Far-Field Terrain Perception Using Max-Margin Markov Networks

Far-field terrain perception plays an important role in performing outdoor robot navigation, such as earlier recognition of obstacles, efficient path planning. Stereo vision is an effective tool to detect obstacles in the near-field, but it cannot provide reliable information in the far-field, which may lead to suboptimal trajectories. This can be settled through the use of machine learning to accomplish near-to-farlearning, in which near-field terrain appearance features and stereo readings are used to train models able to predict far-field terrain. In this paper, we propose a near-to-far learning method using Max-Margin Markov Networks (M3N) to enhance long-range terrain perception for autonomous mobile robots. The method not only includes appearance features as its prediction basis, but also uses spatial relationships between adjacent parts. The experiment results show that our method outperforms other existing approaches.

[1]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

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

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

[4]  Ben Taskar,et al.  Max-Margin Markov Networks , 2003, NIPS.

[5]  Michael J. Procopio,et al.  Learning terrain segmentation with classifier ensembles for autonomous robot navigation in unstructured environments , 2009 .

[6]  Ben Southall,et al.  Stereo perception on an off-road vehicle , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[7]  Reid G. Simmons,et al.  Recent progress in local and global traversability for planetary rovers , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[8]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[9]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10]  Larry D. Jackel,et al.  The DARPA LAGR program: Goals, challenges, methodology, and phase I results , 2006, J. Field Robotics.

[11]  David Filliat,et al.  A visual bag of words method for interactive qualitative localization and mapping , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[12]  Siddheswar Ray,et al.  Determination of Number of Clusters in K-Means Clustering and Application in Colour Image Segmentation , 2000 .

[13]  Pierrick Grandjean,et al.  Fast cross-country navigation on fair terrains , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[14]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[15]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[16]  Jun Zhou,et al.  Large-scale conditional random field for natural outdoor scene labeling , 2009 .

[17]  Larry H. Matthies,et al.  Stereo vision for planetary rovers: Stochastic modeling to near real-time implementation , 1991, Optics & Photonics.

[18]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[19]  Wolfram Burgard,et al.  Robotics: Science and Systems XV , 2010 .

[20]  Jun Zhou,et al.  Learning Long-range Terrain Perception for Autonomous Mobile Robots , 2010 .

[21]  Michael J. Turmon,et al.  Autonomous off-road navigation with end-to-end learning for the LAGR program , 2009 .

[22]  Michael Happold,et al.  Image-based path planning for outdoor mobile robots , 2008, 2008 IEEE International Conference on Robotics and Automation.