Yong Fan

Yong Fan

Auto-generated profile, based on publicly available information

Yong Fan

School of Rail Transportation, Shandong Jiaotong University, Jinan, China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
19 July 2020 in Electronics
Verified
Journal Article
Open access
PDF file
CZChen Zhang
Chen Zhang
Lelai ZhouLelai Zhou
Lelai Zhou
YLYibin Li
Yibin Li
YFYong Fan
Yong Fan
The home environment is a typical dynamic environment with moveable obstacles. The social robots working in home need to search for feasible paths in this complex dynamic environment. In this work, we propose an improved RRT algorithm to plan feasible path in home environment. The algorithm pre-builds a tree that covers the whole map and maintains the effectiveness of all nodes with branch pruning, reconnection, and regrowth process. The method forms a path by searching the nearest node in the tree and then quickly accessing the nodes near the destination. Due to the effectiveness-maintaining process, the proposed method can effectively deal with the complex dynamic environment where the destination and multiple moving obstacles change simultaneously. In addition, our method can be extended to the path-planning problem in 3D space. The simulation experiments verify the effectiveness of the algorithm.

6 July 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Open access
YYYanfang Yin
Yanfang Yin
MLMing Liu
Ming Liu
QZQigang Zhu
Qigang Zhu
SZShuaishuai Zhang
Shuaishuai Zhang
NHNaseer Ali Hussien
Naseer Ali Hussien
YFYong Fan
Yong Fan
The human pose has a natural graphic structure. Therefore, in recent years, many studies on human pose estimation is based on Graph Convolutional Networks (GCN). However, the classical GCN method has a small receptive field and the transformation matrix is shared by all nodes, which limits their feature extraction ability. To address these issues, a novel multi-branch attention graph convolution (MultiBA_GConv) operation is proposed and a regression network model for human 3D position estimation based on the MultiBA_GConv operation is developed in this paper. Several different transformation matrices are used to extract the feature information contributing to the node itself, its neighbors, and other global nodes, and the corresponding attention mechanism is used to focus on these features in the MultiBA_GConv operation. The ablation experiments show that the multi-branch processing and multi-attention mechanism proposed in the MultiBA_GConv operation can greatly improve the feature extraction ability of graph convolution. The comparison experiments with other GCN methods show that MultiBA_GConv has the best feature extraction performance in all graph convolution operations. Based on the MultiBA_GConv, a 3D human pose regression network architecture is designed and the proposed method is evaluated on a challenging benchmark dataset for 3D human pose estimation. The experimental results of the comparison with the state of the art show that our method is highly competitive.

28 July 2025 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
WZWeiliang Zhu
Weiliang Zhu
LQLichao Qiao
Lichao Qiao
YLYichuan Lu
Yichuan Lu
XRXuewen Rong
Xuewen Rong
YFYong Fan
Yong Fan
GZGuoteng Zhang
Guoteng Zhang
For a bipedal robot intended to integrate into human environments, payload capacity serves as a fundamental determinant of its operational capability. A high payload capacity ensures that such robots can support heavy upper limbs and manipulate larger objects. To address this challenge, the robot HalfMan is presented—a human-sized, high-payload research platform distinguished by its well-organized mechatronic architecture and advanced control methodologies. The robot stands approximately 1.2-m tall and weighs around 32 kg, featuring ten actuated degrees of freedom, all powered by custom back-drivable modular actuators. We detail the design of the platform’s hardware, which includes the actuators, integrated leg structure, and on-board control sensing system. To achieve dynamic and robust walking for HalfMan, we propose a simplified model-based task space dynamics approach that balances the demands of precise model control with high-frequency computational requirements. A series of experiments were conducted to evaluate the overall system performance, with a focus on high-speed walking, slope climbing, push recovery, and high payload capacity. Notably, HalfMan achieves a leading payload-to-self-weight ratio of 80%, marking a significant advancement in bipedal robot capabilities.

18 January 2006
Verified
Conference Paper
Closed access
QWQin Wang
Qin Wang
YFYong Fan
Yong Fan
YWYa Dong Wan
Ya Dong Wan
SDShi Hong Duan
Shi Hong Duan
Wireless sensor network (WSN) conformed to IEEE802.15.4 requires that the direct distance between nodes is limited in 10m . However, we find out that IEEE802.15.4 WSN can not be directly used in some reconfigurable network applications, where it is difficult to ensure the actual distance between nodes within the required range, and, on the other hand, it is requisite to receive data from each sensor node reliably and accurately. So, this paper proposes a power auto -adaptive WSN solution, including power auto-adaptive protocol, and implementation of software and hardware. Based on the proposal, we use the MICAz nodes of Crossbow Corporation to construct WSN characterized with auto -adaptive communication distance, low power consumption and high reliability, and conduct actual test and verification.