Happy New Year and after a very exciting 2017, we’re back for our bigger event format for 2018. With a change of venue, to the focal point of the UK’s autonomous industry, Milton Keynes, (just around the corner from the fantastic Transport System Catapult), we’ll be opening the doors to around 150 people and a wide variety of technology companies, demonstration vehicles and guest speakers – all gathering to support your growth and development in this exciting field.
Tickets explained… The standard ticket includes your choice of workshops, autonomous vehicle demonstrations and access to the exhibition, along with refreshments all day and lunch. The ‘networking’ ticket includes access to the exclusive evening session, where you can relax, continue conversations, and enjoy complimentary go-karting and BBQ dinner.
YoE is a government backed programme of events spanning across the UK, encouraging people of all ages (but especially younger people) to engage with science, technology, engineering and maths – and consider working in fields using these topics.
As an event which celebrates and connects engineers, we are proud to support this initiative and are pleased to encourage people from all backgrounds to consider engineering, in all forms, as a potential career.
There is no single industry which does not need engineers, and the ecosystem of technologies used in autonomous vehicles is as diverse as it is exciting, with ideas and applications of STEM skills included in mechanical, electrical, digital and even civil engineering. Outside our regular topic of autonomous road vehicles, these technologies are used in the air, under water, even in space – as well as in logistics, industrial manufacturing processes in factories, and agriculture.
The engineers we see at our events come from and go towards many different industries and we are keen to fly the flag on their behalf and tell everyone that being an engineer can take you anywhere.
Here at Sense Media Group, we’ve grown from 3 to 7 people, have run events in the UK and Austria, plus more workshops and demonstrations in the US and Belgium too, and we’ve been involved in everything from TV shows to development of standards and even government policy!
AutoSens, sister brand to Self Driving Track Days, has gone from strength to strength and has now become the most influential conference in the vehicle perception eco-system, globally, and will next year return to the awesome AutoWorld Museum in Brussels, as well as the Michigan Science Center in Detroit – and of course with driverless technology demonstrations at both!
The AutoSens Awards also launched, celebrating the engineers and technologists working in the commercial sector, as well as highlighting fantastic community efforts and journalism, as well as outreach and education projects supporting the self-driving car revolution.
It’s not just about us…
Some of the startups and smaller innovative companies in our ecosystem, as well as larger more established companies have had a great year too. AutonomouStuff and Quantum, last year’s series sponsors, are working together to create new products, while NXP and Intempora, another pair of last year’s supporters, are jointly marketing products too, finding new efficiencies and customers thanks to embracing our mantra of shared working and collaborative spirit. Innoviz Technologies, a small Israeli LiDAR startup we first came across at the beginning of the year, have ended it with a huge investment (more than $100m) and a haul of awards and plaudits from across industry.
Petrolheads are a significant part of this journey, and last week’s Guy Martin vs the Robot Car, on Channel 4, was an exciting demonstration of why it’s so hard to complete this development journey. We first met the production team in November 2016 at our very first track event, so seeing the final results on TV is tremendously satisfying and great to see an understandable and accessible programme on a complex topic. It was also great to see that the systems put into place by our friends at AB Dynamics, who demonstrated their technology at our first event, were able to beat the famed Roborace car! I’m certain that’s won’t take long to change though…
Save the date!
Coming to the year’s end gives us a chance to review what we’ve achieved, and sometimes that means doing things differently – so we’ll do fewer but bigger events… that includes working on TheLondon Motor Show 2018 developing a brand new exciting feature there.
It would be easy to carry on as before but as an event organiser, it’s important to take on feedback so we are moving to a UK venue in the autonomous vehicle heartland of Milton Keynes and shortening the event to one day.
We trialed this event format in Austria in July 2017 and it worked very well for attendees and sponsors (who typically have quite large overhead costs to consider in their commitment to taking part).
The event will include a number of half-day workshops, a small exhibition and of course, our driverless vehicle demonstrations, with space for 150 attendees to come and take part. Lunch will be included, and there will be a BBQ and karting in the evening as an optional extra.
Please add the date to your diary… Tuesday 10th July 2018 at Daytona Karting, Milton Keynes.
We’ll be confirming more details in early 2018, so if you are not already on the mailing list, please sign up now.
I am looking forward to 2018 being a year when the media hype starts turning into real and lasting positive change, as industries start gearing up for the autonomous future.
