Zhenhua Xu

zhxu.png

Hello, this is Zhenhua Xu(许振华). Currently I work as a postdoc in the School of Vehicle and Mobility, Tsinghua University, supervised by Prof. Jianqiang Wang.

Previously, I spent a wonderful year in the University of Hong Kong (HKU) with Prof. Hengshuang Zhao. I received my Ph.D. from the Computer Science and Engineering (CSE) Department of the Hong Kong University of Science and Technology (HKUST), where I was co-supervised by Prof.Ming Liu and Prof.Huamin Qu. Prior to joining HKUST, I obtained my bachelor degree in Electronics and Information Engineering from Harbin Institute of Technology, under the supervision of Prof. Yun Zhang.

My primary research interests encompass a broad range of topics, including embodied AI, autonomous driving, multimodal language models, end-to-end vehicle planning, high-definition mapping, GIS imitation learning, and more. My specific focus is on the application of computer vision and robotics techniques to develop robust and dependable autonomous driving systems and agents that seamlessly integrate into our daily lives. The core challenges lie in empowering AI agents to accurately comprehend their surroundings and make well-informed decisions accordingly.

Drop me an email if you are interested in these topics. Collaborations in any forms are welcomed!


News

Jul 12, 2024 Our paper DriveGPT4 is accepted by RA-L 2024.
Jul 01, 2024 Our paper InsMapper is accepted by ECCV 2024.
May 01, 2024 Our ICML2024 Workshop Multi-modal Foundation Model meets Embodied AI (MFM-EAI) is online! Visit our official website for more information!
Feb 15, 2024 One paper is accepted by IV 2024.
Jan 15, 2024 One paper is accepted by ICRA 2024.
Apr 03, 2023 One paper is accepted by IEEE Transactions on Automation Science and Engineering (TASE).
Mar 01, 2023 Our paper RNGDet++ is accepted by IEEE Robotics and Automation Letters (RA-L).
Jan 17, 2023 Our paper CenterLineDet is accepted by ICRA 2023.
Jan 06, 2023 Pass my Ph.D. thesis defence.
Jun 03, 2022 Our paper RNGDet is accepted by IEEE Transactions on Geoscience and Remote Sensing (TGRS).
Feb 07, 2022 Our paper csBoundary is accepted by IEEE Robotics and Automation Letters (RA-L) and ICRA 2022.
Feb 01, 2022 One paper accepted by IEEE International Conference on Robotics and Automation (ICRA) 2022.

Selected Publications

  1. Preprint
    VIRT: Vision Instructed Transformer for Robotic Manipulation
    Zhuoling Li Li , Liangliang Ren , Jinrong Yang , and 5 more authors
    2024
  2. Preprint
    LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence
    Zhuoling Li , Xiaogang Xu ,  Zhenhua Xu , and 2 more authors
    2024
  3. RAL
    DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model
    Zhenhua Xu , Yujia Zhang , Enze Xie , and 5 more authors
    IEEE Robotics and Automation Letters, 2024
  4. ECCV2024
    InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping
    Zhenhua Xu , Kwan-Yee K. Wong , and Hengshuang Zhao
    2024 European Conference on Computer Vision (ECCV), 2024
  5. RAL
    RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement
    Zhenhua Xu , Yuxuan Liu , Yuxiang Sun , and 2 more authors
    IEEE Robotics and Automation Letters, 2023
  6. ICRA2023
    CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation
    Zhenhua Xu , Yuxuan Liu , Yuxiang Sun , and 2 more authors
    2023 IEEE/RSJ International Conference on Robotics and Automation (ICRA), 2023
  7. TGRS
    RNGDet: Road Network Graph Detection by Transformer in Aerial Images
    Zhenhua Xu , Yuxuan Liu , Lu Gan , and 3 more authors
    IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2022
  8. RAL/IROS2021
    iCurb: Imitation Learning-Based Detection of Road Curbs Using Aerial Images for Autonomous Driving
    Zhenhua Xu , Yuxiang Sun , and Ming Liu
    IEEE Robotics and Automation Letters, 2021