Learning Stabilizable Dynamical Systems via Control Contraction Metrics

EasyChair Preprint no. 750

Abstract

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key idea is to develop a new control-theoretic regularizer for dynamics fitting rooted in the notion of stabilizability, which guarantees that the learned system can be accompanied by a robust controller capable of stabilizing any open-loop trajectory that the system may generate. By leveraging tools from contraction theory, statistical learning, and convex optimization, we provide a general and tractable semi-supervised algorithm to learn stabilizable dynamics, which can be applied to complex underactuated systems. We validated the proposed algorithm on a simulated planar quadrotor system and observed notably improved trajectory generation and tracking performance with the control-theoretic regularized model over models learned using traditional regression techniques, especially when using a small number of demonstration examples. The results presented illustrate the need to infuse standard model-based reinforcement learning algorithms with concepts drawn from nonlinear control theory for improved reliability.

Keyphrases: contraction theory, control theoretic regularizer, dynamic learning, dynamics modeling, Kernel Hilbert space, Learning from Demonstration, machine learning, model-based reinforcement learning, optimal control and optimization, simulated planar quadrotor system, stabilizable dynamical system, statistical learning, Underactuated mechanical system

@Booklet{EasyChair:750,
  author = {Sumeet Singh and Vikas Sindhwani and Jean-Jacques Slotine and Marco Pavone},
  title = {Learning Stabilizable Dynamical Systems via Control Contraction Metrics},
  howpublished = {EasyChair Preprint no. 750},
  doi = {10.29007/jz9w},
  year = {EasyChair, 2019}}