Supporting Autonomous Vehicle Development in the Virtual World

Autonomous driving has quickly become a hot topic, with not a day passing without an announcement of a new manufacturer programme or consortium study.  The big question on everyone’s lips though, is will they be safe?  The technology is very close but, how do we introduce it safely and overcome the societal and legislative issues that allow autonomous vehicles to become a reality?

As with any credible automotive technology development programme, the Venturer consortia are starting with testing in the virtual world (simulation). We will then progress to physical testing in a controlled environment, correlating results with the simulation before moving on to the intended environment, in this case, the public roads.

simulator view

Having built an immersive simulator using the latest software, a premium projection system and a full car environment, our objective is to create a test facility that is close enough to real world driving so that the results are as close as possible to physical testing later.

So, what will the simulator do?  Participants in the planned trials will be able to drive the simulator manually, as per a conventional car, as well as autonomously. This facilitates the study of how the ‘handover’ from autonomous to manual modes can be safely performed.  Through the scenario scripting capability we can also assess how people react to being driven autonomously in challenging or unusual situations.  Finally, the software code that will drive the BAE Wildcat in the later trials can be validated within a range of scenarios in a safe environment.

The simulator will be used in a number of trials, conducted by the University of West England, to provide results that will contribute towards the overall study of handover and autonomous driving in challenging scenarios, such as T-junctions.

Where will the simulator be?  The simulator was developed and built at Williams Advanced Engineering [1] and has now been transferred and commissioned in Bristol Robotics Laboratories.

Authored by: Dan Burge, Williams Advanced Engineering

[1] Williams Advanced Engineering is the technology and engineering services business within Williams Grand Prix Engineering

The Importance of a thorough design validation regime in the development of Autonomous Road Transport

Many technical advances are afoot in the autonomous road vehicle domain and, in some senses, ‘driverless cars’ are already amongst us in the world. However, I believe that great care needs to be taken in introducing this exciting new technology at large, which offers so much potential in improving the quality and safety of ‘end-to-end’ journeys.

The challenges in introducing this new technology in the safest and most beneficial way are dependent on both technology and societal issues. Here, I will focus on the technology because that is my area of expertise, but those social issues will be ignored at our peril. In other words, quite apart from the relative immaturity of the technology itself, I do not think society, at large, is ready for the sudden introduction of fully autonomous vehicles, we are much better becoming accustomed to them as the new technology is introduced gradually.

Driving along motorway style highways is, from many perspectives, the ‘low hanging fruit’ of the overall challenge. Here, most vehicles are going in the same direction at much the same speed, with clear rules of ‘engagement’ between vehicles, away from distractions and dangers such as pedestrians and cyclists.

Of course, this is often one of the situations where this new technology could be very useful, since we are often behaving pretty closely to “automata” in these circumstances and we are not particularly well suited to such situations in terms of maintaining our awareness. In this situation, a multi-sensor ‘all round view’ autonomous car with reaction times that could typically be at least ten times faster than a human’s could save a great deal of boredom but also, more importantly, injury and even lives, because it will never get bored and will have ‘eyes in the back of its head’.

However, although we have become accustomed to the fact that car travel is a really very unsafe way to get around in general, motorways are relatively safe. Inner city areas see a larger number of accidents, though they tend to be less serious, and the real ‘danger spot’ is the relatively high-speed two- or three-lane suburban/rural highway, the ring roads and ‘A’ trunk roads of the UK. Here, relative speeds between vehicles can still be high, and it is a much more complicated and less structured environment from both a sensor and control perspective. It is inner city and suburban areas where the VENTURER project [2] focuses, on both the required technology advances and human acceptance issues.

Since the technology is really not there yet for these types of environments, there is a great deal of research, and validation of the outcomes of that research, to be carried out over the coming few years. In fact, one could also say that even on motorway driving scenarios a great deal more technical validation and test-track proving for unusual situations is still urgently needed before letting this technology loose on public roads in earnest.

