Neil Kennett - Cars of the Future

The key to the future of self-driving is education, education, education, says Millbrook’s Stoker.

On track and in virtual space, Millbrook tests cars of the future

Our Zenzic CAM Creator series continues with Peter Stoker, Chief Engineer for Connected and Autonomous Vehicles at Millbrook.

Part of CAM Testbed UK, Millbrook Proving Ground in Bedford boasts 700 acres of private roads on which to develop and test connected and autonomous vehicle (CAV) technologies. As Chief Engineer, Peter Stoker is right at the forefront of self-driving in the UK.

Please can you outline Millbrook’s work on connected and automated mobility?

“My primary role is to bring focus to two testbeds, our CAV testbed and our 5G testbed. We are not a purpose-built CAV testbed – we have safety, propulsion and conventional vehicle test facilities too – so CAV is something we’ve blended into the existing business.

“For the CAV testbed, we partnered with the UK Atomic Energy Authority (UKAEA), particularly the Remote Applications in Challenging Environments (RACE) division, to provide a controlled urban environment. We have three open source StreetDrone vehicles and miles of track with targets for very precise measurements, accurate to 1-2cm. We offer safety driver training and also have a simulation environment for driver-in-the-loop and hardware-in-the-loop testing. The whole idea is to fail in private, not in public, and to progress, to evolve out of the testbeds and on to open roads.

“The 5G testbed is a completely separate consortium, backed by the Department for Digital, Culture, Media and Sport (DCMS). We have 59 masts looking at all types of connectivity and I’d say the millimetre wave at 70GHz is currently the most interesting.”

Millbrook graphic — Millbrook Proving Ground graphic

What major shifts in UK road transport do you expect over the next 10 years?

“Getting the crystal ball out, I see increased use of connectivity in existing vehicles and some very interesting new use cases – buses connected to city networks, video analytics from cameras, smart ambulances streaming live data, autonomous deliveries on campuses. What I don’t see within 10 years is millions of privately owned driverless cars. That will start in the luxury sector but to begin with it will be more about transporting goods.”

How do you see the testing framework for CAVs developing?

“There’s a lot of simulation in the automotive world – crash testing, fatigue testing, computational fluid dynamics. These days, manufacturers are developing whole vehicles before building a prototype. You have to have a good simulation on a good simulator and there’s an interesting shift that needs to happen on regulation. It’s early days on that, but it’s essential.

“The strength of virtual space is that you can run hundreds of scenarios in machine time – not only set up complicated scenarios that would take days with real cars, but actually speed up the process so it runs faster than real time. The national scenario database is already really good and regulation will move to being a mixture of real and virtual certification – global, European, UK and perhaps even city-specific. We are happy to advise, but don’t set policy.”

What are the biggest challenges in the shift to self-driving and how can these risks be mitigated?

“The key to the future of self-driving is education, education, education – for everyone, the public, vehicle manufacturers, the aftermarket, recovery operators. We have to work on the terminology – autonomous, driverless, CAV, CAM – it’s confusing, even to people who know what they’re talking about.

“At the moment, we’re making it harder to understand, not easier. We’re in a really grey area of transition with different trade names for systems. There’s a lot of groundwork needed to prepare people and, for example, the brilliant website mycardoeswhat.org does a great job of trying to explain it.

“If you get into a hire car, you need to have the right expectation of what it does and what it doesn’t do. If you buy a new car, you should read the manual, but how many people do? Especially with Covid, more cars are being delivered with minimal interaction – it’s a case of “there’s the key, where’s the station?”. Too often, the customer handover just isn’t there.

“How are garages, the aftermarket and the amber light sector going to deal with all this? Basic questions like how do you put it in neutral? ADAS has already led to huge changes in training and skill sets – how to calibrate and monitor them.

“We haven’t talked about over-the-air (OTA) updates, cameras embedded in the tarmac or even electrification – there’s a huge amount of things! How do you learn about them? Hopefully in testing rather than in crash situations.”

For further info, visit www.millbrook.co.uk

IPG expert says simulations can be better than real world testing.

The road to self-driving: Vehicle Certification Agency urged to accept simulation

Our Zenzic CAM Creator series continues with Elliot Hemes and Will Snyder of IPG Automotive UK.

Chartered engineer and self-proclaimed simulation evangelist, Elliot Hemes, previously worked in global product marketing at Jaguar Land Rover (JLR), covering future automotive trends. Now managing director at IPG Automotive UK, he works with big-hitters including Ford and JLR to provide virtual test driving environments. Here, in discussion with IPG Automotive sales engineer Will Snyder, he explains how simulation will be vital for the shift to self-driving.

