Zeyu Wan

Zeyu Wan

Auto-generated profile, based on publicly available information

Zeyu Wan

State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
19 January 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JLJunyuan Lu
Junyuan Lu
ZWZeyu Wan
Zeyu Wan
YZYu Zhang
Yu Zhang
Inspired by humans' ability to perceive the surface texture of unfamiliar objects without relying on vision, the sense of touch can play a crucial role in robots exploring the environment, particularly in scenes where vision is difficult to apply, or occlusion is inevitable. Existing tactile surface reconstruction methods rely on external sensors or have strong prior assumptions, making the operation complex and limiting their application scenarios. This letter presents a framework for low-drift surface reconstruction through multiple tactile measurements, Tac2Structure. Compared with existing algorithms, the proposed method uses only a new vision-based tactile sensor without relying on external devices. Aiming at the difficulty that reconstruction accuracy is easily affected by the pressure at contact, we propose a correction algorithm to adapt it. The proposed method also reduces the accumulative errors that occur easily during global object surface reconstruction. Multi-frame tactile measurements can accurately reconstruct object surfaces by jointly using the point cloud registration algorithm, loop-closure detection algorithm based on deep learning, and pose graph optimization algorithm. Experiments verify that Tac2Structure can achieve millimeter-level accuracy in reconstructing the surface of objects, providing accurate tactile information for the robot to perceive the surrounding environment.

5 September 2023 in Biomimetics
Verified
Journal Article
Open access
PDF file
RGRuilan Gao
Ruilan Gao
ZWZeyu Wan
Zeyu Wan
SGSitong Guo
Sitong Guo
CJChangjian Jiang
Changjian Jiang
YZYu Zhang
Yu Zhang
Simultaneous localization and mapping (SLAM) is one of the crucial techniques applied in autonomous robot navigation. The majority of present popular SLAM algorithms are built within probabilistic optimization frameworks, achieving high accuracy performance at the expense of high power consumption and latency. In contrast to robots, animals are born with the capability to efficiently and robustly navigate in nature, and bionic SLAM algorithms have received increasing attention recently. Current bionic SLAM algorithms, including RatSLAM, with relatively low accuracy and robustness, tend to fail in certain challenging environments. In order to design a bionic SLAM system with a novel framework and relatively high practicality, and to facilitate the development of bionic SLAM research, in this paper we present LFVB-BioSLAM, a bionic SLAM system with a light-weight LiDAR-based front end and a bio-inspired vision-based back end. We adopt a range flow-based LiDAR odometry as the front end of the SLAM system, providing the odometry estimation for the back end, and we propose a biologically-inspired back end processing algorithm based on the monocular RGB camera, performing loop closure detection and path integration. Our method is verified through real-world experiments, and the results show that LFVB-BioSLAM outperforms RatSLAM, a vision-based bionic SLAM algorithm, and RF2O, a laser-based horizontal planar odometry algorithm, in terms of accuracy and robustness.

23 May 2024 in IET Cyber-Systems and Robotics
Verified
Journal Article
Open access
PDF file
CJChangjian Jiang
Changjian Jiang
ZWZeyu Wan
Zeyu Wan
RGRuilan Gao
Ruilan Gao
YZYu Zhang
Yu Zhang
The colour‐enhanced point cloud map is increasingly being employed in fields such as robotics, 3D reconstruction and virtual reality. The authors propose ER‐Mapping (Extrinsic Robust coloured Mapping system using residual evaluation and selection). ER‐Mapping consists of two components: the simultaneous localisation and mapping (SLAM) subsystem and the colouring subsystem. The SLAM subsystem reconstructs the geometric structure, where it employs a dynamic threshold‐based residual selection in LiDAR‐inertial odometry to improve mapping accuracy. On the other hand, the colouring subsystem focuses on recovering texture information from input images and innovatively utilises 3D–2D feature selection and optimisation methods, eliminating the need for strict hardware time synchronisation and highly accurate extrinsic parameters. Experiments were conducted in both indoor and outdoor environments. The results demonstrate that our system can enhance accuracy, reduce computational costs and achieve extrinsic robustness.

