Xuanxuan Zhang

Xuanxuan Zhang

Auto-generated profile, based on publicly available information

Xuanxuan Zhang

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 February 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
ZLZongbo Liao
Zongbo Liao
XZXuanxuan Zhang
Xuanxuan Zhang
TZTianxiang Zhang
Tianxiang Zhang
ZLZhi Li
Zhi Li
ZZZhenqi Zheng
Zhenqi Zheng
YLYou Li
You Li
LiDAR is widely used in Simultaneous Localization and Mapping (SLAM) and autonomous driving. The LiDAR odometry is of great importance in multi-sensor fusion. However, in some unstructured environments, the point cloud registration cannot constrain the poses of the LiDAR due to its sparse geometric features, which leads to the degeneracy of multi-sensor fusion accuracy. To address this problem, we propose a novel real-time approach to sense and compensate for the degeneracy of LiDAR. Firstly, this paper introduces the degeneracy factor with clear meaning, which can measure the degeneracy of LiDAR. Then, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering method adaptively perceives the degeneracy with better environmental generalization. Finally, the degeneracy perception results are utilized to fuse LiDAR and IMU, thus effectively resisting degeneracy effects. Experiments on our dataset show the method’s high accuracy and robustness and validate our algorithm’s adaptability to different environments and LiDAR scanning modalities.

15 April 2025 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
JXJie Xu
Jie Xu
MMMa Yongxin Ma
Ma Yongxin Ma
YLYixuan Li
Yixuan Li
XZXuanxuan Zhang
Xuanxuan Zhang
JZJun Zhou
Jun Zhou
LXLihua Xie
Lihua Xie
The accuracy of the initial state, including initial velocity, gravity direction, and inertial measurement unit (IMU) biases, is critical for the initialization of LiDAR-inertial simultaneous location and mapping (SLAM) systems. Inaccurate initial values can reduce initialization speed or lead to failure. When the system faces urgent tasks, robust and fast initialization is required while the robot is moving, such as during the swift assessment of rescue environments after natural disasters, bomb disposal, and restarting LiDAR-inertial SLAM in rescue missions. However, existing initialization methods usually require the platform to remain stationary, which is ineffective when the robot is in motion. To address this issue, this article introduces a robust and fast dynamic initialization method for LiDAR-inertial systems (D-LI-Init). This method iteratively aligns LiDAR-based odometry with IMU measurements to achieve system initialization. To enhance the reliability of the LiDAR odometry module, the LiDAR and gyroscope are tightly integrated within the error state iterated Kalman filter framework. The gyroscope compensates for rotational distortion in the point cloud. Translational distortion compensation occurs during the iterative update phase, resulting in the output of LiDAR-gyroscope odometry. The proposed method can initialize the system no matter the robot is moving or stationary. Experiments on public datasets and real-world environments demonstrate that the D-LI-Init algorithm can effectively serve various platforms, including vehicles, handheld devices, and UAVs. D-LI-Init completes dynamic initialization regardless of specific motion patterns. To benefit the research community, we have open-sourced our code and test datasets on GitHub.

20 January 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ZLZongbo Liao
Zongbo Liao
XZXuanxuan Zhang
Xuanxuan Zhang
TZTianxiang Zhang
Tianxiang Zhang
YLYou Li
You Li
We propose a robust, pedestrian gait-enhanced, IMU-centric, LiDAR-inertial navigation system (P-LINS) for pedestrian applications. The system makes full use of the information of IMU in state estimation and LiDAR processing. To improve the system’s performance further, we integrate the physiological characteristics of pedestrian movements, applying constraints on velocity estimates. Additionally, we propose a novel LiDAR degeneracy factor to assess the observability of LiDAR rotation and translation, dynamically adjusting the LiDAR’s weight in the Error State Kalman Filter (ESKF) based on the degeneracy factor. Through experiments in structured scenarios and unstructured scenarios with LiDAR degeneracy, the robustness and precision of P-LINS are thoroughly validated. P-LINS performs comparably in structured scenarios to the SOTA LiDAR-Inertial navigation systems. In unstructured scenarios with LiDAR degeneracy, our method shows better robustness and accuracy. We open-source our codes combined with the dataset on GitHub3.