EH: “As vehicle systems become more complex and interconnected, we ensure that manufacturers can virtually test their systems in realistic traffic situations, using an approach that is quick and accurate.”

WS: “IPG Automotive started in vehicle dynamics, then advanced driver assistance (ADAS) was the next big thing, now it is autonomous vehicles (AVs). The amount of testing required to achieve true autonomy is impossible to do in the real world. I believe we will get to Level5 autonomy, but there are some big hurdles such as accounting for human drivers in other vehicles – it would be much easier if every vehicle on the road was autonomous and connected.”

EH: “We might see it first in a city environment, restricted to less than 20mph. People put up lots of reasons why full autonomy can’t happen, but a blanket statement of “it’s too hard” just isn’t good enough. You could say, for example, you can’t use the M6 Toll unless you have vehicle-to-vehicle (V2V) communications. That would enable platooning – if one vehicle brakes, they all know about it. 99% of the time, great brakes will get you out of trolley problem scenarios.”

WS: “You cannot say AVs will never crash. The question should be: are they safer than human drivers? And the answer is yes, they definitely will be. When people talk about ADAS deskilling drivers, my response is: what skills?! It is well proven that concentration is badly affected by holding a conversion with someone else in the car, let alone fiddling with the radio or holding a hands-free phone call. We all get defensive about our driving prowess, but it needs to be recognised that the bar for driving is very low. You don’t even learn how to drive on a motorway – that’s not part of the driving test, which is one reason you get so many middle lane sitters.”

EH: “At the moment none of the major vehicle manufacturers are taking the leap to level 4/5, partly because they’re worried about litigation. Once the legislation is in place you will see truck platooning very quickly because of the enormous cost savings. It will require vehicle-to-everything (V2X) and V2V communications. The current ADAS technology is great but the systems are very digital and can have issues with poor light and bad weather. It will improve over time.”

WS: “We could even skip Level 3 as it is safer to move straight to Level4. In my opinion, the driver needs to be either active or not – expecting them to retake control in time in an emergency situation is just not realistic.”

EH: “Over the next decade you will see the gradual adoption of ADAS technologies. Adaptive cruise control (ACC) will become standard and that will avert so many crashes, particularly rear-end shunts. It doesn’t take away from the driver, it just intervenes. However, there is a concern about the performance of these systems in low light conditions – we need much more focus on the edge cases.

“OEMs engineer to perfect Euro NCAP test conditions. In the real world, what happens if the sun is low in the sky, or the pedestrian steps out more quickly? You cannot practically test these kinds of things on a track, which is why you have simulations. You can study that edge case over and over. We’ve had customers ask us to recreate exactly the same environment as the test track, including noise that’s nothing to do with the question in hand. Our advice is not to try to simulate the real world – design the simulation to study exactly the question you want to answer.

“In this way simulation can be better than the real world. Say, for example, you want to test a pedestrian Autonomous Emergency Braking (AEB) function in the early stage of development. You just want to know if, in the CarMaker environment, it performs the right output – applying enough braking to stop before it hits the dummy pedestrian. The next step is to put that software into an ECU. You can do all that with hardware-in-the-loop testing, improving the capability step-by-step without building a prototype vehicle or driving billions of real-world miles.

“Further still, under heavy braking, the front camera might well point to the floor, maybe the car might start to drift. You can do all that in simulation, to prove that your algorithms hold up and the car does what you think it will do.”

WS: “Another problem with running prototype vehicles on test tracks is that you spend an awful lot of time fixing thousands of other small faults before you get on with what you’re supposed to be testing. We can get all these edge cases done before you get to the test track. By using simulations you get so much more out of the valuable test track time.”

EH: “The ‘systems engineering V’ has all the theoretical stuff on the left, then hardware on the right and validation at the top. Ideally we’ll get to the stage where only validation happens in the physical world. Until the homologation and certification authorities are able to accept simulation results you can’t do enough testing to get AVs on the road. That’s why it is such a vital part of the Zenzic CAM Roadmap.”

For further info, visit ipg-automotive.com

The UK’s National Physical Laboratory is working on a framework for virtual sensor testing.

Developing test frameworks which build a bridge of trust to driverless cars in the UK

Our Zenzic CAM Creator series continues with Andre Burgess, digital sector strategy leader at the National Physical Laboratory (NPL).

