Robot Assistant to Prevent and Manage Falls (Robotics + Applied Computer Vision + AI + IoT)

Nafis Ahmed


Supervised by Charith Perera; Moderated by Alun D Preece

Falling is a major risk to the health of older people with approximately one third of community dwelling elderly falling at least once a year (NHS, 2021) and numbers are expected to rise in the UK due to an aging population. Falls are the second leading cause of unintentional deaths worldwide with an estimated 684,000 deaths each year globally (WHO, 2021). Falls occur more often at night and a proposed solution to reduce this was to use a guiding night light which would aid mobility from the bed to the bathroom (Tholking et al, 2020). Results showed a 1. 7 times reduction in falls but the fall rate was too low to detect statistical significance. Their conclusion was lighting at night should be evaluated further as a possible solution to reducing falls in the elderly.

The study used a fixed lighting led strip as the light source but this suffers from: - Not being transferable should the user move bed - Requires considerable setup - May affect other occupants living in the house

This project looks at developing a robot which will follow the user and take appropriate action in the event of a fall. The robot will utilise a bespoke Light Emitting Diode (LED) based torch solution (DIY Perks, 2021) and navigation will be performed using artificial intelligence (AI) path tracking and computer vision obstacle detection algorithms. AI will also be used to detect if the user has had a fall. An Internet of Things (IoT) based solution will be utilised to allow the robot to communicate a fall to emergency services.

Initial Plan (06/02/2023) [Zip Archive]

Final Report (12/05/2023) [Zip Archive]

Publication Form