Tony Tao
Tony Tao is a robotics researcher at Carnegie Mellon University, where he completed his master's degree in the School of Computer Science in 2025. His research focuses on robot learning, reinforcement learning, and imitation learning, with a particular emphasis on force-aware manipulation and scaling embodied data for robot learning. He is known for his work on the FACTR and FACTR 2 projects on contact-rich policy learning, the DexWild system for dexterous in-the-wild robot policies, and the AnyCar universal dynamics model for agile mobility.
“NEXT (Neural External Torque Estimation) trains a small LSTM on 10 minutes of free-motion data — no contact, no labels, no force sensor required — and achieves external torque estimation accuracy of 0.547 ± 0.348 Nm L1 error during contact on a Franka arm”
Source→“Tony Tao | Carnegie Mellon University | Equal-contribution first author, part of the CMU core team. Contributed to both FACTR and FACTR 2, indicating sustained focus on force-aware manipulation.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.