#Self-driving - Cars of the Future

Vivacity Labs founder backs the citizen first vision of 21st century privacy.

Time for a grown-up conversation about cameras, AI, traffic flow and privacy

Our Zenzic CAM Creator series continues with the founder of Vivacity Labs, Mark Nicholson.

Vivacity uses sensors, cameras and artificial intelligence (AI) to provide “up-to-the-minute data on urban movement”, helping local councils to promote active travel, improve safety and reduce congestion. Big Brother you say? Well, it’s 2020 not 1984 and CEO Mark Nicholson is very happy to have that debate.

MN: “As the transport network becomes more complicated, local authorities need more powerful tools. Tech giants have invaded the ecosystem, and when you’re dealing with Uber and driverless cars, sending someone out with a clipboard just isn’t going to cut it. We bring new technology which tells them about their transport, so they can adapt and gain control over the ecosystem.

“We started with sensors and then video-based sensors, generating huge data sets and better quality data. We’ve looked at everything from cyclists undertaking to lockdown journey times and asked: how can we use this data to make the road system more efficient? The next phase is autonomous vehicles, because that ecosystem needs to work with both infrastructure and other road users.

“Privacy is not just a key issue in self-driving but in the whole smart city. There are basically two visions – the Chinese and the European. The Chinese vision is very invasive, it’s 1984 and that’s the point. The alternative is the European vision, with the General Data Protection Regulation (GDPR). For a while it looked like there might be a third, a corporate American vision. Google were running a smart city project in Canada, but it didn’t work out so we’re back to two models.”

If you don’t know about the Quayside project in Toronto, a much-shared Guardian article from 2019 warned of surveillance capitalism, data harvesting and the possibility that algorithms could be used to nudge behaviour in ways that favour certain businesses. You can read it here or, er, Google it.

MN: “We’re very much on the European, privacy-centric, citizen first side – an ecosystem that gives the benefits of mass data without the costs to privacy. All our data is anonymised at source, everything. Each camera or sensor unit has its own processor on board which uses AI to extract information, for example, what are the road users? The imagery is discarded within a few milliseconds, all we keep is the data. We recently looked at how socially distanced people were in Kent and, although no personal data was collected, it caused a bit of controversy.”

It did indeed. “Big Brother is watching your social distancing: Fury as traffic flow cameras are secretly switched to monitor millions of pedestrians in government-backed Covid project”, screamed the headline in the Daily Mail. We’d better get back to self-driving.

MN: “Over the last couple of years the hype around driverless cars has died down. There’s been a recognition that autonomous vehicles are not as close as Elon Musk promised. The technology is progressing though. They can drive quite well on motorways and in quiet areas, but in busy, congested areas they struggle.

“What would happen if you rolled out driverless cars today? My suspicion is they would probably perform to about the same level as human drivers. The question is: Are we happy with systemic risk rather than personal risk? Can we engineer out that risk? Can we make the infrastructure intelligent enough so it works with vehicles in even the most challenging situations?

“The best way to end the no-win scenario is to have enough data to dodge it. Most of these incidents come about due to an unforeseen element, such as a pedestrian stepping out, a cyclist skipping a red light or someone speeding round a corner. If the vehicle knows about it in advance, the trolley problem never occurs. For me it’s about having the data earlier, and how we, as representatives of infrastructure, can help to give cars that information.”

For further info, visit vivacitylabs.com.

Bold predictions about our driverless future by petrolhead Clem Robertson.

Meet the maverick radar expert of UK drones and driverless

Welcome to a new series of interviews with our fellow Zenzic CAM Creators. First up, Clem Robertson, CEO of R4dar Technologies.

As a keen cyclist who built his own Cosworth-powered Quantum sportscar from scratch, it’s no surprise that the founder of Cambridge-based R4dar takes a unique approach to self-driving. Indeed, his involvement can be traced directly to one shocking experience: driving down a local country lane one night, he had a near miss with a cyclist with no lights. He vividly remembers how a car came the other way, illuminating the fortunate rider in silhouette and enabling an emergency stop. It proved to be a light bulb moment.

What does R4dar bring to connected and automated mobility (CAM)?

CR: “I’d been working in radar for five or six years, developing cutting edge radar for runways, when the incident with the cyclist got me thinking: Why could my cruise control radar not tell me something was there and, importantly, what it was? This kind of technology has been around for years – in World War II we needed to tell the difference between a Spitfire and a Messerschmitt. They placed a signal on the planes which gave this basic information, but things can be much more sophisticated these days. Modern fighter pilots use five different methods of identification before engaging a potential bogey, because one or more methods might not work and you can’t leave it to chance whether to blow someone out of the sky. The autonomous vehicle world is doing similar with lidar, radar, digital mapping etc. Each has its shortcomings – GPS is no good in tunnels; the cost of 5G can be prohibitive and coverage is patchy; cameras aren’t much good over 100 metres or in the rain, lidar is susceptible to spoofing or misinterpretation; digital maps struggle with temporary road layouts – but together they create a more resilient system.”

