Units:

12

Description:

Radar is an important sensing technology for autonomous systems, and is ubiquitous in modern vehicles as a critical sensor for autonomous driving systems. As a robust, compact, low-cost, and privacy-preserving sensor, radars also have many applications in indoor and human sensing. However, while these applications are largely learning-driven, to date, there has been relatively limited work on sensing methodologies which integrate radar sensing and machine learning at a fundamental level.

This research-focused course will cover the fundamentals of modern FMCW radars, and provide students with a Machine Learning or Wireless Sensing background the knowledge and skills needed to effectively engage in cross-disciplinary collaborations which push the frontiers of Machine Learning-enabled Radar Sensing. The course will feature traditional lectures covering key background, as well as research lectures covering the current state-of-the art and guest lectures from academic researchers and industry insiders. Students will also gain experience working with mmWave radars, as well as large datasets collected from these systems. Finally, students will complete a research project applying Machine Learning techniques to mmWave radar or a wireless sensing modality of their choice.

This course targets PhD, MS, and advanced undergraduate students.

All students should have:
Some machine learning knowledge, e.g., 10-202, 10-301, 18-661
Ability to write python code and use ML frameworks, e.g., Pytorch
Undergraduate-level linear algebra and probability

Students should also have either further machine learning or wireless sensing/communications background.
ML: Any upper-division or graduate-level ML course, e.g., any 106XX any 107XX course
Wireless: Any wireless communications course, e.g., 18-750/18-452

Last Modified: 2026-04-15 12:02PM

Semesters offered:

• Fall 2026
• Spring 1998