arXiv subjects

Vignesh Narayanan

Publications and source records attributed to Vignesh Narayanan.

23 records · Page 2Linked to original sources

arXiv2021

Learning to Control using Image Feedback

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 $Q$-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.

cs.LG↗

arXiv2021

Cooperative Deep $Q$-learning Framework for Environments Providing Image Feedback

In this paper, we address two key challenges in deep reinforcement learning setting, sample inefficiency and slow learning, with a dual NN-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the error-driven learning (EDL) regime is an approximation of the empirical cost and the approximation error reduces as learning progresses, irrespective of the size of the network. Using simulation analysis, we show that the proposed methods enables faster learning and convergence and requires reduced buffer size (thereby increasing the sample efficiency).

eess.SY↗

arXiv2020

Moment-Based Ensemble Control

Controlling a large population, in the limit, a continuum, of structurally identical dynamical systems with parametric variations is a pervasive task in diverse applications in science and engineering. However, the severely underactuated nature and the inability to avail comprehensive state feedback information of such ensemble systems raise significant challenges in analysis and design of ensemble systems. In this paper, we propose a moment-based ensemble control framework, which incorporates and expands the method of moments in probability theory to control theory. In particular, we establish an equivalence between ensemble systems and their moment systems in terms of control and their controllability properties by extending the Hausdorff moment problem from the perspectives of differential geometry and dynamical systems. The developments enable the design of moment-feedback control laws for closing the loop in ensemble systems using the aggregated type of measurements. The feasibility of this closed-loop control design procedure is validated both mathematically and numerically.

math.OC↗

arXiv2020

Disentangling Drift- and Control- Vector Fields for Interpretable Inference of Control-affine Systems

Many engineered as well as naturally occurring dynamical systems do not have an accurate mathematical model to describe their dynamic behavior. However, in many applications, it is possible to probe the system with external inputs and measure the process variables, resulting in abundant data repositories. Using the time-series data to infer a mathematical model that describes the underlying dynamical process is an important and challenging problem. In this work, we propose a model reconstruction procedure for inferring the dynamics of a class of nonlinear systems governed by an input affine structure. In particular, we propose a data generation and learning strategy to decouple the reconstruction problem associated with the drift- and control- vector fields, and enable quantification of their respective contributions to the dynamics of the system. This learning procedure leads to an interpretable and reliable model inference approach. We present several numerical examples to demonstrate the efficacy and flexibility of the proposed method.

math.OC↗

arXiv2014

Plan or not: Remote Human-robot Teaming with Incomplete Task Information

Human-robot interaction can be divided into two categories based on the physical distance between the human and robot: remote and proximal. In proximal interaction, the human and robot often engage in close coordination; in remote interaction, the human and robot are less coupled due to communication constraints. As a result, providing automation for the robot in remote interaction becomes more important. Thus far, human factor studies on automation in remote human-robot interaction have been restricted to various forms of supervision, in which the robot is essentially being used as a smart mobile manipulation platform with sensing capabilities. In this paper, we investigate the incorporation of general planning capability into the robot to facilitate peer-to-peer human-robot teaming, in which the human and robot are viewed as teammates that are physically separated. The human and robot share the same global goal and collaborate to achieve it. Note that humans may feel uncomfortable at such robot autonomy, which can potentially reduce teaming performance. One important difference between peer-to-peer teaming and supervised teaming is that an autonomous robot in peer-to-peer teaming can achieve the goal alone when the task information is completely specified. However, incompleteness often exists, which implies information asymmetry. While information asymmetry can be desirable sometimes, it may also lead to the robot choosing improper actions that negatively influence the teaming performance. We aim to investigate the various trade-offs, e.g., mental workload and situation awareness, between these two types of remote human-robot teaming.

cs.AI↗