Rendezvous Point (RP) method. The RP schedules meeting points for the vehicles throughput the mission. Our model provides an optimal action selection solution for the multi-AUV MCM problem. The computation of the mission plan is performed in the order of minutes. This quick execution demonstrates the model is feasible for real-time applications.
Highlights
Introduction and BackgroundMine Countermeasures (MCM) is the problem of finding and disposing of naval mines
We provide the theoretical formulation of the Markov Decision Process (MDP) framework
The method we propose in this paper, MDP using Rendezvous Point (RP), is relevant to applications and approaches in collaborative robotics, cooperative exploration, search and rescue, swarms, sensor networks
Summary
Mine Countermeasures (MCM) is the problem of finding and disposing of naval mines. Mine hunting is a common method used for MCM. It relies on detecting and classifying a target on the sea bottom, using a sonar sensor, followed by an appropriate disposal procedure. Often a manned surface vessel is employed in the mine hunting task. There are disadvantages of this traditional method. The personnel are at risk, the platforms require complex design and are expensive, and the procedure is time consuming and inflexible, as the sensor is coupled to the platform
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have