Ian Stott

The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators

A learning control architecture which uses a multi-layer feed forward neural network with error back propagation is described. The architecture includes a feed forward estimator which is pre-trained and a feedback controller which continues to learn. The properties of the architectures are investigated through a series of experiments, and the application of the prototype adaptive controllers is described. To examine the performance of this controller, square wave demand signals are applied to the controller and the results are presented.

New powered wheelchair systems for the rehabilitation of some severely disabled users.

This paper describes new powered wheelchair systems. Although some early technical details have been published, this is the first time the work has been presented to the rehabilitation community. Early effort was concerned with gaining the necessary contacts and background knowledge.

A new prototype intelligent mobility system to assist powered wheelchair users

This paper presents new prototype powered wheelchair systems that are easy to use and safe. The systems use simple ultrasonic sensor systems to assist users in steering their powered wheelchairs. The new systems could improve the chances of some disabled children learning that behaviour and interaction with the environment can be controlled. An overview of the benefits to be offered by an automated wheelchair is included. Some results, problems and difficulties are described along with an assessment of the current position and the way forward.

Navigational assistance for disabled wheelchair-users

Many disabilities may impair a disabled wheelchair-users capability in maintaining an accurate course using the conventional joystick controls. This paper describes systems being developed, using low cost ultrasonic sensors, to provide additional data to supplement that derived from the joystick whilst still leaving the user in overall control. Methods are described for following a straight course parallel to a wall, which is one aspect of an ongoing research project to provide comprehensive low-cost navigational assistance for disabled wheelchair-users.

Simple expert systems to improve an ultrasonic sensor‐system for a tele‐operated mobile‐robot

Purpose – The purpose of this paper is to investigate how to make tele‐operated tasks easier using an expert system to interpret joystick and sensor data.Design/methodology/approach – Current tele‐operated systems tend to rely heavily on visual feedback and experienced operators. Simple expert systems improve the interaction between an operator and a tele‐operated mobile‐robot using ultrasonic sensors. Systems identify potentially hazardous situations and recommend safe courses of action. Because pairs of tests and results took place, it was possible to use a paired‐samples statistical test.Findings – Results are presented from a series of timed tasks completed by tele‐operators using a joystick to control a mobile‐robot via an umbilical cable. Tele‐operators completed tests both with and without sensors and with and without the new expert system and using a recently published system to compare results. The t‐test was used to compare the means of the samples in the results.Research limitations/implication...

A software algorithm for the intelligent mixing of inputs to a tele-operated vehicle

Real-time methods of micro-computer assistance for an operator to steer a vehicle are presented. The vehicle is directed along a path using an analogue joystick connected to a microcomputer interface. Data from the joystick is processed and was combined with information from other sensors. The output is used to assist the operator in steering the vehicle by tele-operation. The steering data may be stored in the micro-computer and used later to analyse the movements of the vehicle. The paper concentrates on the new algorithms for the intelligent mixing of the inputs in the vehicle micro-controller.

Analysis of successes and failures with a tele-operated mobile robot in various modes of operation

The effect on failure rates of the way tele-operators interact with mobile robots is investigated. Human tele-operators attempted to move a robot through progressively more complicated environments with reducing gaps, as quickly as possible. Tele-operators used a joystick and either watched robots, while operating them, or used a computer screen to view scenes remotely. Cameras were either mounted on the robot to view the space ahead of the robot or mounted remotely so that they viewed both the environment and robot. Tele-operators completed tests both with and without sensors. Both an umbilical cable and a radio link were used.

Expert system to interpret hand tremor and provide joystick position signals for powered wheelchairs with ultrasonic sensor systems

Purpose – The purpose of this paper is to investigate how to make powered‐wheelchair driving easier using simple expert systems to interpret joystick and ultrasonic sensor data. The expert systems interpret shaky joystick movement and identify potentially hazardous situations and then recommend safe courses of action.Design/methodology/approach – The way that a human user interacts with a powered‐wheelchair is investigated. Some simple expert systems are presented that interpret hand tremor and provide joystick position signals for an ultrasonic sensor system. Results are presented from a series of timed tasks completed by users using a joystick to control a powered‐wheelchair. Effect on the efficiency of driving a powered‐wheelchair is measured using the times to drive through progressively more complicated courses. Drivers completed tests both with and without sensors and the most recently published systems are used to compare results.Findings – The new expert systems consistently out‐performed the most...

Low cost ultrasonic sensors for tele-operated vehicles

Describes a new reliable low‐cost ultrasonic ranging system to assist in steering a powered wheelchair. Detection algorithms have been created and implemented on a micro controller based stand‐alone system suitable for a tele‐operated vehicle. The detection uses the gradient of the echo envelope and is resistant to noise and inconsistencies in the detection circuitry. The sensor array was considered as separate sensors, working independently so the system could quickly gather separate sets of range information. These sets were overlaid on to a 2D grid array. The new system is cheaper and simpler than available systems for powered wheelchairs.

Computer assistance for a disabled user/operator to navigate a vehicle through a doorway

A real time method of computer assistance for a disabled user/operator to move a vehicle through a doorway is presented. An electric wheelchair is used as an example vehicle. Automatic programming, motion planning, obstacle avoidance, sensor integration, and control methods are presented which assist a user/operator in controlling the wheelchair. Electric wheelchairs are generally directed along a path using manual controls, usually a joystick connected to switches. In the work described in this paper, data from ultrasonic sensors and other sensors is processed and combined with the information from these switches. The output is used to assist the user/operator in steering the vehicle. A veto is always left with the operator.<<ETX>>