Model Matters: Leveraging Geometry in Robot Learning

Rob Platt

Associate Professor, Northeastern University

Attendance Link: https://tinyurl.com/robosem-spr-2026

Abstract

Today, most robot learning models ignore the geometry of the environment, focusing instead on enlarging model and dataset size. Whereas this approach has been very successful in language and vision, geometry is more important in robotics than in those fields. How can we leverage geometric sructural priors in robot learning? In this talk, I will summarize our recent work on this topic and make predictions about the future.

Bio: Robert Platt is an associate professor in the Khoury College of Computer Sciences at Northeastern University, based in Boston. He is also affiliated with the College of Engineering.

Platt's work primarily focuses on perception, planning, and control for robotic manipulation, with the goal of enabling robots to perform manipulation tasks in the context of real-world perceptual uncertainties. This area of study is essential to performing robotic assembly or repair tasks, or simply grasping and lifting objects in everyday environments. Platt expects robust robotic manipulation will have a range of future applications in the home, health care, manufacturing, hazardous environments, and the military.

Before joining Northeastern, Platt was a research scientist at the Massachusetts Institute of Technology and a robotics engineer at NASA.

Please visit https://stanfordasl.github.io/robotics_seminar/ for this quarter’s lineup of speakers. Although we encourage live in-person attendance, recordings of talks will be posted also.