LiDAR Simultaneous Localization and Mapping
Short description of portfolio item number 1
Read more
Posts by Collection
portfolio
Efficient Occupancy Mapping for LiDARs
Short description of portfolio item number 2 Read more
publications
ikd-Tree: An Incremental KD Tree for Robotic Applications
Published in Preprint, 2021
This paper proposes an efficient data structure, ikd-Tree, for dynamic space partition. The ikd-Tree incrementally updates a k-d tree with new coming … Read more
Avoiding Dynamic Small Obstacles with Onboard Sensing and Computation on Aerial Robots
Published in IEEE Robotics and Automation Letters (RAL), 2021
In practical applications, autonomous quadrotors are still facing significant challenges, such as the detection and avoidance of very small and even … Read more
Robots’ State Estimation and Observability Analysis Based on Statistical Motion Models
Published in IEEE Transactions on Control Systems Technology (TCST), 2022
This article presents a generic motion model to capture mobile robots' dynamic behaviors (translation and rotation). The model is based on … Read more
FAST-LIO2: Fast Direct Lidar-Inertial Odometry
Published in IEEE Transactions on Robotics (TRO), 2022
This article presents FAST-LIO2: a fast, robust, and versatile LiDAR-inertial odometry framework. Building on a highly efficient tightly coupled … Read more
Gemini II: Design, Modeling, and Control of a Compact Yet Efficient Servoless Bi-copter
Published in IEEE/ASME Transactions on Mechatronics (TMECH), 2022
Unmanned aerial vehicles (UAV) are widely used in the field for tasks that require 3-D movements in space. The simultaneous demand for heavy payload … Read more
A Self-rotating, Single-actuated UAV with Extended Sensor Field of View for Autonomous Navigation
Published in Science Robotics, 2023
Uncrewed aerial vehicles (UAVs) rely heavily on visual sensors to perceive obstacles and explore environments. Current UAVs are limited in both … Read more
MARSIM: A light-weight point-realistic simulator for LiDAR-based UAVs
Published in IEEE Robotics and Automation Letters (RAL), 2023
The emergence of LiDAR sensors have brought new opportunities for autonomous unmanned aerial vehicles (UAVs) by advancing navigation safety and … Read more
Immesh: An immediate lidar localization and meshing framework
Published in IEEE Transactions on Robotics (TRO), 2023
In this paper, we propose a novel LiDAR(-inertial) odometry and mapping framework to achieve the goal of simultaneous localization and meshing in … Read more
Trajectory Generation and Tracking Control for Aggressive Tail-Sitter Flights
Published in International Journal of Robotics Research, 2023
We address the theoretical and practical problems related to the trajectory generation and tracking control of tail-sitter UAVs. Theoretically, we … Read more
Occupancy Grid Mapping without Ray-Casting for High-resolution Sensors
Published in IEEE Transactions on Robotics (TRO), 2023
Occupancy mapping is a fundamental component of robotic systems to reason about the unknown and known regions of the environment. This article … Read more
MARS-LVIG dataset: A multi-sensor aerial robots SLAM dataset for LiDAR-visual-inertial-GNSS fusion
Published in International Journal of Robotics Research, 2023
In recent years, advancements in Light Detection and Ranging (LiDAR) technology have made 3D LiDAR sensors more compact, lightweight, and affordable. … Read more
ROG-Map: An Efficient Robocentric Occupancy Grid Map for Large-scene and High-resolution LiDAR-based Motion Planning
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), 2024
Recent advances in LiDAR technology have opened up new possibilities for robotic navigation. Given the widespread use of occupancy grid maps (OGMs) … Read more
Large-scale Multi-session Point-cloud Map Merging
Published in IEEE Robotics and Automation Letters (RAL), 2024
This paper introduces LAMM, an open-source framework for large-scale multi-session 3D LiDAR point cloud map merging. LAMM can automatically integrate … Read more
Swarm-LIO2: Decentralized Efficient LiDAR-inertial Odometry for UAV Swarms
Published in IEEE Transactions on Robotics (TRO), 2024
Aerial swarm systems possess immense potential in various aspects, such as cooperative exploration, target tracking, search and rescue. Efficient, … Read more
