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

Operations Research, Systems Engineering and Industrial Engineering Commons

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

Series

Computer Sciences

Neural Network

Publication Year

Articles 1 - 4 of 4

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

Neural Network Output Feedback Control Of A Quadrotor Uav, Jagannathan Sarangapani, Travis Alan Dierks Dec 2008

Neural Network Output Feedback Control Of A Quadrotor Uav, Jagannathan Sarangapani, Travis Alan Dierks

Electrical and Computer Engineering Faculty Research & Creative Works

A neural network (NN) based output feedback controller for a quadrotor unmanned aerial vehicle (UAV) is proposed. The NNs are utilized in the observer and for generating virtual and actual control inputs, respectively, where the NNs learn the nonlinear dynamics of the UAV online including uncertain nonlinear terms like aerodynamic friction and blade flapping. It is shown using Lyapunov theory that the position, orientation, and velocity tracking errors, the virtual control and observer estimation errors, and the NN weight estimation errors for each NN are all semi-globally uniformly ultimately bounded (SGUUB) in the presence of bounded disturbances and NN functional ...


Neural Network Control Of Robot Formations Using Rise Feedback, Jagannathan Sarangapani, Travis Alan Dierks Jan 2007

Neural Network Control Of Robot Formations Using Rise Feedback, Jagannathan Sarangapani, Travis Alan Dierks

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, a combined kinematic/torque control law is developed for leader-follower based formation control using backstepping in order to accommodate the dynamics of the robots and the formation in contrast with kinematic-based formation controllers that are widely reported in the literature. A neural network (NN) is introduced along with robust integral of the sign of the error (RISE) feedback to approximate the dynamics of the follower as well as its leader using online weight tuning. It is shown using Lyapunov theory that the errors for the entire formation are asymptotically stable and the NN weights are bounded as ...


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 ...