Active perception for plume source localisation with underwater gliders

We consider the problem of localising an unknown underwater plume source in an energyoptimal manner. We first develop a specialised Gaussian process (GP) regression technique for estimating the source location given concentration measurements and an ambient flow field. Then, we use the GP upper confidence bound (GP-UCB) for active perception to choose sampling locations that both improve the estimate of the source and lead the glider to the correct source location. A trim-based FMT∗planner is then used to find the sequence of controls that minimise the energy consumption. We provide a theoretical guarantee on the performance of the algorithm, and demonstrate the algorithm using both artificial and experimental datasets.

[1]  Ales Zamuda,et al.  Differential evolution and underwater glider path planning applied to the short-term opportunistic sampling of dynamic mesoscale ocean structures , 2014, Appl. Soft Comput..

[2]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[3]  Robert Fitch,et al.  Energy-optimal kinodynamic planning for underwater gliders in flow fields , 2017 .

[4]  R. Andrew Russell,et al.  Robot Odor Localization: A Taxonomy and Survey , 2008, Int. J. Robotics Res..

[5]  Gaurav S. Sukhatme,et al.  Planning and Implementing Trajectories for Autonomous Underwater Vehicles to Track Evolving Ocean Processes Based on Predictions from a Regional Ocean Model , 2010, Int. J. Robotics Res..

[6]  Lian Lian,et al.  Toward Optimal Rendezvous of Multiple Underwater Gliders: 3D Path Planning with Combined Sawtooth and Spiral Motion , 2016, Journal of Intelligent & Robotic Systems.

[7]  T. Tirabassi,et al.  Gaussian plume model and advection-diffusion equation: An attempt to connect the two approaches , 1979 .

[8]  Fumin Zhang,et al.  A bio-inspired plume tracking algorithm for mobile sensing swarms in turbulent flow , 2013, 2013 IEEE International Conference on Robotics and Automation.

[9]  Yi Guo,et al.  Multi-robot cooperative control for monitoring and tracking dynamic plumes , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Jeng-Shyang Pan,et al.  A genetic-based effective approach to path-planning of autonomous underwater glider with upstream-current avoidance in variable oceans , 2017, Soft Comput..

[11]  Ben Hollings,et al.  Using autonomous underwater gliders for geochemical exploration surveys , 2018 .

[12]  Daniel Hernández-Sosa,et al.  Path planning for underwater gliders using iterative optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[13]  M. Ani Hsieh,et al.  Zig-zag wanderer: Towards adaptive tracking of time-varying coherent structures in the ocean , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Yu Jiancheng,et al.  Path planning in stronger ocean current for underwater glider , 2015, 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER).

[15]  D. C. Webb,et al.  SLOCUM: an underwater glider propelled by environmental energy , 2001 .

[16]  Jie Ma,et al.  Path planning for underwater glider under control constraint , 2017 .

[17]  Stefan B. Williams,et al.  Large-scale path planning for Underwater Gliders in ocean currents , 2009 .

[18]  David M. Fratantoni,et al.  UNDERWATER GLIDERS FOR OCEAN RESEARCH , 2004 .

[19]  Andrea L. Bertozzi,et al.  Tracking Environmental Level Sets with Autonomous Vehicles , 2004 .

[20]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[21]  Massimo Vergassola,et al.  ‘Infotaxis’ as a strategy for searching without gradients , 2007, Nature.

[22]  M. Ani Hsieh,et al.  Information Theoretic Source Seeking Strategies for Multiagent Plume Tracking in Turbulent Fields , 2017 .

[23]  Mark R. Morelande,et al.  Parameter estimation of a continuous chemical plume source , 2008, 2008 11th International Conference on Information Fusion.

[24]  Naomi Ehrich Leonard,et al.  Model-based feedback control of autonomous underwater gliders , 2001 .

[25]  Simo Särkkä,et al.  Infinite-Dimensional Kalman Filtering Approach to Spatio-Temporal Gaussian Process Regression , 2012, AISTATS.