Published multiple papers including CuRobo: Parallelized Collision-Free Robot Motion Generation, STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation, Correcting Robot Plans with Natural Language Feedback, etc. Some works were selected for oral presentations or as finalists for best paper awards.
Research Experience
Senior Research Scientist at NVIDIA Learning and Perception Research Group, led by Dr. Jan Kautz. Worked on cuRobo project, which formulates motion planning as a trajectory optimization problem and uses parallel compute on GPU to solve in 30ms. Also developed the STORM framework, which leverages sampling-based optimization techniques (like MPPI) to optimize over non-differentiable cost terms.
Education
Received a Ph.D. in Computing (Robotics) from the University of Utah under the supervision of Prof. Tucker Hermans. Ph.D. research focused on planning and tactile perception for in-hand manipulation leveraging trajectory optimization, learned models, and structured inference.
Background
Research interests include enabling robots to navigate and interact in unstructured environments, involving perception, machine learning, numerical optimization, and control theory. Focuses on the efficient and practical implementation of invented techniques in modern robotic systems.
Miscellany
Personal interests and other information not provided.