Asynchronous Deep Model Reference Adaptive Control

TL;DR

This paper introduces an asynchronous deep neural network-based adaptive control system for quadcopters, demonstrating robustness to faults and disturbances, with real-time implementation and generalization across flight regimes.

Contribution

It presents a novel asynchronous neuro-adaptive control architecture with real-time deep learning inference for high-bandwidth attitude control of nonlinear robots.

Findings

Successfully handled severe system faults and wind disturbances.

Demonstrated long-term learning and generalization across flight regimes.

Achieved real-time inference on a computation-limited platform.

Abstract

In this paper, we present Asynchronous implementation of Deep Neural Network-based Model Reference Adaptive Control (DMRAC). We evaluate this new neuro-adaptive control architecture through flight tests on a small quadcopter. We demonstrate that a single DMRAC controller can handle significant nonlinearities due to severe system faults and deliberate wind disturbances while executing high-bandwidth attitude control. We also show that the architecture has long-term learning abilities across different flight regimes, and can generalize to fly different flight trajectories than those on which it was trained. These results demonstrating the efficacy of this architecture for high bandwidth closed-loop attitude control of unstable and nonlinear robots operating in adverse situations. To achieve these results, we designed a software+communication architecture to ensure online real-time inference of the deep network on a high-bandwidth computation-limited platform. We expect that this architecture will benefit other deep learning in the closed-loop experiments on robots.