Yunhai Feng

Email:

Hi! I'm a master's student in Computer Science at UC San Diego, advised by Prof. Xiaolong Wang. I'm broadly interested in Robotics, Reinforcement Learning, and Computer Vision.

I received my Bachelar's degree with honors from the National Elite Program of Computer Science at Nanjing University, where I worked with Prof. Yang Yu in Leaning And Mining from DatA (LAMDA) Group. I was also fortunate to work with Prof. Kenneth Salisbury at Stanford Artificial Intelligence Lab (SAIL), Prof. Lin Shao and Prof. Xiangyu Yue.

Google Scholar Github LinkedIn Twitter

Yunhai's photo

Research

My research goal is to endow embodied agents with versatile skills by learning efficiently and continually in the physical world. Toward that end, my research is focused on data-driven and model-based decision-making, especially the following directions:

  • World models/Model-based reinforcement learning for sample-efficient learning,
  • Hierarchical learning/planning/control for solving long-horizon tasks, and
  • Grounding foundation models(LLMs/VLMs) to handle complex robotic tasks.

Publications

owmcorl
Finetuning Offline World Models in the Real World

Yunhai Feng*, Nicklas Hansen*, Ziyan Xiong*, Chandramouli Rajagopalan, Xiaolong Wang

Proceedings of the 7th Conference on Robot Learning (CoRL), November 2023
Oral presentation

arXiv Website Code BibTeX

@inproceedings{feng2023finetuning,
  title={Finetuning Offline World Models in the Real World},
  author={Feng, Yunhai and Hansen, Nicklas and Xiong, Ziyan and Rajagopalan, Chandramouli and Wang, Xiaolong},
  booktitle={Proceedings of the 7th Conference on Robot Learning (CoRL)},
  year={2023}
}

SAM-RL
SAM-RL: Sensing-Aware Model-based Reinforcement Learning via Differentiable Physics-based Simulation and Rendering

Jun Lv, Yunhai Feng, Cheng Zhang, Shuang Zhao, Lin Shao*, Cewu Lu*

Proceedings of Robotics: Science and Systems (RSS), July 2023
🏆 Best System Paper Award Finalist

arXiv Website Video BibTeX

@inproceedings{lv2023sam,
  title={SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering},
  author={Lv, Jun and Feng, Yunhai and Zhang, Cheng and Zhao, Shuang and Shao, Lin and Lu, Cewu},
  booktitle={Proceedings of Robotics: Science and Systems (RSS)},
  year={2023}
}

ViPRoM
Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods

Ya Jing*, Xuelin Zhu*, Xingbin Liu*, Qie Sima, Taozheng Yang, Yunhai Feng, Tao Kong

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2023
CoRL 2022 Workshop on Pre-training for Robot Learning, December 2022

arXiv Website Video BibTeX

@inproceedings{jing2023explore
  author={Ya Jing, Xuelin Zhu, Xingbin Liu, Qie Sima, Taozheng Yang, Yunhai Feng, Tao Kong},
  title={Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods},
  booktitle={2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2023}
}

RGV3
Design and Control of Roller Grasper V3 for In-Hand Manipulation

Shenli Yuan, Lin Shao, Yunhai Feng, Jiatong Sun, Teng Xue, Connor Yako, Jeannette Bohg, Kenneth Salisbury

Website Video

Projects

Roller Grasper V3 NeRF render Laikago demo multi-cloud demo

Teaching

Service

  • Conference reviewer: IROS 2023, ICRA 2024
  • Journal reviewer: IEEE Robotics and Automation Letters (RA-L)

Awards

  • Best System Paper Award Finalist, RSS 2023
  • Graduate Excellence Award, 2022
  • Special Scholarship for Fundamental Subjects, 2021
  • People's Scholarship (first prize), 2021
  • National Elite Program Scholarship (first prize), 2020
  • National Elite Program Scholarship (specialty prize), 2019