by , ,
Abstract:
Learning algorithms have shown considerable prowess in simulation by allowing robots to adapt to uncertain environments and improve their performance. However, such algorithms are rarely used in practice on safety-critical systems, since the learned policy typically does not yield any safety guarantees and thus the required exploration may cause physical harm to the robot or its environment. In this paper, we present a method to learn accurate safety certificates for nonlinear, closed-loop dynamic systems. Specifically, we construct a neural network Lyapunov function and a training algorithm that adapts it to the shape of the largest safe region in the state space. The algorithm relies only on knowledge of inputs and outputs of the dynamics, rather than on any specific model structure. We demonstrate our method by learning the safe region of attraction for a simulated inverted pendulum. Furthermore, we discuss how our method can be used in safe learning algorithms together with statistical models of dynamic systems.
Reference:
The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamic Systems S. M. Richards, F. Berkenkamp, A. KrauseTechnical report, arXiv, 2018
Bibtex Entry:
@techreport{spencer18lyapunovnn,
	Author = {Spencer M. Richards and Felix Berkenkamp and Andreas Krause},
	Institution = {arXiv},
	Month = {August},
	Title = {The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamic Systems},
	Year = {2018}}