Information-Driven Autonomous Exploration for a Vision-Based Mav

Abstract. Most micro aerial vehicles (MAV) are flown manually by a pilot. When it comes to autonomous exploration for MAVs equipped with cameras, we need a good exploration strategy for covering an unknown 3D environment in order to build an accurate map of the scene. In particular, the robot must select appropriate viewpoints to acquire informative measurements. In this paper, we present an approach that computes in real-time a smooth flight path with the exploration of a 3D environment using a vision-based MAV. We assume to know a bounding box of the object or building to explore and our approach iteratively computes the next best viewpoints using a utility function that considers the expected information gain of new measurements, the distance between viewpoints, and the smoothness of the flight trajectories. In addition, the algorithm takes into account the elapsed time of the exploration run to safely land the MAV at its starting point after a user specified time. We implemented our algorithm and our experiments suggest that it allows for a precise reconstruction of the 3D environment while guiding the robot smoothly through the scene.

[1]  Marc Pollefeys,et al.  Vision-based autonomous mapping and exploration using a quadrotor MAV , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Jens Wawerla,et al.  Feature-rich path planning for robust navigation of MAVs with Mono-SLAM , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Horst Bischof,et al.  Active monocular localization: Towards autonomous monocular exploration for multirotor MAVs , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Uwe D. Hanebeck,et al.  Closed-form optimization of covariance intersection for low-dimensional matrices , 2012, 2012 15th International Conference on Information Fusion.

[5]  Brian Yamauchi,et al.  A frontier-based approach for autonomous exploration , 1997, Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA'97. 'Towards New Computational Principles for Robotics and Automation'.

[6]  Sven Behnke,et al.  Layered Mission and Path Planning for MAV Navigation with Partial Environment Knowledge , 2014, IAS.

[7]  Wolfram Burgard,et al.  Which landmark is useful? Learning selection policies for navigation in unknown environments , 2009, 2009 IEEE International Conference on Robotics and Automation.

[8]  Cyrill Stachniss,et al.  Fast and effective online pose estimation and mapping for UAVs , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Gerd Hirzinger,et al.  A surface-based Next-Best-View approach for automated 3D model completion of unknown objects , 2011, 2011 IEEE International Conference on Robotics and Automation.

[10]  Roland Siegwart,et al.  Structural inspection path planning via iterative viewpoint resampling with application to aerial robotics , 2015, ICRA 2015.

[11]  Wolfram Burgard,et al.  OctoMap: an efficient probabilistic 3D mapping framework based on octrees , 2013, Autonomous Robots.

[12]  Davide Scaramuzza,et al.  Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles , 2014, Robotics: Science and Systems.

[13]  Davide Scaramuzza,et al.  An information gain formulation for active volumetric 3D reconstruction , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Vijay Kumar,et al.  Information-Theoretic Planning with Trajectory Optimization for Dense 3D Mapping , 2015, Robotics: Science and Systems.

[15]  Cyrill Stachniss,et al.  Predictive exploration considering previously mapped environments , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[16]  R. Bajcsy.  Active perception , 1988 .

[17]  Luis Enrique Sucar,et al.  View planning for 3D object reconstruction , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  George J. Pappas,et al.  Decentralized active information acquisition: Theory and application to multi-robot SLAM , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Alan Yuille,et al.  Active Vision , 2014, Computer Vision, A Reference Guide.

[20]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[21]  Rafael Murrieta-Cid,et al.  Volumetric Next-best-view Planning for 3 D Object Reconstruction with Positioning Error Regular , 2014 .

[22]  Gerd Hirzinger,et al.  View Planning for Multi-View Stereo 3D Reconstruction Using an Autonomous Multicopter , 2012, J. Intell. Robotic Syst..

[23]  Wolfram Burgard,et al.  Information Gain-based Exploration Using Rao-Blackwellized Particle Filters , 2005, Robotics: Science and Systems.

[24]  Michael M. Zavlanos,et al.  A hybrid control approach to the Next-Best-View problem using stereo vision , 2013, 2013 IEEE International Conference on Robotics and Automation.

[25]  Davide Scaramuzza,et al.  REMODE: Probabilistic, monocular dense reconstruction in real time , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).