Open Access. Powered by Scholars. Published by Universities.®

Operations Research, Systems Engineering and Industrial Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 8 of 8

Full-Text Articles in Operations Research, Systems Engineering and Industrial Engineering

Reinforcement Learning-Based Output Feedback Control Of Nonlinear Systems With Input Constraints, Pingan He, Jagannathan Sarangapani Feb 2005

Reinforcement Learning-Based Output Feedback Control Of Nonlinear Systems With Input Constraints, Pingan He, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

A novel neural network (NN) -based output feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multi-input-multi-output (MIMO) discrete-time strict feedback nonlinear systems. Reinforcement learning in discrete time is proposed for the output feedback controller, which uses three NN: 1) a NN observer to estimate the system states with the input-output data; 2) a critic NN to approximate certain strategic utility function; and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. The magnitude constraints are manifested as saturation nonlinearities in the output feedback ...


Block Phase Correlation-Based Automatic Drift Compensation For Atomic Force Microscopes, Qinmin Yang, Eric W. Bohannan, Jagannathan Sarangapani Jan 2005

Block Phase Correlation-Based Automatic Drift Compensation For Atomic Force Microscopes, Qinmin Yang, Eric W. Bohannan, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

Automatic nanomanipulation and nanofabrication with an Atomic Force Microscope (AFM) is a precursor for nanomanufacturing. In ambient conditions without stringent environmental controls, nanomanipulation tasks require extensive human intervention to compensate for the many spatial uncertainties of the AFM. Among these uncertainties, thermal drift is especially hard to solve because it tends to increase with time and cannot be compensated simultaneously by feedback. In this paper, an automatic compensation scheme is introduced to measure and estimate drift. This information can be subsequently utilized to compensate for the thermal drift so that a real-time controller for nanomanipulation can be designed as if ...


Decentralized Discrete-Time Neural Network Controller For A Class Of Nonlinear Systems With Unknown Interconnections, Jagannathan Sarangapani Jan 2005

Decentralized Discrete-Time Neural Network Controller For A Class Of Nonlinear Systems With Unknown Interconnections, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

A novel decentralized neural network (NN) controller in discrete-time is designed for a class of uncertain nonlinear discrete-time systems with unknown interconnections. Neural networks are used to approximate both the uncertain dynamics of the nonlinear systems and the unknown interconnections. Only local signals are needed for the decentralized controller design and the stability of the overall system can be guaranteed using the Lyapunov analysis. Further, controller redesign for the original subsystems is not required when additional subsystems are appended. Simulation results demonstrate the effectiveness of the proposed controller. The NN does not require an offline learning phase and the weights ...


A Robust Controller For The Manipulation Of Micro Scale Objects, Qinmin Yang, Jagannathan Sarangapani Jan 2005

A Robust Controller For The Manipulation Of Micro Scale Objects, Qinmin Yang, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

A suite of novel robust controllers is presented for the manipulation and handling of micro-scale objects in a micro-electromechanical system (MEMS) where adhesive, surface tension, friction and van der Waals forces are dominant. Moreover, these forces are typically unknown. The robust controller overcomes the unknown system dynamics and ensures the performance in the presence of actuator constraints by assuming that the upper bounds on these forces are known. On the other hand, for the robust adaptive controller, the unknown forces are estimated online. Using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the closed-loop manipulation error is shown for ...


Energy-Efficient Rate Adaptation Mac Protocol For Ad Hoc Wireless Networks, Maciej Jan Zawodniok, Jagannathan Sarangapani Jan 2005

Energy-Efficient Rate Adaptation Mac Protocol For Ad Hoc Wireless Networks, Maciej Jan Zawodniok, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

Resource constraints in ad hoc wireless networks require that they are energy efficient during both transmission and rate adaptation. In this paper, we propose a novel energy-efficient rate adaptation protocol that selects modulation schemes online to maximize throughput based on channel state while saving energy. This protocol uses the distributed power control (DPC) algorithm (M. Zawodniok et al., 2004) to accurately determine the necessary transmission power and to reduce the energy consumption. Additionally, the transmission rate is altered using energy efficiency as a constraint to meet the required throughput, which is estimated with queue fill ratio. Moreover, back-off scheme is ...


Neural Network-Based Control Of Nonlinear Discrete-Time Systems In Non-Strict Form, Jagannathan Sarangapani, Zheng Chen, Pingan He Jan 2005

Neural Network-Based Control Of Nonlinear Discrete-Time Systems In Non-Strict Form, Jagannathan Sarangapani, Zheng Chen, Pingan He

Electrical and Computer Engineering Faculty Research & Creative Works

A novel reinforcement learning-based adaptive neural network (NN) controller, also referred as the adaptive-critic NN controller, is developed to deliver a desired tracking performance for a class of non-strict feedback nonlinear discrete-time systems in the presence of bounded and unknown disturbances. The adaptive critic NN controller architecture includes a critic NN and two action NNs. The critic NN approximates certain strategic utility function whereas the action neural networks are used to minimize both the strategic utility function and the unknown dynamics estimation errors. The NN weights are tuned online so as to minimize certain performance index. By using gradient descent-based ...


Predictive Congestion Control Mac Protocol For Wireless Sensor Networks, Maciej Jan Zawodniok, Jagannathan Sarangapani Jan 2005

Predictive Congestion Control Mac Protocol For Wireless Sensor Networks, Maciej Jan Zawodniok, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

Available congestion control schemes, for example transport control protocol (TCP), when applied to wireless networks results in a large number of packet drops, unfairness with a significant amount of wasted energy due to retransmissions. To fully utilize the hop by hop feedback information, a suite of novel, decentralized, predictive congestion control schemes are proposed for wireless sensor networks in concert with distributed power control (DPC). Besides providing energy efficient solution, embedded channel estimator in DPC predicts the channel quality. By using the channel quality and node queue utilizations, the onset of network congestion is predicted and congestion control is initiated ...


Neural Network -Based Nearly Optimal Hamilton-Jacobi-Bellman Solution For Affine Nonlinear Discrete-Time Systems, Jagannathan Sarangapani, Zheng Chen Jan 2005

Neural Network -Based Nearly Optimal Hamilton-Jacobi-Bellman Solution For Affine Nonlinear Discrete-Time Systems, Jagannathan Sarangapani, Zheng Chen

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, we consider the use of nonlinear networks towards obtaining nearly optimal solutions to the control of nonlinear discrete-time systems. The method is based on least-squares successive approximation solution of the Generalized Hamilton-Jacobi-Bellman (HJB) equation. Since successive approximation using the GHJB has not been applied for nonlinear discrete-time systems, the proposed recursive method solves the GHJB equation in discrete-time on a well-defined region of attraction. The definition of GHJB, Pre-Hamiltonian function, HJB equation and method of updating the control function for the affine nonlinear discrete time systems are proposed. A neural network is used to approximate the GHJB ...