A) Deep Learning for Embedded Automotive Platforms:
The goal is to:
1) Research semi-supervised training methods in order to make neural networks more resilient to adverse imaging conditions, causing the performance drop (wrt. nominal imaging conditions) to decrease with one order of magnitude.
2) Research inference methods that exploit spatio-temporal coherency in video streams, to increase computational efficiency by one order of magnitude.
All research results will be validated in real-world conditions using TU/e’s Highly Automated Driving research vehicle. NXP will make available its Bluebox automotive computation platform.
B) Spread-spectrum Modulated And interfeRence resilienT RADAR:
To develop novel nm CMOS 77-81GHz radars frontends that generate ultra-fast arbitrary radar waveforms that alleviate radar interference through spread spectrum techniques. To exploit smartness concepts in the front-ends such as instantaneous receive signal analysis, self-interference cancellation using known transmit signal properties, etc. To design breakthrough performance building blocks such as beamforming receivers and GHz data converters that support reception of high rate long encrypt bitstreams for coding orthogonality with increased range and velocity resolution. Concepts will be demonstrate on NXP’s modulated radar demonstration platforms that will be made compatible and available for the test chips of this project.
Consortium: NXP Semiconductors BV, TU/e, with the intention of expanding the consortium
An update of the Smart Mobility project
Interview with the project leaders TU/e professors Gijs Dubbelman and Marion Matters.
Building the Future: Fully autonomous driving on public roads is possible in the future
Cars are taking over more and more tasks from drivers. Think of parking or driving on the highway. So, technically a lot is already possible when it comes to autonomous driving. But how realistic is it that in the future a car will take over all tasks from humans?
Smart Mobility @ Eindhoven Engine during DTW
Eindhoven Engine accelerates innovation in the BIn the Smart Mobility project the goal is develop new perception technology for next-generation automated driving systems. The project focusses both on sensors, by researching and prototyping new imaging radar systems, and on artificial intelligence, by researching highly-efficient deep binary neural networks that can interpret sensor data.
Remote working and online conferencing
The corona impact on Smart Mobility
The project is fine,” says Gijs Dubbelman, Assistant Professor in EE-SPS’s Mobile Perception Systems Lab at TU/e. “Everyone is on track and no delay is expected. However, far fewer demos could be done than planned, so the valorization side is leading. Because of the coronavirus, there’s a (good!) focus on research.”