Have a great holiday season and we’ll hopefully see you soon.
Our Self Driving Track Days events aren’t just for learning, outreach or marketing, they’re also about helping media outlets start to really understand some of the technologies that are used in autonomous vehicles, how they work, why they are necessary and how they are used.
We always work closely with media outlets to help provide the message that there are many opportunities for technology development (for new companies looking at this field) as well as research, and of course skills development and employment opportunities for individuals – these outlets reach far more people than we could just through our own marketing.
We often attract coverage on national TV, as well as national-publications in the auto and technology industries – and our event in Austria was no exception!
Here’s a selection of some of the coverage we’ve received for this event:
Meridian Mobility Technology is the new name for the UK’s Connected and Autonomous Vehicle Hub, announced in March, and will take on some of the direct oversight tasks managing R&D projects which have been part-funded by the UK government.
Its role is wide ranging and as yet, slightly fluid, but will be a grant-funded (by the taxpayer) subsidiary of the Advanced Propulsion Centre and work closely with the government’s Centre for Connected and Autonomous Vehicles.
Some of its indirect responsibilities will be to act as a central body for promotion of the industry, attracting investment from outside the UK, support export from companies in the sector, and develop approaches to improve skills development in the sector.
We have been consulted and involved in some of the events leading up to this organisation’s creation and look forward to its activities and influence in this quickly growing and exciting sector.
Further details about the organisation’s exact structure, purpose, funding and activities will be announced in the near future, but you heard it here first!
NovAtel are a series-sponsor for Self Driving Track Days and will be presenting in the afternoon workshop session of Introduction to self-driving car technologies (positioning, software and processing).
In the last few days before the event, we talked to Andreas Niemann, NovAtel’s Business Development Manager, based in Germany – about positioning technology for autonomous vehicles, and what changes are expected in the future.
Satellite-based navigation has been a useful tool for consumers for 20 years, how will that change in the next 20 years?
Although current tools may be sufficient for consumer applications that are not safety critical, this is not a tool that can be used ‘as is’ for applications like (conditionally) autonomous cars or other unmanned vehicles.
Accuracy levels required for applications such as military vehicles, ships, agriculture or in the offshore oil industry already since the beginning of GPS more than 20 years ago, must be adopted for safety critical functions for cars within the next generations of car lines. NovAtel has been a pioneer in positioning for the mentioned non-consumer markets since the beginning.
The biggest differences for future satellite-based navigation systems to today’s navigation devices performance will be in the availability of positioning (always available) and in the integrity of positioning (always trustable). It will become a system that is crucial for safety-of-life applications.
GPS signals are prone to atmospheric interference, problems in urban environments and even bad weather – how can you counter-act these?
NovAtel, being part of the Hexagon group, is able to utilize our group-owned correction services for satellite-based positioning. They can compensate and correct the known issues: clock differences between satellites and receivers, satellite orbit deviations and errors caused by the ionosphere.
For example, customers can access to the global Terrastar PPP service (Precise Point Positioning by Hexagon) with NovAtel receivers either through a certain satellite constellation or through cellular internet connection. Correction performance will be continuously improved by investing in further ground stations and continuous R&D. Already today, cm-level accuracy is possible to achieve, even under non-ideal reception situations.
NovAtel is a leader in designing multi-constellation multi-frequency receivers – not only GPS (USA), but GLONASS (Russia), Beidou (China) and Gallileo (Europe) – that greatly improve availability and accuracy of the positioning performance and reduction of outages.
Another great step will be achieved for example in cars by utilizing inertial sensors or simply sensors that are installed in cars anyway (wheel, steering etc.) to optimize the output. The performance of that kind of positioning will be incomparably better than all systems that are available today in consumer type devices.
What are the drawbacks of these techniques?
The backbone of the techniques mentioned is already existing:
Correction networks are running, more satellite constellations will be added and go into operation mode. Positioning algorithms have been developed to improve positioning continuously. NovAtel has a further roadmap to improve algorithms further.
This will take more time and continuous improvement and requires close cooperation with the end customer, the car maker and/or system integrators.
We expect the positioning system to become more customer specific i.e. for autonomous cars as the car behaviour (delivered by sensors installed in the car) will be an input for the navigation system itself. It will take a lot of development effort on both sides, at the car maker as well as the GNSS system provider, but we know that the awareness and understanding has been built.
