I am a passionate researcher and engineer working at the intersection of Robotics and Embodied AI. I graduated from Shanghai Jiao Tong University (ARWU30, QS 36, US News 37, THE 40), where I was advised by Prof. Danping Zou and Prof. Wenxian Yu at SJTU-VISYS Lab.
I have also been fortunate to work with Prof. Chuang Gan as a research intern at the MIT-IBM Watson AI Lab, and with Prof. Fu Zhang during SRP2023 at HKU MaRS Lab. Previously, I spent productive and memorable time at Tencent Robotics X Lab, Shanghai AI Lab IPEC group, and Shanghai Beidou Research Institute, working on robotics and intelligent systems.
My work has appeared in leading robotics and AI venues, including ICRA, IROS, RA-L, CVPR, TRO, TAES, and GPS Solutions. My research has been supported by the National Key R&D Program and the NSFC. Representative projects include M2DGR, Ground-Fusion, DAF, Ground-Fusion++ / M3DGR and so on, with Google Scholar citations. I am also an active open-source contributor, with GitHub stars across my projects.
News
- 06.2026 NIDAR is accepted to IROS2026!
- 02.2026 In-P3VIO is accepted to TAES2026!
- 06.2025 LIGO is successfully transfered to IROS2025!
- 06.2025 Ground-Fusion++/M3DGR isaccepted to IROS2025!
- 01.2025 M2DGR is awarded ESI Highly Cited Paper(Top 1%)!
- 01.2025 LIGO is accepted to TRO2025!
- 06.2024 DAF is accepted to IROS2024!
- 03.2024 Ground-Fusion is accepted to ICRA2024!
- 03.2024 EN-SLAM is accepted to CVPR2024!
- 03.2024 A paper is accepted to GPS Solutions!
- 08.2023 M2C-GVIO is accepted to Satellite Navigation!
- 06.2023 I won the HKU Summer Research Programme Scholarship!
- 12.2021 M2DGR is accepted to RAL and ICRA2022!
Research Themes
Reliable localization and rich scene understanding are prerequisites for robots that operate in the real world. My research builds this foundation through multi-sensor fusion SLAM and multimodal navigation — unifying LiDAR, vision, IMU, GNSS, audio, and reflectance cues for robust perception and autonomous mobility under corner cases.
Multi-sensor Fusion SLAM
Where is the robot?
Tightly-coupled fusion frameworks and large-scale benchmarks that keep ground robots localized under sensor degradation, spatiotemporal perturbation, and challenging outdoor corner cases.
Publication
Currently, I focus on reinforcement learning, dexterous manipulation, and whole-body control. My long-term goal is to build practical intelligent robots that can operate safely and reliably in human environments, assisting people with everyday physical tasks. Previously, I worked on multi-sensor fusion SLAM algorithms and benchmarks under corner cases and multimodal navigation. Representative works are highlighted.
 | Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation for Intelligent Transportation Systems Representative Work arXiv preprint 2026 |
 | In-P3 VIO: Tightly-Coupled PPP-Visual-Inertial Odometry Based on Invariant Filter Approach IEEE Transactions on Aerospace and Electronic Systems 2026 |
 | Towards Robust Sensor-Fusion Ground SLAM: A Comprehensive Benchmark and A Resilient Framework IROS 2025 |
 | LIGO: A Tightly Coupled LiDAR-Inertial-GNSS Odometry Based on a Hierarchy Fusion Framework for Global Localization With Real-Time Mapping |
 | Disentangled Acoustic Fields For Multimodal Physical Scene Understanding Representative Work IROS 2024 (Internship at MIT-IBM AI Lab) |
 | Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases Representative Work ICRA 2024 |
 | Implicit Event-RGBD Neural SLAM (CVPR Highlight) CVPR 2024 (Internship at Shanghai AI Lab) |
 | Innovation-based Kalman filter fault detection and exclusion method against all-source faults for tightly coupled GNSS/INS/Vision integration |
 | Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons Geo-spatial Information Science (JCR Q1) 2023 |
 | M2C-GVIO: motion manifold constraint aided GNSS-visual-inertial odometry for ground vehicles |
 | Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots |
 | M2DGR: A Multi-Sensor and Multi-Scenario SLAM Dataset for Ground Robots(ESI Highly Cited Paper, Top 1%) Representative Work RA-L 2021 (SJTU-Beidou Joint Training Program) |
Projects
 | Design, Sensing and Control of Service Robotic System for Intelligent Navigation and Operation in Internet Data Centers (Reddot Design Award2022) IEEE CASE 2022 (Internship at Tencent Robotics X Lab) |
 | A GNSS-Visual-IMU benchmark Dataset for SLAM Github 2022 |
Academic Service
- Conference reviewer for ICRA(2023, 2024, 2025) and IROS (2023, 2024, 2025, 2026) .
- Transaction reviewer for IEEE RA-L(2022, 2023, 2024, 2025, 2026),IEEE TRO(2024) and IEEE TASE(2024,2026).
Honors
- HKU Summer Research Programme (SRP) Scholarship 2023
- Academic Scholarship (2018, 2020, 2022, 2023) in SJTU
- Outstanding Graduate of SJTU 2021
- Third Prize in National English Competition for College Students(NECCS) 2018
Teaching
- Teaching assistant for Visual Localization & Perception (EE382) in SJTU.
- Course tutor on SLAM in CVLIFE.