Just like teenagers, self-driving cars need practice to really learn to drive

A self-driving car, of unknown level of education. Image: Grendelkhan/Flickr/creative commons.

What do self-driving cars and teenage drivers have in common?

Experience. Or, more accurately, a lack of experience.

Teenage drivers – novice drivers of any age, actually – begin with little knowledge of how to actually operate a car’s controls, and how to handle various quirks of the rules of the road. In North America, their first step in learning typically consists of fundamental instruction conveyed by a teacher. With classroom education, novice drivers are, in effect, programmed with knowledge of traffic laws and other basics. They then learn to operate a motor vehicle by applying that programming and progressively encountering a vast range of possibilities on actual roadways. Along the way, feedback they receive – from others in the vehicle as well as the actual experience of driving – helps them determine how best to react and function safely.

The same is true for autonomous vehicles. They are first programmed with basic knowledge. Red means stop; green means go, and so on. Then, through a form of artificial intelligence known as machine learning, self-driving autos draw from both accumulated experiences and continual feedback to detect patterns, adapt to circumstances, make decisions and improve performance.

For both humans and machines, more driving will ideally lead to better driving. And in each case, establishing mastery takes a long time. Especially as each learns to address the unique situations that are hard to anticipate without experience – a falling tree, a flash flood, a ball bouncing into the street, or some other sudden event. Testing, in both controlled and actual environments, is critical to building know-how. The more miles that driverless cars travel, the more quickly their safety improves. And improved safety performance will influence public acceptance of self-driving car deployment – an area in which I specialise.

Starting with basic skills

Experience, of course, must be built upon a foundation of rudimentary abilities – starting with vision. Meeting that essential requirement is straightforward for most humans, even those who may require the aid of glasses or contact lenses. For driverless cars, however, the ability to see is an immensely complex process involving multiple sensors and other technological elements:

  • radar, which uses radio waves to measure distances between the car and obstacles around it;
  • LIDAR, which uses laser sensors to build a 360-degree image of the car’s surroundings;
  • cameras, to detect people, lights, signs and other objects;
  • satellites, to enable GPS, global positioning systems that can pinpoint locations;
  • digital maps, which help to determine and modify routes the car will take;
  • a computer, which processes all the information, recognising objects, analysing the driving situation and determining actions based on what the car sees.

How a driverless car ‘sees’ the road.

All of these elements work together to help the car know where it is at all times, and where everything else is in relation to it. Despite the precision of these systems, however, they’re not perfect. The computer can know which pictures and sensory inputs deserve its attention, and how to correctly respond, but experience only comes from traveling a lot of miles.

The learning that is occurring by autonomous cars currently being tested on public roads feeds back into central systems that make all of a company’s cars better drivers. But even adding up all the on-road miles currently being driven by all autonomous vehicles in the U.S. doesn’t get close to the number of miles driven by humans every single day.

Dangerous after dark

Seeing at night is more challenging than during the daytime – for self-driving cars as well as for human drivers. Contrast is reduced in dark conditions, and objects – whether animate or inanimate – are more difficult to distinguish from their surroundings. In that regard, a human’s eyes and a driverless car’s cameras suffer the same impairment – unlike radar and LIDAR, which don’t need sunlight, streetlights or other lighting.

This was a factor in March in Arizona, when a pedestrian pushing her bicycle across the street at night was struck and killed by a self-driving Uber vehicle. Emergency braking, disabled at the time of the crash, was one issue. The car’s sensors were another issue, having identified the pedestrian as a vehicle first, and then as a bicycle. That’s an important distinction, because a self-driving car’s judgments and actions rely upon accurate identifications. For instance, it would expect another vehicle to move more quickly out of its path than a person walking.


Try and try again

To become better drivers, self-driving cars need not only more and better technological tools, but also something far more fundamental: practice. Just like human drivers, robot drivers won’t get better at dealing with darkness, fog and slippery road conditions without experience.

Testing on controlled roads is a first step to broad deployment of driverless vehicles on public streets. The Texas Automated Vehicle Proving Grounds Partnership, involving the Texas A&M Transportation Institute, University of Texas at Austin, and Southwest Research Institute in San Antonio, Texas, operates a group of closed-course test sites.

Self-driving cars also need to experience real-world conditions, so the Partnership includes seven urban regions in Texas where equipment can be tested on public roads. And, in a separate venture in July, self-driving startup Drive.ai began testing its own vehicles on limited routes in Frisco, north of Dallas.

These testing efforts are essential to ensuring that self-driving technologies are as foolproof as possible before their widespread introduction on public roadways. In other words, the technology needs time to learn. Think of it as driver education for driverless cars.

People learn by doing, and they learn best by doing repeatedly. Whether the pursuit involves a musical instrument, an athletic activity or operating a motor vehicle, individuals build proficiency through practice.

The ConversationSelf-driving cars, as researchers are finding, are no different from teens who need to build up experience before becoming reliably safe drivers. But at least the cars won’t have to learn every single thing for themselves – instead, they’ll talk to each other and share a pool of experience.

Johanna Zmud, Senior Research Scientist, Texas A&M Transportation Institute, Texas A&M University .

This article was originally published on The Conversation. Read the original article.

 
 
 
 

Everybody hates the Midlands, and other lessons from YouGov’s latest spurious polling

Dorset, which people like, for some reason. Image: Getty.

Just because you’re paranoid, the old joke runs, doesn’t mean they’re not out to get you. By the same token: just because I’m an egomaniac, doesn’t mean that YouGov isn’t commissioning polls of upwards of 50,000 people aimed at me, personally.

