Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain

Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of perception and planning systems, but on how well these systems are coupled. When traversing complex unstructured terrain, this coupling (in the form of a cost function) has a large impact on robot behavior and performance, necessitating a robust design. This paper explores the application of Learning from Demonstration to this task for the Crusher autonomous navigation platform. Using expert examples of desired navigation behavior, mappings from both online and offline perceptual data to planning costs are learned. Challenges in adapting existing techniques to complex online planning systems and imperfect demonstration are addressed, along with additional practical considerations. The benefits to autonomous performance of this approach are examined, as well as the decrease in necessary designer effort. Experimental results are presented from autonomous traverses through complex natural environments.

[1]  R. E. Kalman,et al.  When Is a Linear Control System Optimal , 1964 .

[2]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[3]  K. E. Olin,et al.  Autonomous cross-country navigation: an integrated perception and planning system , 1991, IEEE Expert.

[4]  Martial Hebert,et al.  A complete navigation system for goal acquisition in unknown environments , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[5]  Alonzo Kelly,et al.  An intelligent, predictive control approach to the high-speed cross-country autonomous navigation problem , 1996 .

[6]  Peter L. Bartlett,et al.  Boosting Algorithms as Gradient Descent , 1999, NIPS.

[7]  Steven Dubowsky,et al.  Rapid physics-based rough-terrain rover planning with sensor and control uncertainty , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[8]  Stephen Balakirsky,et al.  World modeling and behavior generation for autonomous ground vehicle , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[9]  Andrew Y. Ng,et al.  Pharmacokinetics of a novel formulation of ivermectin after administration to goats , 2000, ICML.

[10]  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).

[11]  Roberto Manduchi,et al.  Fast and reliable obstacle detection and segmentation for cross-country navigation , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[12]  Karl Murphy,et al.  Autonomous Mobility for the Demo III Experimental Unmanned Vehicles , 2002 .

[13]  Homayoun Seraji,et al.  Behavior-based robot navigation on challenging terrain: A fuzzy logic approach , 2002, IEEE Trans. Robotics Autom..

[14]  Christopher Rasmussen,et al.  Combining laser range, color, and texture cues for autonomous road following , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[15]  Pat Langley,et al.  Editorial: On Machine Learning , 1986, Machine Learning.

[16]  Steven Dubowsky,et al.  Online terrain parameter estimation for wheeled mobile robots with application to planetary rovers , 2004, IEEE Transactions on Robotics.

[17]  Martial Hebert,et al.  Classifier fusion for outdoor obstacle detection , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[18]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[19]  Homayoun Seraji,et al.  A human-robot mentor-protege relationship to learn off-road navigation behavior , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[20]  Larry H. Matthies,et al.  Stereo-Based Tree Traversability Analysis for Autonomous Off-Road Navigation , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[21]  Yann LeCun,et al.  Off-Road Obstacle Avoidance through End-to-End Learning , 2005, NIPS.

[22]  Roberto Manduchi,et al.  Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation , 2005, Auton. Robots.

[23]  Sebastian Scherer,et al.  Learning obstacle avoidance parameters from operator behavior , 2006, J. Field Robotics.

[24]  J. Andrew Bagnell,et al.  Maximum margin planning , 2006, ICML.

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

[26]  Martin Buehler,et al.  Summary of DGC 2005 results , 2006, J. Field Robotics.

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

[28]  William Whittaker,et al.  A robust approach to high‐speed navigation for unrehearsed desert terrain , 2006, J. Field Robotics.

[29]  James M. Rehg,et al.  Traversability classification using unsupervised on-line visual learning for outdoor robot navigation , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[30]  Sebastian Thrun,et al.  A Self-Supervised Terrain Roughness Estimator for Off-Road Autonomous Driving , 2006, UAI.

[31]  Larry H. Matthies,et al.  Towards learned traversability for robot navigation: From underfoot to the far field , 2006, J. Field Robotics.

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

[33]  Martin Buehler,et al.  Summary of DGC 2005 results , 2006, J. Field Robotics.