NPL is the UK’s National Metrology Institute, responsible for developing and maintaining the national primary measurement standards. For over a century, it has worked to translate scientific expertise into economic prosperity, skilled employment and improved quality of life, covering everything from cancer treatments to quantum computing. In the self-driving sector, Andre Burgess’s focus is test frameworks to support the deployment of safe and reliable autonomous transport on land, sea and air.

Andre Burgess, digital sector strategy leader at NPL.

AB: “We’re all about measurement and how it can be applied to the autonomous vehicle space. Artificial intelligence (AI) and machine learning represents a great transformation. Whereas in the past we’ve developed tests for whether a human is fit to do something, in this new world we need a new set of tests to assure autonomous systems and build a bridge of trust. This is not a one-off test, it is ongoing work to develop new methodologies and support the development of new standards.

“One of the key things this country has developed is Testbed UK, a collaboration between government and industry which has delivered a formidable testing environment – a network of safe, highly controlled environments increasingly linked to virtual testing.

“Working with the Met Office on behalf of the Centre for Connected and Autonomous Vehicles (CCAV) over the last year we have focused on the usability and reliability of sensors in different weather conditions. How do you know if sensors are performing well? How do you validate the decision making? How do you apply metrics and KPIs to this? Having undertaken a proof of concept for a testing framework, we are confident this can be delivered and deployed throughout the industry.

“There is much talk about pass/fail tests but our focus is confidence, improving confidence in the outputs and building confidence in the system. We collaborate across the board, with regulators, testers, developers – engaging with them to understand their requirements. Our approach is to provide tools which help reduce the barriers to innovation without compromising regulation and safety assurance. Striking the right balance between reliability and usability is key. Our work will support validation and help the UK to influence international standards.

“The biggest transformation in road transport over the next decade will be emissions reduction and self-driving vehicles and smart mobility systems will be key drivers. It will require changes to infrastructure and changes in habits – batteries or hydrogen will be critical, perhaps a need to drive more slowly, maybe less private car ownership. The impact of Covid has led to a move away from trains and buses, so a resurgence of public transport is vital.

“In terms of self-driving, I envisage there will be personally driven vehicles and on-demand vehicles. Increasingly I expect we’ll see a transition into smaller public transport vehicles, perhaps for 8-10 people, in continuous use. There’s real value in getting to places that don’t have bus stops and there’ll be benefits from autonomous safety features too. It won’t be everywhere but I hope within 10 years there’ll be good examples of that in the UK. The question is will we be ahead or behind the curve? In some more authoritarian countries implementation might be faster but maybe not better.

“We’ll also start to see autonomous low level aviation and autonomous shipping, for example, short cargo sea freight. Combined, these things will make roads less congested. Key transport stakeholders have expressed the need to integrate, to pursue the most efficient way to get goods into and around the UK.

“For our part, we are focused on the framework for virtual sensor testing, and also integration between virtual and physical testing. To give an accurate level of confidence requires understanding the common metrics and the areas of uncertainty. The human factor is so important, for example, what about the people with cars that don’t have this tech – how do they respond?”

For further info visit www.npl.co.uk.

Autonomous vehicle software specialist set to become a major UK success story.

Oxbotica secures huge BP investment and targets anything that moves people or goods

Oxford University spin-out, Oxbotica, has been on our must-speak-to list for a while, and on Friday we got some Zoom time with the top people – CEO, Ozgur Tohumcu, and co-founder and CTO, Professor Paul Newman.

It’s three weeks since the autonomous vehicle software specialist announced a US$47m Series B investment led by bp ventures. Yes, that BP. The press release asserts that this will accelerate the deployment of Oxbotica’s platform “across multiple industries and key markets”, but Prof. Newman is quick to emphasise this is not about robotaxis, not even about cars.

Prof Paul Newman, Oxbotica co-founder and CTO.

“We’ve been deploying our software in industrial settings – mines, airports – for six years now, and not only in the UK, in Europe, North America, Australia,” he says. “Everyone talks about cars but all vehicles are game for us – anything that requires moving people or goods. That’s the advantage of being pure software.

“We’re a global business and raising this kind of money during a pandemic speaks volumes. We have clear water behind and blue sky ahead. Having these new investors and strategic partners will really allow us to drive home the opportunities that came last year. Vehicles are common but software of our standard is not. We’re showing that great IP can be generated everywhere, not just Silicon Valley, and that’s very refreshing.”

