Learning Stabilizable Dynamical Systems via Control Contraction Metrics
Name
1808.00113.pdf
Description
Submitted version
Size
2.43 MB
Format
Adobe PDF
Checksum (MD5)
bf46966d0b385c378c21f67a106837ac
Author(s)
Singh, Sumeet
Sindhwani, Vikas
Slotine, Jean-Jacques E
Pavone, Marco
Date Issued
2020
Publisher
Springer International Publishing
Citation
Singh, Sumeet, Sindhwani, Vikas, Slotine, Jean-Jacques E and Pavone, Marco. 2020. "Learning Stabilizable Dynamical Systems via Control Contraction Metrics." 14.
Version
Original manuscript
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.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-44051-0_11
