Data-Efficient Model Learning for Control

Data-Efficient Model Learning for Control

Plane Cartpole

We present a data-efficient algorithm for learning models for model-predictive control (MPC). Our approach, Jacobian-Regularized Dynamic-Mode Decomposition (JDMD), offers improved sample efficiency over traditional Koopman approaches based on Dynamic-Mode Decomposition (DMD) by leveraging Jacobian information from an approximate prior model of the system, and improved tracking performance over traditional model-based MPC. We demonstrate JDMD’s ability to quickly learn bilinear Koopman dynamics representations across several realistic examples in simulation, including a perching maneuver for a fixed-wing aircraft with an empirically derived high-fidelity physics model. In all cases, we show that the models learned by JDMD provide superior tracking and generalization performance within a model-predictive control framework, even in the presence of significant model mismatch, when compared to approximate prior models and models learned by standard Extended DMD (EDMD).

dist quad


Related Papers

PDF Data-Efficient Model Learning for Control with Jacobian-Regularized Dynamic Mode Decomposition
Brian Jackson, Jeong Hun (JJ) Lee, Kevin Tracy, and Zac Manchester
The Conference on Robot Learning (CoRL)


Zac Manchester
Assistant Professor
Brian Jackson
Real-time motion planning
Jeong Hun (JJ) Lee
Swimming Dynamics and Control
Last updated: 2022-08-12