Phd position foundation models for autonomous vehicle perception

Autonomous vehicles have been shown to underperform when deployed on conditions that differ substantially from the training conditions, so-called domain gaps. These domain gaps can include deployment in different regions, weather or using different sensors. Numerous domain adaptation methods have been proposed to bridge these domain gaps and let the model operate well on the target data. In this project we seek to find an intermediate representation for data coming from varied sources. By bringing new data into this representation, we overcome domain gaps and are able to train models that are robust to different conditions, also referred to as foundation models. While foundation models have achieved widespread success on images and text, currently few exist for lidar and radar data, making this a promising research direction. These foundation models will bring superior performance and allow us to utilize data from varied sources, thus reducing the data collection and labeling costs.

The Intelligent Vehicles group at TU Delft, the Netherlands, invites applications for a fully funded 4-year PhD position in the area of foundation models for autonomous vehicles. This position is partially funded by the EU Horizon project Cynergie4MIE, as well as by internal funding sources. Due to this combination, the topic for the last 1.5 years is somewhat flexible. Large Language Models and/or Gen AI are two potential topics, as long as they fit into the overall thesis direction.

Your results will be published in top tier conferences like CVPR, ICCV, ECCV, ICRA and NeurIPS. For your work you will have access to the compute resources of TU Delft, ranging from personal machines, to shared GPU servers, the Delft AI Cluster that is shared across departments, as well as DelftBlue, which is one of the top 250 supercomputers in the world. Your main supervisor will be Dr. Holger Caesar, creator of the nuScenes dataset and co-author of the PointPillars method for lidar-based object detection. You will receive hands-on mentoring for your career development.

• We are seeking PhD applicants with an interest in performing cutting edge research in an active and exciting research area.
• Prospective applicants should have a strong academic record with a solid background in sensor processing (vision/radar/lidar, sensor fusion) and Machine Learning (Deep Learning, domain adaptation, foundation models).
• Good programming skills (Python/Matlab) and knowledge of deep-learning frameworks (PyTorch/TensorFlow) are expected.
• A certain affinity towards turning complex concepts into real-world practice (i.e. Vehicle demonstrator) is desired.
• The successful candidate is expected to be able to act independently as well as to collaborate effectively with members of a larger team and supervise Master students.
• Good English skills are required.

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

At TU Delft we embrace diversity as one of our core values and we actively engage to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. That is why we invite you to apply. Your application will receive fair consideration.

Challenge. Change. Impact!

From chip to ship. From machine to human being. From idea to solution. Driven by a deep-rooted desire to understand our environment and discover its underlying mechanisms, research and education at the ME faculty focusses on fundamental understanding, design, production including application and product improvement, materials, processes and (mechanical) systems.

ME is a dynamic and innovative faculty with high-tech lab facilities and international reach. It's a large faculty but also versatile, so we can often make unique connections by combining different disciplines. This is reflected in ME's outstanding, state-of-the-art education, which trains students to become responsible and socially engaged engineers and scientists. We translate our knowledge and insights into solutions to societal issues, contributing to a sustainable society and to the development of prosperity and well-being. That is what unites us in pioneering research, inspiring education and (inter)national cooperation.

Click here to go to the website of the Faculty of Mechanical Engineering. Do you want to experience working at our faculty? These videos will introduce you to some of our researchers and their work.

• CV
• Motivational letter

Doing a PhD at TU Delft requires English proficiency at a certain level to ensure that the candidate is able to communicate and interact well, participate in English-taught Doctoral Education courses, and write scientific articles and a final thesis. For more details please check the Graduate Schools Admission Requirements.

• You can apply online. We will not process applications sent by email and/or post.
• A pre-employment screening can be part of the selection procedure.
• For the final candidates, a knowledge security check will be part of the application procedure. For more information on this check, please consult Chapter 8 of the . We carry out this check on the basis of legitimate interest.
• Please do not contact us for unsolicited services.