How will your solutions improve the performance of self-driving cars?

CR: “Radar only communicates with itself, so it is cyber-resilient, and our digital tags can be used on smart infrastructure as well as vehicles – everything from platooning lorries to digital high vis jackets, traffic lights to digital bike reflectors. They can tell you three things: I am this, I am here and my status is this. For example, I’m a traffic light up ahead and I’m going to turn red in 20 seconds. Radar works in all weathers. It is reliable up to 250-300m and very good at measuring range and velocity, while the latest generation of radars are getting much better at differentiating between two things side-by-side. We are working with CAM partners looking to use radar in active travel, to improve safety and traffic management, as well as with fleet and bus operators. We are also working with the unmanned aerial vehicle (UAV) industry to create constellations of beacons that are centimetre-accurate, so that delivery drones can land in a designated spot in the garden and not on the dog!”

What major developments do you expect over the next 10-15 years?

CR: “Fully autonomous vehicles that don’t carry passengers will come first. There are already little robots on the streets of Milton Keynes and, especially with Covid, you will see a big focus on autonomous last mile delivery – both UAVs and unmanned ground vehicle (UGVs). You never know, we might see delivery bots enacting a modern version of the computer game Paperboy. More and more people in urban areas with only roadside parking will realise that electric cars are tricky to charge, unless you put the chargers in the road, which is expensive. If you only need a car one or two days a month, or even for just a couple of hours, there will be mobility as a service (MAAS) solutions for that. Why would you bother with car ownership? E-scooters are one to keep an eye on – once they’re regulated they will be a useful and independent means of getting around without exercising. Town centres will change extensively once MAAS and CAM take off. There will be improved safety for vulnerable road users, more pedestrianisation, and you might see segmented use at certain times of day.”

Do you see any downsides in the shift to self-driving?

CR: “Yes! I love driving, manual gearboxes, the smell of petrol, the theatre, but you can see already that motorsport, even F1, is becoming a dinosaur in its present form. People are resistant to change and autonomous systems prompt visions of Terminator, but it is happening and there will be consequences. Mechanics are going to have less work and will have to retrain because electric motors have less moving parts. Courier and haulage driving jobs will go. Warehouses will be increasingly automated. MAAS will mean less people owning their own cars and automotive manufacturers will have to adapt to selling less vehicles – it’s a massive cliff and it’s coming at them much faster than they thought – that’s why they’re all scrambling to become autonomous EV manufacturers, it’s a matter of survival.”

So, to sum up….

CR: “Fully autonomous, go-anywhere vehicles are presented as the utopia, but there’s a realisation that this is a difficult goal, or at least a first world problem. There might always be a market for manned vehicles in more remote locations. A lot of the companies in this industry specialise in data, edge processing and enhanced geospatial awareness, and that will bring all kinds of benefits. How often have you driven in fog unable to see 10m in front of you? Self-driving technology will address that and many other dangers.”

Hearing bold predictions like these from a petrolhead like Clem, suddenly Zenzic’s ambitious 10-year plan seems eminently achievable.

For further info, visit the R4dar website.

In an explosive exclusive interview with Cars of the Future, transport expert Christian Wolmar presents a devastating critique of the self-driving dream.

Are driverless cars the future? Don’t believe the hype says Wolmar

As an arch critic of the UK’s autonomous vehicle plans, transport commentator Christian Wolmar sums up his views in the title of his book, Driverless Cars: On a Road to Nowhere.

“The problems are almost too great to list, but my primary concerns are two-fold: technological and environmental,” he says. “There are huge worries about rushing into it, cutting corners which might result in accidents and deaths, as they already have.

“Then there’s a bigger issue: what is the positive outcome? I just don’t see it. People are not asking for it, it doesn’t solve problems such as congestion or pollution, yet huge amounts of money are going into it with almost no return.

“The technology can be hacked. There’s the risk of deskilling drivers with the adoption of more automated driving aids, then expecting them to take over in the event of an emergency. The more you look at the driverless vision, the more dystopian it appears.”

At this point, Wolmar casually mentions a host of other potential pitfalls concerning legality, privacy, practicality. You get the picture. He’s not a fan. Following this initial brutal attack on the foundation stones of the self-driving dream, he quickly covers off some popular retorts.