10 April 2026 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
MMMa Yongxin Ma
Ma Yongxin Ma
CZChengwei Zhao
Chengwei Zhao
JXJie Xu
Jie Xu
YLYixuan Li
Yixuan Li
XZXuanxuan Zhang
Xuanxuan Zhang
LXLihua Xie
Lihua Xie
Multi-session SLAM is essential for long-term robotic operations in indoor environments such as warehouses, office buildings, and industrial facilities. However, the thin walls separating enclosed spaces in such environments introduce a challenge known as the double-sided issue, where point clouds from opposite sides are mistakenly associated as a single surface during single-session mapping, and are prone to being grouped into the same voxel during voxelization in multi-session map fusion, leading to poor voxel planarity, which causes voxel invalidation and reduces the available constraints for global optimization. To address this, we propose NVMS-SLAM, a normal vector-based multi-session LiDAR SLAM system tailored for indoor environments. For single-session mapping, an extended voxel map is designed to preserve normal vector information and to distinguish between primary and secondary surfaces, thereby improving data association. At the multi-session level, a density-encoded indoor scan-context descriptor is introduced for robust loop closure. In addition, a two-stage global map fusion strategy is adopted, combining joint pose graph optimization and normal vector-based bundle adjustment to ensure globally consistent mapping. Experiments on simulated datasets and real-world environments demonstrate that NVMS-SLAM can effectively resolve the double-sided issue at both the single-session and multi-session stages. The code and datasets will be released on GitHub (https://github.com/lian-yue0515/NVMS-SLAM) for further research. Note to Practitioners—This paper is motivated by the challenges of multi-session LiDAR mapping in indoor environments, where thin walls can cause point clouds from opposite sides to merge incorrectly, producing the double-sided issue. Existing methods struggle with such cases, whereas NVMS-SLAM integrates normal vector information throughout the pipeline for greater robustness. A normal vector-based extended voxel map in single-session mapping separates primary and secondary surfaces for accurate data association, while a two-stage map fusion optimization, combining joint pose graph optimization with normal vector-based bundle adjustment, ensures globally consistent maps. This is the first multi-session SLAM system specifically designed for indoor environments to effectively address the double-sided issue. It is suitable for warehouse automation, facility inspection, and long-term monitoring, with future work focusing on dynamic environments and large-scale deployment.

19 March 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XGXueli Guo
Xueli Guo
ZWZhichao Wen
Zhichao Wen
XZXuanxuan Zhang
Xuanxuan Zhang
YXYizhou Xue
Yizhou Xue
SLSi kang Liu
Si kang Liu
YLYou Li
You Li
Accurate positioning and navigation capabilities are essential for Internet of Things (IoT) devices. Event cameras, inspired by biological vision sensors, exhibit robust performance in high-dynamic and low-texture environments and are particularly suitable for IoT applications. However, it faces challenges with accuracy and scale in conventional slow-motion scenarios. Conversely, light detection and ranging (LiDAR) offers high precision in normal motion conditions but degrades significantly under high-dynamic motion. To integrate the advantages of both sensors, this article introduces the EVLINS algorithm, a multisource elastic fusion method based on an extended Kalman filter (EKF). This algorithm combines event-visual-inertial odometry (EVIO), LiDAR-inertial odometry (LIO), and an inertial measurement unit (IMU), utilizing a loosely coupled trajectory layer post-processing technique. This algorithm leverages the robustness of event cameras in highly dynamic environments and the precision of LiDAR in conventional settings, utilizing normalized uncertainty and nonholonomic constraint (NHC) strategies to address LIO’s degradation and EVIO’s accuracy issues. Thorough testing in various indoor and outdoor scenarios with real-world data demonstrates that EVLINS exhibits significantly improved accuracy and robustness compared to both LIO and EVIO algorithms. In large-scale, high-dynamic outdoor environments, EVLINS achieves a 3-D position accuracy of 0.68% over 1333.58 m, improving by 33.21% over LIO and 96.10% over EVIO, which diverged mid-way. In extreme indoor dynamic scenarios, EVLINS reduces maximum position error by 41.55% compared to LIO and improves overall position accuracy by 43.48%, and 22.96% compared to EVIO.

17 November 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XSXuehang Sun
Xuehang Sun
YLYou Li
You Li
YWYan Wang
Yan Wang
HYHongji Yan
Hongji Yan
XZXuanxuan Zhang
Xuanxuan Zhang
ZWZhichao Wen
Zhichao Wen
In various pedestrian motion scenarios, data-driven pedestrian dead reckoning (PDR) methods have demonstrated strong localization performance, significantly enhancing system adaptability and robustness. However, most existing deep learning models have high computational costs. This makes them difficult to deploy on energy-constrained mobile devices for long-term use. Current lightweight PDR networks adopt a single-input–single-output structure. Although effective in complex dynamics, this design becomes redundant in low-dynamic conditions, such as static or slow walking. To address this challenge, we propose a lightweight network architecture named motion-aware early-exit inertial odometry network (MEIO-Net). The model adopts a multiexit design and incorporates a dedicated training scheme. Displacement covariance is used to assess motion difficulty. An early-exit mechanism is then introduced to adaptively adjust the inference depth based on dynamic complexity. With a slight improvement in accuracy, MEIO-Net significantly reduces computational cost across multiple datasets. In the self-collected dataset, it achieves a 48.9% reduction in FLOPs compared to state-of-the-art lightweight models. In typical simple pedestrian motion scenarios, the computational cost of the proposed model is reduced by 50.5%–80.5%. Ablation studies further confirm that MEIO-Net can flexibly terminate inference according to the intensity of the pedestrian motion. These results demonstrate its strong generalizability and practical potential for real-world deployment. Code and dataset are available at: https://github.com/SunXuehang/MEIO-Net.git