Autonomous Tail-Sitter Flights in Unknown Environments
Published in IEEE Transactions on Robotics (TRO), 2024
Trajectory generation for fully autonomous flights of tail-sitter unmanned aerial vehicles (UAVs) presents substantial challenges due to their highly … Read more
LVBA: LiDAR-Visual Bundle Adjustment for RGB Point Cloud Mapping
Published in 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
Point cloud maps with accurate color are crucial in robotics and mapping applications. Existing approaches for producing RGB-colorized maps are … Read more
Neural Surface Reconstruction and Rendering for LiDAR-Visual Systems
Published in 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
This paper presents a unified surface reconstruction and rendering framework for LiDAR-visual systems, integrating Neural Radiance Fields (NeRF) and … Read more
Safety-assured high-speed navigation for MAVs
Published in Science Robotics, 2025
Micro air vehicles (MAVs) capable of high-speed autonomous navigation in unknown environments have the potential to improve applications like search … Read more
GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction
Published in Robotics: Science and Systems (RSS) 2025, 2025
This research tackles the challenge of real-time active view selection and uncertainty quantification on visual quality for active 3D reconstruction. … Read more
FAST-LIVO2 on Resource-Constrained Platforms: LiDAR-Inertial-Visual Odometry with Efficient Memory and Computation
Published in Robotics and Automation Letters (RA-L), 2025
This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a … Read more
Efficient Swept Volume-Based Trajectory Generation for Arbitrary-Shaped Ground Robot Navigation
Published in International Conference on Intelligent Robots and Systems (IROS 2025), 2025
Navigating an arbitrary-shaped ground robot safely in cluttered environments remains a challenging problem. The existing trajectory planners that … Read more
Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation
Published in International Conference on Computer Vision (ICCV 2025), 2025
Moving object segmentation (MOS) on LiDAR point clouds is crucial for autonomous systems like self-driving vehicles. Previous supervised approaches … Read more
Slope inspection under Dense Vegetation Using LiDAR-based Quadrotors
Published in Nature Communications, 2025
Landslides pose significant threats to residents’ safety and daily lives. To mitigate such risks, flexible debris-resisting barriers are constructed … Read more
A High-Payload Robotic Hopper Powered by Bidirectional Thrusters
Published in Transactions on Robotics (T-RO), 2025
Mobile robots have revolutionized various fields, offering solutions for manipulation, environmental monitoring, and exploration. However, payload … Read more
A Survey on LiDAR-Based Autonomous Aerial Vehicles
Published in Transactions on Mechatronics (T-Mech), 2025
This survey offers a comprehensive overview of recent advancements in LiDAR-based autonomous uncrewed aerial vehicles (UAVs), covering their design, … Read more
DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
Published in NeurIPS 2025 (Spotlight), 2025
Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the … Read more
talks
Presentation in IROS2022
Published:
In October 2022, I had the privilege of showcasing FAST-LIO2 in International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan. It was my first academic presentation in an international conference. I was truly inspired by the passion from the audience about our work and the insightful questions in the Q&A period. I’m delighted to see that FAST-LIO2 has been gaining increasing interest (and GitHub stars :>) since the conference, contributing to the advancement of LiDAR-inertial Odometry espicially in the aspect of incremental data structures. Read more
teaching
MECH3433 Robotics, drones and autonomous ground vehicles (2020-2024)
Teaching Assistant in Undergraduate Course, University of Hong Kong, Department of Mechanical Engineering, 2024
This course aims to cover: modelling of robot kinematics / dynamics; programming on robot embedded control units; characterization and specification of robot actuation; sensing interface for robot feedback control; implementation of machine intelligence algorithms. Read more