The fulfillment of the promise of the self-driving car takes longer than everyone hoped. But that shouldn’t detract from the fact that vehicles are getting smarter. And they will continue to do so until we’re ready to – slowly but surely – let go of the steering wheel.
Provided, of course, that the core technologies behind advanced driver assistant systems (ADAS) can evolve fast enough.
We need affordable on-chip sensors to scan the car’s environment – in all road and weather conditions. There could be a special role there for LiDAR, if its system size and cost can be significantly reduced.
Novel sensor fusion algorithms can then combine the data into a full picture. And advanced energy-aware AI software can turn information into knowledge.
The result will be a truly intelligent driving system. One that’s not only aware of traffic, but can assess situations, anticipate future events, and take timely action.
Realizing these advances will be far from effortless. It will require a quantum leap forward instead of incremental improvements.
The massive amounts of data involved can only be processed by an AI-driven sensor fusion & compute architecture that reaches an energy-efficiency that’s up to 1,000 times higher than the current state of the art. If not, tomorrow’s ‘computers on wheels’ won’t even make it out of the driveway before they run out of power.
In this webinar, imec experts Steven Latré and Marcus Dahlem present the paths imec is exploring to enable next-gen ADAS. They present recent advances on the integrated photonics components for solid-state LiDAR, introduce novel sensor fusion strategies, explain why system requirements are essential for efficient technology development, and how this ties in with imec’s position in the automotive ecosystem.
Are you active in the automotive industry and interested in its innovation potential? Then you'll surely pick up some new insights from this webinar – whether or not you’re in a technical, commercial or executive role.
Prof. Steven Latré, is leading the artificial intelligence research at imec. His main expertise focuses on combining sensor technologies and chip design with AI to provide end-to-end solutions. Next to this, he’s also a part-time professor at the University of Antwerp.
Steven received a Master of Science degree in computer science and a Ph.D. in computer science engineering from Ghent University. Before joining imec, he led the IDLab research group at the University of Antwerp, a 100+ research group focusing on wireless networks and machine learning. He is the author or co-author of more than 150 papers published in international journals or in the proceedings of international conferences. He is the recipient of the IEEE COMSOC award for best PhD in network and service management 2012, the IEEE COMSOC Young Professional award 2015, and the Laureate award of the Academy of Sciences, Belgium.
Dr. Marcus Dahlem joined imec in 2018 as principal member of technical staff, and is currently the program manager for optical 3D sensing technologies, where he leads a team developing solid-state LiDAR systems.
Marcus obtained his Licenciatura degree (BSc+MSc) in applied physics (optoelectronics and lasers) from the University of Porto, and his MSc and PhD degrees in electrical engineering from MIT, working in the optics and quantum electronics group at the research laboratory of electronics. He has co-authored over 110 peer-reviewed papers in journals and conference proceedings. Before joining imec, he was an associate professor and the director of the center of excellence on integrated photonics at the Khalifa University of Science and Technology in Abu Dhabi. He also worked at the IBM Zurich Research Laboratory in the exploratory photonics group, and at the Institute for Systems and Computer Engineering of Porto (INESC Porto) in the optoelectronics group. In addition, he served as a teaching assistant at MIT and as a laboratory instructor at the University of Porto.