Imperial College London

Finalist category: Inclusive Design Award

#T4Gimperial

Visit website

Finalist, Inclusive Design Award, 2019

The self-driving AI-powered wheelchair combines existing widely available technologies, such as eye tracking system and laptops, with electric wheelchairs.

In 156 developing countries in the world, it is estimated that at least 2% or 121,800,000 people require a wheelchair. The team believe that this technology will be a huge step for improving everyday independence. For example, users could specify that they want to drive out of a cluttered kitchen, and leave it to the wheelchair to navigate the route and avoid obstacles without further human input.

To do this, the wheelchair uses a Light Detection and Ranging (LiDAR) sensor, which is an infrared-based sensor commonly used on self-driving cars, to build a 360-degree map of the user’s environment. The eye tracker gathers information on eye movements, the AI programme defines where the wheelchair should move to, and guides it to avoid obstacles. The AI system uses the LiDAR to build maps of the environment as the wheelchair moves about, just as in self-driving cars.

The use of eye gaze technology harnesses AI in a very practical way for people with a huge range of needs, but is a very powerful way for wheelchair users with physical impairments to take control of their chairs. The latest technology allows users to guide their chair around the room – with the next generation solutions using AI to map the space and respond to requests to move the chair without needing the user to keep their eyes locked on a screen. They will be able to focus on a specific destination – for example the other side of the room – use a gesture to indicate their desire to get there and the wheelchair will then navigate to that spot on its own (with obvious safety features).

The self-driving wheelchair brings together a range of technologies to deliver a solution that empowers people and provides a huge sense of independence for its users.

Dr Faisal says: “Our wheelchair is a great example of what we call a frugal innovation. It demonstrates that the power of AI is becoming accessible and affordable to regular people. We at Imperial are harnessing its power to improve lives.”

Such intelligent AI systems can learn and improve specific to the user over time, so they are able to work with patients from day one to pinpoint their needs and expectations. The technology will help severely disabled people restore their independence at low cost.

The lab works closely with disabled people at all stages of the project development – putting their needs at the centre of the design process and using their feedback to guide the development of features. They hope that this is the start of a new generation of technology and will herald a new era of independence for the millions of people around the world who need to use a wheelchair.

The wheelchair is still in the research and development stage and the team has recently won $50,000 from the Mobility Challenge Fund for further development. Their next step will be to compete for $1 million prize, for which the winner will be announced at the Tokyo 2020 Summer Paralympics. If won, this will go towards making necessary improvements and putting the wheelchair on the market.

Sponsors

The Tech4Good Awards are organised by AbilityNet and BT and supported by a range of sponsors and partners:

Subscribe to News