“The argument goes that driverless cars will help the blind and others who can’t drive, but logically this must mean more cars on the road and therefore more congestion,” he says. “The response is “ah, no, because there will be shared use”, but there’s no evidence that people want that. It isn’t a realistic concept, but even if we get there it will not be a good place.”

So why are governments, vehicle manufacturers and tech companies so obsessed with it? “The proponents of driverless have managed to create a climate in which the public and politicians think it is inevitable, but it isn’t,” he says.

“After 12 years of testing robotaxis in sunny climates on nice wide geofenced highways you still have to sign a nondisclosure agreement to get in one! The developers are driven by fear that someone else will make the technology work and become the market leader, but everything points to the fact that this is a technological dead end. Like Concorde, lots of great ideas have floundered.”

Finally, Wolmar relents briefly from his devastating critique. “There may be some limited uses such as airport transit,” he admits. “It’s a bit like the moon landing, some great technologies will come out of it. Indeed, if you speak to people at trade shows, a lot of them are very skeptical about driverless ever becoming a dominant technology. They already have successful businesses supplying cameras or software or lidar, and that’s where their interest lies.

“Outside of the industry, many think driverless cars are already available to buy. It is pure hype. They don’t exist. Headlines in the media claim driverless cars can do this or that, and then in paragraph five it says there’s a safety driver.

“You saw it with covid and the supposed benefits of driverless delivery. If anything, the impact of the pandemic on driverless was to completely undermine the shared use argument, which is vital to the business case. Coronavirus, and whatever comes after it, is as much a problem for shared use as it is for public transport.”

So, what’s Wolmar’s preferred solution? “The approach must be different for each town or city, but urban areas are not suitable for the unregulated use of private cars,” he says. “You have to recognise that road space is a limited asset, to do otherwise is bad economics. This is not a war on the motorist. There will be cars of the future, but cars in their proper place, particularly rural areas.”

Driverless Cars: On a Road to Nowhere second edition (2020)

For more detailed analysis (and scathing criticism), the second edition of Wolmar’s book “Driverless Cars: On a Road to Nowhere” is out now via London Publishing Partnership priced at £9.99. Alternatively, email christian.wolmar@gmail.com or visit www.christianwolmar.co.uk.

Given how quickly they’ve revolutionised the motor industry, who’s to say Tesla won’t also win the race to driverless?

Fully autonomous by 2023? Tesla leads the charge to self-driving cars

2020 has been an epic year for Tesla. While virtually every other vehicle manufacturer continues to build petrol, diesel and hybrid cars, Elon Musk’s commitment to pure electric has paid off handsomely.

Back in February, the Model 3 was named UK Car of the Year. By July, a share price surge had made Tesla the world’s most valuable car company, worth a staggering $208bn, overtaking Toyota (on $203bn) and miles ahead of Volkswagen ($74bn), General Motors ($36bn) and Ford ($24bn).

Since 2016, with the introduction of the Autopilot Hardware 2 package, Tesla has made ever bolder claims about full self-driving. “It’s almost getting to a point where I can go from my house to work with no interventions,” boasted Musk this summer.

Such remarks have drawn stinging criticism. “Tesla has repeatedly rolled out crude beta features, some of which can put people’s safety at risk and shouldn’t be used anywhere but on a private test track,” said William Wallace, manager of safety policy for Washington-based Consumer Reports.

Not so long ago, rival carmakers were similarly dismissive of battery power. What they’d give to be as desirable as Tesla now!

Last week, as part of his 2020 annual shareholder meeting (and much-publicised #BatteryDay), Musk laid down an ambitious new marker: “I think probably like in about three years from now, we’re confident we can make a very competent, very compelling $25,000 electric vehicle that’s also fully autonomous,” he said.

Given how quickly they’ve revolutionised the industry, who’s to say Tesla won’t also win the race to driverless?

Driverless delivery vehicle maker Nuro gets billion-dollar boost

Whenever anyone spends a billion dollars in the self-driving world it is probably worthy of a mention here.

In this case, unmanned delivery vehicle specialist, Nuro, has been boosted by a US$940m investment from Japanese multinational, SoftBank.

Founded in 2016 by two former Google engineers, Dave Ferguson and Jiajun Zhu, Nuro operates mainly in San Francisco but plans to expand its delivery service to new areas, add new partners and expand its fleet.

“We’ve spent the last two and a half years building an amazing team, launching our first unmanned service, working with incredible partners and creating technology to fundamentally improve our daily lives,” said Ferguson.

“This partnership gives us the opportunity to take the next step in realizing our vision for local commerce and the broad application of our technology.”

Nuro’s other backers include Greylock Partners and Gaorong Capital.

