Online Informative Path Planning for Active Information Gathering of a 3D Surface

This paper presents an online informative path planning approach for active information gathering on three-dimensional surfaces using aerial robots. Most existing works on surface inspection focus on planning a path offline that can provide full coverage of the surface, which inherently assumes the surface information is uniformly distributed hence ignoring potential spatial correlations of the information field. In this paper, we utilize manifold Gaussian processes (mGPs) with geodesic kernel functions for mapping surface information fields and plan informative paths online in a receding horizon manner. Our approach actively plans information-gathering paths based on recent observations that respect dynamic constraints of the vehicle and a total flight time budget. We provide planning results for simulated temperature modeling for simple and complex 3D surface geometries (a cylinder and an aircraft model). We demonstrate that our informative planning method outperforms traditional approaches such as 3D coverage planning and random exploration, both in reconstruction error and information-theoretic metrics. We also show that by taking spatial correlations of the information field into planning using mGPs, the information gathering efficiency is significantly improved.

[1]  Bayesian fusion using conditionally independent submaps for high resolution 2.5D mapping , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Franz S. Hover,et al.  Sampling-Based Coverage Path Planning for Inspection of Complex Structures , 2012, ICAPS.

[3]  Marc Peter Deisenroth,et al.  Matern Gaussian processes on Riemannian manifolds , 2020, NeurIPS.

[4]  Vijay Kumar,et al.  Minimum snap trajectory generation and control for quadrotors , 2011, 2011 IEEE International Conference on Robotics and Automation.

[5]  Raphael Falque,et al.  Skeleton-Based Conditionally Independent Gaussian Process Implicit Surfaces for Fusion in Sparse to Dense 3D Reconstruction , 2020, IEEE Robotics and Automation Letters.

[6]  Christophe Geuzaine,et al.  Gmsh: A 3‐D finite element mesh generator with built‐in pre‐ and post‐processing facilities , 2009 .

[7]  Roland Siegwart,et al.  Uniform coverage structural inspection path–planning for micro aerial vehicles , 2015, 2015 IEEE International Symposium on Intelligent Control (ISIC).

[8]  Roland Siegwart,et al.  Receding horizon path planning for 3D exploration and surface inspection , 2018, Auton. Robots.

[9]  Marc Carreras,et al.  A survey on coverage path planning for robotics , 2013, Robotics Auton. Syst..

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

[11]  Franz S. Hover,et al.  Advanced perception, navigation and planning for autonomous in-water ship hull inspection , 2012, Int. J. Robotics Res..

[12]  Roland Siegwart,et al.  Adaptive continuous‐space informative path planning for online environmental monitoring , 2017, J. Field Robotics.

[13]  Michel Devy,et al.  UAV-based Inspection of Airplane Exterior Screws with Computer Vision , 2019, VISIGRAPP.

[14]  Jin-Won Nam,et al.  Development of Crack Detection System with Unmanned Aerial Vehicles and Digital Image Processing , 2015 .

[16]  Charles Richter,et al.  Polynomial Trajectory Planning for Aggressive Quadrotor Flight in Dense Indoor Environments , 2016, ISRR.

[17]  C. Ian Connolly,et al.  The determination of next best views , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[18]  David B. Dunson,et al.  Intrinsic Gaussian processes on complex constrained domains , 2018, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[19]  Nicholas M. Patrikalakis,et al.  Asymptotically optimal inspection planning using systems with differential constraints , 2013, 2013 IEEE International Conference on Robotics and Automation.

[20]  Roland Siegwart,et al.  An incremental sampling-based approach to inspection planning: the rapidly exploring random tree of trees , 2016, Robotica.

[21]  Roland Siegwart,et al.  An informative path planning framework for UAV-based terrain monitoring , 2018, Autonomous Robots.

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

[23]  Andrew Fitzgibbon,et al.  Gaussian Process Implicit Surfaces , 2006 .

[24]  Howard V. Kennedy.  Modeling noise in thermal imaging systems , 1993, Defense, Security, and Sensing.

[25]  Howie Choset,et al.  Morse Decompositions for Coverage Tasks , 2002, Int. J. Robotics Res..

[26]  Siyuan Chen,et al.  UAV Bridge Inspection through Evaluated 3D Reconstructions , 2019, Journal of Bridge Engineering.

[27]  Roland Siegwart,et al.  Obstacle-aware Adaptive Informative Path Planning for UAV-based Target Search , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[28]  Richard Pito,et al.  A Solution to the Next Best View Problem for Automated Surface Acquisition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Enrique del Castillo,et al.  Geodesic Gaussian Processes for the Parametric Reconstruction of a Free-Form Surface , 2015, Technometrics.

[30]  Hongdong Li,et al.  Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Daniel D. Lee,et al.  Online Continuous Mapping using Gaussian Process Implicit Surfaces , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[32]  Teresa A. Vidal-Calleja,et al.  Learning spatial correlations for Bayesian fusion in pipe thickness mapping , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[33]  Sebastian Scherer,et al.  Autonomous Exploration for Infrastructure Modeling with a Micro Aerial Vehicle , 2015, FSR.

[34]  Masashi Sugiyama,et al.  Geodesic Gaussian kernels for value function approximation , 2008, Auton. Robots.

[35]  James H. Elder,et al.  Effects of Specular Highlights on Perceived Surface Convexity , 2014, PLoS Comput. Biol..

[36]  Howie Choset,et al.  Exact Cellular Decomposition of Closed Orientable Surfaces Embedded in R3. , 2001 .

[37]  Roland Siegwart,et al.  Three-dimensional coverage path planning via viewpoint resampling and tour optimization for aerial robots , 2015, Autonomous Robots.

[38]  Marc Toussaint,et al.  Gaussian process implicit surfaces for shape estimation and grasping , 2011, 2011 IEEE International Conference on Robotics and Automation.