About me

NOTE: Website content is not updated frequently. Please check LinkedIn for the most recent updates.

I am a Robotics Researcher at Samsung Research America, working on robot learning and multimodal foundation models for contact-rich manipulation. My current research focuses on World Action Models (WAMs), dexterous manipulation, and multimodal learning for physical interaction, with the broader goal of building general-purpose robot intelligence for home and manufacturing applications.

I completed my M.S. in Robotics at Georgia Tech, where I worked with Dr. Danfei Xu in the Robot Learning and Reasoning (RL2) Lab on robot learning from embodied human data. My research spanned bimanual and mobile manipulation, Vision-Language-Action models, and embodiment-agnostic representation learning, with projects including EgoMimic, EgoBridge, and EgoMimic-Mobile. I also contributed to EgoVerse, a broader multi-institution effort on embodied human data for robot learning involving researchers from UC San Diego, Stanford, ETH Zurich, Meta AI, and other collaborators.

Across academia and industry, I have worked on robot learning, computer vision, autonomous systems, SLAM, and embodied AI. I have worked at Path Robotics on an initial robot learning POC for manufacturing manipulation; at Honda Research Institute USA on perception and scene understanding for autonomous vehicles at intersections; and as a Google Summer of Code contributor on differentiable SLAM and multi-framework support for GradSLAM.

Prior to Georgia Tech, I was a Research Associate at the Robotics Research Center, IIIT Hyderabad, focusing on adverse-weather perception for autonomous driving in collaboration with Queensland University of Technology (QUT) and ZF Friedrichshafen, while also leading research on UAV-based visual remote sensing for automated building inspection and civil infrastructure assessment. Earlier, I contributed to SLAM and LiDAR mapping for autonomous driving at Swaayatt Robots and held a Software Engineering role at Amdocs.

My broader research interests lie in robot foundation models, multimodal robot learning, dexterous and contact-rich manipulation and learning from human data.

I am always open to research collaborations, technical discussions, and interesting conversations around AI and Robotics. Feel free to connect with me on LinkedIn or reach out via email.

Recent

• May '25: Extended EgoMimic to study behavior and scene-level generalization from human data. Also, a part of active collaborative effort on collecting large-scale embodied human dat for robot learning (More details soon!)
• Feb '25: Meta AI did a story covering our work - EgoMimic. Check it out here. EgoMimic is also accepted at ICRA 2025
• Jan '25: Starting as Graduate Teaching Assistant for CS 3630: Intro to Perception and Robotics.
• Nov '24: Presented EgoMimic at Conference on Robot Learning (CoRL) 2024 (Munich, Germany)
• August '24: Graduate Teaching Assistant for CS6476: Computer Vision
• May '24: Summer Intern at Honda Research Institute, USA.
• Jan '24: Graduate Teaching Assistant for CS4476: Intro to Computer Vision.
• Nov '23: Started working with Prof. Danfei Xu at the Robot Learning and Reasoning Lab (RL2), Georgia Tech.
• August '23: Started MS in Robotics at Georgia Tech! Graduate Teaching Assistant for CS6476: Computer Vision.
• May '23: Proposal accepted at Google Summer of Code (GSoC)!
• May '23: Presented GDIP at ICRA 2023.
• Nov '22: Presented SRTGAN at CVIP 2022.
• Oct '22: Presented UVRSABI as a spotlight paper at CVCIE workshop, ECCV 2022.
• Sept '22: UVRSABI released as an open-source software at IHub Data Mobility Summit 2022 and would be used for deployment of civil inspection by CRRI (Govt. of India).