Tag Archives: self-driving cars

Head case

Prof. Guglielmo Tamburrini posed an interesting question in a talk this afternoon. Imagine a self-driving car faced with the option of having to hit one of two motorcyclists. One is wearing a helmet, and the other isn’t. Should it aim for the helmet-wearing guy, to reduce the risk of loss of life?

Philosophers must be having a field day with this stuff. They’re being invited to comment on the latest in sexy new technologies in a way that doesn’t happen very often. (Douglas Adams fans may remember Majikthise & Vroomfondel.) Much of the ethical discussion relating to autonomous vehicles, though, boils down to variations on the Trolley Problem, and the key thing about this — the thing that makes it an interesting ethical conundrum in the first place — is that there is no right answer. If deployment of the railways had required the Trolley Problem to be solved first, we would still be using horse-drawn carts.

The question is not, ‘What should a car do in this situation?’, but ‘How do we get to a point where society is comfortable that we’ve had enough discussion about this?’ Or, more precisely, ‘How do we get to a point where a large enough fraction of society is comfortable, that a party proposing to allow such vehicles on our roads would be elected to government?’

Many technologies, historically, have first been used, and then later have had restrictions placed upon them to reduce the risks which are discovered, with experience, to be the key ones: motorcyclists needing helmets, cars needing seat-belts, pilots needing licences, smokers needing to go outside.

What I presume will happen here is that societies who are less risk-averse will go ahead with greater degrees of autonomous driving, and the more conservative nations will watch with interest until they can amass enough vicarious experience to follow in their footsteps.

I imagine, however, that in 50 years’ time, we’ll still be debating the motorcycle question raised above. By then, though, it will be even more hypothetical, since we’ll have long-since banned motorcycles.

Altruistic Autonomous Vehicles

One of my shortest recent posts generated quite a lot of discussion, both here and on Facebook. I wrote:

When we have proper and affordable self-driving vehicles, will that be the end of the railways?

Clearly there are some things that railways will do better for the foreseeable future, like long-range high-speed links, or carrying heavy freight. And don’t get me wrong: I like train journeys. But it seemed to me that the key reasons people currently take trains for normal day-to-day journeys — wanting to read en route, a lack of parking at their destination, avoiding congestion — could very soon be overcome when, for example, your car can go and valet-park itself after dropping you off at the office.

And the disadvantages of train travel: the fact that instead of going from point A to point B, you have to go at least from point A to point B to point C to point D, possibly waiting on a cold platform at point B for an indeterminate period, and not being sure whether you’ll get a seat from point C to B on the return journey. Will it be worth the hassle?

One of my assumptions is that traffic congestion will become less of an issue when cars are smarter, of course, which may not be a valid one, especially if lots of train travellers take to their cars instead.

There’s an interesting question as to whether lots of small independent agents trying to meet their own goals are going to result in an optimal solution for road congestion as a whole. We may start off with vehicles that are pretty autonomous initially, but become less so in due course, as the road infrastructure starts to adapt to them. Network packets on the internet know their destination, but it’s the routers (the junctions) that tell them which exit from the roundabout to take.

Will the Department of Transport manage overall use of the network better than each individual car? Well, that depends on who has the better computer scientists, of course! But it also depends on the amount of knowledge each vehicle can get about the overall road network, and, of course, on how selfish your car is: will it decide that the needs of the many outweigh the needs of the one (or the few)?

Perhaps we need Altruistic Autonomous Vehicles? (You heard it here first!) There could be financial incentives to encourage this. You get lower road tax if your car agrees to obey centrally-prescribed rules at times of high congestion. Perhaps you get to use the high-speed autonomous-only lanes if you’re willing to hand over to the cloud-based algorithms. Of course, this could open up all sorts of wonderful opportunities for hackers, too. Remember the movie?

Anyway, perhaps congestion will be less of an issue, but for a completely different reason. If you can be having a coffee, working on your laptop and taking Skype calls while you slip quietly along in your electric car, you may be more productive than if you’d got to the office on time.

© Copyright Quentin Stafford-Fraser