BS-MS
Sattwik Kumar Sahu
I develop large-scale multimodal models for zero-shot robot navigation and generative control, deploying them on real hardware, with a focus on self-supervised representation learning and latent predictive world models for robotics.
Research Interests
Multimodal Models
Embodied Intelligence
Self-supervised Learning
World Models
Off-road Navigation
Human-in-the-Loop Systems
Unmanned Ground Vehicles