Sisil Kumarawadu

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

Neuroadaptive Output Tracking of Fully Autonomous Road Vehicles With an Observer

Automated vehicle control systems are a key technology for intelligent vehicle highway systems (IVHSs). This paper presents an automated vehicle control algorithm for combined longitudinal and lateral motion control of highway vehicles, with special emphasis on front-wheel-steered four-wheel road vehicles. The controller is synthesized using an online neural-estimator-based control law that works in combination with a lateral velocity observer. The online adaptive neural-estimator-based design approach enables the controller to counteract for inherent model discrepancies, strong nonlinearities, and coupling effects. The neurocontrol approach can guarantee the uniform ultimate bounds (UUBs) of the tracking and observer errors and the bounds of the neural weights. The key design features are (1) inherent coupling effects will be taken into account as a result of combining of the two control issues, viz., lateral and longitudinal control;(2) rather ad hoc numerical approximations of lateral velocity will be avoided via a combined controller-observer design; and (3) closed-loop stability issues of the overall system will be established. The algorithm is validated via a formative mathematical analysis based on a Lyapunov approach and numerical simulations in the presence of parametric uncertainties as well as severe and adverse driving conditions.

Smart metering design and applications

Description based on online resource; title from PDF title page (ebrary, viewed November 10, 2013).

A robust vision-based hand gesture recognition system for appliance control in smart homes

Adopting a hand gesture based appliance control system would be a virtuous idea for smart homes. However, complexity of the home background makes it challenging to work such systems in real home environments. In this paper, we present developing a robust system which can practically be used in complex backgrounds. The users are required to wear neither wristbands nor long-sleeved garments. In order to achieve this, we use TRS moment invariants combined with Viola-Jones object detection framework. We demonstrate the performance of the system in different complex backgrounds by controlling a pedestal fan.

RFID-based anti-theft auto security system with an immobilizer

This paper presents a novel radio frequency identification (RFID) based vehicle immobilizer system, which features low hacking probability while preserving the safety of the passengers of the hijacked vehicle. The immobilizer uses the active RFID technology where the tag is generated with comparatively large character sets. The receiving unit is intelligently integrated into three control circuits in the vehicle, namely, ignition circuit, power control unit, and automatic gear changing system, enabling it to bring the vehicle speed down to zero in a safe step by step manner. The anti-theft auto security system proposed here was tested under different weather conditions and possible signal distortion situations to verify its reliability.

On the speed control for automated surface vessel operation

Automated surface vessels (ASVs) are used in intelligent transportation systems, autonomous oceanographic research, and cargo handling in harbors. Combined surge, sway, and yaw control of surface vessels still remains as an open problem. In this paper, the problem of control with guaranteed sway and yaw stability for automated surface vessel operation is addressed with special emphasis on speed control. A control scheme to solve this problem without simplifying the dynamics is proposed and extensively studied using formative mathematical analyses and simulations.

On the speed control for automated vehicle operation

The problem of control with guaranteed lateral and yaw stability for automated vehicle operation is addressed with special emphasis on speed control. A control scheme to solve this problem without simplifying the dynamics is proposed and extensively studied using formative mathematical analyses and simulations.

Adaptive output tracking of partly known robotic systems using SoftMax function networks

In this paper, a neural-network-based adaptive control scheme is presented to solve the output-tracking problem of a robotic system with unknown nonlinearities. The control scheme ingeniously combines the conventional resolved velocity control technique and a neurally-inspired adaptive compensating paradigm constructed using SoftMax function networks and neural gas algorithm. Results of simulations on our active binocular head are reported. The neural network model constructed to has two neural subnets to separately control the robot head neck and eye movement, simplifying the design and leading to faster weight tuning algorithms.

Direct-adaptive neurocontrol of robots with unknown nonlinearities and velocity feedback

A neural network (NN) adaptive tracking controller for rigid revolute robots is presented that requires position measurements only. The controller is synthesized using a computed torque like control part of which a modified version of the nonlinear part of Lagrangian dynamics is learnt online by a neural estimator that needs no offline training phase. Therefore, the implementation of the control algorithm needs a reasonable knowledge of the inertia matrix alone. The combined neurocontroller-linear observer scheme can guarantee the uniform ultimate bounds (UUB) of the tracking errors and the observer errors under fairly general conditions on the controller-observer gains.

Intelligent lightning warning system

In developing countries like Sri Lanka, lightning warning systems are rare, and simple low cost methods adopted have not lived up to expectations. It would thus be very advantageous if warnings could be made localized to a specific area. This paper presents a method that is affordable to the ordinary person and informs him of the risk of lightning hazards in advance. The system is simple, yet effective, and produces specific warnings accurately using an effective technology. The lightning threat is assessed by monitoring the static electric field between the thundercloud and the earth using a user made made field mill unit. This triggers an alarm, or a rotating beacon according to the degree of the lightning threat, with the aid of a simple neural network. Intra cloud flashes, which occur in the vicinity of imminent lightning flashes in the region, emits radio frequency signals. By combining this as an additional input to the neural network, more accurate predictions can be made. Test results are also presented on the prototype lightning warning system developed at the University of Moratuwa.