Vision and learning for sim-to-real robots
I'm in my final year of doctoral studies and looking for a job starting Spring 2026!
Some topics of interest: multimodal perception, policy adaptation from simulation or large data corpora, leveraging uncertainties of large models, and learned navigation policies.
I am a doctoral student at GRASP with Nikolai Matni and Vijay Kumar. I aim to improve real robot agility and ability with novel perception and learning techniques. In practice, this has recently meant working on bridging the sim-to-real gap in vision-based quadrotor navigation policies. I've interned at Microsoft Research and Zoox and have been a visiting student at RPG (Davide Scaramuzza). I'm grateful to be supported by the NSF GRFP.
Check out my recent research with the links below or feel free to contact me!
anish1 [at] seas.upenn.edu