Yandong Ji

I am a PhD student at UC San Diego with Prof. Xiaolong Wang.

Before that, I was a visiting researcher at MIT CSAIL with Prof. Pulkit Agrawal. I received an MEng in Mechnical Engineering from UC Berkeley in 2022 advised by Prof. Koushil Sreenath, and BEng in EECS from Nankai University in 2021 in close collaboration with Prof. Juanjuan Zhang.

Email  /  Resume  /  Google Scholar  /  Twitter

profile photo
Research

I am interested in robotics, machine learning and reinforcement learning.

sym Visual whole-body control for legged loco-manipulation
Minghuan Liu*, Zixuan Chen*, Xuxin Cheng, Yandong Ji, Rizhao Qiu, Ruihan Yang, Xiaolong Wang
CoRL, 2024

paper / project page

sym Expressive Whole-Body Control for Humanoid Robots
Xuxin Cheng*, Yandong Ji*, Junming Chen, Ruihan Yang, Ge Yang, Xiaolong Wang
RSS, 2024

paper / project page / UC San Diego Today

Humanoid robot tracking root movement and expression goal with whole-body controller.

sym Learning Force Control for Legged Manipulation
Tifanny Portela, Gabriel B. Margolis, Yandong Ji, Pulkit Agrawal
ICRA, 2024

paper / project page

Learning to control the force applied by a legged robot's arm for compliant and forceful manipulation.

sym Learning to See Physical Properties with Active Sensing Motor Policies
Gabriel B. Margolis, Xiang Fu, Yandong Ji, Pulkit Agrawal
CoRL, 2023

paper / project page

Learn to see how terrains feel by collecting self-supervised data with information-maximizing motor skills.

sym DribbleBot: Dynamic Legged Manipulation in the Wild
Yandong Ji*, Gabriel B. Margolis* , Pulkit Agrawal
International Conference on Robotics and Automation (ICRA), 2023

paper / project page / MIT homepage spotlight / MIT Technology Review / MIT News / NVIDIA Robotics / Boston.com / WHDH / IEEE Spectrum / Yahoo! Finance / BBC News / Mashable / Business Insider / Bot vs The New England Revolution

Dynamic object manipulation with legs using onboard computation and sensing.

Hierarchical reinforcement learning for precise soccer shooting skills using a quadrupedal robot
Yandong Ji*, Zhongyu Li*, Yinan Sun, Xue Bin Peng, Sergey Levine, Glen Berseth, Koushil Sreenath
IROS, 2022, (Best RoboCup Paper Award Finalist)
project page / arXiv / TechXplore

Honing soccer shooting skills in the real world



Reinforcement Learning for Collaborative Quadrupedal Manipulation of a Payload over Challenging Terrain
Yandong Ji, Bike Zhang, Koushil Sreenath
IEEE CASE, 2021
project page

A decentralized payload manipulation system in simulation

Evaluation of lower leg muscle activities during human walking assisted by an ankle exoskeleton
Wei Wang, Jianyu Chen, Yandong Ji, Wei Jin, Jingtai Liu, Juanjuan Zhang
IEEE Transactions on Industrial Informatics, 2020

Systematic evaluation of exoskeleton assistance performance based on EMG metrics

Service

Reviewer

CoRL, RA-L, Soft Robotics, IROS, ICRA, EMNLP



Designed and sourced code based on Jon Barron's website.