Adaptive sampling of cumulus clouds with UAVs

This paper presents an approach to guide a fleet of Unmanned Aerial Vehicles (UAVs) to actively gather data in low-altitude cumulus clouds with the aim of mapping atmospheric variables. Building on-line maps based on very sparse local measurements is the first challenge to overcome, for which an approach based on Gaussian Processes is proposed. A particular attention is given to the on-line hyperparameters optimization, since atmospheric phenomena are strongly dynamical processes. The obtained local map is then exploited by a trajectory planner based on a stochastic optimization algorithm. The goal is to generate feasible trajectories which exploit air flows to perform energy-efficient flights, while maximizing the information collected along the mission. The system is then tested in simulations carried out using realistic models of cumulus clouds and of the UAVs flight dynamics. Results on mapping achieved by multiple UAVs and an extensive analysis on the evolution of Gaussian processes hyperparameters is proposed.

[1]  Nicholas R. J. Lawrance,et al.  Path planning for autonomous soaring flight in dynamic wind fields , 2011, 2011 IEEE International Conference on Robotics and Automation.

[2]  Nicholas R. J. Lawrance,et al.  Energy-constrained motion planning for information gathering with autonomous aerial soaring , 2013, 2013 IEEE International Conference on Robotics and Automation.

[3]  M. Ani Hsieh,et al.  Robotic Tracking of Coherent Structures in Flows , 2014, IEEE Transactions on Robotics.

[4]  J. Spall.  Implementation of the simultaneous perturbation algorithm for stochastic optimization , 1998 .

[5]  Jean-Christophe Golaz,et al.  Large‐eddy simulation of the diurnal cycle of shallow cumulus convection over land , 2002 .

[6]  Joachim L. Grenestedt,et al.  Wind field estimation for autonomous dynamic soaring , 2012, 2012 IEEE International Conference on Robotics and Automation.

[7]  Gaurav S. Sukhatme,et al.  Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena , 2013, 2013 IEEE International Conference on Robotics and Automation.

[8]  M. V. Ramana,et al.  Warming trends in Asia amplified by brown cloud solar absorption , 2007, Nature.

[9]  Jonghyuk Kim,et al.  GPmap: A Unified Framework for Robotic Mapping Based on Sparse Gaussian Processes , 2013, FSR.

[10]  Véronique Ducrocq,et al.  The Meso-NH Atmospheric Simulation System. Part I: adiabatic formulation and control simulations , 1997 .

[11]  Simon Lacroix,et al.  Monitoring the evolution of clouds with UAVs , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Nicholas R. J. Lawrance,et al.  Autonomous Exploration of a Wind Field with a Gliding Aircraft , 2011 .

[13]  Michaël Soulignac,et al.  Feasible and Optimal Path Planning in Strong Current Fields , 2011, IEEE Transactions on Robotics.

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

[15]  Maciej Stachura,et al.  Overview of Small Fixed-Wing Unmanned Aircraft for Meteorological Sampling , 2015 .

[16]  Bjorn Stevens,et al.  What Are Climate Models Missing? , 2013, Science.

[17]  James C. Spall,et al.  Introduction to Stochastic Search and Optimization. Estimation, Simulation, and Control (Spall, J.C. , 2007 .

[18]  J. Neidhoefer,et al.  Wind Field Estimation for Small Unmanned Aerial Vehicles , 2010 .

[19]  James C. Spall,et al.  Introduction to stochastic search and optimization - estimation, simulation, and control , 2003, Wiley-Interscience series in discrete mathematics and optimization.

[20]  Nicola Basilico,et al.  Exploration strategies based on multi-criteria decision making for searching environments in rescue operations , 2011, Auton. Robots.

[21]  G. J. Holland,et al.  The Aerosonde Robotic Aircraft: A New Paradigm for Environmental Observations , 2001 .

[22]  Fabio Tozeto Ramos,et al.  Bayesian optimisation for active perception and smooth navigation , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Jean-Marc Moschetta,et al.  Development of a Long Endurance Mini-UAV: ETERNITY , 2013 .

[24]  A. Genio,et al.  The Role of Entrainment in the Diurnal Cycle of Continental Convection , 2010 .

[25]  S. Ravela,et al.  Tracking and Mapping Coherent Structures , 2013 .

[26]  Eric W. Frew,et al.  The tempest unmanned aircraft system for in situ observations of tornadic supercells: Design and VORTEX2 flight results , 2011, J. Field Robotics.

[27]  Jean-Philippe Condomines,et al.  Experimental Wind Field Estimation and Aircraft Identification , 2015 .

[28]  Yan Pailhas,et al.  Path Planning for Autonomous Underwater Vehicles , 2007, IEEE Transactions on Robotics.

[29]  Judith A. Curry,et al.  Application of Aerosondes to Melt-Pond Observations over Arctic Sea Ice , 2006 .

[30]  David C. Pieri,et al.  Utilization of in situ airborne MS-based instrumentation for the study of gaseous emissions at active volcanoes , 2010 .

[31]  Payman Sadegh,et al.  Constrained optimization via stochastic approximation with a simultaneous perturbation gradient approximation , 1997, Autom..

[32]  M. V. Ramana,et al.  Capturing vertical profiles of aerosols and black carbon over the Indian Ocean using autonomous unmanned aerial vehicles , 2007 .

[33]  Nicholas R. J. Lawrance,et al.  Learning to soar: Resource-constrained exploration in reinforcement learning , 2015, Int. J. Robotics Res..

[34]  M. V. Ramana,et al.  Simultaneous observations of aerosol–cloud–albedo interactions with three stacked unmanned aerial vehicles , 2008, Proceedings of the National Academy of Sciences.

[35]  Jack Elston,et al.  Energy efficient UAS flight planning for characterizing features of supercell thunderstorms , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[36]  Kian Ming Adam Chai,et al.  Multi-task learning with Gaussian processes , 2010 .