About Me

I am a Ph.D. student at University of California, Berkeley, working with Prof. Masayoshi Tomizuka. I am mainly focusing on the problems of policy generalization for robotic manipulation.

Before coming to UC Berkeley, I received my B.S. degree from Shanghai Jiao Tong University in 2019. During my undergraduate years, I was fortunate to work with Cewu Lu at SJTU, Jiajun Wu and Josh Tenenbaum at MIT. I have also spent time doing internship at X, the moonshot factory (formerly Google[x]).

Publications

  1. Prim-LAfD: a framework to learn and adapt primitive-based skills from demonstrations for insertion tasks.
    Zheng Wu, Wenzhao Lian, Changhao Wang, Mengxi Li, Stefan Schaal, Masayoshi Tomizuka
    arxiv preprint
    Paper

  2. Reinforcement learning with demonstrations from mismatched task under sparse reward.
    Yanjiang Guo, Jingyue Gao, Zheng Wu, Chengming Shi, Jianyu Chen
    The Conference on Robot Learning (CoRL), 2023
    Paper

  3. Zero-shot policy transfer with disentangled task representation of meta-reinforcement learning.
    Zheng Wu*, Yichen Xie*, Wenzhao Lian, Changhao Wang, Yanjiang Guo, Jianyu Chen, Stefan Schaal, Masayoshi Tomizuka
    International Conference on Robotics and Automation (ICRA), 2023
    Paper

  4. Offline-online learning of deformation model for cable manipulation with graph neural networks.
    Changhao Wang, Yuyou Zhang, Xiang Zhang, Zheng Wu, Xinghao Zhu, Shiyu Jin, Te Tang, Masayoshi Tomizuka
    IEEE Robotics and Automation Letters (RA-L)
    Paper

  5. Learning dense reward for contact-rich manipulation tasks.
    Zheng Wu, Wenzhao Lian, Vaibhav Unhelkar, Masayoshi Tomizuka, Stefan Schaal
    International Conference on Robotics and Automation (ICRA), 2021
    Paper

  6. Efficient sampling-based maximum entropy inverse reinforcement learning with application to autonomous driving.
    Zheng Wu*, Liting Sun*, Wei Zhan, Chenyu Yang, Masayoshi Tomizuka (* denotes equal contribution)
    IEEE Robotics and Automation Letters (RA-L)
    Paper

  7. Expressing diverse human driving behavior with probabilistic rewards and online inference.
    Liting Sun*, Zheng Wu*, Hengbo Ma, Masayoshi Tomizuka (* denotes equal contribution)
    Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
    Paper

  8. See, feel, act: Hierarchical learning for complex manipulation skills with multisensory fusion.
    Nima Fazeli , Miquel Oller, Jiajun Wu, Zheng Wu, Joshua B Tenenbaum, Alberto Rodriguez
    Science Robotics
    Paper / Video / MIT News / BBC / CNN

  9. Learning to describe scenes with programs.
    Yunchao Liu, Zheng Wu, Daniel Ritchie, William T. Freeman, Joshua B Tenenbaum, Jiajun Wu
    International Conference on Learning Representations (ICLR), 2019
    Paper

  10. Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters.
    Zheng Wu, Ruiheng Chang, Jiaxu Ma, Cewu Lu, Chi-Keung Tang
    International Joint Conference on Artificial Intelligence (IJCAI), 2018
    Paper / Slides