While Prof. Newman focuses on the vision, Tohumcu provides the detail. “Since the funding announcement, the exchange rate means it’s actually worth closer to $50m, so that’s not bad,” he says. “We’ve just conducted a review of the business and it was pleasing to see that we achieved exactly what we said we’d do two years ago – delivering results against measurable goals.

“We’ve done a lot of planning recently – some well-defined, other things we’re still making choices about. We’ve been approached by new companies interested in using our tech and there are exciting deals in the pipeline, deals that come with investment. We’ll be making further announcements over the coming weeks and months.”

Make no mistake, Oxbotica is set to become a major UK success story… just don’t mention driverless cars!

Humanising Autonomy uses behavioural psychology and computer algorithms to make cities safer for pedestrians and cyclists.

Using cameras and AI to protect vulnerable road users

Our Zenzic CAM Creator series continues with Raunaq Bose, co-founder of Humanising Autonomy.

Before establishing predictive artificial intelligence (AI) company Humanising Autonomy in 2017, Raunaq Bose studied mechanical engineering at Imperial College London and innovation design engineering at the Royal College of Art. Focusing on the safety of vulnerable road users, Humanising Autonomy aims to redefine how machines and people interact, making cities safer for pedestrians, cyclists and drivers alike.

RB: “Our model is a novel mix of behavioural psychology, deep learning and computer algorithms. We work with OEMs and Tier 1 suppliers on the cameras on vehicles, with the aftermarket on retrofitted dashcams, and also with infrastructure. Our software works on any camera system to look for interactions between vulnerable road users, vehicles and infrastructure in order to prevent accidents and near misses. While most AI companies use black box systems where you can’t understand why decisions are made, we set out to make our models more interpretable, ethically compliant and safety friendly.

“When it comes to questions like ‘Is this pedestrian going to cross the road?’, we look at body language and factors like how close they are to the edge of the pavement. We then put a percentage on the intention. Take distraction, for example, we cannot see it but we can infer it. Are they on the phone? Are they looking at the oncoming vehicle? Is their view blocked? These are all behaviours you can see and our algorithm identifies them and puts a numerical value on them. So we can say, for example, we’re 60% sure that this pedestrian is going to cross. This less binary approach is important in building trust – you don’t want lots of false positives, for the system to be pinging all the time.

“One of the main things we’re likely to see over the next decade is increased use of micromobility, such as cycling and e-scootering. At the same time you will see more communication between these different types of transportation, and also with vehicles and infrastructure. The whole point of ADAS is to augment the driver’s vision, to reduce blind spots and, if necessary, take control of the vehicle to avoid a shunt. Then there’s the EU agreement that by 2022 all buses and trucks must have safety features to detect and warn of vulnerable road users.

“We currently only look at what’s outside the vehicle, but with self-driving there will be monitoring of the cabin. In terms of privacy, we have a lot of documentation about our GNPR processes and how we safeguard our data. Importantly, we never identify people, for example, we never watch for a particular individual between camera streams. We look to the future with autonomous cars but for now we’re focused on what’s on the road today.”

For further info visit humanisingautonomy.com.

UK government sparks global business sharing transport sector data.

Sharing data collected by connected cars

Our Zenzic CAM Creator series continues with Mika Rasinkangas, founder and President of Chordant.

Originally part of the global wireless and internet of things (IoT) research company, InterDigital, Chordant was spun out as a separate business in 2019, as “a dynamic data sharing expert”. The spark was a UK government initiative to test the hypothesis that regional transportation data has tremendous value, especially when shared between different parties. The results of this two-year public-private partnership were startling.

Please can you outline your work on connected and automated mobility?

MR: “First of all we looked at the mobility space. There’s the segment that maintains the road network and their supply chain, the mobility service providers – bus companies, train operators and new entrants such as Uber – then the whole automotive sector, OEMs and their supply chain partners. We sit right in the middle of all this and our role is data exchange – bringing dynamic data sets from different sources to come up with something different that solves problems with data driven solutions.

“The hypothesis was that a lot of data in the transport segment was either underutilised, in really small silos, or not utilised at all. The idea was to work with different entities – organisations, companies and universities – to bring data together and make it more widely available, leading to innovation and efficiency.

“It was obvious from early on that this was not only a technical issue, there was a human element. Data is controlled by different entities and departments so the challenge was to get these different data owners comfortable with the idea that their data could be used for other purposes, and to get consumers comfortable with it too. The result was more usable and more reliable dynamic data.”

