Powered-wheelchair transducers and systems are presented that provided more control, reduced veer on slopes, and improved energy conservation, while reducing effort. They are especially significant for people with movement disorders who lack sufficient hand-grasp and release ability or sufficient targeting skill to use joysticks. Design/methodologies/approach Laboratory test rigs were created to test the proportional switches and to teach potential users. Then a rolling road was created and trials were conducted with the road and real situations. Caster angle measurement was selected to provide feedback to minimize drift away from a chosen course and an electronic solution was created to match driver control to caster steering position. A case study is described as an example. Findings Results and advantages are presented from changing from using a set of digital-switches on a wheelchair to a set of new variable-switches and then adding a sensor system to prevent veer on slopes. The systems have been tested for more than 18 months and shown to assist powered-wheelchair users with poor targeting skills. Research limitations The research used typical wheelchairs with caster wheels but systems could easily be used on other wheelchairs. Practical implication Simple input-devices are presented that isolate gross motor function and are tolerant to involuntary movements (proportional-switches). A sensor system is presented that assists users in steering across sloping or uneven ground. Originality/Value The proportional-switches and sensors were shown to reduce veer and to provide more control over turn and forward speed and turn radius while reducing frustration and improving energy conservation. The simple and affordable systems could be created and attached to many standard powered-wheelchairs in many organisations.. The powered-wheelchair users became more independent when using the new systems.
Time taken to complete a tele-operated task with a mobile-robot partly depends on how a human operator interacts with the mobile-robot. Current tele-operated systems tend to rely heavily on visual feedback and experienced operators and this paper investigates how to make their tasks easier using an expert system to interpret joystick and sensor data. Simple expert systems improve that interaction for a tele-operated mobile-robot using ultrasonic sensors. Systems identify potentially hazardous situations and recommend safe courses of action. 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 and watching the robot while operating it or sitting at a computer and viewing the area ahead of the robot. Tele-operators completed tests both with and without sensors and using the recently published systems to compare results. The new systems described here consistently performed tasks more quickly than some recently published systems. The paper also suggests that the amount of sensor support should be varied depending on circumstances.
A system is described that depicts where a user is pointing on either a CRT or TFT computer screen. The system uses a kaleidoscope of colours flashed onto the screen around a colour sensor at a speed that is not registered by a human user. This is made possible by using an artificial neural network (ANN) to predict the next pointer position of the sensor on the screen.
Purpose-A Multi Expert System is presented that can analyse a design and provide designers with suggestions for improvement and changes to designs at an early stage in order to improve assembly later in the manufacturing process. The Multi Expert System can analyse a design and provide designers with suggestions for improvement and changes to designs at an early stage in order to improve assembly later in the manufacturing process. Design/methodology/approach-The whole system consists of four expert systems: Computer Aided Design (CAD) Expert, Automated Assembly Expert, Manual Assembly Expert and Design Analysis Expert. The Design Analysis Expert includes a subsystem to collate the information from the Assembly Experts and to provide costs and advice Findings-The approach and the systems can reduce manufacturing costs and lead times. Research limitations/implications-A knowledge-based reckoning approach to design-for-assembly automation is used. The approach and systems can reduce manufacturing-costs and lead-times. The system can estimate assembly-time and cost for manual or automatic assembly and select suitable assembly techniques. Practical implications-The system can estimate assembly time and cost for manual or automatic assembly and select a suitable assembly technique. Originality/value-The new system models assembly, product and process design using a natural approach for capturing intelligence. The new approach categorised automated assembly and manual assembly into separate individual experts. Intelligence and knowledge from each was captured and embedded within the individual expert that represented the process. This approach enabled greater flexibility and made the subsystems easier to modify, upgrade, extend and reuse.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.