|Published||November 18, 2022|
Eindhoven University of Technology is home to the Mobile Perception Systems lab that researches computer vision and machine learning to improve perception technology of mobile autonomous systems. The MPS lab has a strong background in scene parsing methods such as semantic and panoptic segmentation and vision-based motion and collision prediction methods. In total, the MPS lab has 5 fully funded PhD and/or postdoc positions covering specific topics but there is also the opportunity to define your research.
Our research positions:
We are looking for highly motivated candidates to work on any of the following topics (when applying for a position, you can choose to focus your application letter on one of them) :
- Multi-modal self-supervised learning for vision and radar-based collision risk prediction
- Due to the complexity of collision risk prediction of an autonomous vehicle in urban conditions, and the many edge cases that can be encountered, it is practically impossible to gather comprehensive enough training data. The solution space that will be explored consists of a combination of i) learning from auxiliary simulated tasks, ii) domain randomization and iii) domain invariant/resilient deep representations.
- Multi-objective neural architecture search for resource-constrained inference
- Considering Multi-objective Neural Architecture Search, the research will explore (i) how to define a radar-targeted DNN search space, (ii) how to efficiently explore that space while not being overly constrained to straightforward solutions, (iii) which hardware-aware metrics are realistic, relevant, and feasible to evaluate and optimize.
- Explainable inference for safety-critical decision-making by autonomous vehicles
- This research requires rigorous analysis of the concepts ‘explainable’, ‘interpretable’, and ‘transparent’ and relating these concepts to the specific requirements of stakeholders in autonomous driving. On this basis, it is possible to derive concrete technical requirements and to research and improve state-of-the-art techniques from Explainable AI, such as saliency mapping, counterfactual explanation, and linear approximation, to satisfy the requirements.
- Self-supervised continual learning at the edge
- Many AI systems are deployed at the edge, e.g. in an autonomous vehicle or robots, and require updating their off-line trained models according to experiences in the environment. This research focuses on self-supervised training techniques, such as those used in state-of-the-art unsupervised domain adaption, to continuously update and improve the model from experiences in the deployment environment. Specific focus is needed on the resource constraints that exist at edge devices.
- Open application
- If you have a proven and strong academic track record and you want to work on your research ideas that are related to computer vision and machine learning for mobile autonomous systems, then send us your research proposal.
What are you going to do:
You are going to carry out AI research in one of the projects mentioned above, as part of the MPS lab. There will be regular interactions with researchers at NXP Semiconductors. At the Eindhoven University of Technology, your primary supervisor will be dr. Gijs Dubbelman. The goal of the research is to develop and validate new machine learning and computer vision methods within the context of one of the three research projects;
- Collaborate with other researchers within the MPS lab.
- Regularly present intermediate research results at international conferences and workshops, and publish them in proceedings and journals.
- Assist in relevant teaching activities.
- And, in case of a PhD position, complete and defend a PhD thesis within the official appointment duration of four years.
Your experience and profile:
- A Master’s degree in Artificial Intelligence, Computer Science, Engineering, or related field.
- An excellent education profile (cum laude) and a (about to be) published MSc. thesis.
- A strong background in computer vision and machine learning.
- Excellent programming skills in Python.
- Solid mathematics foundations, especially statistics, calculus and linear algebra.
- You are highly motivated and creative.
- You have a research-oriented attitude with an analytical mindset.
- You like to write publications and give presentations on your research.
- Excellent communication, presentation, and writing skills in English.
Conditions of employment
- A meaningful job in a dynamic and ambitious university with the possibility to present your work at international conferences.
- In the case of a PhD position, full-time employment for four years, with an intermediate evaluation after one year.
- In the case of a Postdoc position, full-time employment for two years, with an intermediate evaluation after which the contract can be extended for another two years.
- The start date would ideally be March 1, 2023, but is flexible.
- To support you during your PhD and to prepare you for the rest of your career, you will have free access to a personal development program for PhD students (PROOF rogram).
- A TU/e Postdoc Association that helps you to build a stronger and broader academic and personal network, and offers tailored support, training and workshops.
- A gross monthly salary and benefits under the Collective Labor Agreement for Dutch Universities. For PhDs, the gross monthly salary, based on 38 hours per week, ranges between €2,541 to €3,247. For postdocs, the gross monthly salary starts at €3,557 (the salary depends on the experience).
- Additionally, an annual holiday allowance of 8% of the yearly salary, plus a year-end allowance of 8.3% of the annual salary.
- Should you come from abroad and comply with certain conditions, you can make use of the so-called ‘30% facility’, which permits you not to pay tax on 30% of your salary.
- A broad package of fringe benefits, including an excellent technical infrastructure, moving expenses, and savings schemes.
- Family-friendly initiatives are in place, such as an international spouse program, and excellent on-campus children's daycare and sports facilities.
- A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.
Information and application
Eindhoven University of Technology is an internationally top-ranking university in the Netherlands that combines scientific curiosity with a hands-on attitude. Our spirit of collaboration translates into an open culture and a top-five position in collaborating with advanced industries. Fundamental knowledge enables us to design solutions for the highly complex problems of today and tomorrow.
Are you inspired and would like to know more about working at TU/e? Please visit our career page.
We invite you to submit a complete application by using the Apply button.
Applications should include the following information to be provided in two separate pdf files:
File 1: a detailed CV including the months (not just years) when referring to your education and work experience; a transcript of your MSc. diploma including course names and grades; a list of your publications; the contact details of two references who can provide letters of recommendation (please do not include any letters).
File 2: a letter of motivation including a 2-page plan on how your research is going to contribute to beyond state-of-the-art research on the specific project topics. In case you apply for a position on basis of your research idea, provide a 1-page motivation together with the 2-page research plan.
We are looking for candidates that can contribute to the project’s research objectives directly from the start. Therefore, a strong motivation letter and research plan are a must to be considered a candidate for the research positions. Only complete applications will be considered.
A selection of applications will be invited for job interviews. During the interviews, the applicants will be asked to present and defend their research plans. If completed successfully and depending on the candidate, we will ask the candidate to do a specific assignment of which the results will need to be presented during a second interview.