What major shifts in UK transport do you expect over the next 10-15 years?

MR: “Last mile transport, micromobility solutions are ballooning and Covid19 will only accelerate this. People are walking, scootering and biking more, making short trips by means which don’t involve public transport or being in close contact to others.

“In terms of automotive, we’re living through a massive change in how people perceive the need to own a car, and this shift in perception is changing the fundamental business models. Autonomous vehicle technology keeps developing, connected vehicles are everywhere already and electric cars represent an ever bigger proportion of the vehicle population. In all these segments data utilisation will continue to increase. New cars collect huge amounts of data for lots of purposes and this can be used for lots of things other than what it was originally collected for.”

Can you address the data privacy concerns surrounding connected cars?

MR: “Data privacy is a multifaceted topic. On the one hand, Europe has been at the forefront of it with GDPR. That puts businesses operating in Europe on a level playing field. In terms of connected and autonomous vehicles (CAVs), these regulations set limitations on what data can be harvested and what has to be anonymised in order for someone to use it. It fits the norms of today’s society, but you can see in social media that this kind of privacy seems less important to younger people, however perspectives vary greatly and companies need to be transparent in usage of people’s data.

“From a business perspective, we have to take privacy extremely seriously. The explosion of data usage can have unintended consequences but by and large the regulatory environment works quite reasonably.

“We typically deal with conservative entities which put privacy and security in the middle of everything – if there’s any uncertainty it’s better to not do it, is the attitude. Think of all the sensitive personal data that entities like car companies and mobile telephone companies have. It can give an extremely accurate picture of peoples’ behaviour. There are well established procedures to anonymise data so customers can be comfortable that their personal data cannot be identified.”

What are the main risks in the shift to self-driving and how can these be mitigated?

MR: “One could talk about a lot of different challenges. What about the latency in connectivity in order to ensure processing takes place fast enough? There’s a gazillion of things, but to me these are technical nuts that will be cracked, if they haven’t been already. One of the biggest challenges is the interaction between human-controlled vehicles and automated vehicles. When you add in different levels of driver assistance, urban and rural, different weather conditions – all sorts of combinations can happen.

“The UK is at the forefront of CAV testing. There are government sponsored testbeds and companies are running trials on open roads, so the automotive industry can test in real-life environments. We cannot simulate everything, and the unpredictability of interactions is one of the biggest challenges. A traffic planner once told me that in his nightmares he sees a driverless car heading toward a granddad in a pick-up truck, because there’s just no telling how he might react!”

Is there anything else you’d like to mention?

MR: “I’d like to address the explosion of data usage in mobility and how dynamic data enables not only efficiency improvements but new business models. According to recent studies by companies like Inrix, congestion costs each American nearly 100 hours or $1,400 a year. Leveraging data-driven insights can drive change in both public policies and behaviours. In turn, these can result in reduced emissions, improved air quality and fewer pollution-caused illnesses.

“CAVs can be data sources providing tons of insight. Think about potholes – new vehicles with all these cameras and sensors can report them and have them fixed much more efficiently. This is just one example of entirely data-driven efficiency, much better than eyeballing and human reporting. There will be a multitude of fascinating uses.

“Organisations such as vehicle OEMs, transport authorities and insurance providers will require facilities for the secure and reliable sharing of data, and that’s where we come in. I would urge anyone interested in data driven solutions in the mobility space to visit chordant.io or our Convex service site at convexglobal.io.”

Dr Charlie Wartnaby says there’s an industry consensus that Level3 self-driving is not reasonable if it requires quick driver intervention.

Self-driving world first: multi-car cooperative crash avoidance

Our Zenzic CAM Creator series continues with Dr Charlie Wartnaby, chief engineer at Applus IDIADA.

Way back in 2019 we covered IDIADA’s role in the construction of the new CAVWAY testing facility, and that investment continued with a large new venture. With a PhD in physical chemistry from the University of Cambridge, Charlie Wartnaby was technical lead for the ground-breaking Multi-Car Collision Avoidance (MuCCA) project.

CW: “Certainly the funding from the Centre for Connected and Autonomous Vehicles (CCAV) for MuCCA and CAVWAY were big wins for us. Traditionally, we’d focused on automotive electrics and engine management, but we could see there was all this exciting CAV work. Now we’re working with an OEM I can’t name to run an field operational test using our IDAPT development tool – a high performance computer with GPS and car-to-car communications – as a spin-off from MuCCA.

