High-performance object tracking and fixation with an online neural estimator.

Vision-based target tracking and fixation to keep objects that move in three dimensions in view is important for many tasks in several fields including intelligent transportation systems and robotics. Much of the visual control literature has focused on the kinematics of visual control and ignored a number of significant dynamic control issues that limit performance. In line with this, this paper presents a neural network (NN)-based binocular tracking scheme for high-performance target tracking and fixation with minimum sensory information. The procedure allows the designer to take into account the physical (Lagrangian dynamics) properties of the vision system in the control law. The design objective is to synthesize a binocular tracking controller that explicitly takes the systems dynamics into account, yet needs no knowledge of dynamic nonlinearities and joint velocity sensory information. The combined neurocontroller-observer scheme can guarantee the uniform ultimate bounds of the tracking, observer, and NN weight estimation errors under fairly general conditions on the controller-observer gains. The controller is tested and verified via simulation tests in the presence of severe target motion changes.     

Neuroadaptive Combined Lateral and Longitudinal Control of Highway Vehicles Using RBF Networks

A neural network (NN) adaptive model-based combined lateral and longitudinal vehicle control algorithm for highway applications is presented in this paper. The controller is synthesized using a proportional plus derivative control coupled with an online adaptive neural module that acts as a dynamic compensator to counteract inherent model discrepancies, strong nonlinearities, and coupling effects. The closed-loop stability issues of this combined control scheme are analyzed using a Lyapunov-based method. The neurocontrol approach can guarantee the uniform ultimate bounds of the tracking errors and bounds of NN weights. A complex nonlinear three-degree-of-freedom dynamic model of a passenger wagon is developed to simulate the vehicle motion and for controller design. The controller is tested and verified via computer simulations in the presence of parametric uncertainties and severe driving conditions     

Self-Adaptive Output Tracking with Applications to Active Binocular Tracking

In this article we present a neurally-inspired self-adaptive active binocular tracking scheme and an efficient mathematical model for online computation of desired binocular-head trajectories. The self-adaptive neural network (NN) model is general and can be adopted in output tracking schemes of any partly known robotic systems. The tracking scheme ingeniously combines the conventional Resolved Velocity Control (RVC) technique and an adaptive compensating NN model constructed using SoftMax basis functions as nonlinear activation function. Desired trajectories to the servo controller are computed online by the use of a suitable linear kinematics mathematical model of the system. Online weight tuning algorithm guarantees tracking with small errors and error rates as well as bounded NN weights.     

NEURAL NETWORK‐BASED OPTIMAL ADAPTIVE TRACKING USING GENETIC ALGORITHMS

This paper presents the use of neural networks (NNs) and genetic algorithms (GAs) to enhance the output tracking performance of partly known robotic systems. Two of the most potential approaches of adaptive control, i.e., the concept of variable structure control (VSC) and NN‐based adaptive control, are ingeniously combined using GAs to achieve high‐performance output tracking. GA is used to make the maximum use of different performance characteristics of two self‐adaptive NN modules by finding the switching function which best combines them. The method will be valid for any rigid revolute robot system. Computer simulations on our active binocular head are included for illustration and verification.     

Remarkable stability of the enhanced sharp photocurrent in methylviolet–C18 and rhodamine–C18 dye-sensitized photoelectrochemical cell with p-CuSCN

A remarkable stability in the sharp photo-current peak at 570 nm was found when p-CuSCN semiconductor photocathode was sensitized with double-dye LB films of rhodamine-C₁₈ (R-C₁₈) monolayers and methylviolet-C₁₈ (M-C₁₈) monolayers. At first, M-C₁₈ four monolayers were deposited on p-CuSCN and then, R-C₁₈ four monolayers were deposited on M-C₁₈ monolayers to make an molecular arrangement on the semiconductor (LB-(R-C₁₈(4)/M-C₁₈(4))/p-CuSCN). Such a photo-cathode exhibited a remarkable stability of steady-state photo-current in (10⁻² M) KI+(10⁻⁴ M) I₂ aqueous solution of pH=6.5, where the quantum efficiency reached was 45%, as estimated by correcting the dye absorption in the sharp photo-current peak at 570 nm. When four monolayers of M-C₁₈ and four monolayers of R-C₁₈ were separated with an arachidic acid LB films, sharp photo-current peak and its stability gradually decreased. This remarkable stability may be due to an efficient energy transfer process and an efficient charge separation caused by a strong interaction between the parallel electron-vibration planes of both M-C₁₈ and R-C₁₈ molecules.     

Crystal violet dye-sensitized photocurrent by participation of surface states on p-CuSCN photocathode

Surface states on p-CuSCN are sensitized by aggregated crystal violet in addition to the cathodic sensitization process between semiconductor valence band and the excited monomeric dye molecules. Formation of surface states on bare p-CuSCN is confirmed by experimental results of photocurrent measurements, diffuse reflectance spectra and photoluminescence measurements. Photocurrent quantum efficiency obtained for the aggregated dyes sensitized the surface is 25% at λ=460 nm, and 14% for the monomeric dyes at λ=580 nm. From the variation of photocurrent quantum efficiency with surface concentration of crystal violet at various biased electrode potentials and diffuse reflectance spectra of dye coated p-CuSCN, it is found that the appearance of the sharp photocurrent quantum efficiency peak (λ=460 nm) is due to the sensitization process with the aggregated dye and that of the broad photocurrent quantum efficiency peak (λ=580 nm) is due to the sensitization process with the monomeric dye.