Seriously, that particular pollster has form for this: almost exactly a year ago, it published the results of a poll about London’s tube network that I’m about 98 per cent certain* was inspired by an argument Stephen Bush and I had been having on Twitter, at least partly on the grounds that it was the sort of thing that muggins here would almost certainly write up. 

And, I did write it up – or, to put it another way, I fell for it. So when, 364 days later, the same pollster produces not one but two polls, ranking Britain’s cities and counties respectively, it’s hard to escape the suspicion that CityMetric and YouGuv are now locked in a co-dependent and potentially abusive relationship.

But never mind that now. What do the polls tell us?

Let’s start with the counties

Everybody loves the West Country

YouGov invited 42,000 people to tell it whether or not they liked England’s 47 ceremonial counties for some reason. The top five, which got good reviews from between 86 and 92 per cent of respondents, were, in order: Dorset, Devon, Cornwall, North Yorkshire and Somerset. That’s England’s four most south westerly counties. And North Yorkshire.

So: almost everyone likes the South West, though whether this is because they associate it with summer holidays or cider or what, the data doesn’t say. Perhaps, given the inclusion of North Yorkshire, people just like countryside. That would seem to be supported by the fact that...


Nobody really likes the metropolitan counties

Greater London was stitched together in 1965. Nine years later, more new counties were created to cover the metropolitan areas of Manchester, Liverpool (Merseyside), Birmingham (the West Midlands), Newcastle (Tyne&Wear), Leeds (West Yorkshire and Sheffield (South Yorkshire). Actually, there were also new counties covering Teesside (Cleveland) and Bristol/Bath (Avon), too, but those have since been scrapped, so let’s ignore them.

Not all of those seven counties still exist in any meaningful governmental sense – but they’re still there for ’ceremonial purposes’, whatever that means. And we now know, thanks to this poll, that – to the first approximation – nobody much likes any of them. The only one to make it into the top half of the ranking is West Yorkshire, which comes 12th (75 per cent approval); South Yorkshire (66 per cent) is next, at 27th. Both of those, it may be significant, have the name of a historic county in their name.

The ones without an ancient identity to fall back on are all clustered near the bottom. Tyne & Wear is 30th out of 47 (64 per cent), Greater London 38th (58 per cent), Merseyside 41st (55 per cent), Greater Manchester 42nd (53 per cent)... Not even half of people like the West Midlands (49 per cent, placing it 44th out of 47). Although it seems to suffer also from the fact that...

Everybody hates the Midlands

Honestly, look at that map:

 

Click to expand.

The three bottom rated counties, are all Midlands ones: Leicestershire, Northamptonshire and Bedfordshire – which, hilariously, with just 40 per cent approval, is a full seven points behind its nearest rival, the single biggest drop on the entire table.

What the hell did Bedfordshire ever do to you, England? Honestly, it makes Essex’s 50 per cent approval rate look pretty cheery.

While we’re talking about irrational differences:

There’s trouble brewing in Sussex

West Sussex ranks 21st, with a 71 per cent approval rating. But East Sussex is 29th, at just 65 per cent.

Honestly, what the fuck? Does the existence of Brighton piss people off that much?

Actually, we know it doesn’t because thanks to YouGov we have polling.

No, Brighton does not piss people off that much

Click to expand.

A respectable 18th out of 57, with a 74 per cent approval rating. I guess it could be dragged up by how much everyone loves Hove, but it doesn’t seem that likely.

London is surprisingly popular

Considering how much of the national debate on these things is dedicated to slagging off the capital – and who can blame people, really, given the state of British politics – I’m a bit surprised that London is not only in the top half but the top third. It ranks 22nd, with an approval rating of 73 per cent, higher than any other major city except Edinburgh.

But what people really want is somewhere pretty with a castle or cathedral

Honestly, look at the top 10:

City % who like the city Rank
York 92% 1
Bath 89% 2
Edinburgh 88% 3
Chester 83% 4
Durham 81% 5
Salisbury 80% 6
Truro 80% 7
Canterbury 79% 8
Wells 79% 9
Cambridge 78% 10

These people don’t want cities, they want Christmas cards.

No really, everyone hates the Midlands

Birmingham is the worst-rated big city, coming 47th with an approval rating of just 40 per cent. Leicester, Coventry and Wolverhampton fare even worse.

What did the Midlands ever do to you, Britain?

The least popular city is Bradford, which shows that people are awful

An approval rating of just 23 per cent. Given that Bradford is lovely, and has the best curries in Britain, I’m going to assume that

a) a lot of people haven’t been there, and

b) a lot of people have dodgy views on race relations.

Official city status is stupid

This isn’t something I learned from the polls exactly, but... Ripon? Ely? St David’s? Wells? These aren’t cities, they’re villages with ideas above their station.

By the same token, some places that very obviously should be cities are nowhere to be seen. Reading and Huddersfield are conspicuous by their absence. Middlesbrough and Teesside are nowhere to be seen.

I’ve ranted about this before – honestly, I don’t care if it’s how the queen likes it, it’s stupid. But what really bugs me is that YouGov haven’t even ranked all the official cities. Where’s Chelmsford, the county town of Essex, which attained the dignity of official city status in 2012? Or Perth, which managed at the same time? Or St Asaph, a Welsh village of 3,355 people? Did St Asaph mean nothing to you, YouGov?

Jonn Elledge is the editor of CityMetric. He is on Twitter as @jonnelledge and on Facebook as JonnElledgeWrites.

Want more of this stuff? Follow CityMetric on Twitter or Facebook.

*A YouGov employee I met in a pub later confirmed this, and I make a point of always believing things that people tell me in pubs.