Yilin Wu 吴怡琳

yilinwu.jpg

PhD student @ RI, SCS, CMU

yilinwu [at] andrew [dot] cmu [dot] edu

Email is the best way to contact me!

I am a second-year Ph.D student at Intent Lab in CMU Robotics Institute, advised by Prof. Andrea Bajcsy. Previously, I am fortunate to work with Prof. David Held on generalizable methods for long-horizon contact-rich manipulation.

Before coming to CMU, I was a master student with a focus on assistive feeding and bimanual manipulation in Computer Science Department at Stanford University, supervised by Prof. Dorsa Sadigh.

In the past, I am also fortunate to work with Prof. Yi Wu from Tsinghua University at Shanghai Qi Zhi Institute on reinforcement learning and self-imitation. In my undergrad, I also worked closely with Prof. Pieter Abbeel and Prof. Lerrel Pinto on reinforcment learning for deformable object manpulation.

My current research focuses on human-robot interaction and learning-based manipulation, particularly on enabling robots to understand and recover from failures in human-centered environments. The ultimate goal is to enhance the robots’ generalization and robustness with continual learning. I am also broadyly interested in developing various deep learning methods like reinforcement learning and imitation learning to enhance robot’s capability for more complex manipulation tasks.

News

Jun 2024 One paper Learning Generalizable Tool-use Skills through Trajectory Generation got accepted at IROS 2024.
May 2024 Open X-Embodiment wins the Best Paper Award at ICRA 2024.
May 2024 Two papers DROID and HACMan++ are accepted by RSS 2024.
Sep 2023 Our work on bimanual manipulation inspired by human coordination is accepted to CoRL 2023 as Oral presentation.
Aug 2023 Starting my Ph.D study at CMU Robitic Institute.

Publications

  1. IROS
    toolgen.gif
    Learning Generalizable Tool-use Skills through Trajectory Generation
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
  2. RSS
    hacman.gif
    HACMan++: Spatially-Grounded Motion Primitives for Manipulation
    In Robotics: Science and Systems (RSS), 2024
  3. RSS
    droid.gif
    DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
    DROID Dataset Team
    In Robotics: Science and Systems (RSS), 2024
  4. ICRA
    openx.gif
    Open X-Embodiment: Robotic Learning Datasets and RT-X Models
    Open X-Embodiment Team
    In IEEE International Conference on Robotics and Automation (ICRA), 2023
    Best Paper Award
  5. CoRL
    buds.gif
    Stabilize to Act: Learning to Coordinate for Bimanual Manipulation
    In Proceedings of the 7th Conference on Robotic Learning (CoRL), 2023
    Oral Presentation [6.6%]
  6. ICRA
    bite_transfer.gif
    In-Mouth Robotic Bite Transfer with Visual and Haptic Sensing
    In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023
  7. CoRL
    carbs_after.gif
    Learning Bimanual Scooping Policies for Food Acquisition
    In Proceedings of the 6th Conference on Robot Learning (CoRL), 2022
  8. ICLR
    sir_fetch.gif
    Solving Compositional Reinforcement Learning Problems via Task Reduction
    Yunfei LiYilin WuHuazhe XuXiaolong Wang, and Yi Wu
    In International Conference on Learning Representations (ICLR), 2021
  9. RSS
    mvp.gif
    Learning to Manipulate Deformable Objects without Demonstrations
    In Robotics: Science and Systems, (RSS), 2020