TU/e is opening several PhD and PDeng vacancies in the field of Robust AI for automotive signal processing ICs:
- PhD position on AI for radar multipath classification and removal.
- PDEng position on Radar Data Base development.
- PhD position on smart digital filters for audio processing.
- PhD position on smart digital filters for radio broadcast interference rejection in electrical vehicles.
- PhD position on AI assisted calibration for data converters.
Background:Future cars will incorporate ever more artificial intelligence (AI) to support driver safety, navigation, and comfort. Much of this AI will be embedded in integrated circuits (ICs) that serve, for example, to sense and perceive the car's environment and to support wireless communication and radio reception.
To help drive this development TU/e has teamed up with NXP, the globally leading Automotive IC design company, in a joint research program. In this program PhD and PDEng students will be co-supervised by top AI experts from TU/e and top automotive IC-design experts from NXP, and students will also be hosted by NXP on a part-time basis. As a result, the positions in the program offer a unique combination of high-quality scientific and industrial experience.
The following positions in this program are still available:
1. PhD position on AI for radar multipath classification and removalRadar is an important sensor modality for mobile perception, and future cars are expected to contain multiple radar ICs distributed across the surface of the car. Future radar ICs will require increased range, velocity and angular resolution and this causes an increasing number of false detections due to multipath reflections. These false detections can overload radar target lists and mislead target classification and autonomous driving tasks.
This PhD position aims to investigate AI techniques that exploit multipath propagation models for strongly improved real-world radar multipath/clutter detection and labeling. We consider
neural augmentation and combinations of generative and discriminative deep neural modeling as viable strategies to exploit and integrate prior domain/physics knowledge into modern AI solutions. Besides high performance, the techniques should also permit
real-time implementation and hence the tradeoff between performance and implementation complexity will figure prominently.
2. PDEng position on Radar Data Base developmentFor the develpment of radar AI techniques a rich data base of real-world radar data is essential. Within NXP an experimental car equipped with radar sensors is available for this purpose. This PDEng position is aimed at upgrading this car for future research needs. The candidate is expected to familiarize him/herself with the existing car (HW and SW), collect the upgrade requirements by interfacing with the multiple stakeholders and design and implement the upgrade with regular interactions with the stakeholders and the support of NXP experts. The candidate is also expected to support the implementation of measurement campaigns, use the car to collect data for specific experiments and ensure that the database is properly populated with the collected data.
N.b.: the Professional Doctorate in Engineering (PDEng) program is a 2-year program that develops students' capabilities to work within a professional engineering context, in an application- and system-design-oriented setting.
3. PhD position on smart digital filters for audio processingModern headphones, earbuds and hearing aids already have active noise cancelation. However, the user experience must be further improved. Whether a component of an audio signal contains relevant information or just irrelevant noise depends on the context. E.g., while most environmental noises must be suppressed, certain alarms or anomalous sounds might have to be passed on to the user. Or, a hearing aid should help its user to focus on a certain conversation in a setting with many simultaneous speakers (the cocktail party effect). This might be done by adaptive spectral/spatial digital filtering of multi-channel audio signals. Again, the required filter response depends on the context. In addition, user feedback might be used for adaptive selection of the operation mode (listening to music, following a conversation, etc.) and personalization.
This PhD position seeks to develop neural network-based (controllers for) multi-channel adaptive filters that accomplish these objectives at low latency and complexity levels consistent with ultra-low-power implementation as required e.g. for hearing aids. To train these networks an existing data base of labeled audio signals will be exploited and further extended. We envisage
hybrid AI solutions in which neural networks efficiently predict auto-labeled target filter coefficients from extracted audio signal features (e.g. Mel-spectrograms). Validation of the developed approach will moreover require
innovative neural model compression solutions that are tailored to the hardware specifications, facilitating hardware implementation and convincing real-time demos.
4. PhD position on smart digital filters for radio broadcast interference rejection in electrical vehiclesInterference is a common problem in wireless communications and is becoming more severe as the wireless spectrum becomes more crowded. Conventional interference rejection methods focus on radiated interferences, which originate from dedicated wireless transmitters. Recently, due to the fast development of electrical vehicles, a new vehicle-internal type of interference has emerged. For example, it is observed that DC/DC converters in electrical-cars introduce significant interference to radio receivers from the low-frequency (around 1 MHz) Amplitude Modulation (AM) signal-band all the way up to the Digital Audio Broadcasting (DAB) band (around 200 MHz). This new type of interference differs from the conventional interference in many respects. For example, it varies widely in time, frequency, and among different car models, and no statistical or deterministic interference models are available yet.
As such, this PhD position seeks to go all the way from
characterizing and modeling these statistically complex interferences using generative AI models (e.g. normalizing flows, VAEs or score-based models) to developing and validating
AI based techniques to suppress it. Also here algorithmic complexity is an essential constraint, and complexity levels should be consistent with low-power real-time implementation.
5. PhD position on AI assisted calibration for data convertersTechnology downscaling has been very beneficial for digital processers, but it has created major challenges for the implementation of analog front-ends and data converters. As the size of transistors decrease, they become more sensitive to process variation, exhibit worse matching, and become more noisy, exhibiting high levels of 1/f fluctuations. These trends end up limiting the resolution of data-converters. To achieve automotive-worth, 5-6 sigma coverage of key performance parameters, accurate calibration loops are needed to precisely tune or compensate circuit mismatches. Calibration of static first-order errors (for example the bandwidth variation of a filter) is straightforward and widely used. Calibration of (a multitude of) second- or higher order and dynamic errors over product lifetime, is extremely challenging in terms of prediction and extraction of (non-orthogonal) frequency dependent non-linear errors.
This PhD position seeks to investigate machine learning techniques (in the analogue and digital domain) for stand-alone circuit self-calibration, and to investigate the capability of learning machines to perform periodic adaptation to operating conditions and/or aging of the circuits, while optimizing test cost and performance. Architectural, algorithmic and transistor-level design approaches will be considered in this challenging exploration. Hands-on e
xperience with custom integrated circuit design is a fundamental prerequisite for the successful candidate.For all of these positions we are looking for talented, team-working-oriented and inquisitive candidates with an electrical engineering background and strong signal processing or AI skills. Applications from computer science and AI MSc students with strong affinity for signal processing, sensing and hardware implementation are also welcomed.