Yilin Wu

 |  News  |  Research  |  Education  |  Contact  | 

I am a first-year Ph.D student at CMU Robotics Institute, advised by Prof. David Held. I previously did my master in Computer Science at Stanford University, supervised by Prof. Dorsa Sadigh at ILIAD Lab. My research interest lies in the area of robotic manipulation and human robot interactions.

In 2020, I received my B.S. in Information Security from Shanghai Jiao Tong University. After graduation, I took a gap year and worked as RA at Shanghai Qi Zhi Institute, advised by Prof. Yi Wu.

In 2019, I studied as an exchange student at UC Berkeley and worked as a summer intern at BAIR Lab, advised by Prof. Pieter Abbeel and Prof. Lerrel Pinto.

Please feel free to contact me with email if you want!

profile photo

 ~  Email  |  Resume  |  Github  |  Google Scholar  |  Linkedin  ~ 


Our work on bimanual manipulation inspired by human coordination is accepted to CoRL 2023 as oral presentation.


Starting my Ph.D study at CMU.


One work on assistive feeding is covered by Stanford Human-Centered Artificial Intelligence(HAI) News.

Learning Generalizable Tool-use Skills through Trajectory Generation
Carl Qi *, Yilin Wu *, Lifan Yu, Haoyue Liu, Bowen Jiang, Xingyu Lin **, David Held **

Under review, 2024
project page / paper / video

In this work, we propose to learn a generative model of the tool-use trajectories as a sequence of point clouds, which generalizes to different tool shapes. We train a single model for four different challenging deformable object manipulation tasks, including cutting, rolling, large scooping, small scooping.

Spatially-Grounded Motion Primitives for Manipulation
Bowen Jiang, Yilin Wu, Wenxuan Zhou, Chris Paxton, David Held

Under review, 2024
project page / Preprint / video

In this work, we introduce spatially-grounded parameterized motion primitives to improve policy generalization for robotic manipulation tasks. By grounding the primitives on a spatial location in the environment, our proposed method is able to effectively generalize across object shape and pose variations.

DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset
DROID Dataset Team

In submission to RSS, 2024
project page / paper / video

In this work, we introduce DROID (Distributed Robot Interaction Dataset), a diverse robot manipulation dataset with 76k demonstration trajectories or 350h of interaction data, collected across 564 scenes and 86 tasks by 50 data collectors in North America, Asia, and Europe over the course of 12 months. We demonstrate that training with DROID leads to policies with higher performance, greater robustness, and improved generalization ability.

Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment Collaboration Team

ICRA, 2024
project page / paper / video

We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks).

Stabilize to Act: Learning to Coordinate for Bimanual Manipulation
Jennifer Grannen, Yilin Wu, Brandon Vu, Dorsa Sadigh

CoRL, 2023, Oral Presentation
project page / paper / video

We present a system for bimanual manipulation that coordinates by assigning roles to arms: a stabilizing arm holds an object stationary while an acting arm acts in this simplified environment.

In-Mouth Robotic Bite Transfer With Visual and Haptic Sensing
Lorenzo Shaikewitz*, Yilin Wu*, Suneel Belkhale*, Jennifer Grannen, Priya Sundaresan, Dorsa Sadigh

ICRA, 2023
project page / blog post / paper / video

We build a semi autonomous robotic system to do in-mouth transfer of food safely and comfortably for disabled people. The system is composed of a force-reactive controller to safely accommodate the user’s motions throughout the transfer, a novel dexterous wrist-like end effector to reduce the discomfort and a visual sensor to identify the user mouth.

Learning Bimanual Scooping Policies for Food Acquisition
Jennifer Grannen*, Yilin Wu*, Suneel Belkhale, Dorsa Sadigh

Corl, 2022
project page / blog post / paper / video

We propose a general bimanual scooping primitive and an adaptive stabilization strategy that enables successful acquisition of a diverse set of food geometries and physical properties with close-loop visual feedback.

Solving Compositional Reinforcement Learning Problems via Task Reduction
Yunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang, Yi Wu

ICLR, 2021
project page / arXiv / video

With task reduction and self-imitation, our RL agent is able to progressively tackle challenging sparse-reward and continuous control tasks with high efficiency.

Learning to Manipulate Deformable Objects without Demonstrations
Yilin Wu*, Wilson Yan*, Thanard Kurutach, Lerrel Pinto, Pieter Abbeel

RSS, 2020
project page / blog post / arXiv / video / code

Our work is to train a RL agent to acquire rope-spreading and cloth-spreading skills without any human demonstrations and the method applies to real robots after domain adaptation.

Carnegie Mello University
Doctor of Philosophy in Robotics
Aug '23 - Now


  • Working as a Research Assistant at CMU Robots Perceiving and Doing Lab (RPAD)

Stanford University
Master of Science in Computer Science
Sept '21 - Jun '23


  • Worked as a Research Assistant at Stanford ILIAD Lab
  • Worked on Assistive Feeding Project
Teaching Experience:
  • CA for CS 148 Introduction to Computer Graphics and Imaging | Fall 2022
  • CA for CS 221: Artificial Intelligence: Principles and Techniques | Spring 2023, Spring 2022 and Fall 2021
  • CA for CS 182 Ethics, Public Policy, and Technological Change | Winter 2023, Winter 2022

Shanghai Jiao Tong University
Bachelor of Science in Information Security
Sept '16 - June '20


  • Graduated with honor: Outstanding Graduate of Shanghai | 2020
  • Hongyi Scholarship (Top 10 Summer Research among Undergraduates) | 2019
  • Academic Excellence Scholarship(Second-Class) of SJTU | 2017 & 2018
  • National Scholarship (<1%) | 2017

University of California, Berkeley
Exchange Student in Computer Science
Jan '19 - Sept '19


  • Worked as a Research Assistant at UC Berkeley BAIR Lab
  • Worked on Deformable Object Manipulation Project

This template is a modification to Jon Barron's website and Rishab Khincha's website. Find the source code to my version here. Feel free to clone it for your own use while attributing the original author Jon Barron.