LGSYSep 18, 2019

Deep Model Reference Adaptive Control

arXiv:1909.08602v170 citations
Originality Incremental advance
AI Analysis

This provides a high-performance control architecture for nonlinear systems with long-term learning properties, representing an incremental improvement over existing MRAC methods.

The authors tackled the problem of controlling nonlinear systems by developing Deep Model Reference Adaptive Control (DMRAC), which combines deep neural networks for modeling nonlinearities with boundedness guarantees from MRAC controllers, resulting in a method that can subsume previous learning-based MRAC approaches like concurrent learning and GP-MRAC.

We present a new neuroadaptive architecture: Deep Neural Network based Model Reference Adaptive Control (DMRAC). Our architecture utilizes the power of deep neural network representations for modeling significant nonlinearities while marrying it with the boundedness guarantees that characterize MRAC based controllers. We demonstrate through simulations and analysis that DMRAC can subsume previously studied learning based MRAC methods, such as concurrent learning and GP-MRAC. This makes DMRAC a highly powerful architecture for high-performance control of nonlinear systems with long-term learning properties.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes