Active learning from demonstration for robust autonomous navigation

Building robust and reliable autonomous navigation systems that generalize across environments and operating scenarios remains a core challenge in robotics. Machine learning has proven a significant aid in this task; in recent years learning from demonstration has become especially popular, leading to improved systems while requiring less expert tuning and interaction. However, these approaches still place a burden on the expert, specifically to choose the best demonstrations to provide. This work proposes two approaches for active learning from demonstration, in which the learning system requests specific demonstrations from the expert. The approaches identify examples for which expert demonstration is predicted to provide useful information on concepts which are either novel or uncertain to the current system. Experimental results demonstrate both improved generalization performance and reduced expert interaction when using these approaches.

[1]  Siddhartha S. Srinivasa,et al.  Planning-based prediction for pedestrians , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Oliver Brock,et al.  High Performance Outdoor Navigation from Overhead Data using Imitation Learning , 2009 .

[3]  Daniel H. Grollman,et al.  Dogged Learning for Robots , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[4]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[5]  I K Fodor,et al.  A Survey of Dimension Reduction Techniques , 2002 .

[6]  J. Andrew Bagnell,et al.  Anytime online novelty detection for vehicle safeguarding , 2010, 2010 IEEE International Conference on Robotics and Automation.

[7]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.

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

[9]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[10]  Rajesh P. N. Rao,et al.  Active Imitation Learning , 2007, AAAI.

[11]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[12]  Stefan Schaal,et al.  Learning locomotion over rough terrain using terrain templates , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Manuela M. Veloso,et al.  Confidence-based policy learning from demonstration using Gaussian mixture models , 2007, AAMAS '07.

[14]  Christopher G. Atkeson,et al.  Optimization and learning for rough terrain legged locomotion , 2011, Int. J. Robotics Res..

[15]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[16]  Paul Newman,et al.  Planning most-likely paths from overhead imagery , 2010, 2010 IEEE International Conference on Robotics and Automation.

[17]  Martial Hebert,et al.  Enabling learning from large datasets: applying active learning to mobile robotics , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[18]  Martial Hebert,et al.  Active Learning For Outdoor Obstacle Detection , 2005, Robotics: Science and Systems.

[19]  Pieter Abbeel,et al.  Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion , 2007, NIPS.

[20]  David Silver,et al.  Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain , 2010, Int. J. Robotics Res..

[21]  Karl Iagnemma,et al.  Visual detection of novel terrain via two-class classification , 2009, SAC '09.