Xinliang Zhong

About

Xinliang Zhong is a robotics researcher whose work centers on state estimation, sensor fusion, and simultaneous localization and mapping (SLAM) for mobile robots. His most influential contribution is **LVIO-SAM**, a multi-sensor fusion odometry framework that integrates LiDAR, visual, and inertial data through smoothing and mapping—a system that has garnered 13 citations since 2021. Zhong addresses a fundamental challenge in robotics: how to reliably fuse heterogeneous sensors to overcome individual limitations, such as the wide-angle constraints of cameras or drift in visual-inertial odometry. His 2021 paper on visual localization in a prior 3D LiDAR map innovatively combines points and lines to boost accuracy, while his earlier work on binocular vision and IMU-based SLAM (2020) and Octomap-based multi-sensor fusion (2021) further demonstrates his systematic approach to robust mapping and navigation. Though early in his career, Zhong’s research is already shaping how robots perceive and navigate complex environments, offering practical solutions for autonomous exploration. His focus on fusing diverse sensor modalities positions him as a rising contributor to the SLAM community, with clear potential for future impact.

Research Focus

Key Achievements

Top Papers

1. 1
   LVIO-SAM: A Multi-sensor Fusion Odometry via Smoothing and Mapping

   13 citations · 2021
2. 2
   Visual Localization in a Prior 3D LiDAR Map Combining Points and Lines

   3 citations · 2021
3. 3
   Research on simultaneous localization and mapping of indoor mobile robot

   2 citations · 2018
4. 4
   Research on SLAM System Based on Binocular Vision and IMU Information

   2 citations · 2020
5. 5
   Meteor Tail: Octomap Based Multi-sensor Data Fusion Method

   2 citations · 2021

Key Collaborators

Contact & Links