Safe Learning of Quadrotor Dynamics Using Barrier Certificates

To effectively control complex dynamical systems, accurate nonlinear models are typically needed. However, these models are not always known. In this paper, we present a data-driven approach based on Gaussian processes that learns models of quadrotors operating in partially unknown environments. What makes this challenging is that if the learning process is not carefully controlled, the system will go unstable, i.e., the quadcopter will crash. To this end, barrier certificates are employed for safe learning. The barrier certificates establish a non-conservative forward invariant safe region, in which high probability safety guarantees are provided based on the statistics of the Gaussian Process. A learning controller is designed to efficiently explore those uncertain states and expand the barrier certified safe region based on an adaptive sampling scheme. Simulation results are provided to demonstrate the effectiveness of the proposed approach.

[1]  Paulo Tabuada,et al.  Robustness of Control Barrier Functions for Safety Critical Control , 2016, ADHS.

[2]  Duy Nguyen-Tuong,et al.  Stability of Controllers for Gaussian Process Forward Models , 2016, ICML.

[3]  Carl E. Rasmussen,et al.  Gaussian Processes for Data-Efficient Learning in Robotics and Control , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Yunpeng Pan,et al.  Probabilistic Differential Dynamic Programming , 2014, NIPS.

[5]  George J. Pappas,et al.  A Framework for Worst-Case and Stochastic Safety Verification Using Barrier Certificates , 2007, IEEE Transactions on Automatic Control.

[6]  Markus Hehn,et al.  Real-Time Trajectory Generation for Quadrocopters , 2015, IEEE Transactions on Robotics.

[7]  Koushil Sreenath,et al.  3D dynamic walking on stepping stones with control barrier functions , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[8]  Toshiharu Sugie,et al.  Adaptive model predictive control for a class of constrained linear systems based on the comparison model , 2007, Autom..

[9]  G. Chesi.  Domain of Attraction: Analysis and Control via SOS Programming , 2011 .

[10]  Magnus Egerstedt,et al.  Safe certificate-based maneuvers for teams of quadrotors using differential flatness , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

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

[12]  Duy Nguyen-Tuong,et al.  Local Gaussian Process Regression for Real Time Online Model Learning , 2008, NIPS.

[13]  Kenji Fujimoto,et al.  Second-order Bounds of Gaussian Kernel-based Functions and its Application to Nonlinear Optimal Control with Stability , 2017 .

[14]  Andreas Krause,et al.  Safe Model-based Reinforcement Learning with Stability Guarantees , 2017, NIPS.

[15]  Aude Billard,et al.  Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions , 2014, Robotics Auton. Syst..

[16]  S. Shankar Sastry,et al.  Provably safe and robust learning-based model predictive control , 2011, Autom..

[17]  George J. Pappas,et al.  Stochastic safety verification using barrier certificates , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[18]  J. Lofberg,et al.  YALMIP : a toolbox for modeling and optimization in MATLAB , 2004, 2004 IEEE International Conference on Robotics and Automation (IEEE Cat. No.04CH37508).

[19]  Andreas Krause,et al.  Safe learning of regions of attraction for uncertain, nonlinear systems with Gaussian processes , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[20]  Mac Schwager,et al.  Vector field following for quadrotors using differential flatness , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Li Wang,et al.  Multi-objective compositions for collision-free connectivity maintenance in teams of mobile robots , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[22]  Paulo Tabuada,et al.  Control Barrier Function Based Quadratic Programs for Safety Critical Systems , 2016, IEEE Transactions on Automatic Control.

[23]  Alberto Bemporad,et al.  Robust model predictive control: A survey , 1998, Robustness in Identification and Control.

[24]  Guofan Wu,et al.  Safety-critical control of a planar quadrotor , 2016, 2016 American Control Conference (ACC).

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

[26]  Sriram Sankaranarayanan,et al.  Learning Lyapunov (Potential) Functions from Counterexamples and Demonstrations , 2017, Robotics: Science and Systems.