Cautious NMPC with Gaussian Process Dynamics for Miniature Race Cars

This paper presents an adaptive high performance control method for autonomous miniature race cars. Racing dynamics are notoriously hard to model from first principles, which is addressed by means of a cautious nonlinear model predictive control (NMPC) approach that learns to improve its dynamics model from data and safely increases racing performance. The approach makes use of a Gaussian Process (GP) and takes residual model uncertainty into account through a chance constrained formulation. We present a sparse GP approximation with dynamically adjusting inducing inputs, enabling a real-time implementable controller. The formulation is demonstrated in simulations, which show significant improvement with respect to both lap time and constraint satisfaction compared to an NMPC without model learning.

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

[2]  Francesco Borrelli,et al.  Learning Model Predictive Control for Iterative Tasks , 2016, ArXiv.

[3]  John Lygeros,et al.  Racing miniature cars: Enhancing performance using Stochastic MPC and disturbance feedback , 2017, 2017 American Control Conference (ACC).

[4]  Carl E. Rasmussen,et al.  Sparse Spectrum Gaussian Process Regression , 2010, J. Mach. Learn. Res..

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

[6]  Agathe Girard,et al.  Prediction at an Uncertain Input for Gaussian Processes and Relevance Vector Machines Application to Multiple-Step Ahead Time-Series Forecasting , 2002 .

[7]  Sebastian Thrun,et al.  A probabilistic approach to mixed open-loop and closed-loop control, with application to extreme autonomous driving , 2010, 2010 IEEE International Conference on Robotics and Automation.

[8]  J. Christian Gerdes,et al.  Using the centre of percussion to design a steering controller for an autonomous race car , 2012 .

[9]  J. Maciejowski,et al.  Soft constraints and exact penalty functions in model predictive control , 2000 .

[10]  Hans B. Pacejka,et al.  THE MAGIC FORMULA TYRE MODEL , 1991 .

[11]  Marc Peter Deisenroth,et al.  Efficient reinforcement learning using Gaussian processes , 2010 .

[12]  Benjamin Rosman,et al.  Online Constrained Model-based Reinforcement Learning , 2017, UAI.

[13]  Manfred Morari,et al.  Optimization‐based autonomous racing of 1:43 scale RC cars , 2015, ArXiv.

[14]  Massimo Guiggiani,et al.  The Science of Vehicle Dynamics: Handling, Braking, and Ride of Road and Race Cars , 2014 .

[15]  Carl E. Rasmussen,et al.  A Unifying View of Sparse Approximate Gaussian Process Regression , 2005, J. Mach. Learn. Res..

[16]  Francesco Borrelli,et al.  Autonomous racing using learning Model Predictive Control , 2016, 2017 American Control Conference (ACC).

[17]  J. Christian Gerdes,et al.  Path tracking of highly dynamic autonomous vehicle trajectories via iterative learning control , 2015, 2015 American Control Conference (ACC).

[18]  Angela P. Schoellig,et al.  Robust Constrained Learning-based NMPC enabling reliable mobile robot path tracking , 2016, Int. J. Robotics Res..

[19]  Volker Tresp,et al.  A Bayesian Committee Machine , 2000, Neural Computation.

[20]  Jaime F. Fisac,et al.  Reachability-based safe learning with Gaussian processes , 2014, 53rd IEEE Conference on Decision and Control.

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