SmartCaveDrone: 3D cave mapping using UAVs as robotic co-archaeologists

This paper proposes the concept of drones capable of functioning as “Co-Archaeologists” that can map large caves and enter dangerous or hard-to-reach spaces. Using RGB-D data collected by drones, we will be able to produce accurate 3D models and semantic maps with proper lighting co-supervised by human archaeologists. This is going to be a major advance in archaeological practice, which can accelerate the speed of archaeological exploits by extending the archaeologists' sight and perception range. This will enable us to conduct 3D analyses so that we may answer new questions and create new insights into the archaeological record. The archaeologists will be able to visualize data collected by drones and instruct the drones' next step in real-time. These data will also be important in site management, data sharing and visualization. Human/drone interaction becomes important, not only for operating the equipment, but also for guiding drones to areas of interest to be mapped. Maps or real-time “fly-throughs” only make sense when they are organized by human interactions with the space. This human interaction is vital when visualizing and understanding a space and should be reflected in the imagery. We envision that this technology will be game changing in cave mapping and pertinent to anyone rendering interior spaces. It creates longer term impacts in archaeology and digital heritage and potentially creates a transformative way for further enhancing the performance of 3D mapping.

[1]  Bastian Leibe,et al.  Dense 3D semantic mapping of indoor scenes from RGB-D images , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Daniel Cremers,et al.  Dense visual SLAM for RGB-D cameras , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Andrew W. Fitzgibbon,et al.  KinectFusion: Real-time dense surface mapping and tracking , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[4]  Michael P. Hayes,et al.  Biologically inspired UAV obstacle avoidance and control using monocular optical flow & divergence templates , 2011, The 5th International Conference on Automation, Robotics and Applications.

[5]  Stefan Leutenegger,et al.  ElasticFusion: Dense SLAM Without A Pose Graph , 2015, Robotics: Science and Systems.

[6]  Andrew Owens,et al.  Discrete-continuous optimization for large-scale structure from motion , 2011, CVPR 2011.

[7]  Patrick Pérez,et al.  Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Andrew Owens,et al.  Discrete-continuous optimization for large-scale structure from motion , 2011, CVPR.

[9]  Andrew Owens,et al.  SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels , 2013, 2013 IEEE International Conference on Computer Vision.

[10]  Berat A. Erol,et al.  Formation control implementation using Kobuki TurtleBots and Parrot Bebop drone , 2016, 2016 World Automation Congress (WAC).

[11]  Brandon Stark,et al.  Adaptive minimum energy cognitive lighting control: Integer order vs fractional order strategies in sliding mode based extremum seeking , 2013 .

[12]  Jörg Stückler,et al.  Direct visual-inertial odometry with stereo cameras , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Vibhav Vineet,et al.  Conditional Random Fields as Recurrent Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Olaf Kähler,et al.  Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices , 2015, IEEE Transactions on Visualization and Computer Graphics.

[15]  Jitendra Malik,et al.  Learning Rich Features from RGB-D Images for Object Detection and Segmentation , 2014, ECCV.

[16]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[17]  Alkis Gotovos,et al.  Efficient visual exploration and coverage with a micro aerial vehicle in unknown environments , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[18]  Nassir Navab,et al.  When 2.5D is not enough: Simultaneous reconstruction, segmentation and recognition on dense SLAM , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Richard Szeliski,et al.  Building Rome in a day , 2009, ICCV.

[21]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[22]  Ali Shahrokni,et al.  Mesh Based Semantic Modelling for Indoor and Outdoor Scenes , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Silvio Savarese,et al.  3D Semantic Parsing of Large-Scale Indoor Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Miguel A. Olivares-Méndez,et al.  See-and-avoid quadcopter using fuzzy control optimized by cross-entropy , 2012, 2012 IEEE International Conference on Fuzzy Systems.

[25]  Matthias Nießner,et al.  Combining Inertial Navigation and ICP for Real-time 3D Surface Reconstruction , 2014, Eurographics.

[26]  Dieter Fox,et al.  RGB-(D) scene labeling: Features and algorithms , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Wolfram Burgard,et al.  Robust map optimization using dynamic covariance scaling , 2013, 2013 IEEE International Conference on Robotics and Automation.

[28]  Jiann-Der Lee,et al.  Fuzzy-based obstacle avoidance for a mobile robot navigation in indoor environment , 2015, 2015 IEEE International Conference on Consumer Electronics - Taiwan.

[29]  Vladlen Koltun,et al.  Fast Global Registration , 2016, ECCV.

[30]  Vladlen Koltun,et al.  Robust reconstruction of indoor scenes , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  John J. Leonard,et al.  Kintinuous: Spatially Extended KinectFusion , 2012, AAAI 2012.

[32]  Javier González,et al.  A Novel Measure of Uncertainty for Mobile Robot SLAM with Rao—Blackwellized Particle Filters , 2008, Int. J. Robotics Res..

[33]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Roland Siegwart,et al.  Receding Horizon "Next-Best-View" Planner for 3D Exploration , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[35]  Richard Szeliski,et al.  Towards Internet-scale multi-view stereo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[36]  Vijay Kumar,et al.  Autonomous robotic exploration using occupancy grid maps and graph SLAM based on Shannon and Rényi Entropy , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[37]  Dorian Gálvez-López,et al.  Bags of Binary Words for Fast Place Recognition in Image Sequences , 2012, IEEE Transactions on Robotics.

[38]  Jitendra Malik,et al.  Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Florentin Wörgötter,et al.  Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.