Precision GPS equipment is really expensive – If organisations like startups and universities need hardware to develop a new product, what support is available?
We are opening channels to work with Universities and customers at the same time to maximise the efficiency of such cooperation, i.e. in 3-party agreements. NovAtel works actively together with Universities, such as Stanford, and has established relationships with a large number of startups and we are supporting them in their R&D work.
It is not all about providing equipment to customers, universities or startups, the key of success is understanding their intention and then decide together what the best technical and commercial approach is to achieve the target. Our partners trust NovAtel to propose the best solution short and long term.
Can’t they just use their smartphone with the accelerometer?
Smartphones are receiving satellite signals on a single frequency without any of the corrections mentioned above. That is accurate-enough for a lot of consumer type of application (i.e. simple navigation from A to B or tracking sports activities) but not accurate enough to deliver precise positioning results under different conditions (open sky, urban environment etc).
Ideally they could deliver metre-level accuracy but not as often as required for high-precision and safety-critical applications, hence, they are not reliable.
Speaking of smartphones, why does my smartphone get hot when I’m using the maps – and is this also a problem that affects precision-grade GPS systems?
Navigation/Positioning is a hardware and software feature of smartphones, which requires computing power within the GPS/GNSS receiver of the smartphone and also by the central processor of the smartphone. Same as with any other computer the device gets warm indicating significant computing activity.
That’s normal and no problem for any system running within specified limits at all.
In battery powered portable devices it will just discharge the battery faster than without using GPS/GNSS and requires earlier recharging.
The electronic content of cars has grown a lot in the past and will grow significantly. The power consumption caused by electronic systems in general will increase but high-precision GPS/GNSS alone represents only a very small fraction of that.
The next generation of satellite navigation systems will include what features to make them more accurate?
Similar as the answer to the question what will happen in the next 20 years, features such as multi-constellation (not only receiving the positioning signals from the US’ GPS satellite constellation, but also from the Russian GLONASS, the European Galileo, the Chinese BEIDOU or other future constellations) will increase availability.
Multifrequency reception will increase accuracy which will be supported by further software optimization. Other things such a as sensor fusion of various external signals such as inertial sensors, wheel sensors etc will be limited to applications where this is absolutely needed as it will also increase the system cost. Sensor fusion algorithms will also achieve a yet to be determined increase in positioning reliability.
For automotive, compliance to ISO26262 (Road Vehicles – Functional safety) is mandatory and will develop the GPS/GNSS feature into application that are safety (of life) critical. In that case it is important that the positioning is not only precise but absolutely trustworthy. Methods to enable that are currently been researched.
What are the biggest priorities with GPS research and product development right now?
Development of hardware and software-algorithms to make them compliant with ISO26262 for automotive safety and integrity.
Sensor-fusion to provide a consistent and reliable position.
Instant availability of global correction services (i.e. PPP)
The company is one of the leading developers of new positioning technologies, and have published An Introduction to GNSS, a free eBook, to help improve understanding of the technology. [Andreas kindly responded to our questions in his second language, we have edited lightly for clarity.]
Everyone’s talking about testing and safety of Autonomous vehicles, from design through production and evaluation – all well before the general public get into production vehicles – but who does this, and how?
Functional Safety is the automotive industry’s answer. Developed from the pioneering work on safety that evolved through the US space programme, the main standard for the automotive sector is ISO 26262, the second edition of which will be released in late 2017.
I caught up briefly with the very busy but charming John Birch, Chief Engineer for Functional Safety at Horiba Mira, who will be leading a special ½ day workshop on Functional Safety Considerations for ADAS and Autonomous Vehicles at OAMTC Teesdorf on 28 July.
You’re with us in Austria talking about Functional Safety with Autonomous Vehicles – why is that important, even for people new to the area?
Even for a prototype vehicle used in a controlled environment there are functional safety considerations that should be evaluated and addressed.
These should addressed in a documented safety case that can be reviewed and assessed by the relevant stakeholders. What is important is to be able to tailor the ISO 26262 standard to the vehicle systems and use cases of interest to ensure a safety case that adds maximum value.
Can’t everything be picked up in the testing of the system after it’s complete?
System test is an important piece of the jigsaw but would never be considered to be sufficient due to the infinite number of cases to be considered. A solid basis for developing the safety requirements upon which the testing can be founded is crucial.