“With the MuCCA project, we think we achieved a world first by having multiple full-sized vehicles do real-time cooperative collision avoidance. We still have the cars for further R&D when time, budget and Covid allow.

IDIADA’s Multi-Car Collision Avoidance (MuCCA) project

“In the UK, we’re focussed on building a new proving ground (CAVWAY) near Oxford, which should open in 2021. There’s also our CAVRide Level4 taxi project, at our headquarters near Barcelona. CAVRide shares some of the technology developed for MuCCA and they’ve done some really interesting vehicle-in-the-loop testing, having the real vehicle avoid virtual actors in a simulation environment.

“In the short term, we’re really working hard on the C in CAV. Connected vehicles offer massive safety and efficiency improvements, for example, by warning about stopped vehicles or advising on speed to get through traffic lights on green. There’s a bit of a VHS versus Betamax situation, with both WiFi-based short-range communications and the C-V2X 5G-based protocol, so we’ve upgraded IDAPT to support both.

“Personally I think that while heroic work by the big players shows robotaxi applications are feasible, economic viability is a long way off, 2030 maybe. Watch the latest Zoox and Waymo videos from America, they’re mesmerising! No way is that kind of tech going to be installed in private cars any time soon because it’s eye-wateringly expensive. Think about the costs involved in making every taxi driverless – it’d be out of all proportion to replacing driver salaries, especially considering backup teleoperators and maintenance and charging personnel.

“These big self-driving companies aren’t operating in the UK yet, but we do have very successful smaller players with intellectual property to sell. The UK government has been supporting a good number of R&D projects, via the CCAV and UK Research and Innovation (UKRI), and the regulatory environment has been reasonably friendly so far.

“I feel the first practical applications are likely to be low-speed shuttle buses and small autonomous delivery droids, but trucking is a very important area. If lorry drivers were permitted to stop their tachographs while napping in the back of the cab once on the motorway – only clocking up hours for parts of long journeys – that would make a viable economic case for a Level4 operating design domain (ODD) of ‘just motorways’, which is harder to justify merely as a convenience feature in private cars.

“In terms of current tech, emergency lane keeping systems (ELK), to stop drifting, are a major breakthrough, requiring cameras, sensors and autonomous steering. I welcome the road safety, however, if drivers engage automation systems like ALKS (automated lane keeping) by habit, for sure their skills will be affected. Perhaps there’s a case for the system enforcing some periods of manual driving, just as airline pilots perform manual landings to stay in practice even in planes that can land themselves.

“Concerns about timely handover are well-founded and I think there’s an industry consensus now that Level3 is not reasonable if it requires quick driver intervention. We see up to 20 seconds before some unprepared drivers are properly in control when asked to resume unexpectedly. It really requires that the vehicle can get itself into (or remain in) a safe state by itself, or at least there needs to be a generous takeover period. The difference between L3 and L4 is that the latter must always be able to achieve that safe state.”

For further info, visit www.idiada.com

Prof John McDermid says the trolley problem is a nonsense, requiring self-driving vehicles to make distinctions that you or I could not.

Why assuring machine learning is crucial to self-driving

Our Zenzic CAM Creator series continues with Professor John McDermid OBE FREng, Director of the Assuring Autonomy International Programme at the University of York.

Professor John McDermid has been Director of the Assuring Autonomy International Programme, a partnership between Lloyd’s Register Foundation and the University of York, since 2018. He advises government and industry on safety and software standards, including Five and the Ministry of Defence, and was awarded an OBE in 2010. The author of 400 published papers, his 2019 article, Self-driving cars: why we can’t expect them to be ‘moral’, was highly critical of the oft-quoted trolley problem in relation to driverless vehicles.

Professor John McDermid, University of York

PJM: “I’ve been at York for 30 years working on the safety of complex computer-controlled systems. What you define as complex changes all the time. In January 2018 we started a new programme, looking at the assurance of robots and autonomous systems, including automated mobility, but also robots in factories, healthcare and mining.

“It’s important to demonstrate the safety and security of novel technologies like machine learning, but there’s often a trade-off involved, because you can make things so secure they become unusable. If I open my car with the remote key I have a couple of minutes before it automatically locks again, and there’s a small possibility that someone could get their finger trapped if they try to open the door just as it automatically re-locks. We encounter these types of trade-offs all the time.”

What major shifts in UK transport do you expect over the next 10-15 years?

