Yifeng Zhu 朱毅枫

I am a fifth-year Ph.D. student in Computer Science at the University of Texas at Austin, co-advised by Prof. Yuke Zhu and Prof. Peter Stone. My research lies on the intersection of robot learning, robot control, and robot planning. I am interested in general-purpose robot autonomy, especially its social impact to our daily life in all aspects.

Email  /  GitHub  /  Google Scholar  /  CV

profile photo

Education

  • 2019 - Now, Ph.D. student in Computer Science, The University of Texas at Austin
  • 2014 - 2018, B.Eng. in Automation & B.A. in English Language and Literature, Zhejiang University
  • 2017 - 2018, Visiting Student, Machine Learning Department, Carnegie Mellon University

News

Talks

  • Building Human-Like Learning Household Robots via Perceptual and Motor Abstractions. RSS'23 Pioneers Workshop, Jul 2023.
  • LIBERO: Benchmarking Knowledge Transfer in Robot Learning. CoRL'23 Workshops TGR and OOD, Nov 2023.
  • LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery. CoRL'23 Workshop, Nov 2023.
  • Invited talk at Stanford, Oct 2021.
  • Robot Manipulation with Geometric and Symbolic Scene Graphs. ICCV'21 workshop on Structural and Compositional Learning on 3D Data, Oct 2021. (video)

Research

Here is a selected set of research projects. For a full list of publication record, please refer to the publication page.

To look up research that might be relevant or useful, you can now use Yifeng's Research GPT!

Open-Sourced Efforts for Robot Learning

Deoxys: A Modular, Real-Time Controller Library for Robot Learning


Yifeng Zhu
A user-friendly interface in Python and real-time controller implementation in C++
project   code   bibtex  

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning


Yuke Zhu, Josiah Wong, Ajay Mandlekar, Roberto Martín-Martín, Abhishek Joshi, Soroush Nasiriany, Yifeng Zhu
Technical Report, 2022
project   paper   code   bibtex  

Learning for Robot Manipulation

LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery


Weikang Wan, Yifeng Zhu*, Rutav Shah*, Yuke Zhu
Technical Report, 2023
project   paper   bibtex  

Learning Generalizable Manipulation Policies with Object-Centric 3D Representations


Yifeng Zhu, Zhenyu Jiang, Peter Stone, Yuke Zhu
Conference on Robot Learning (CoRL), 2023
project   paper   video   code   bibtex   poster  

LIBERO: Benchmarking Knowledge Transfer in Lifelong Robot Learning


Bo Liu*, Yifeng Zhu*, Chongkai Gao*, Yihao Feng, Qiang Liu, Yuke Zhu, Peter Stone
NeurIPS 2023 Datasets and Benchmarks Track, 2023
project   paper   code   bibtex  

Symbolic State Space Optimization for Long Horizon Mobile Manipulation Planning


Xiaohan Zhang, Yifeng Zhu, Yan Ding, Yuqian Jiang, Yuke Zhu, Peter Stone, Shiqi Zhang
International Conference on Intelligent Robots and Systems (IROS), 2023
project   paper   poster  

VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors


Yifeng Zhu, Abhishek Joshi, Peter Stone, Yuke Zhu
Conference on Robot Learning (CoRL), 2022
project   paper   code   bibtex   poster   media  

Visually Grounded Task and Motion Planning for Mobile Manipulation


Xiaohan Zhang, Yifeng Zhu, Yan Ding, Yuke Zhu, Peter Stone, Shiqi Zhang
International Conference on Robotics and Automation (ICRA), 2022
project   paper   code  

Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation


Yifeng Zhu, Peter Stone, Yuke Zhu
IEEE Robotics and Automation Letters (RA-L), 2022
project   paper   video   code   bibtex  

Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations


Zhenyu Jiang, Yifeng Zhu, Maxwell Svetlik, Kuan Fang, Yuke Zhu
Robotics: Science and Systems (RSS), 2021
project   paper   video   code  

Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs


Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Yuke Zhu
International Conference on Robotics and Automation (ICRA), 2021
project   paper   video   bibtex  

Fast Uncertainty Quantification for Deep Object Pose Estimation


Guanya Shi, Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Fabio Ramos, Animashree Anandkumar, Yuke Zhu
International Conference on Robotics and Automation (ICRA), 2021
project   paper   video  

Human-Like Learning

Machine versus Human Attention in Deep Reinforcement Learning Tasks


Sihang Guo, Ruohan Zhang, Bo Liu, Yifeng Zhu, Mary Hayhoe, Dana Ballard, Peter Stone
Advances in Neural Information Processing Systems (NeurIPS), 2021, 2021
paper   bibtex  

Human Gaze Assisted Artificial Intelligence: A Review


Ruohan Zhang, Akanksha Saran, Bo Liu, Yifeng Zhu, Sihang Guo, Scott Niekum, Dana Ballard, Mary Hayhoe
International Joint Conference on Artificial Intelligence (IJCAI) Survey Track, 2020, 2020
paper   bibtex  

Multi-Agent Reinforcement Learning

Tensor action spaces for multi-agent robot transer learning


Devin Schwab, Yifeng Zhu, Manuela Veloso
International Conference on Intelligent Robots and Systems (IROS), 2020
paper   video  

Zero Shot Transfer Learning for Robot Soccer


Devin Schwab, Yifeng Zhu, Manuela Veloso
Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems, 2018
paper  

RoboCup

UT Austin Villa: An Open-source Gym Environment forDeep Reinforcement Learning on 3DSim


Bo Liu, William Macke, Caroline Wang, Yifeng Zhu, Patrick MacAlpine, Peter Stone
Technical Report, 2021
paper  

Learning Primitive Skills for Mobile Robots


Yifeng Zhu, Devin Schwab, Manuela Veloso
International Conference on Robotics and Automation (ICRA), 2019
paper   video  

Learning Skills for Small Size League RoboCup


Devin Schwab, Yifeng Zhu, Manuela Veloso
Robocup Symposium, 2018
paper  


Teaching

Skills and Interests

Language

  • Chinese native
  • English professional
  • Japanese intermediate

Sports

  • Soccer
  • Tae Kwon Do
  • Chinese Martial Arts

Contact

Computer Science Department, The University of Texas at Austin

Email: yifeng.zhu [at] utexas.edu

Design and source code from Jon Barron's website