Kushal Kedia

kk837@cornell.edu

kushal_kedia.jpg

PhD Student

Cornell University

I am a third-year Ph.D. candidate in Computer Science at Cornell University, advised by Prof. Sanjiban Choudhury. My research focuses on robot learning from humans and with humans. I develop algorithms that enable robots to acquire both dexterous manipulation skills and collaboration strategies by observing human videos.

I completed my undergraduate studies at IIT Kharagpur. I’ve also spent summers as a research intern at Cruise, working on motion prediction for self-driving cars, and at Microsoft Research India, focusing on multi-lingual LLMs.

Link to CV.

News

May, 2025 Released preprint on X-Sim! X-Sim introduces a real-to-sim-to-real framework that uses object motion from human videos to train robot policies without requiring any robot data.
Jan, 2025 Our work on One-Shot Imitation under Mismatched Execution (RHyME) was accepted to ICRA 2025! RHyME enables robots to replicate long-horizon videos of demonstrators, even with significant execution differences.
Oct, 2024 Gave a talk at RobIn Lab, UT Austin on “Transferring Collaborative Behaviors from Human-Human Teams.”
May, 2024 Gave talks at ICRA 2024 workshops on MOSAIC, our year-long work that combines multiple foundation models to design a multi-robot collaborative cooking system. MOSAIC wins the best paper award at the VLMNM workshop and the best poster at MoMa workshop!
Oct, 2023 Gave a talk at RPM Lab, University of Minnesota on “Collaborative Manipulation via Human Motion Prediction”.
Sep, 2023 Excited to release the Collaborative Manipulation Dataset (CoMaD)! CoMaD captures over 6 hours of motion data from 14 unique users involving both human-human and human-robot (Franka robot arm) interactions in a kitchen setting.
May, 2023 First paper of my PhD on Game theoretic forecasting & planning accepted to IROS 2023! Framing forecasting and planning as an adversarial game leads to safer interactions.

Selected Papers

  1. xsim.gif
    X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
    Prithwish Dan*, Kushal Kedia*, Angela Chao, Edward Weiyi Duan, Maximus Adrian Pace, Wei-Chiu Ma, and Sanjiban Choudhury
    In Submission, 2025
    project page  /  paper  /  code
  2. rhyme.png
    One-Shot Imitation under Mismatched Execution
    Kushal Kedia*, Prithwish Dan*, Angela Chao, Maximus A. Pace, and Sanjiban Choudhury
    IEEE International Conference on Robotics and Automation (ICRA), 2025
    project page  /  paper  /  code
  3. mosaic.png
    MOSAIC: A Modular System for Assistive and Interactive Cooking
    Huaxiaoyue Wang*, Kushal Kedia*, Juntao Ren*, and ..... Sanjiban Choudhury
    8th Annual Conference on Robot Learning (CoRL), 2024
    project page  /  paper  /  code
  4. interact.png
    InteRACT: Transformer Models for Human Intent Prediction Conditioned on Robot Actions
    Kushal Kedia, Atiksh Bhardwaj, Prithwish Dan, and Sanjiban Choudhury
    IEEE International Conference on Robotics and Automation (ICRA), 2024
    project page  /  paper  /  code
  5. manicast.gif
    ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting
    Kushal Kedia, Prithwish Dan, Atiksh Bhardwaj, and Sanjiban Choudhury
    7th Annual Conference on Robot Learning (CoRL), 2023
    project page  /  paper  /  code
  6. game.gif
    A Game-Theoretic Framework for Joint Forecasting and Planning
    Kushal Kedia, Prithwish Dan, and Sanjiban Choudhury
    2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
    project page  /  paper  /  code