Dr. Sergey Levine
UC Berkeley / Physical Intelligence
Associate Professor of EECS at UC Berkeley and co-founder of Physical Intelligence (Pi). World-renowned pioneer of deep reinforcement learning for robotic control, vision-action models, and the generalist physical foundation model π₀ (pi_0).
Areas of focus
Professional niches
Proof of Work
End-to-End Training of Deep Visuomotor Policies
Published the foundational Journal of Machine Learning Research paper proving that robotic controllers can map raw camera pixels directly to continuous motor torque voltages using guided policy search.
Direct pixel-to-torque policies are vulnerable to novel environmental lighting and visual background shifts.
Context: Convolutional neural network visuomotor policies operating on physical PR2 robotic systems.
View missionπ₀ (pi_0): Generalist Physical Intelligence Robot Foundation Model
Co-developed π₀, a generalist physical intelligence foundation model trained across diverse robotic embodiments and tasks, demonstrating zero-shot physical manipulation, folding laundry, and assembly.
Physical real-world manipulation requires sub-millisecond control loops and collision avoidance safeguards.
Context: Flow-matching vision-action transformer architecture controlling multi-degree-of-freedom robotic arms.
View mission