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.
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.
With the support from Eindhoven Engine, this project successfully hired EngD trainees and student assistants enhancing the project’s overall impact. The team also benefited from using the garage in Disruptor, which served as a collaborative workspace for developing the self-driving research vehicle. This co-creation space also served as a showroom, where demonstrations were given to stakeholders and external parties.
Project updates
An update on the Smart Mobility project
Building the Future: Fully autonomous driving on public roads is possible in the future
Smart Mobility @Eindhoven Engine during DTW
A non-invasive approach to treatment
Using EEG- and MR-imaging based transcranial electrical stimulation, the Eindhoven Engine project PerStim (Personalized neurostimulation) investigates how treatments for patients with refractory focal epilepsy and prevalent co-morbid disorders can be personalized effectively. Via transcutaneous direct/alternating current stimulation (tDCS/tACS), the overall aim is to develop personalized, non-invasive neurostimulation protocols to provide (non-)refractory epilepsy patients with a better quality of life. This non-invasive approach to treatment is a method whereby an operation is not needed and treatment outside the body, as it were, is made possible.
Tight technical-clinical cooperation
To realize these ambitions, TU/e has teamed up with Philips Electronics Nederland B.V. and Kempenhaeghe, the Academic Center for Epileptology. UZ Ghent is also involved through the part-time neuromodulation chair of Professor Paul Boon. PPP Allowance co-funding has been made available to Epilepsiefonds by Health~Holland’s Top Sector Life Sciences & Health in order to stimulate public-private partnerships. Project partner meetings take place approximately once per month, with Fontys and TU/e student projects expected to be held in Eindhoven Engine’s building Disruptor. Such close collaboration and the integration of their results in clinical trials will allow for direct testing of PerStim’s neurostimulation hypothesis.
First clinical study
With the support of Eindhoven Engine, PerStim successfully completed the first clinical study and developed a suitable skull model to commence the second clinical study. The project also integrated two Fontys students into the team, whose contributions will be included in a PhD thesis. Additionally, a spin-off project was launched under PerStim to extend the non-invasive neurostimulation approach to transcranial focused ultrasound stimulation. This initiative was further bolstered by recruiting an additional postdoc, in collaboration with the Donders Institute in Nijmegen.
Videos
In the Netherlands one third of the epilepsy patients (100.000+) keep having seizures; even after trying several medicines. The next treatment will be surgery. But there is a promising alternative treatment: neurostimulation.
Rob Mestrom – Project Leader
In this project PerStim Rob Mestrom and his team do research in personalizing neurostimulation for epileptic patients. He does this with a tight technical clinical cooperation with partners TU/e, Philips Electronics, Kempenhaeghe, UZ Ghent, and Epilepsiefonds.
Steven Beumer – PhD candidate
Steven Beumer uses brain images and brain recordings to try to optimize stimulation protocol for patients. Together with Fontys graduation students, they are working on artificially skull that mimics the real skull and its electrical properties.
Infographic

- Creating opportunities to present and discuss Neurotrend’s research findings.
- Providing access to a multidisciplinary workspace for meetings and collaboration.
- Organizing thematic sessions that delivered relevant insights for ongoing research.
This collaboration not only strengthened the research outcomes but also contributed to a dynamic and knowledge‑sharing community.
More project info
Infographic
Infographic

More project info
A simulation of emergency vehicles in connected and autonomous traffic
SmartTwo+: a maverick collaboration in telecoms
More project info
From Unlikely to Unstoppable: Embracing Diversity in the Building Industry
In full speed with students and young professionals
Videos
Marieke van Beurden – Project leader
The POWerFITTing project focuses on the optimization of a person’s vitality both at work and the (home) office to remain healthy and productive.
Steven Vos – Professor Fontys & TU/e
We are optimizing the relationship between vitality and the (home) office environment. By taking into account individual, societal and contextual factors, this enables employees to remain both healthy and productive.
Hans Brombacher – PhD candidate
Hans, PhD candidate in the POWErFITTing project, researches the improvement of a healthier and active environment for people in (home) offices. By the combination of data acquisition, integration and application for the validation and acceleration of user-oriented solutions, Hans is optimizing the relationship between vitality and the (home) office environment.
Infographic

More project info
Human-data interaction to enhance office well-being
Moving faster!
Talkshow ‘a Vital Working Environment’
Key outcomes
iHeat@home gained valuable connections with Brainport stakeholders, including VDL. Periodical sessions broadened the team’s perspective and provided useful feedback from engineers and researchers, speeding up concept development. The project also benefited from access to consortium meeting spaces, student workrooms, and shared lab facilities—offering equipment and test setups not available elsewhere.
Additionally, the project initiated new collaboration between TNO, TU/e, and Fontys on the topic of TCM, strengthening regional knowledge exchange.
Videos
Olaf Adan – Project leader
The Eindhoven Engine project iHeat@Home works on a breakthrough innovation in thermal energy storage: a heat battery which is better, cheaper, smaller and greener than any competitor.
Evelien created an experimental set up and used flow simulations to research the improvement of heat batteries.
Infographic

More project info
Update Carbyon project
Crossover of two Eindhoven Engine projects



