Efficient off-road localization using visually corrected odometry

We describe an efficient, low-cost, low-overhead system for robot localization in complex visual environments. Our system augments wheel odometry with visual orientation tracking to yield localization accuracy comparable with “pure” visual odometry at a fraction of the cost. Such a system is well-suited to consumer-level robots, small form-factor robots, extraterrestrial rovers, and other platforms with limited computational resources. Our system also benefits high-end multiprocessor robots by leaving ample processor time on all cameracomputer pairs to perform other critical visual tasks, such as obstacle detection. Experimental results are shown for outdoor, off-road loops on the order of 200 meters. Comparisons are made with corresponding results from a state-of-the-art pure visual odometer.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Hugh F. Durrant-Whyte,et al.  A high integrity IMU/GPS navigation loop for autonomous land vehicle applications , 1999, IEEE Trans. Robotics Autom..

[4]  Alison K. Brown,et al.  Inertial Navigation Electro-Optical Aiding During GPS Dropouts , 2002 .

[5]  Gerhard Lakemeyer,et al.  Exploring artificial intelligence in the new millennium , 2003 .

[6]  James R. Bergen,et al.  Visual odometry , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[7]  M. Veth,et al.  Stochastic constraints for efficient image correspondence search , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[8]  J. Borenstein,et al.  Current-Based Slippage Detection and Odometry Correction for Mobile Robots and Planetary Rovers , 2006, IEEE Transactions on Robotics.

[9]  Larry Matthies,et al.  Two years of Visual Odometry on the Mars Exploration Rovers: Field Reports , 2007 .

[10]  K. Konolige.  Rough Terrain Visual Odometry , 2007 .

[11]  Karsten Berns,et al.  Real-Time Visual Self-Localisation in Dynamic Environments , 2007, AMS.

[12]  Larry H. Matthies,et al.  Two years of Visual Odometry on the Mars Exploration Rovers , 2007, J. Field Robotics.

[13]  Karl Iagnemma,et al.  Model-Based Wheel Slip Detection for Outdoor Mobile Robots , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[14]  Clark N. Taylor,et al.  Improving MAV pose estimation using visual information , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Karl Iagnemma,et al.  Classification-Based Wheel Slip Detection and Detector Fusion for Outdoor Mobile Robots , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[16]  Ian D. Reid,et al.  Simultaneous Localisation and Mapping in Dynamic Environments (SLAMIDE) with Reversible Data Associa , 2007, Robotics: Science and Systems.

[17]  Wolfram Burgard,et al.  Simultaneous Localisation and Mapping in Dynamic Environments (SLAMIDE) with Reversible Data Association , 2008 .

[18]  David W. Murray,et al.  Improving the Agility of Keyframe-Based SLAM , 2008, ECCV.

[19]  Yann LeCun,et al.  A multirange architecture for collision-free off-road robot navigation , 2009 .

[20]  Yann LeCun,et al.  Learning long‐range vision for autonomous off‐road driving , 2009, J. Field Robotics.