PJM: “Over the next decade we will get to Level4 autonomous driving, so in defined parts of the road network cars will drive themselves. We will solve the safety problems of that technology, but I’d be surprised if it is within five years. Despite the rhetoric, Tesla’s approach is not on track for safe autonomous driving within the year.

“At the same time, there will be a trend towards Mobility as a Service (MAAS). I love my car, but I’ve had it for 18 months and have only driven 7,000 miles. I sometimes ask myself why I have this expensive piece of machinery. A recent study showed that the average car in the UK is only used for 53 minutes a day. Mostly, they sit doing nothing, which, considering the huge environmental impact of manufacturing all these vehicles, is very wasteful.

“If I could call upon a reliable autonomous vehicle and be 99% certain that it would arrive in a timely manner, say within five minutes, I’d probably give up my car. It should also be noted that the two trends go hand-in-hand. Having Level4 is critical to achieving MAAS, delivering all the convenience of having your own car without any of the hassle.”

Can you address some of the data privacy concerns surrounding connected cars?

PJM: “We are back to this issue of trade-offs again. I want my MAAS so I’ve called it up and given the service provider some information about where I am. If they delete that information after I’ve paid then I’m prepared to accept that. What if the company wants to keep the information but won’t allow access except for law enforcement – would that be acceptable to the public? What can government agencies require this company to do?

“Another example: What if your 10-year-old daughter needs MAAS to take her to school? A reasonable concerned parent should be able to track that. What if the parents are divorced, can they both access that data? There’s clearly a privacy issue and there needs to be a legislative framework, but it’s a balance. For the purposes of getting from A to B, most people would accept it, so long as their data is normally kept private.”

Can you address concerns about the trolley problem in relation to self-driving cars?

PJM: “My basic feeling is that the trolley problem is a nonsense, a distraction. All these elaborate versions require self-driving vehicles to make distinctions that you or I could not.

“The big Massachusetts Institute of Technology (MIT) study sets a higher standard for autonomous vehicles than any human can manage. Who do you save, a child or an older person? The child because they can be expected to live longer and benefit more. However, this is based on false assumptions. I don’t believe in the split second of a crash you go into that sort of thought process – you focus on controlling the vehicle and in most cases the best option is to (try to) stop.

“I don’t know why people find the trolley problem so compelling, why they waste so much energy on it. I really wish it would go away. Fortunately, most people seem to be coming to that conclusion, although one of our philosophy lecturers strongly disagrees with me.”

Which sectors do you think will adopt self-driving first?

PJM: “Farming applications might come first as they are short of people in agriculture and the problems are simpler to overcome. If you geofence a field where you wish to use a combine harvester and equip it with technology so it doesn’t run over a dog lying asleep in the field – there’s already tech which is getting quite close to that – then that’s an attractive solution.

“Last mile freight via small delivery robots (like Nuro in the US and Starship here in the UK) might also come quickly, but longer distance freight will probably require a segregated lane. Even last mile robots come with risks, like people tripping over them.

“There’s a lot of commercial desire for robotaxis, and this is potentially a very big market. There are already genuine driverless taxis in the US now, but they have a much simpler road structure than here in the UK.

“The crucial technical bit is finding accepted ways of assuring the machine learning. I would say that, I work on it, but without that regulators and insurers won’t allow it.”

For further info, visit www.york.ac.uk/assuring-autonomy

Dr Joanna White says Highways England is currently more focused on the connected bit of connected and automated mobility (CAM).

Highways England expert predicts Level4 self-driving in towns before motorways

Our Zenzic CAM Creator series continues with Dr Joanna White, Head of Intelligent Transport Systems at Highways England.

As the body responsible for designing, building and maintaining our motorways and major A-roads, Highways England (HE) is a uniquely important player in the UK connected and automated mobility (CAM) ecosystem. Here, Head of Intelligent Transport Systems at Highways England, chartered engineer Dr Joanna White, outlines its work on CAM.

JW: “A key aim in improving our service is to look at how we can safely use emerging technology to better connect the country – people and places, families and friends, businesses and customers. This includes what digital channels we might use, delivering a cleaner road environment and achieving net zero carbon.

“Our connected corridor project on the A2/M2 in Kent finished 10 months ago and we are just completing the evaluation. Collaboration is vital and this was a joint project with Kent County Council (KCC), Transport for London (TfL), the Department for Transport (DfT) and others. It was also part of a wider European project, Intercor.