What do you think about the Self Driving Track Days project – is community outreach important?
Absolutely. Many of the safety-related considerations of autonomous vehicles have an ethical element that will need to be informed by forming and gauging the views of the general public.
Join us at OAMTC Teesdorf to attend the workshop, with a general Introduction to functional safety, Introduction to ISO 26262; Lifecycle, Safety Management, Concept Phase, System Development, Hardware and Software Development and Specific functional safety considerations for ADAS and autonomy.
Dr Árpád Takács works as an Outreach Scientist for AI Motive, one of the leading lights in development of new techniques to help driverless vehicles understand their surroundings and start thinking for themselves. The company has offices in Budapest, Helsinki and Mountain View, California.
Today, most of the ADAS (advanced driver assistance systems) are relying on classical computer algorithms, especially in the vision domain. This is very suitable for simple, independent tasks, such as lane detection, forward collision warning, even simple decision making.
As the number of ADAS functionalities increases, the simultaneous detection, interpretation of the environment gets more complex, requiring a large number of hand-written rules and methods for solving the task of self-driving.
The power of AI is that it is a scalable approach, AI-based methods rely on a training data where visual or behavioral features are learned automatically (i.e. we don’t have to tell the AI what features to look for on an images), and most importantly, AI can generalize much better than classical algorithms, increasing its robustness.
Can you quickly explain the difference between AI, Machine Learning and Deep Learning?
These phrases mean different things to experts, and the definition of AI is a difficult task even today.
In my interpretation, AI can be a machine, an application or an artificially created consiousness, reflecting cognitive intelligence.
Machine Learning is a tool, which provides th AI the ability to change a behaviour intentionally and in a reproducable way – Machine Learning is the ‘training method’ of AI.
Deep Learning is closely assiciated with Neural Networks, one of the most promising methods of AI, where Deep Learning is hierarchical, structured learning method for Neural Networks with multiple hidden layers.
Getting started with artificial intelligence is daunting – any tips for a first-time software developer on how to get started?
One of the best ways to start understanding AI is through vision-based detection tasks, where image recognition (particularly digit recognition) is a well-documented, popular area. Starting with the basics of machine learning, SVMs, simple classification tasks, then moving towards Neural Networks, Deep Learning and evolutionary algorithms is a standard way to go.
Software frameworks and public datasets can help with the training, such as using Caffe, Theano or Tensorflow.
[Video courtesy of NVidia]
What do you think about the Self Driving Track Days project – is community outreach important?
Self-driving is one of the hottest topics of our times technology-wise. This is going to be the first technology where AI will be used in a safety-critical system on a world-wide basis, and it is crucial that the public understands the driving force and brain behind these machines.
So yes, community outreach is a key to bringing self-driving cars on the streets. Self Driving Track Days is a great opportunity for this.
You’re recruiting – what qualifications and experience are you looking for?
In general, we are looking for qualified, agile professionals with excellent programming skills, string mathematical background (for AI researchers especially) and people with experience in working with automotive development.
More precisely, we are looking for AI and image processing researchers, C++ developers, software and embedded system engineers, control engineers.
Is finding enough good recruits challenging?
It has always been challenging since the beginning – as a small company, we need professionals with a wide field of knowledge, out-of-the-box thinking and the ability to switch focus in a short time.
While finding such recruits is not easy the problems around self-driving are so exciting and challenging that it really helps us finding the brightest minds.
What advice would you give to automotive technology companies that are worried about how they fit into the next generation of cars – the new driverless ecosystem?
The automotive industry started going under a major change in the last years, software is taking over the most important place, and the position of OEMs as integrators is less stable than it used to be.
Most of the OEMs and Tier 1s have recognized this and started with the development in-house, but now there is a lot of space for new companies and technologies in the new ecosystem (such as self-driving software, connectivity etc.).
The industry is opening up, so my advice for worrying companies is to take this as an opportunity to start developing new technologies together with the newcomers – OEMs and Tier 1s have the experience in productizing an idea, but this idea can now come from someone outside of the traditional automotive field.
With more than 50 attendees registered from more than 30 companies, time is running out to book your place!
Join us for a full day of training and workshops, no prior learning required – ideal for people wanting to learn more about driverless vehicle technology!