Must-see video: new driverless cars world record set in China

Guinness World Records has posted this video of what is officially now the largest parade of autonomous cars ever:

55 self-driving cars built by Changan Autmobile set the record at the Dianjiang test site in Chongqing, China, on 28 November 2018.

Design Boom reported that a 56th car was disqualified after the safety driver briefly took back control of the vehicle.

Must-see video: VR world enables billions of driverless test miles

Having made its name in gaming graphics, it should come as no surprise that Nvidia has created an autonomous vehicle (AV) simulator – a computer platform which enables developers to design a near-infinite variety of conditions and scenarios for driverless cars.

The US tech giant (which already has links with manufacturers including Audi, Mercedes, Tesla, Toyota, Volvo and VW) says its new Drive Constellation will help the global automotive industry to drive billions of test miles safely in virtual reality.

In another notable move, Nvidia recently announced a joint initiative with the government of Luxembourg to create a national artificial intelligence (AI) laboratory.

“Luxembourg is nurturing a pan-European innovation ecosystem,” said Prime Minister Xavier Bettel. “This cooperation is big news for our local innovators, and our country is proud to be the first European country to create an AI partnership with Nvidia.”

UK plans ‘advanced’ driverless car road trials… meaning no safety driver

Driverless cars are a hot topic in the UK today (6 February 2019) thanks to a Government announcement on “advanced trials for self-driving vehicles”.

Stories ran in most of the biggest-selling newspapers focusing on the removal of the requirement for a safety driver. Actually, all the Department for Transport (DfT) committed itself to was to develop a process to help support advanced trials of automated vehicles.

Automotive Minister, Richard Harrington, said: “We need to ensure we take the public with us as we move towards having self-driving cars on our roads by 2021. The update to the code of practice will provide clearer guidance to those looking to carry out trials on public roads.”

The door to the removal of safety drivers is opened in point 1.4 of the introduction, on page 5 of the newly updated Code of Practice: Automated vehicle trialling (pictured).

It states that: “The Government acknowledges the desire to conduct advanced trials on public roads. Such trials may not readily fit within current UK legislation, so the Department for Transport’s motoring agencies will introduce and operate a process to support those looking to safely conduct advanced trials.”

The DfT emphasised that the Centre for Connected and Autonomous Vehicles (CCAV) must be informed in advance and trials would not be supported unless they pass rigorous safety assessments.

So, what have we learnt? That “advanced trials” in this context is broadly a euphemism for road tests without a safety driver, and that the timetable for implementation is ambitious: “for self-driving cars on our roads by 2021”.

With the lack of clarity around The driverless dilemma: who to save in no-win crash situations and a plethora of other unresolved issues, there is much to debate.

The fact is today’s announcement brings us closer to having driverless cars on UK roads.

A dystopian vision of polluted London

Recycling company First Mile has released this striking image of how London’s Oxford Street could look if we fail to tackle air pollution.

Two technologies being championed to avoid such a dystopian fate are electric powertrains and route optimisation programmes – both popular concepts in connected and autonomous vehicle (CAV) design.

However, new research by Adam Millard-Ball, associate professor of environmental studies at the University of California, suggests that, rather than solving the issue of congestion in city centres, self-driving cars could exacerbate the problem, creating gridlock.

“Parking prices are what get people out of their cars and on to public transit, but autonomous vehicles have no need to park at all,” he said. “They can get around paying for parking by cruising. They will have every incentive to create havoc.”

According to Interesting Engineering, his paper, The Autonomous Vehicle Problem, estimates that just 2,000 self-driving vehicles in the San Francisco area will slow traffic to less than 2mph – a nightmare scenario.

Telematics combined with smart congestion charging could conceivably negate this undesirable impact, but the study is grist to the mill for those advising stricter regulation of driverless cars.

Driverless river transport: the roboat

We profiled various “other driverless vehicles” in our recent bikes, trucks, bots and planes article, well here’s another one… and it has a great name: the roboat.

So far, only small prototypes have been deployed but a bigger model with a 6x13ft hull is in development, featuring GPS, water quality testers, cameras and LIDAR.

The robotic boat is the result of a five-year research project – a collaboration between the Massachusetts Institute of Technology (MIT) and the Amsterdam Institute for Advanced Metropolitan Solutions (AMS).

Carlo Ratti, of MIT’s senseable city lab, envisages a new kind of on-demand infrastructure – autonomous platforms joining together to form floating bridges or stages, as well as individual roboats being able to deliver goods, transport people or collect waste.

This 1min 43sec video gives an overview of the project to date:

Looking ahead, the team will concentrate on finding ways to account for waves, currents, more passengers and heavier cargos.