A simple expert system is described that helps wheelchair users to drive their wheelchairs. The expert system takes data in from sensors and a joystick, identifies obstacles and then recommends a safe route. Wheelchair users were timed while driving around a variety of routes and using a joystick controlling their wheelchair via the simple expert system. Ultrasonic sensors are used to detect the obstacles. The simple expert system performed better than other recently published systems. In more difficult situations, wheelchair drivers did better when there was help from a sensor system. Wheelchair users completed routes with the sensors and expert system and results are compared with the same users driving without any assistance. The new systems show a significant improvement.
This paper investigates whether using sensors during training is more effective than not. Results are presented from investigating novice vehicle drivers learning while using varying amounts of sensor support. Qualitative and quantitative data evaluations are made to compare drivers with sensors against those without while they learn to drive a vehicle. Reliance on the teaching processes used was recorded while various amounts of support were given by the intelligent systems. The work considers whether skilled drivers trained with sensors assisting them during training, could then work well without any assistance from sensors. Finally, some results are included. In all situations, assistance becomes more useful as environments became more complicated.
Using an expert system to make driving a poweredwheelchair less problematic is investigated. The system interprets sensor and joystick signals and then mixes them and improves that collaboration to control speed and direction. Ultrasonic sensors are used to identify hazardous circumstances and suggest a safer direction and speed. Results from drivers completing a series of timed routes are presented. Users completed tests using joysticks to control their chair with and then without a microcomputer and sensor system. A recent system is used to compare and contrast the results. This new system consistently performed quicker than the recent system. It also appears that the quantity of support provided by the sensors and microcomputer should be adjusted depending on situations and surroundings
The research presented in this paper creates an intelligent system that collects powered wheelchair users' driving session data. The intelligent system is based on a Python programming platform. A program is created that will collect data for future analysis. The collected data considers driving session details, the ability of a driver to operate a wheelchair, and the type of input devices used to operate a powered wheelchair. Data is collected on a Raspberry Pi microcomputer and is sent after each session via email. Data is placed in the body of the emails, in an attached file and saved on microcomputer memory. Modifications to the system is made to meet confidentiality and privacy concerns of potential users. Data will be used for future analysis and will be considered as a training data set to teach an intelligent system to predict future path patterns for different wheelchair users. In addition, data will be used to analyze the ability of a user to drive a wheelchair, and monitor users' development from one session to another, compare the progress of various users with similar disabilities and identify the most appropriate input device for each user and path.
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.