“We are currently more focused on the connected bit of CAM, building on the services we already provide. This includes beaming information directly into vehicles (replicating what you see on the gantries) and also what data we can anonymously collect from vehicles’ positioning sensors. Can we maintain service from one part of the network to another? Can we do it in an accurate, timely and secure way? How do people feel about it?

“We try not to choose particular technologies – whether it’s radar, lidar, cellular – we are interested in all of it. It could be 5G and, via the DfT, we work closely with the Department for Digital, Culture, Media and Sport (DCMS), which leads on that. One of the most positive government actions was the requirement for mobile operators to provide 90% coverage of the motorway network by 2026.

Highways England car interior 2 — Highways England in-car upcoming junction message

“We were very proud to be involved with the HumanDrive project in which a self-driving Nissan Leaf navigated 230 miles from Cranfield to Sunderland. It was a great learning experience in how to conduct these trials safely, underpinned by our safety risk governance. We had to identify all the risks of running such a vehicle on the strategic road network (SRN), and find ways to mitigate them. It was fascinating to see how it coped on different types of roads, kept to the lines and responded to road sign information.

“Then there’s our Connected and Autonomous Vehicles: Infrastructure Appraisal Readiness (CAVIAR) project, which has been slightly delayed due to Covid. We are building a simulation model of a section of the M1, a digital twin, and we have a real-world car equipped with all the tech which will start operating in 2021. That will collect a lot of data. This is one of our Innovation competition winning projects, run by InnovateUK.

“Within Highways England we have a designated fund for this kind of research, and that means we can invest in further trials and do the work needed to provide more vehicle-to-infrastructure (V2I) communications.

“Personally, I think that Level4 self-driving, eyes off and mind off, is years away, perhaps decades, certainly in terms of motorway environments. However, we are constantly in discussion with government on these issues, for example, we contributed to the recent consultation on Automated Lane Keeping Systems (ALKS).

“Working closely with industry and academia, we have already started off-road freight platooning and are looking to move to on-road trials. We’ve had lots of discussions about freight-only lanes and the left lane is often suggested, but you have to consider the design of the road network. There are lots of junctions close to each other, so how would that work, especially at motorway speeds? At first, I see self-driving more for deliveries at slower speeds in urban areas but, as always, we will listen to consumer demand.”

For further info see highwaysengland.co.uk.

Why digital twins are crucial to the development of ADAS and CAV.

This is no game: how driving simulations save lives

Our Zenzic CAM Creator series continues with Josh Wreford, automotive manager at driving simulation software provider, rFpro.

With digital twins so crucial to the development of advanced driver assistance systems (ADAS), carmakers including Ferrari, Ford, Honda and Toyota have turned to driving simulation software provider, rFpro. Here, automotive manager Josh Wreford explains the company’s cutting-edge work.

JW: “While others use gaming engines, our simulation engine has been designed specifically for the automotive industry, and particularly connected and autonomous vehicles (CAVs). That’s a big difference because gaming software can use clever tricks to make things seem more realistic, whereas our worlds are all about accuracy.

“We use survey grade laser scanning to create highly detailed virtual models and have an array of customers testing many different ADAS and CAV features, everything from Level1 right up to Level5. We can go into incredible detail, for example, with different render modes for lidar, radar and camera sensors, it is possible to simulate different wavelengths of the electromagnetic spectrum for detailed sensor modelling. It is up to the customer to decide when their system is ready for production, but we save them a lot of time and money in development.

rFpro simulation Coventry — rFpro simulation: Coventry town centre

“Safety critical situations are extremely difficult to test in the real world because it’s dangerous and crashing cars is expensive! That’s why digital twins are great for things like high speed safety critical scenarios – you can test human inputs in any situation in complete safety. Whenever you have a human in play you’re going to have problems because we’re great at making mistakes and are very unpredictable! rFpro provides high quality graphics running at high frame rates to immerse the human in the loop as much as possible. This allows accurate human inputs for test scenarios like handover to a remote driver. We can even allow multiple humans to interact by driving in the same world.

rFpro simulation Holyhead — rFpro simulation: Holyhead

“Before joining rFpro, I worked at McLaren Automotive on gearbox control software, which involved very similar control coding to ADAS. Ethical questions are always interesting, but ultimately a control engineer has to decide what the next action should be based on the exact situation. Our simulations drive robust engineering and better algorithms, so you get the best reaction no matter what occurs.”

For further info, visit rfpro.com.