Design and implementation of a smart wheelchair

Abstract

Wheelchairs have improved the lives of many people with limited mobility. Yet, even after decades of development, conventional wheelchairs are still not a viable option for millions of people with some particular special needs. Many medical conditions like for example, cerebral palsy or Amyotrophic Lateral Sclerosis (ALS), prevent people from having the right amount of coordination or strength to propel or steer a conventional wheelchair. In some cases these people may not be strong enough to control the joystick on a Powered Wheelchair (PW).

A possible solution for many who cannot use a normal or powered wheelchair is a Smart Wheelchair (SW). A SW is the product of the merging of mobile robotics and artificial intelligence with current PW technology. SWs overcome many of the limitations of normal wheelchairs by adding an extra level of intelligence to the system. For example, a navigation aid could allow a SW to take care of movement autonomously with only simple prompts from the user. On another level, one could perform a complete overhaul of a PW, by making it fully-autonomous and capable of navigating a building by itself or by following a guide or a carer. Various prototypes have been built by a number of research institutions worldwide. In some way or another these all attempt to fulfill these needs. However, SW systems have only very recently been introduced to the commercial world due to robustness and pricing limitations. Thus, SW research and development is still very active, and prototype hardware systems are still being developed and tested to this day.

The aim of this project is to pioneer SW research at the University of Malta through the design and implementation of a new SW system utilising modern hardware. A normal PW was upgraded by the attachment of sensors and a computer rig to its chassis. A software infrastructure using Robot Operating System (ROS) was built on top of this hardware, connecting each sensor and hardware unit together into a unified system. Various semi-autonomous and autonomous algorithms were designed and implemented onto the wheelchair. Practical tests in typical use scenarios showcased the successful operation of these algorithms. The developed prototype SW has the potential to restore autonomy to people who are unable to use conventional or powered wheelchairs.