Towards improved AUV control through learning of periodic signals

Designing a high-performance controller for an Autonomous Underwater Vehicle (AUV) is a challenging task. There are often numerous requirements, sometimes contradicting, such as speed, precision, robustness, and energy-efficiency. In this paper, we propose a theoretical concept for improving the performance of AUV controllers based on the ability to learn periodic signals. The proposed learning approach is based on adaptive oscillators that are able to learn online the frequency, amplitude and phase of zero-mean periodic signals. Such signals occur naturally in open water due to waves, currents, and gravity, but can also be caused by the dynamics and hydrodynamics of the AUV itself. We formulate the theoretical basis of the approach, and demonstrate its abilities on synthetic input signals. Further evaluation is conducted in simulation with a dynamic model of the Girona 500 AUV on a hovering task.

[1]  Marc Carreras,et al.  Girona 500 AUV: From Survey to Intervention , 2012, IEEE/ASME Transactions on Mechatronics.

[2]  Konstantinos Kyriakopoulos,et al.  Persistent Autonomy: the Challenges of the PANDORA Project , 2012 .

[3]  M. Caccia,et al.  Modeling and identification of open-frame variable configuration unmanned underwater vehicles , 2000, IEEE Journal of Oceanic Engineering.

[4]  Jürgen Kurths,et al.  Synchronization - A Universal Concept in Nonlinear Sciences , 2001, Cambridge Nonlinear Science Series.

[5]  K.J. Kyriakopoulos,et al.  Towards the stabilization of an underactuated underwater vehicle in the presence of unknown disturbances , 2008, OCEANS 2008.

[6]  Darwin G. Caldwell,et al.  Improving the energy efficiency of autonomous underwater vehicles by learning to model disturbances , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  A. Ijspeert,et al.  Adaptive Frequency Oscillators and Applications , 2009 .

[8]  Darwin G. Caldwell,et al.  Autonomous robotic valve turning: A hierarchical learning approach , 2013, 2013 IEEE International Conference on Robotics and Automation.

[9]  Andres El-Fakdi,et al.  On the identification of non-linear models of unmanned underwater vehicles , 2004 .

[10]  Thor I. Fossen,et al.  Guidance and control of ocean vehicles , 1994 .

[11]  B. Jouvencel,et al.  Robust Nonlinear Path-Following Control of an AUV , 2008, IEEE Journal of Oceanic Engineering.

[12]  A. Ijspeert,et al.  Frequency Analysis with coupled nonlinear Oscillators , 2008 .

[13]  A. Ijspeert,et al.  Dynamic hebbian learning in adaptive frequency oscillators , 2006 .

[14]  Darwin G. Caldwell,et al.  Reinforcement Learning in Robotics: Applications and Real-World Challenges , 2013, Robotics.