UAV parameter estimation with multi-output local and global Gaussian Process approximations

Learning the flight model for an Unmanned Aerial Vehicle (UAV) involves estimating stability and control parameters from flight data. A non-parametric approach to perform this task is to use Dependent Gaussian Processes (DGPs). It has many benefits, including not having to know a prior model structure, captures any dependencies embodied in the outputs and learns the system noise. However, the main drawback of this approach is the heavy computational cost which makes it prohibitive to learn the model from large test flight data sets. In addition, DGPs do not capture any non-stationary behavior in the aerodynamic coefficients. This paper presents a novel approach to address these issues while maintaining all the other benifits that was gained using DGPs. The proposed algorithm uses an additive sparse model that combines global and local Gaussian processes to learn a multi-output system. We demonstrate that having a combined approximation makes the model suitable for all regions of the flight envelope. To capture the global properties we introduce a new sampling method to gather information about the output correlations. Local properties were captured using a non-stationary covariance function with KD-trees for neighbourhood selection. This makes the model scalable to learn from high dimensional large-scale data sets. Finally, the method explained in this paper was demonstrated in several examples using real flight tests from a delta-winged UAV.

[1]  Phillip Boyle,et al.  Gaussian Processes for Regression and Optimisation , 2007 .

[2]  Aki Vehtari,et al.  Modelling local and global phenomena with sparse Gaussian processes , 2008, UAI.

[3]  Robert F. Stengel,et al.  Identification of aerodynamic coefficients using computational neural networks , 1992 .

[4]  Vladislav Klein,et al.  Estimation of aircraft aerodynamic parameters from flight data , 1989 .

[5]  Jun Nakanishi,et al.  Composite adaptive control with locally weighted statistical learning , 2005, Neural Networks.

[6]  Zoubin Ghahramani,et al.  Local and global sparse Gaussian process approximations , 2007, AISTATS.

[7]  Michael J. Allen,et al.  Modeling Aircraft Wing Loads from Flight Data Using Neural Networks , 2003 .

[8]  Jan Peters,et al.  Model Learning with Local Gaussian Process Regression , 2009, Adv. Robotics.

[9]  Eugene A. Morelli,et al.  Aircraft system identification : theory and practice , 2006 .

[10]  Raman K. Mehra,et al.  Maximum likelihood identification of aircraft stability and control derivatives , 1974 .

[11]  Pieter Abbeel,et al.  An Application of Reinforcement Learning to Aerobatic Helicopter Flight , 2006, NIPS.

[12]  Hugh F. Durrant-Whyte,et al.  Gaussian Process modeling of large scale terrain , 2009, 2009 IEEE International Conference on Robotics and Automation.

[13]  Zoubin Ghahramani,et al.  Sparse Gaussian Processes using Pseudo-inputs , 2005, NIPS.

[14]  Salah Sukkarieh,et al.  The Demonstration of a Cooperative Control Architecture for UAV Teams , 2006, ISER.

[15]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[16]  Salah Sukkarieh,et al.  Non-parametric UAV system identification with dependent Gaussian processes , 2011, 2011 IEEE International Conference on Robotics and Automation.

[17]  Salah Sukkarieh,et al.  Real-Time Navigation, Guidance, and Control of a UAV Using Low-Cost Sensors , 2003, FSR.

[18]  Fabio Tozeto Ramos,et al.  Multi-task learning of system dynamics with maximum information gain , 2011, 2011 IEEE International Conference on Robotics and Automation.

[19]  Andreas Krause,et al.  Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies , 2008, J. Mach. Learn. Res..