Skip to content
View Zjj587's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Chongqing University

Highlights

  • Pro

Block or report Zjj587

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Zjj587/README.md

Hi there, I'm Junjie Zhang, a robotics researcher and engineer.

About Me

Email WeChat Xiaohongshu Bilibili

Hi, I'm Junjie Zhang (张骏杰), a self-motivated researcher with a deep interest in robotics. I hope to witness, and contribute to, the arrival of Physical AGI. My current research focuses on multi-sensor fusion localization, UMI (Universal Manipulation Interface), sensor data simulation, VLA, WAM and JEPA.

Previously, I have interned at Shanghai AI Lab, PokeBot(破壳机器人), and ENGINEAI(众擎机器人), where I worked on robotics-related perception, localization, and system engineering problems.

Research Highlights

  • 06.2026 NIDAR is accepted to IROS 2026. I am the first author.
  • 06.2026 Ultra-Fusion is released as a strong SLAM system beyond prior Ground-Fusion and Ground-Fusion++. I am the second author.
  • 06.2025 Ground-Fusion++ and M3DGR are accepted to IROS 2025. I am a co-first author and a major contributor to the repository code.
  • 2025 APGC-LVIW, a LiDAR-visual-inertial-wheel SLAM system with adaptive planar geometric constraints, is published in Measurement and Control.
  • 2023 Structure and Gait Design of an Eight-legged Bionic Robot is published at ISRIMT 2023.

Current Interests

  • Multi-sensor Fusion SLAM and Localization
  • Visual-Inertial Odometry and LiDAR-Inertial Odometry
  • UMI and Robot Data Collection
  • VLA, WAM and JEPA
  • Sensor data Simulation

Tech Stack

  • Language & Platform:   Python C++ ROS ROS2 MATLAB Git GitHub Ubuntu Docker

  • Robotics:   ROS/ROS2, SLAM, VIO, LIO, calibration, multi-sensor synchronization, robot data pipelines, VLA, WAM, JEPA

  • Sensors:   Camera, LiDAR, IMU, wheel odometry, depth camera, motion capture systems

  • Simulation:   Sensor data simulation, Isaac Sim, SAPIEN

Featured Projects and Publications

TitleVenue / StatusMy RoleLinks
NIDAR IROS 2026 First author Project
Ground-Fusion++
Towards Robust Sensor-Fusion Ground SLAM: A Comprehensive Benchmark and A Resilient Framework
IROS 2025 Co-first author; major repository code contributor Code | Paper
M3DGR
A multi-sensor dataset and benchmark for robust ground robot SLAM
IROS 2025 Co-first author; major repository code contributor Code | Paper
Ultra-Fusion Released in 2026 Second author Code
APGC-LVIW
LiDAR-visual-inertial-wheel SLAM with adaptive planar geometric constraints
Measurement and Control, 2025 Co-author Paper
Structure and Gait Design of an Eight-legged Bionic Robot ISRIMT 2023 First author Paper

Contact

I am always happy to discuss robotics, SLAM, robot data collection, simulation, and Physical AGI.

Pinned Loading

  1. sjtuyinjie/M2DGR-Benchmark sjtuyinjie/M2DGR-Benchmark Public

    A benchmark based on M2DGR and M2DGR-plus dataset with adapted SOTA SLAM algorithms

    C++ 93 3

  2. sjtuyinjie/M3DGR sjtuyinjie/M3DGR Public

    M3DGR: A Multi-sensor, Multi-scenario and Massive-baseline SLAM Dataset for Ground Robots(IROS2025)

    C++ 389 31

  3. sjtuyinjie/Ground-Fusion2 sjtuyinjie/Ground-Fusion2 Public

    Ground-Fusion++: a modular sensor-fusion SLAM system(IROS2025)

    C++ 186 15

  4. Point_LIO_Mid360 Point_LIO_Mid360 Public

    This project uses Point-LIO in Livox Mid-360.

    17 2

  5. sjtuyinjie/Awesome-Visual-Inertial-Odometry sjtuyinjie/Awesome-Visual-Inertial-Odometry Public

    9

  6. Awesome-UMI Awesome-UMI Public

    6