The team of researchers studied the various ways drivers and cyclists co-communicate — both directly and indirectly — while on the road, with the research highlighting the need for new systems in autonomous vehicles (AVs) capable of replicating these complex social interactions.

The team’s findings have resulted in a series of recommendations and suggestions on how, in the decades to come, self-driving AVs should behave safely around cyclists.

One of the suggestions is that self-driving cars could have displays integrated onto the car’s exterior. This could take the form of a series of traffic-light-like coloured LEDs which outwardly display the driver’s intentions to slow down or speed up, give way, and manoeuvre.

Another recommendation is that cyclists could wear “smart glasses,” which could display the AV driver’s intentions to the wearer, facilitating direct communication. For example, AVs could signal that the right of way is up for negotiation, with orange lights displayed on the vehicle and a vibration sent to cyclists’ glasses as a non-verbal message.

Leading the research was Stephen Brewster of the University of Glasgow’s School of Computing Science. On the research — and why it was undertaken in the first place — he said: “Cars and bikes share the same spaces on the roads, which can be dangerous – between 2015 and 2020, 84% of fatal bike accidents involved a motor vehicle, and there were more than 11,000 collisions.”

“There has been a lot of research in recent years on building safety features into autonomous vehicles to help keep pedestrians safe, but comparatively little on how AVs can safely share the road with cyclists.

“That’s a cause for concern as AVs become more commonplace on the roads. While pedestrians tend to meet AVs in highly controlled situations like road crossings, cyclists ride alongside cars for prolonged periods and rely on two-way interactions with drivers to determine each other’s intentions.

“It’s a much more complicated set of behaviours, which makes it a big challenge for future generations of AVs to tackle. Currently, self-driving cars currently offer very little direct feedback to cyclists to help them make critically important decisions like whether it’s safe to overtake or to switch lanes. Adding any guesswork to the delicate negotiations between car and bike has the potential to make the roads less safe.”

Recommended

• NCA and Social Media Firms Removing Swathes of Criminal Content
• UK Gov Draft CMA Bill to Crack Down on “Unfair” Big Tech Practices
• 164% Increase in Tax-related Phishing Emails Since February 2023

To develop and recommend potential solutions for these challenges, the team conducted their research by setting up two observational studies of road users in and around Glasgow.

They watched 414 separate interactions between cyclists and motorists at several city intersections during busy periods. The team then noted whether the riders and drivers were aware of each other occupying nearby space, how they indicated their intent for their next manoeuvre, how they negotiated who would move first, and how they communicated positive or negative feedback once the manoeuvre was completed.

The research team also equipped 12 volunteer cyclists with eye-tracking glasses and head-mounted video cameras, and then asked them to ride their regular commuting route to and from work.

The eye-tracking glasses recorded where the cyclists were looking during their journey, catching data on their gaze as it moved to the road surface, the exteriors and interiors of cars, road signs, and traffic signals.

According to the captured data, cyclists more frequently relied on information from road signs and traffic signals in situations like controlled intersections. That said, it was also found that cyclists looked at cars much more often to gauge drivers’ intentions in situations like roundabouts, uncontrolled junctions, and road works.

Ammar Al-Taie, who’s also of the University of Glasgow’s School of Computing Science, is a co-author of the paper. He commented: “Just like spoken languages, communication between cyclists and drivers varies from country to country.”

“We’re very conscious that this paper focuses specifically on UK roads – any future developments will need to take into account the differences in drivers’ and cyclists’ interactions across the world.”

The research, which was supported with funding from the University of Glasgow and the Royal Society of Edinburgh, will be presented at the Association for Computing Machinery Conference on Human Factors in Computing Systems in Hamburg, Germany next week.