[34]  James M. Rehg,et al.  Learning from examples in unstructured, outdoor environments , 2006, J. Field Robotics.

[35]  David Silver,et al.  Experimental Analysis of Overhead Data Processing To Support Long Range Navigation , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[36]  Sebastian Thrun,et al.  Stanley: The robot that won the DARPA Grand Challenge , 2006, J. Field Robotics.

[37]  David M. Bradley,et al.  Boosting Structured Prediction for Imitation Learning , 2006, NIPS.

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

[39]  Anthony Stentz,et al.  Using interpolation to improve path planning: The Field D* algorithm , 2006, J. Field Robotics.

[40]  Ibrahim Halatci.  Vision-based terrain classification and classifier fusion for planetary exploration rovers , 2006 .

[41]  J. Andrew Bagnell,et al.  Improving robot navigation through self‐supervised online learning , 2006, J. Field Robotics.

[42]  J.J. Biesiadecki,et al.  The Mars Exploration Rover surface mobility flight software driving ambition , 2006, 2006 IEEE Aerospace Conference.

[43]  J. Andrew Bagnell,et al.  Improving Robot Navigation Through Self-Supervised Online Learning , 2006, Robotics: Science and Systems.

[44]  Karl Iagnemma,et al.  Terrain Classification and Classifier Fusion for Planetary Exploration Rovers , 2008, 2007 IEEE Aerospace Conference.

[45]  Michael Happold,et al.  A Bayesian approach to imitation learning for robot navigation , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[46]  Gregory Z. Grudic,et al.  Long-Term learning using multiple models for outdoor autonomous robot navigation , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[47]  Anthony Stentz,et al.  The Crusher System for Autonomous Navigation , 2007 .

[48]  Gary Witus,et al.  Terrain understanding for robot navigation , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[49]  Michael Happold,et al.  Using Learned Features from 3D Data for Robot Navigation , 2007 .

[50]  William Whittaker,et al.  A robust approach to high‐speed navigation for unrehearsed desert terrain , 2007 .

[51]  David M. Bradley,et al.  Vegetation Detection for Driving in Complex Environments , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[52]  Pietro Perona,et al.  Learning and prediction of slip from visual information: Research Articles , 2007 .

[53]  Pietro Perona,et al.  Learning and prediction of slip from visual information , 2007, J. Field Robotics.

[54]  James S. Albus,et al.  Learning traversability models for autonomous mobile vehicles , 2008, Auton. Robots.

[55]  David Silver,et al.  High Performance Outdoor Navigation from Overhead Data using Imitation Learning , 2008, Robotics: Science and Systems.

[56]  Sebastian Thrun,et al.  Apprenticeship learning for motion planning with application to parking lot navigation , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[57]  Larry H. Matthies,et al.  Learning long-range terrain classification for autonomous navigation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[58]  David Silver,et al.  Perceptual Interpretation for Autonomous Navigation through Dynamic Imitation Learning , 2009, ISRR.

[59]  David Silver,et al.  Applied Imitation Learning for Autonomous Navigation in Complex Natural Terrain , 2009, FSR.

[60]  Daniel M. Helmick,et al.  Terrain Adaptive Navigation for planetary rovers , 2009 .

[61]  Anthony Stentz,et al.  Global planning on the Mars Exploration Rovers: Software integration and surface testing , 2009 .

[62]  Larry H. Matthies,et al.  Terrain Adaptive Navigation for planetary rovers , 2009, J. Field Robotics.

[63]  John J. Leonard,et al.  Cooperative AUV Navigation Using a Single Surface Craft , 2009, FSR.

[64]  David Silver,et al.  Learning to search: Functional gradient techniques for imitation learning , 2009, Auton. Robots.

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

[66]  David Silver,et al.  Learning Rough-Terrain Autonomous Navigation , 2009 .

[67]  Anthony Stentz,et al.  Global planning on the Mars Exploration Rovers: Software integration and surface testing , 2009, J. Field Robotics.

[68]  David M. Bradley,et al.  Learning for Autonomous Navigation , 2010, IEEE Robotics & Automation Magazine.