Specialists from the University of Glasgow believe self-driving cars "need to learn the language of cyclists", with their research suggesting such improvements are necessary to help autonomous vehicles safely share the roads with those riding bicycles.
In a paper titled 'Keep it Real: Investigating Driver-Cyclist Interaction in Real-World Traffic', which will be published later in 2023 and was today reported by The Herald newspaper, researchers looked to unpick the relationship between cyclists and automated vehicles, saying there had been "comparatively little" research into how self-driving technology can keep cyclists safe.
Professor Stephen Brewster of the university's School of Computing Science said there had been "a lot of research in recent years on building safety features into autonomous vehicles to help keep pedestrians safe", something that needs to be repeated with cyclists.
> "These are completely safe autonomous vehicles": Cyclist spots driverless car using cycle lane
"Cars and bikes share the same spaces on the roads, which can be dangerous – between 2015 and 2020, 84 per cent of fatal bike accidents involved a motor vehicle, and there were more than 11,000 collisions," he said.
"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 automated vehicles can safely share the road with cyclists.
"That's a cause for concern as automated vehicles become more commonplace on the roads. While pedestrians tend to meet automated vehicles 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 automated vehicles to tackle. Currently, self-driving cars 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."
> Tesla car in Full Self-Driving Beta almost rams cyclist
Brewster's team studied the ways drivers and cyclists directly and indirectly communicate in real-world situations. From the research they have formed recommendations for future generations of automated vehicles.
The researchers suggest the vehicles' intentions could be displayed on their exteriors, for example displaying animations signalling intention to speed up, slow down, give way or manoeuvre.
At the other end of the relationship they suggest cyclists could wear 'smart glasses' communicating the vehicle's intentions to them, for example when coloured LEDs on the car light up to signal right of way is up for negotiation a vibration could be sent to the glasses as a non-verbal message.
> Tesla using Full Self-Driving Beta crashes into cycle lane bollard...weeks after Elon Musk's zero collisions claim
The paper's co-author, Ammar Al-Taie, said he hopes the research will inform autonomous vehicle designers, encouraging them to develop "new ways that self-driving cars can work safely alongside cyclists by speaking their language".
"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 will be presented, at the ACM Conference on Human factors in Computing Systems, in Germany next week.
Add new comment
105 comments
Or... hear me out... we should just enforce better driving standards that don't kill or maim people in large numbers.
Sorry, now I've read that back to myself I realise how ridiculous it sounds. Crack on with the technology glasses lads!
Did you miss the part where this is about autonomous vehicles ... i.e. not being driven by a human?
Are all motorvehicles driverless now? That's a big change since last week. Not sure how my two cars are going to drive themselves though?
No ... I get that. But the proposal to have cyclists wearing smartspecs is specifically to aid interaction between cyclists and driverless vehicles and has nothing to do with how we currently enforce (or don't) driving standards.
Frankly, as I have to wear glasses all the time anyway, if wearing a pair of smart glasses helps provide the data to make it safer for me and future riders to travel around driverless cars then bring it on.
Somehow, the point is still sailing over your head.
Perhaps we should put the onus on the vehicles that are causing the harm?
AI usually gets trained by example. Hence the problem. No source data.
As there are at least 5 different types of EV charging cable, are cyclists going to have to wear a different set of glasses per car manufacturer?
Once we work out what might need to be communicated, and now to do it best, then we would make that open. Then we could make apps for phones/bike computers/headsets. There are some very early stage ISO standards emerging, so we should try and get it in there. So, hopefully avoid your issue!
* of course, stuff that the cyclist might use should be optional. The AV should be safe if the rider has no tech at all.
My point was that there is no one "standard" charge cable connector for an EV ... which let's face it is essential a couple of bits of wire.
How are you going to get *all* the existing vehicle and *all* the future manufacturers to agree on how the technology will interface, use, information provided and cost?
As a potential false equivalence, the SMART meter roll out turned in to a fiasco because 3 suppliers couldn't agree on data and protocol... how are you going to get vehicle manufacturers to agree?
should be easy, after all we have managed a single standard for bottom brackets and that's much more complex
/sarcasm.
"* of course, stuff that the cyclist might use should be optional."
Of course it should. Just as now nobody ever gets shouted at/publicly condemned/judged for contributory negligence for not wearing hi vis or a helmet. Oh wait..
I assume there would be an app for that.
I read somewhere that if you wanted to make sure you had the app to be able to park a car anywhere in the UK, you'd now need something like 38 different apps.
Individual motorized transport is an inefficient waste of public space, valuable ressources and energy, and we have to get rid of it asap. Does any of that change with autonomous cars? No.
Autonomous cars would make ride sharing far easier so... Yes.
Why?
The vehicles will be easily subdivided to give the privacy of a private car along with the door to door convenience.
All at a fraction of the cost.
Have a look at the Cruise Origin vehicle, that's where we're heading imminently, it's designed around ride sharing and is being launched in the next few weeks.
I have just looked at the Cruise Origin. I don't see the privacy you are lauding.
Nor me...
https://topelectricsuv.com/news/cruise/cruise-origin-latest/
You can't see how that space could be subdivided easily to provide private space?
Yes, but it would be pretty claustrophobic...
It depends on your frame of reference I suppose. Relative to the 'personal space' you get on most public transport at rush hour it would be positively luxurious.
It looks like a bus...
I said the vehicles will be "easily subdivided".
It's pretty obvious that the space could be easily subdivided.
Quite, this is existing technology.
So could a bus? Why does taking out the driver's seat make such a massive difference? And if it's so obviously the way forward, why hasn't the actual example that you put forward done it?
That you would choose to believe the unfounded publicity of the manufacturers comes as no surprise.
I'm just looking at the economics.
Autonomous vehicles will give people the option of door to door transport in privacy at a fraction of the cost of a private vehicle. The vehicles being built right now will be easily subdivided into compartments allowing all of the above at an even lower cost.
Why wouldn't people use that service?
If we're not to believe 'unfounded' predictions then please share the evidence you're basing your predictions on?
(Many) people don't really like sharing.
If you had your own private door and space within a lot of that opposition to ride sharing would likely disappear.
Pages