3D Convolutional Neural Networks for landing zone detection from LiDAR

We present a system for the detection of small and potentially obscured obstacles in vegetated terrain. The key novelty of this system is the coupling of a volumetric occupancy map with a 3D Convolutional Neural Network (CNN), which to the best of our knowledge has not been previously done. This architecture allows us to train an extremely efficient and highly accurate system for detection tasks from raw occupancy data. We apply this method to the problem of detecting safe landing zones for autonomous helicopters from LiDAR point clouds. Current methods for this problem rely on heuristic rules and use simple geometric features. These heuristics break down in the presence of low vegetation, as they do not distinguish between vegetation that may be landed on and solid objects that should be avoided. We evaluate the system with a combination of real and synthetic range data. We show our system outperforms various benchmarks, including a system integrating various hand-crafted point cloud features from the literature.

[1]  Surya P. N. Singh,et al.  A Pipeline for the Segmentation and Classification of 3D Point Clouds , 2010, ISER.

[2]  nbsp,et al.  Field-Testing of a Helicopter UAV Obstacle Field Navigation and Landing System , 2009 .

[3]  John Amanatides,et al.  A Fast Voxel Traversal Algorithm for Ray Tracing , 1987, Eurographics.

[4]  Larry H. Matthies,et al.  Foliage discrimination using a rotating ladar , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[5]  Brett Browning,et al.  Automatic data driven vegetation modeling for lidar simulation , 2012, 2012 IEEE International Conference on Robotics and Automation.

[6]  Hans P. Moravec,et al.  High resolution maps from wide angle sonar , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[7]  Martial Hebert,et al.  Natural terrain classification using three‐dimensional ladar data for ground robot mobility , 2006, J. Field Robotics.

[8]  Sebastian Scherer,et al.  The Planner Ensemble and Trajectory Executive: A High Performance Motion Planning System with Guaranteed Safety , 2014 .

[9]  Andrew Y. Ng,et al.  Convolutional-Recursive Deep Learning for 3D Object Classification , 2012, NIPS.

[10]  Roberto Manduchi,et al.  Ladar-Based Discrimination of Grass from Obstacles for Autonomous Navigation , 2000, ISER.

[11]  Martial Hebert,et al.  Accurate rough terrain estimation with space-carving kernels , 2009, Robotics: Science and Systems.

[12]  O. Barinova,et al.  NON-ASSOCIATIVE MARKOV NETWORKS FOR 3D POINT CLOUD CLASSIFICATION , 2010 .

[13]  Andrew Y. Ng,et al.  Learning Feature Representations with K-Means , 2012, Neural Networks: Tricks of the Trade.

[14]  Andrew E. Johnson,et al.  Lidar-Based Hazard Avoidance for Safe Landing on Mars , 2002 .

[15]  Dieter Fox,et al.  Unsupervised feature learning for 3D scene labeling , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Luis Mejías Alvarez,et al.  Enabling Aircraft Emergency Landings Using Active Visual Site Detection , 2013, FSR.

[17]  Najla Megherbi Bouallagu,et al.  A 3D extension to cortex like mechanisms for 3D object class recognition , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Honglak Lee,et al.  Deep learning for detecting robotic grasps , 2013, Int. J. Robotics Res..

[19]  Sebastian Scherer,et al.  Autonomous landing at unprepared sites by a full-scale helicopter , 2012, Robotics Auton. Syst..

[20]  David D. Cox,et al.  Making a Science of Model Search , 2012, ArXiv.

[21]  Aaron C. Courville,et al.  A Generative Model of Terrain for Autonomous Navigation in Vegetation , 2006, Int. J. Robotics Res..

[22]  Martial Hebert,et al.  Space-carving Kernels for Accurate Rough Terrain Estimation , 2010, Int. J. Robotics Res..

[23]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[25]  Martial Hebert,et al.  Onboard contextual classification of 3-D point clouds with learned high-order Markov Random Fields , 2009, 2009 IEEE International Conference on Robotics and Automation.

[26]  Kaiguang Zhao,et al.  Ground Filtering Algorithms for Airborne LiDAR Data: A Review of Critical Issues , 2010, Remote. Sens..

[27]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[28]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[29]  Alonzo Kelly,et al.  Toward Reliable Off Road Autonomous Vehicles Operating in Challenging Environments , 2006, Int. J. Robotics Res..

[30]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[31]  Kai Oliver Arras,et al.  FLIRT - Interest regions for 2D range data , 2010, 2010 IEEE International Conference on Robotics and Automation.