Let’s consider just two issues worthy of brief note here, in order to give a feeling for the scale of challenges to be dealt with, are as follows:

  • Planned control handover: let us assume that you want to drive your car to the motorway junction, let it do the ‘boring bit’ of going up the motorway, then warn you that you should take back control to drive on the smaller roads to your destination. What happens if, by that time, you are asleep, or immersed in reading a book? How should the Autonomous Control System (ACS) handle giving control back to you and ascertain whether you are in an appropriate attentional state to do so? Emergency handover is even more contentious, and it is hard to think of many times when this would be a good idea, compared to the ACS finding a safe way to bring the journey to a temporary halt.
  • Turning out from a minor-road T-junction onto the main highway: it is a busy main road, and there could never in the foreseeable reason future, be an allowable chanced for the manoeuvre whilst obeying the highway code. If driven manually, then the driver would find ways, eventually, to signal a request to approaching traffic using a wide variety of methods. How would an autonomous vehicle do this, especially if communicating with another manually driven vehicle?

These two examples are the first two (of three) trial topics for the VENTURER project, which will consider the technology and its impact.

Professor Tony Pipe, Bristol Robotics Laboratory [1], UWE Bristol[2]

[1] The author is Deputy Director of the Bristol Robotics Laboratory http://www.brl.ac.uk/

[2] The author is leading technology integration in the Innovate UK-funded autonomous vehicles project ‘Venturer’ http://www.venturer-cars.com/.

Participants’ Feedback – Trial 1

The Development and testing of autonomous vehicle technology is only one aspect of introducing driverless cars to UK roads. The other core element is focused on understanding the needs of the end-user.

Making driverless vehicles a reality will therefore rely on the willingness of the user to embrace and trust the technology. As a result, VENTURER seeks to obtain a deeper understanding of the requirements and challenges of integrating driverless vehicles into urban environments.

 

Wildcat 22

Trial 1 of the project engaged a number of participants in an effort to gather their reaction during the handover process. By interviewing a small sample of participating drivers, following the completion of testing on the BAE Wildcat vehicle, we found that participants were mostly excited by the new technology. Although, there were remnants of nervousness and the uncertainty of what to expect when the vehicle was in full control of their ‘journey’.

“I was always monitoring the distances of the car with respect to pavements and other cars and was constantly monitoring mirrors as I couldn’t totally rely on the car; but the vehicle behaved pretty much as if it was human driven.” (Respondent 1)

Feedback further indicated that participants began to feel more relaxed as the trial progressed.

“I was quite worried at first but as the experiment progressed I began to trust the self-driving ability and became more at ease.” (Respondent 2)

The first tranche of the project will be completed in September 2016; and interestingly, participants are keen for the VENTURER consortium to test how drivers will cope with “a changeover after an extended period of autonomy or deal with distractions.” (Respondent 3).  VENTURER will explore a range of challenges as the programme evolves.

Undoubtedly, these responses and the involvement of end-users throughout the project will play a key role in facilitating change that can better meet the needs of future drivers.

*For the purpose of this article, participants will remain anonymous.

 

Authored by: Rebecca Tommey, Atkins

The Importance of Citizen Engagement

The Importance of the Citizen Perspective in the Development of Autonomous Road Vehicles

Professor Graham Parkhurst, Centre for Transport & Society, UWE Bristol[1]; graham.parkhurst@uwe.ac.uk

Government departments, technology developers and industrial strategy advisors across the globe have identified numerous potential benefits from the introduction of autonomous road vehicles (ARVs). These include ‘vision zero’ levels of road safety through eliminating human driver error, greater social inclusion in the case that people without driving licences or driving skills can gain access to cars, and reduced congestion and emissions if vehicle progress is smoother due to the motion being managed with respect to the road conditions and coordinated with other vehicle movements.

However, as has been highlighted by recent political currents, the views of experts are not necessarily simply accepted by the wider population. This creates a dilemma for the promoters of new ideas: individual citizens rarely have the time or motivation to themselves become expertly-informed on a topic. So if the professional experts are not seen as a trusted source of information, ideas about and behaviours towards an innovation, such as ARVs, will be formed drawing on a subset of the available information. This subset will be perceptually filtered to a manageable level, and this process is likely to be influenced by, and potentially biased by, a range of processes. Individuals may be influenced by information sources which are trusted, but may have particular vested interests to promote, or themselves may have selected information in a subjective way in order to support a particular perspective. Individuals may draw upon those past personal experiences with new technologies judged to be nearest. However, those experiences may or may not provide a relevant precedent. Or wider emotional-perceptual frames, for example suspicion with respect to robots and artificial intelligence in general, may dominate judgements, before any analysis of the specific capabilities of the particular new technology product is undertaken.

