Skip to content
View siddancha's full-sized avatar

Highlights

  • Pro

Organizations

@robustrobotics @r-pad @CMU-Light-Curtains

Block or report siddancha

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
siddancha/README.md

Hi there πŸ‘‹ πŸ‘¨β€πŸ’»

I'm Sid, a research scientist at UC Berkeley working on robot learning. My current research interests are in diffusion/flow-matching policies for robotic manipulation and vision-language-action (VLA) models. Previously, I was a postdoc at MIT working with Nicholas Roy, Leslie Kaelbling and TomΓ‘s Lozano-PΓ©rez.

Previosuly, I was a PhD student in the Machine Learning Department at CMU, co-advised by David Held and Srinivasa Narasimhan. My PhD work developed active perception algorithms for Programmable Light Curtains, a fast and high-resolution depth sensor that needs to be controlled intelligently in order to sense efficiently.

Pinned Loading

  1. streaming-flow-policy streaming-flow-policy Public

    Simplifying diffusion/flow policies by treating action trajectories as flow trajectories

    Jupyter Notebook 124 16