Pratik Kunapuli

prof_pic.jpg

I’m a doctoral student in Computer and Information Science (CIS) at GRASP at the University of Pennsylvania. I am co-advised by Vijay Kumar and Dinesh Jayaraman, and am grateful to be supported by the NSF as a GRFP Fellow. My research interests lie at the intersection of machine learning and robotics, specifically related to using reinforcement learning for control of agile and dynamic systems as well as transferring learning approaches from simulation to the real world (sim2real).

Previously, I completed both my BSc and MSc at Georgia Institute of Technology in Electrical and Computer Engineering. During my time there, I worked with Aaron Young in the Exoskeleton Prosthetic Intelligent Controls Lab (EPIC Lab) initially developing controllers for a powered knee and ankle prosthetic and eventually applying machine learning-based state estimation to autonomous hip exoskeletons. My work culminated in my Masters thesis, “Online Adaptation of User State Estimation in a Powered Hip Exoskeleton using Machine Learning”.

Curriculum Vitae

News

Feb 10, 2025 Two papers were accepted to ICRA 2025 in Atlanta this year! Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems and Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance will be presented as posters in person.
Dec 14, 2024 Honered that our work Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems was awarded the Best Paper Award in the Neuroscience and Interpretability track in the NeurReps Workshop at NeurIPS 2024! This is one of three best paper awards from the workshop, and this work wouldn’t have been possible without the oustanding work of my co-first-authors Jake Welde and Nishanth Rao!
Nov 29, 2024 Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems was accepted as an oral presentation at the NeurReps workshop at NeurIPS 2024!
Oct 11, 2024 Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems will be presented at the SymRob workshop at IROS 2024!

Selected Publications

  1. Under Review
    Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
    Pratik Kunapuli, Jake Welde, Dinesh Jayaraman, and Vijay Kumar
    Under Review, , 2025
  2. NeurIPS / ICRA
    Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems
    Pratik Kunapuli*, Jake Welde*, Nishanth Rao*, Dinesh Jayaraman, and Vijay Kumar
    ICRA 2025, IROS 2024 (Equivariant Robotics Workshop); NeurIPS 2024 (NeurReps Workshop) - Oral (Best Paper Award), 2025
  3. ICRA
    Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance
    Anish Bhattacharya, Nishanth Rao, Dhruv Parikh, Pratik Kunapuli, Nikolai Matni, and Vijay Kumar
    International Conference on Robotics and Automation (ICRA), 2025
  4. IEEE RAL
    Real-Time Gait Phase Estimation for Robotic Hip Exoskeleton Control During Multimodal Locomotion
    Inseung Kang, Dean D. Molinaro, Srijan Duggal, Yanrong Chen, Pratik Kunapuli, and Aaron J. Young
    IEEE Robotics and Automation Letters, 2021
  5. IEEE TMRB
    Real-Time Neural Network-Based Gait Phase Estimation Using a Robotic Hip Exoskeleton
    Pratik Kunapuli*, Inseung Kang*, and Aaron J. Young
    IEEE Transactions on Medical Robotics and Bionics, 2020

Mentored Students

Current Students

Nishanth Rao : Robo MS, UPenn
Bryan Alfaro : Robo MS, UPenn

Past Students

Harsh Goel : Robo MS, UPenn PhD, UT Austin
Akshay Manikandan : Robo MS, UPenn Tech Consultant, Birlasoft