Context-Aware Recognition of Drivable Terrain with Automated Parameters Estimation

This paper deals with the terrain classification problem for autonomous service robots in semi-structured outdoor environments. The aim is to recognize the drivable terrain in front of a robot that navigates on roads of different surfaces, avoiding areas that are considered non-drivable. Since the system should be robust to such factors as changing lighting conditions, mud and fallen leaves, we employ multi-sensor perception with a monocular camera and a 2D laser scanner. The labeling of the terrain obtained from a Random Trees classifier is refined by context-aware inference using the Conditional Random Field. We demonstrate that automatic learning of the parameters for Conditional Random Fields improves results in comparison to similar approaches without the context-aware inference or with parameters set by hand.

[1]  Michal R. Nowicki,et al.  Exploring OpenStreetMap Publicly Available Information for Autonomous Robot Navigation , 2015, Progress in Automation, Robotics and Measuring Techniques.

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

[3]  Piotr Skrzypczynski,et al.  Estimating terrain elevation maps from sparse and uncertain multi-sensor data , 2012, 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[4]  Michael I. Jordan,et al.  Graphical Models, Exponential Families, and Variational Inference , 2008, Found. Trends Mach. Learn..

[5]  Matti Pietikäinen,et al.  Performance evaluation of texture measures with classification based on Kullback discrimination of distributions , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[6]  Gary Witus,et al.  Terrain characterization and classification with a mobile robot , 2006, J. Field Robotics.

[7]  Andrew McCallum,et al.  An Introduction to Conditional Random Fields , 2010, Found. Trends Mach. Learn..

[8]  Jan Wietrzykowski,et al.  Boosting support vector machines for RGB-D based terrain classification , 2014 .

[9]  Michael Happold,et al.  Enhancing Supervised Terrain Classification with Predictive Unsupervised Learning , 2006, Robotics: Science and Systems.

[10]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[11]  Urs A. Muller,et al.  Learning long-range vision for autonomous off-road driving , 2009 .

[12]  Dietrich Paulus,et al.  Terrain Classification with Markov Random Fields on fused Camera and 3D Laser Range Data , 2011, ECMR.

[13]  J. Nocedal.  Updating Quasi-Newton Matrices With Limited Storage , 1980 .

[14]  Andreas Zell,et al.  Building local terrain maps using spatio-temporal classification for semantic robot localization , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Sebastian Thrun,et al.  Self-supervised Monocular Road Detection in Desert Terrain , 2006, Robotics: Science and Systems.

[16]  Jan Wietrzykowski,et al.  Terrain classification for autonomous navigation in public urban areas , 2017 .

[17]  Martin J. Wainwright,et al.  Tree-based reparameterization framework for analysis of sum-product and related algorithms , 2003, IEEE Trans. Inf. Theory.

[18]  Andreas Zell,et al.  Terrain classification with conditional random fields on fused 3D LIDAR and camera data , 2013, 2013 European Conference on Mobile Robots.

[19]  Wolfram Burgard,et al.  Improving robot navigation in structured outdoor environments by identifying vegetation from laser data , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  K. Madhava Krishna,et al.  Fast and Spatially-Smooth Terrain Classification Using Monocular Camera , 2010, 2010 20th International Conference on Pattern Recognition.