Kushal Kedia

kk837@cornell.edu

kushal_kedia.jpg

PhD Student

Cornell University

I am a third-year Ph.D. student in the Computer Science Department at Cornell University, advised by Prof. Sanjiban Choudhury. I completed my undergraduate studies from IIT Kharagpur.

The goal of my research is to scale up learning for robotics by utilizing large-scale human data. To this end, I develop transferable algorithms that enable robots to extract skills and knowledge from mismatched human demonstrations. I focus on two core applications:

  1. Skill Learning via Imitation: Enabling robots to acquire diverse abilities from large-scale human videos.
  2. Human-Robot Collaboration: Teaching robots to collaborate with humans by learning from human-human teams.

In the past, I have completed research internships at Cruise, working on motion prediction for self-driving cars and at Microsoft Research Lab India, working on multi-lingual LLMs.

Link to CV.

News

Oct, 2024 Gave a talk at RobIn Lab, UT Austin on “Transferring Collaborative Behaviors from Human-Human Teams.”
Sep, 2024 Released preprint on One-Shot Imitation under Mismatched Execution! We present RHyME, enabling robots to replicate long-horizon videos of demonstrators, even when task execution differs significantly between the demonstration and the robot’s actions.
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. rhyme.png
    One-Shot Imitation under Mismatched Execution
    Kushal Kedia*, Prithwish Dan*, Angela Chao, Maximus A. Pace, and Sanjiban Choudhury
    1st Workshop on X-Embodiment Robot Learning, CoRL, 2024
  2. 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
  3. 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
  4. 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
  5. 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