Anti-collision and Navigation Systems for Powered Wheelchairs
Keywords: Anti-collision, cognitive impairments, intelligent wheelchair, older adults, physical disability
In collaboration with: The Laboratory for Computational Intelligence, University of British Colombia and the School of Computing, University of Dundee
Overview of Research
Older adults who have lost their ability to walk often rely on wheelchairs for their mobility. Adults who lack the physical strength to use manual wheelchairs are given powered wheelchairs, but only if they have the memory and judgement required to safely operate one. These necessary skills are often too difficult for adults who suffer from cognitive impairments. As a result, cognitively impaired adults that are in need of powered wheelchairs are unable to obtain them and have severely reduced mobility. Independent mobility has been linked to quality of life and a decrease in mobility contributes to a decrease in quality of life [1].
This project aims to provide a safe and intuitive means of mobility for individuals who have cognitive impairments. To accomplish this goal an intelligent wheelchair is proposed. This powered wheelchair will have three main features:
- The ability to assist a cognitively impaired individual with navigation through the use of audio prompts.
- An anti-collision system to prevent injury to the user and bystanders.
- A balanced control approach where the system will aid the user with navigation according to user’s preferences/intents.
Anti-collision protection is paramount when dealing with older adults. Studies have shown that a fall is the most probable outcome after being hit by a wheelchair. Falls for elderly could have severe consequences such as hip fractures, which may even lead to death [2].
To accomplish the navigation and anti-collision objectives a stereovision camera (Figure 1) is mounted on the wheelchair and is used as an input to the intelligent wheelchair system. Images from the camera are used to compute the distance of objects from the wheelchair. This distance reading is then translated to an occupancy grid (Figure 2), which is used by the system to determine the safest routes to the desired location. As well the distance reading is used to prevent objects from getting too close to the wheelchair, thus avoiding collisions.
Current research on this project includes development of:
- Hardware for the intelligent wheelchair system into a user-friendly form
- Planning/mapping algorithms to incorporate the user's schedule/preferences
- Clinical trials with older adults with dementia
Read more about the project's technical details.
Figure 1: The wheelchair (with Bumblebee stereovision
camera)
Figure
2: Images from camera and corresponding occupancy grid (Click
on image to enlarge)
Research Team
Alex Mihailidis, PhD, PEng (University of Toronto)
Jim Little, PhD (University of British Colombia)
Alan Mackworth, PhD (University of British Colombia)
Jesse
Hoey, PhD (University of Dundee)
Tuck-Voon How, MASc candidate
(University of Toronto)
Pooja Viswanathan,
PhD candidate (University of British Colombia)
Funding
Natural Sciences and Engineering Research Council (NSERC)
References
- Mihailidis, A., Elinas, P., Boger, J. and Hoey, J.
(2007). An Intelligent Powered Wheelchair to Enable Mobility of Cognitively
Impaired Older Adults: An Anti-Collision System. IEEE Transactions
on Neural Systems & Rehabilitation Engineering, 15(1), 136-143.
- Viswanathan, P., Boger, J., Hoey, J., Elinas, P. and Mihailidis, A. (2007). The Future of Wheelchairs: Intelligent Collision Avoidance and Navigation Assistance. Geriatrics and Aging Magazine, 10(4), 253–256.
