Postdoctoral Researcher, Foundation Models for Driving
Human Interactive Driving Human Interactive Driving /
For a complete understanding of this opportunity, and what will be required to be a successful applicant, read on.
At Toyota Research Institute (TRI), we’re on a mission to improve the quality of human life. We’re developing new tools and capabilities to amplify the human experience.
To lead this transformative shift in mobility, we’ve built a world-class team in Robotics, Human-Centered AI, Human Interactive Driving, and Energy & Materials.
We are looking for a data-driven robotics researcher with a strong background in embodied machine learning and a make it happen mentality who is interested in spending a year collaborating with our research team as a visiting scholar to drive the state-of-the-art in prediction and behavior learning for automated driving.
The ideal candidate is able to operate independently when needed but works well as part of a larger integrated group at the cutting edge of state-of-the-art robotics and machine learning.
Experience with robots or other embodied systems (such as autonomous vehicles) is strongly preferred.
An ideal candidate has a proven track record of leading independent research efforts, preferably including mentoring and collaborating with less experienced students and researchers.
A current postdoc looking to take an additional year of research before beginning a faculty position would be a great fit for this role, as would a more experienced existing faculty member looking to take a year-long sabbatical with us.
This position requires a hands-on researcher interested in formulating research ideas and implementing and evaluating them in collaboration with our team.
We expect this position to result in peer-reviewed publications, including the potential for ongoing long-term collaboration with TRI.
Responsibilities
- Conduct ambitious research to advance the state-of-the-art in using new capabilities in generative AI (e.g., recent results in diffusion policy 1 , 2 ) for end-to-end perception, planning and prediction in automated driving with a focus on computer vision as the primary sensing modality
- Push the boundaries of knowledge and implement, extend, and create innovative methods for prediction and behavior learning from human-driving data
- Work with high-performance machine-learning pipelines and deploy onboard for closed-loop evaluation with scalability, efficiency, and performance in mind
- Collaborate with a multidisciplinary team including other researcher scientists and engineers across TRI, Woven by Toyota, and university partners
- Take the lead on writing and publishing research results in peer-reviewed venues
Qualifications
- A PhD in a robotics-relevant / embodied-AI field such as Computer Science, Mathematics, Physics or Engineering
- Consistent track record of publishing at high-impact conferences / journals (CVPR, ICLR, NeurIPS, ICML, CoRL, RSS, ICRA, ICCV, ECCV, PAMI, IJCV, etc.)
- A strong background of independent research
- Ability to independently formulate and implement a research agenda while collaborating with partners across a spectrum of subject areas
- Sufficient software engineering proficiency to implement and evaluate research ideas. We generally work in C++ and Python internally, and experience with either of those languages is a strong bonus.
Please add a link to Google Scholar and include a full list of publications when submitting your CV to this position.
J-18808-Ljbffr