RoboGuide walks and talks to assist blind and partially sighted people

Blind and partially sighted people could soon navigate indoor spaces with the help of RoboGuide, a communicative robot guide dog in development at Glasgow University.

RoboGuide was tested for the first time with volunteers at the Hunterian museum
RoboGuide was tested for the first time with volunteers at the Hunterian museum - Glasgow University

A team from the University has partnered with industry and charities to develop the RoboGuide, an AI-powered four-legged robot which aims to help visually impaired people move more independently through public places in the future. 

The RoboGuide prototype integrates a range of technologies into an off-the-shelf Unitree robot to help overcome the challenges preventing robots from being more widely used to assist blind and partially sighted people. 

The project aims to bring a more complete version of the technology to market in the years to come to help support the 2.2 billion people around the world, and two million people in the UK, living with sight loss.

In a statement, principal investigator Dr Olaoluwa Popoola, of Glasgow University’s James Watt School of Engineering, said: “Assistive technologies like the RoboGuide have the potential to provide blind and partially sighted people with more independence in their daily lives.

“One significant drawback of many current four-legged, two-legged and wheeled robots is that the technology which allows them to find their way around can limit their usefulness as assistants for the visually impaired.

“Robots which use GPS to navigate, for example, can perform well outdoors, but often struggle in indoor settings, where signal coverage can weaken. Others, which use cameras to ‘see’, are limited by line of sight, which makes it harder for them to safely guide people around objects or around bends.”

MORE FROM ROBOTICS & UAVs

The RoboGuide system uses sensors mounted on the robot’s exterior to map and assess its surroundings. Software developed by the team helps it learn the optimal routes between locations and interpret the sensor data in real-time to help the robot avoid the many moving obstacles it might encounter. 

The RoboGuide also incorporates large language model technology, giving it the ability to understand questions and comments from users and provide verbal responses. 

The Forth Valley Sensory Centre (FVSC) Trust (FVSC) and the Royal National Institute of Blind People (RNIB) Scotland have lent their support to RoboGuide’s development. 

RoboGuide was tested for the first time with volunteers from FVSC and RNIB at the Hunterian museum where the assistive robot helped the volunteers find their way around the first floor of the museum and provided interactive spoken guidance on six exhibits. 

Team member Dr Wasim Ahmad, of the James Watt School of Engineering, said: “We’re pleased to be working closely with the FVSC and RNIB Scotland to test the RoboGuide in real-world environments, and to integrate their feedback into more refined iterations of the technology.

“Ultimately, our aim is to develop a complete system which can be adapted for use with robots of all shapes and sizes to help blind and partially sighted people in a wide range of indoor situations. We hope that we can create a robust commercial product which can support the visually impaired wherever they might want extra help.”

The nine-month research project is supported by funding from the Engineering and Physical Sciences Research Council (EPSRC) through the Impact Acceleration Account programme.