Safe Learning of Regions of Attraction with Gaussian Processes (CDC 2016 presentation)

Extended version of the paper:
https://arxiv.org/abs/1603.04915

Code:
https://github.com/befelix/lyapunov-l...

Authors: Felix Berkenkamp, Riccardo Moriconi, Angela P. Schoellig, Andreas Krause

Abstract:
Control theory can provide useful insights into the properties of controlled, dynamic systems. One important property of nonlinear systems is the region of attraction (ROA), a safe subset of the state space in which a given controller renders an equilibrium point asymptotically stable. The ROA is typically estimated based on a model of the system. However, since models are only an approximation of the real world, the resulting estimated safe region can contain states outside the ROA of the real system. This is not acceptable in safety-critical applications. In this paper, we consider an approach that learns the ROA from experiments on a real system, without ever leaving the true ROA and, thus, without risking safety-critical failures. Based on regularity assumptions on the model errors in terms of a Gaussian process prior, we use an underlying Lyapunov function in order to determine a region in which an equilibrium point is asymptotically stable with high probability. Moreover, we provide an algorithm to actively and safely explore the state space in order to expand the ROA estimate. We demonstrate the effectiveness of this method in simulation.

More information:
https://las.ethz.ch
http://dynsyslab.org
http://berkenkamp.me