- This event has passed.
Spring 2026 GRASP SFI: Chris Paxton, Agility Robotics, “How Close Are We To Generalist Humanoid Robots?”
February 11 @ 3:00 pm - 4:00 pm
This was a hybrid event with in-person attendance in Levine 307 and virtual attendance…
ABSTRACT
With billions of dollars of funding pouring into robotics, general-purpose humanoid robots seem closer than ever. And certainly it feels like the pace of robotics is faster than ever, with multiple companies beginning large-scale deployments of humanoid robots. In this talk, I’ll go over the challenges still facing scaling robot learning, looking at insights from a year of discussions with researchers all over the world.
In particular, there are three areas where robotics is changing quickly: (1) humanoid whole body control is increasingly solved, and we’re learning to leverage the whole body of a humanoid robot effectively; (2) scaling of both robotics data and hardware is now possible in ways it never has been before; and (3) methods like world models and VLAs are finally showing real progress towards building general-purpose robot brains. Ultimately, I will argue that the biggest challenge remaining is evaluation: that distinguishing signal from noise in robotics research is too hard, and that we ultimately must rely on real-world deployments.
Presenter
Chris Paxton
Chris Paxton leads AI innovation at Agility Robotics and co-hosts the RoboPapers podcast covering cutting-edge robotics research. He’s a roboticist who has worked for FAIR labs at Meta, NVIDIA research, and Hello Robot, as AI lead. He got his PhD in Computer Science in 2019 from the Johns Hopkins University in Baltimore, Maryland, focusing on using learning to create powerful task and motion planning capabilities for robots operating in human environments. His past research has looked at using language, perception, planning, and policy learning to make robots into general-purpose assistants.