Kushal Kedia

kk837@cornell.edu

kushal_kedia.jpg

PhD Student

Cornell University

I am a 2nd year Ph.D. student in the Computer Science Department at Cornell University, advised by Prof. Sanjiban Choudhury.

My research is aimed at making robots accessible, user-friendly, and practical for everyday tasks from cooking to cleaning. I am interested in effective human-robot teaming behaviors by learning from demonstrations of human activities.

Previously, I received by B.Tech. from IIT Kharagpur. I have worked with Prof. Kostas Bekris at Rutgers University to integrate machine learning to increase the efficiency of kinodynamic planning algorithms, developed optimal algorithms for multi-agent path finding in my undergraduate thesis, and worked on multilingual LLMs at Microsoft Research Lab India.

Updated link to CV.

Publications

  1. mosaic.png
    MOSAIC: A Modular System for Assistive and Interactive Cooking
    Kushal Kedia*, Huaxiaoyue Wang*, Juntao Ren*, Rahma Abdullah, Atiksh Bhardwaj, Angela Chao, Kelly Y Chen, Nathaniel Chin, Prithwish Dan, Xinyi Fan, Gonzalo Gonzalez-Pumariega, Aditya Kompella, Maximus Adrian Pace, Yash Sharma, Xiangwan Sun, Neha Sunkara, and Sanjiban Choudhury
    In Submission, 2024
    project page  /  paper
  2. 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
  3. 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
  4. 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
  5. raft.png
    Rationale-Guided Few-Shot Classification to Detect Abusive Language
    Punyajoy Saha, Divyanshu Sheth, Kushal Kedia, Binny Mathew, and Animesh Mukherjee
    26th European Conference on Artificial Intelligence, 2023
  6. terrain.png
    Terrain-Aware Learned Controllers for Sampling-Based Kinodynamic Planning over Physically Simulated Terrains
    Troy McMahon, Aravind Sivaramakrishnan, Kushal Kedia, Edgar Granados, and Kostas E. Bekris
    2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
  7. mapf.png
    Optimal Multi-Agent Path Finding for Precedence Constrained Planning Tasks
    Kushal Kedia, Rajat Kumar Jenamani, Aritra Hazra, and P. P. Chakrabarti
    ArXiv, 2022
  8. eacl.jpg
    Offensive Language Identification in Dravidian Languages
    Kushal Kedia, and A. Nandy
    First Workshop on Speech and Language Technologies for Dravidian Languages at IEEE International Conference on Robotics and Automation, 2021
  9. csrrt.png
    Robotic Motion Planning Using Learned Critical Sources and Local Sampling
    Kushal Kedia*, Rajat Jenamani*, Rahul Kumar*, and Parth Mall*
    MLPC Workshop at IEEE International Conference on Robotics and Automation (ICRA), 2020