02 Jul Tech.AD award for most advanced real-life trainings data for autonomous driving
The Tech.AD Europe Award honors extraordinary projects in the automotive industry and celebrates exceptional solutions & innovations. This year, ALP.Labs submission “Traffic Monitoring as Source of Training Data for Autonomous Vehicles” was rewarded with the 1st price in the category “Most Advanced Real-Life Testing & Simulation Techniques in Autonomous Driving”. The project convinced the international expert jury as well as Europe’s largest community of autonomous driving decision-makers in a live-voting.
The international jury of experts:
- Mathias Reimann, Vice President Engineering at Robert Bosch GmbH
- Hagen Böhmert, Head of Safety and Security Engineering at Continental
- Pierre Olivier, CTO at LeddarTech
- Matthieu Worm, Director autonomous vehicles at Siemens Digital Industries Software
The winning project turns commuters and Sunday drivers into test drivers
Large amounts of training data are required for developing autonomous driving functions that work safely in real road traffic. The common way of collecting this data involves large fleets of specially equipped cars and thousands of measurement drives. ALP.Lab instead equipped selected crossings with radar, LiDAR and optical sensors. That way, normal traffic can be monitored to collect training data faster, more cost-effectively and more environmental-friendly.
“We collect 7 million kilometers of training data a year – without driving a single meter.”
(Gerhard Greiner, Managing Director)
From bird view to ego view – a clever change in perspective
The sensors are mounted on street poles or traffic lights, enabling a perfect (GDPR conform) overview over all road users (“bird view”). Using special algorithms, every situation can then be represented from the perspective of cars, cyclists etc. (“Ego-View”) – just like it needs to be to work as training data for autonomous vehicles.
“The results are available for simulations and as test data for machine learning in different formats, even as a live stream,” Mohamed Berrazouane, Technical Project Manager at ALP.Lab explains. “Also, the traffic data can be enriched with additional information, such as weather, sunlight-angles, road surface condition, visibility, or temperature.”
The collected data can be accessed via international sales partnerships and the in-house data platform from ALP.Lab (www.alp-lab.at/platform).
The beginning of a new era – efficient green testing
Every day, ALP.Lab records and evaluates tens of thousands of traffic movements – with no additional emissions (CO2, noise etc.). The new method is also economically convincing, as it works without expensive measuring vehicles and test drivers. And the clear vote of the international experts in the online voting proves that the method also makes technological sense.
“The winners have set a new standard for innovation and creative technology within the autonomous driving industry,” said Swetlana Torosyan, Producer of the Tech.AD Europe 2021. “This award is a testament to the skill, ingenuity, and vision of the creators.”
Strong partners for the mobility of the future
It took teamwork to make this successful project possible. Therefore, we would like to thank our technology partners Cepton, Bernard Gruppe, LeddarTech, Ouster and Smartmicro, as well as the municipalities Graz, Feldbach, Straden, Tamsweg and St. Michael/Lungau and the project partners Citycom Austria and A1 for their great support.
“This international award is a great confirmation for the whole team and shows the enormous potential of our approach that is both ecologically and economically convincing.”
(Jost Bernasch, Managing Director)