16 August 2023 in IET Cyber-Systems and Robotics
Verified
Journal Article
Open access
ZWZeyu Wan
Zeyu Wan
CJChangjian Jiang
Changjian Jiang
YZYu Zhang
Yu Zhang
Localization is a core problem in mobile robot navigation. Simultaneous localization and mapping (SLAM) costs much for an unmanned aerial vehicle (UAV). This research aims to design an orthogonal laser scan device for localization and to save computation costs. Based on disturbance analysis, residual influences on sensor state are quantitative, and they are related to uncertainty and sensitivity. This research applied the residual selection method to a UAV. The feature point detection utilises multi‐scale and Gaussian model fitting techniques to guarantee true positives. The map is represented by Gaussian Mixture Models (GMM) with lower memory costs. The orthogonal laser scan device is composed and placed on a UAV for real‐time three‐dimensional localization, whose errors are at the centimeter level.

17 January 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ZWZeyu Wan
Zeyu Wan
CJChangjian Jiang
Changjian Jiang
XWXiaolong Wang
Xiaolong Wang
RGRuilan Gao
Ruilan Gao
YZYu Zhang
Yu Zhang
This paper introduces the design and implementation of MS-Mapper, a LiDAR mapping system incorporating a mechanical structure based on a step motor and steering gear. The hardware configuration of MS-Mapper allows for adjustable vertical and horizontal orientations of the LiDAR sensor. The MS-Mapper has two configurations during the mapping process: stationary mapping (S-mapping), which is dedicated to generating detailed point cloud maps and providing pose drift correction. mobile mapping (M-mapping), which is utilized for completing map cavities and ensuring comprehensive coverage mapping. This dual-configuration approach employed by MS-Mapper significantly enhances pose estimation accuracy, particularly in challenging environments such as lengthy corridors. To further improve pose estimation accuracy, we propose a residual selection-based bundle adjustment algorithm. Additionally, we propose a dynamic Gaussian Mixture Model (GMM) tree map representation, which is designed to accommodate dynamic growth. This representation effectively reduces the number of redundant Gaussian models, and minimizes data association costs compared to utilizing a dense point cloud. Furthermore, a configuration selection algorithm is proposed to detect pose estimation degeneration and determine optimal opportunities for switching configurations. In summary, the MS-Mapper system amalgamates the strengths of traditional Terrestrial Laser Scanner (TLS) and LiDAR SLAM approaches. MS-Mapper provides a robust solution for achieving accurate mapping results.

12 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
JLJunyuan Lu
Junyuan Lu
ZWZeyu Wan
Zeyu Wan
YZYu Zhang
Yu Zhang
Inspired by humans' ability to perceive the surface texture of unfamiliar objects without relying on vision, the sense of touch can play a crucial role in robots exploring the environment, particularly in scenes where vision is difficult to apply, or occlusion is inevitable. Existing tactile surface reconstruction methods rely on external sensors or have strong prior assumptions, making the operation complex and limiting their application scenarios. This paper presents a framework for low-drift surface reconstruction through multiple tactile measurements, Tac2Structure. Compared with existing algorithms, the proposed method uses only a new vision-based tactile sensor without relying on external devices. Aiming at the difficulty that reconstruction accuracy is easily affected by the pressure at contact, we propose a correction algorithm to adapt it. The proposed method also reduces the accumulative errors that occur easily during global object surface reconstruction. Multi-frame tactile measurements can accurately reconstruct object surfaces by jointly using the point cloud registration algorithm, loop-closure detection algorithm based on deep learning, and pose graph optimization algorithm. Experiments verify that Tac2Structure can achieve millimeter-level accuracy in reconstructing the surface of objects, providing accurate tactile information for the robot to perceive the surrounding environment.