The involvement of citizens in the research and development process of ARVs can assist in aligning the expert and citizen perspectives in a number of ways. First, a small number of citizens can become users of the technology under test, and have the potential to become ambassadors for the innovation as ‘trusted informants’ in society: trusted because they are ‘people like us’ with no particular vested interests. Second, the involvement of citizens demonstrates that the technological development is being conducted, as far as possible, in an open, transparent way. Lastly, and most importantly, citizen involvement provides information about people’s actual usage and experiences: in the form of physiological measurements, observations, and volunteered insights. This information can assist with the evolving design and deployment of ARVs to meet social needs and expectations more effectively, and at the same time assisting commercial producers with their marketing.

Indeed, the exchange of knowledge brought by citizen involvement emphasises that the expert perspectives are not infallible: the adoption of ARVs must not be seen as simply a problem of effective communication. In particular, the expert claims about the range and extent of benefits are dependent on a host of assumptions and particular scenarios of adoption. For example, safety benefits will likely arise in proportion to the share of ARVs in the circulating vehicle fleet. Other benefits, such as the smoothing of traffic flow, might need certain thresholds of fleet share to be achieved. And some benefits, such as social inclusion, will only arise with particular thresholds of technological development being achieved, for example, full automation will be required before citizens unable to drive can travel without a qualified driver in an ARV. Whilst there is not a consensus on when full autonomy can be achieved, even if it began today, a complete transition to full ARVs would take decades. So a major challenge for social researchers working on ARV innovation is how to present this transition in a way that is sufficiently detailed to be realistic, honest and inclusive, whilst not exceeding the willingness of citizens to engage in a project that may not be fully realised in their own lifetimes.

[1] The author is leading the social and behavioural work package of the Innovate UK-funded autonomous vehicles project ‘Venturer’ http://www.venturer-cars.com/ .

Planned Handover – an overview of trial 1 of the VENTURER project

VENTURER will undertake three trials in order to assess user responses to driverless cars.  The first of these trials is currently on the way.

Trial 1 is testing planned handover of control between a vehicle and driver. This is when the driver knows they might be alerted to take control in certain situations as the vehicle is unable to operate in all conditions.

VENTURER TRIAL 1 GRAPHIC

For an overview of VENTURER’s first trial, please click here.

The changing nature of liability

The VENTURER project is a fascinating one to be involved in. As we have said before, we understand that autonomous technologies have the potential to dramatically improve road safety as well as impact positively on other areas of society. This is why we want to play our part in enabling driverless vehicles to be on UK roads in the near future.

Yes, the nature of motor insurance will be drastically altered. However, there is no doubt that there will still be a need for motor insurance, but it will not be as we know it today.

Our first annual report looks at the changing nature of liability on the road as more grades of autonomous vehicles enter the market and the projected timetable for full automation to evolve onto UK roads. A key issue addressed by the report is defining liability and understanding who or what is responsible in the event of a motor incident. This is a critical element of AXA’s role in the VENTURER project, relating to how liability is shared between driver and the manufacturer of the autonomous vehicle, particularly how this alters for autonomous and non-autonomous modes.

Looking forward we will be analysing the data that is produced from the first VENTURER trial which is focussed on the handover period from human to vehicle and back again. By understanding this crucial element we will continue to work towards an understanding of the risk modelling that will likely be needed to underwrite insurance policies for cars with higher levels of automation.

 

Authored by: Daniel O’Byrne – Public Affairs Manager, AXA UK

Understanding the socioeconomic adoption scenarios for Autonomous Vehicles: A literature review

There is great and growing interest in autonomous vehicles (AVs), both in relation to rapid technological developments and the trialling of these developments, and the potential for their far reaching impacts on transport systems and society. The present report examines scenarios and policy and practice challenges for the adoption of AVs. Whilst it has broad relevance for societies, in the industrialised democracies at least, there is a particular focus on the UK context.

Read full review here.

Clark, B., Parkhurst, G. and Ricci, M. (2016) Understanding the socioeconomic adoption scenarios for autonomous vehicles: A literature review. Project Report. University of the West of England, Bristol, UK.

Handover issues in autonomous driving: A literature review

The present review was undertaken to inform a work package of the VENTURER Project undertaking studies into the handover of control between a human driver and an autonomous road vehicle.

Read full review here.

Morgan, P., Alford, C. and Parkhurst, G. (2016) Handover Issues in Autonomous Driving: A Literature Review. Project Report. University of the West of England, Bristol.