In the last two weeks before the Self Driving Track Days event at OAMTC Teesdorf, near Vienna, Austria, we talked to Dr Daniel Watzenig, Head of the Electronic Engineering & Software department at the Virtual Vehicle Research Center in Austria.
Daniel is also Vice President of the Artemis Industrial Association, which supports organisations involved with Embedded Intelligent Systems across Europe.
Can you tell us more about the Virtual Vehicle Research Center?
The Virtual Vehicle Research Center is an international platform for research and development in the automotive and rail industry, located in Graz, Austria.
Virtual Vehicle addresses “smart mobility” and, in particular, the vehicles of tomorrow, which should be safe, environmentally-friendly and more and more connected with its surroundings, so cutting-edge research and technology development is essential, and simulation is a key opening completely new possibilities.
The research center provides a close linkage of numerical simulation and experimental validation, and offers comprehensive system simulation up to the complete vehicle.
Our network has over 80 international industry partners including leading OEM‘s, tier 1+2 suppliers and SW vendors, more than 40 scientific partner institutions worldwide and more than 200 employees.
The Virtual Vehicle Research Center is part of the Austrian COMET K2 Program, and the Center actively engages in numerous EU funded projects (27 ongoing, 20 competed projects) and offers a broad portfolio of commissioned research and services.
What can employers do to improve the quality of potential recruits?
There is a strong need for Software engineers and people who are able to work on AI-based solutions and fault-tolerant algorithms/systems.
Industry, especially in Europe, has to engage more with universities to help to educate the right competences
Brexit might be damaging for the Automotive industry in the UK – will you still work with UK companies afterwards?
Yes, we have a long history with British partners (academia and industry). We do not expect that the Brexit will influence that. Let’s see what the ongoing negotiations (EC and UK) will result in.
I am still confident that we will see a positive outcome.
What do you think about the Self Driving Track Days project – is community outreach important?
Yes, Austria is catching up. The newly created public test region “ALP.Lab” (highway, city of Graz, rural roads) and the upcoming one “DigiTrans” (trucks, intermodal traffic) clearly show that.
Having more and more demonstration activities in Austria will certainly improve our visibility.
There has been lots of news about driverless cars recently – are there any business opportunities left?
When ever it comes to Software, Artificial Intelligence, Internet of Things and Testing… Europe might be too conservative, however, most European OEMs and Tier 1 have locations in the San Francisco Bay area in California.
The Virtual Vehicle Research Center team will be running an autonomous vehicle demonstrator (on-track) at the event, as well as looking in on some of the workshops.
Book now to secure your place at this unique event!
Mark O’Donnell is Senior Product Manager for the Blue Box at NXP, the Dutch semiconductor company, with Mark himself specialising in automotive micro-controller systems.
NXP have supported the inaugural Self Driving Track Days series and will be presenting a short technology session and demonstration on 28 July at OAMTC Teesdorf.
Tell us about this version of the Blue Box – what’s it for and how is it different from the first version?
The main things that changed were the form factor and connectivity options – so it is configured to be deployed in development vehicles.
How are these systems different from offerings from companies like NVidia, with their behemoth $20,000 PX2?
The basic configuration of BlueBox2 is a platform for developing up to L3 applications.
NXP provides solutions that can be taken into production vehicles today, that satisfy automotive application requirements – functional safety, auto qualification, automotive reliability. BlueBox2 can be expanded, in terms of its hardware (via pcie slot) enabling it to support more autonomy use cases.
You’re doing a special joint demonstration with Intempora at our event on 28 July – tell us about that?
The demonstration integrates Intempora’s Real Time Multisensor Applications (RTMaps) software onto the NXP BlueBox. This highlights Multi-Sensor synchronization and fusion technology, which is required for Autonomous driving development and testing. The demo has Radar, Vision, and LiDAR sensors.
Who else are you working with at the moment?
So far we have announced our partnership with Elektrobit, in that RobinOS now supports BlueBox.
What other products does NXP produce for driverless vehicles and problems like computer vision and AI?
NXP provides products for front camera and surround view applications. Hardware accelerators that are used by NXP today have been used to demonstrate their capabilities in the field of AI. NXP is the market leader in Radar processors and a leading provider of V2X products for beyond line of sight sensing – all of which are required for driverless vehicles.
Mark will be presenting during the afternoon introductory session “Introduction to self driving car technologies” coming up on 28 July.