Learning to Control using Image Feedback
Abstract
Learning to control complex systems using non-traditional feedback, e.g., in the form of snapshot images, is an important task encountered in diverse domains such as robotics, neuroscience, and biology (cellular systems). In this paper, we present a two neural-network (NN)-based feedback control framework to design control policies for systems that generate feedback in the form of images. In particular, we develop a deep -network (DQN)-driven learning control strategy to synthesize a sequence of control inputs from snapshot images that encode the information pertaining to the current state and control action of the system. Further, to train the networks we employ a direct error-driven learning (EDL) approach that utilizes a set of linear transformations of the NN training error to update the NN weights in each layer. We verify the efficacy of the proposed control strategy using numerical examples.
Cite
@article{arxiv.2110.15290,
title = {Learning to Control using Image Feedback},
author = {Krishnan Raghavan and Vignesh Narayanan and Jagannathan Saraangapani},
journal= {arXiv preprint arXiv:2110.15290},
year = {2021}
}