Simple Calibration for Vehicle Pose Estimation Using Gaussian Processes

D.J. Broderick, J. Britt, J. Ryan, D.M. Bevly, J.Y. Hung

Abstract:	A method of estimating a vehicle's attitude in relation to the road surface using only light detection and ranging (LiDAR) measurements is presented. Gaussian processes, a machine learning technique, are used to relate the measurements of the road surface to the pitch and roll of the vehicle. Difficulties regarding sensor calibration are discussed and addressed successfully. The method and associated calibration of the LiDAR sensor are focused on allowing realtime calculation and simplifying calibration so that it can be performed in the field without any additional mechanisms or specialized targets. A method of determining the lever arm between the LiDAR and the center of gravity of the vehicle is developed and presented. On-vehicle results show that the attitude calculations are able to be implemented in a real-time system and have been compared against a multi-antenna GPS attitude measurement for accuracy.
Published in:	Proceedings of the 2011 International Technical Meeting of The Institute of Navigation January 24 - 26, 2011 Catamaran Resort Hotel San Diego, CA
Pages:	447 - 458
Cite this article:	Broderick, D.J., Britt, J., Ryan, J., Bevly, D.M., Hung, J.Y., "Simple Calibration for Vehicle Pose Estimation Using Gaussian Processes," Proceedings of the 2011 International Technical Meeting of The Institute of Navigation, San Diego, CA, January 2011, pp. 447-458.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In