Yu Han

Mr. Yu Han


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
22 July 2026 in Sensors
Verified
Journal Article
Open access
PDF file
YDYuanzhi Deng
Yuanzhi Deng
CCCheng Chi
Cheng Chi
JSJianhao Shen
Jianhao Shen
YHYu Han
Yu Han
SHShanyin He
Shanyin He
SCShaolong Chen
Shaolong Chen
Modern autonomous systems rely on heterogeneous sensing modalities—including vision sensors, millimeter-wave radar, and LiDAR—yet each individual sensor exhibits characteristic failure modes in challenging real-world conditions. While LiDAR-vision co-processing has received extensive attention, the synergistic potential of 4D radar paired with monocular optics remains comparatively unexplored. To fill this gap, we develop a graph-enhanced multi-modal architecture that jointly leverages sparse 4D radar returns and high-resolution camera imagery for scene-level 3D perception. The proposed system is organized around four tightly coupled processing stages: (i) an image-guided point densification scheme (SAA) that augments sparse radar clouds with camera-derived pseudo measurements; (ii) a pose-invariant cross-modal fusion layer that harmonizes enriched radar features with image descriptors and object saliency maps; (iii) a dynamic hypergraph assembly stage that captures higher-order inter-object and cross-sensor dependencies; and (iv) a HyperGCN inference module that regresses 3D bounding parameters and class labels on the resulting relational graph. Integrating the temporal velocity cues native to radar with the rich appearance information from cameras, the system delivers reliable perception under diverse environmental conditions. On the View-of-Delft (VOD) evaluation suite, the proposed model records an mAP of 69.3 and mAOS of 59.8. A systematic ablation further quantifies how geometric invariance—across translation, rotation, and scale transformations—individually affects end-to-end detection fidelity.

6 October 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YHYu Han
Yu Han
FZFengshou Zhang
Fengshou Zhang
CFChong Feng
Chong Feng
JXJichao Xu
Jichao Xu
Unordered parcel sorting corresponds to collision-free motion planning for manipulators within 3D unstructured obstacle-laden environments. Random poses of sorted objects impose stringent requirements on planning real-time performance and trajectory smoothness. The standard rapidly exploring random tree (RRT) relies on uniform random sampling and fixed-step expansion, which tends to yield weak sampling bias toward the goal, excessive invalid nodes, jagged redundant paths, and poor planning efficiency in complex environments under such three-dimensional constraints. To tackle these limitations, this paper proposes an improved algorithm based on the rapidly expanding random tree (RRT) algorithm and combining multiple strategies: GAB-RRT algorithm. In the sampling stage, the gravity bias strategy and the adaptive step size strategy are introduced to improve the nodes of the algorithm, expand the purpose and reduce invalid sampling. In the path planning link, the strategy of traversing connecting nodes to avoid obstacles and eliminate redundancy, and the strategy of cubic B-spline local optimization are combined to realize path simplification and smooth optimization. Considering the characteristics of the working environment, three-dimensional sorting space simulation experiments and robot path planning simulation experiments were designed and completed. The experimental results show that, compared with the standard RRT algorithm, the GAB-RRT algorithm is significantly optimized in terms of path cost, time cost and the number of nodes, among which the time cost is reduced by over 51%, the number of nodes is reduced by 87.3%, and the path cost is reduced by 4.93%, which can meet the requirements of high-precision path planning of robotic arms in the disorderly parcel sorting scene and provide a reference for the research on improving the performance of intelligent sorting equipment in the logistics sorting industry.