I am a research assistant at IIIT-Hyderabad, currently advised by Prof. K. Madhava Krishna (IIIT-Hyderabad) and Prof. Arun Kumar Singh (University of Tartu) in the Robotics lab (RRC), and Prof. Makarand Tapaswi (IIIT-Hyderabad) and Dr. Vladimir Petrik (CTU, Prague) in the Computer Vision lab (CVIT). I currently work at the intersection of generative models, robot learning, and video understanding.
I earned my Bachelor of Technology with honors in Computer Science and Engineering (CSE) from IIIT-Hyderabad, India. During my undergraduate years, I led various projects involving robotic manipulators, reinforcement learning, motion planning, and collision avoidance, under the guidance of Prof. K. Madhava Krishna.
Research Interests: I see a future where robots are omnipresent, replacing human labor in dangerous or boring tasks, speeding up science, and scaling up accessibility to resources that are otherwise difficult to reach. The two big bottlenecks for this are perception and action (sounds like pretty much everything, but not really, ha ha!). I work on scalable Perception ('Perception Heads') and Action modules ('Action Tails'), with a subtle twist on Sutton's Bitter Lesson.
- Everything is theoretically impossible, until it is done - Robert A. Heinlein
Publications
|
EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning* denotes equal contribution and random author order |
|
Disentangling Planning and Control for Non-prehensile Tabletop Manipulation |
|
Approaches and Challenges in Robotic Perception for Table-top Rearrangement and PlanningAditya Agarwal*, Bipasha Sen*, Shankara Narayanan V*, Vishal Reddy Mandadi*, Brojeshwar Bhowmick, K Madhava Krishna * denotes equal contribution and random author order |