Yang Yi

Yang Yi

Auto-generated profile, based on publicly available information

Yang Yi

College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 March 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
WZWenjun Zhu
Wenjun Zhu
YLYanghong Liu
Yanghong Liu
MZMengyi Zhang
Mengyi Zhang
YYYang Yi
Yang Yi
A reliable prediction of traffic participants’ trajectories is challenging for automated driving. We attempt to integrate human trajectory’s temporal and spatial reciprocal consistency into the prediction network structure. Moreover, humans are intention-driven agents, and modelling human intentions will continuously provide more accurate and detailed information for future trajectory prediction. In this paper, we propose a Reciprocal Consistency Prediction Network (RCPNet), a bi-directional prediction network consisting of the forward and the backward with a similar structure. The prior work of human trajectory prediction is mainly a unidirectional process, while RCPNet fully uses the past and future trajectory information at reverse temporal scales. By training the backward part to optimize the whole network parameters based on the reciprocal consistency, we can improve the prediction accuracy of the forward network. In particular, the framework incorporates a destination variational auto-encoder (DVAE) to estimate the target intention of humans and generate multi-modal trajectory prediction. In order to adapt to the offline prediction situation, we refer to the calculation method of correlation between two variables to present “Predictive Confidence” to clarify the reliability of offline predicted trajectories. Experimental results show that the RCPNet improves state-of-the-art performance on the SDD and ETH/UCY benchmarks.

9 July 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
YMYimin Mu
Yimin Mu
WZWenjun Zhu
Wenjun Zhu
MZMengyi Zhang
Mengyi Zhang
YYYang Yi
Yang Yi
The sandwiched laminated soft magnetic films/planar coils Giant Magneto-Impedance sensors exhibit prominent advantages in miniaturization due to compatibility with Micro-Electro-Mechanical Systems. However, the inevitable shape demagnetization leads to the effective permeability of the magnetic films being far less than the nominal permeability of the functional material, which hinders the sensitivity promotion for film-based magnetic sensors. Here, a novel approach is proposed to enhance the effective permeability by introducing micro-grating patterns on the magnetic film surface for developing high-sensitivity magnetic sensorics. The magnetic characterizations of the patterned films demonstrate that the magnetic polarization field generated from the groove wall end faces can significantly compensate for the shape demagnetization. Therefore, a high-sensitivity giant magneto-impedance micro-sensor with grooved grating patterned magnetic films is designed and fabricated by micromachining technology. The experimental results indicate the impedance ratio peaks to 522% at 17.5 MHz, which demonstrates significant potential in developing the sensor array for biosensing and geomagnetic navigation. The strategy, modifying the surface morphology of a film instead of adjusting its compositions, opens a new way to enhance the feature property of a functional material, especially feasible for micro-fabrication.

28 October 2026 in Robotic Intelligence and Automation
Verified
Journal Article
Closed access
TCTongqing Cai
Tongqing Cai
WZWenjun Zhu
Wenjun Zhu
YYYang Yi
Yang Yi
MZMengyi Zhang
Mengyi Zhang
YMYimin Mu
Yimin Mu
Purpose: Category-level 6D object pose estimation is essential for robotic grasp detection and manipulation. However, large distribution gaps between synthetic and real data, the limited capacity of single-branch architectures to capture multi-modal features and the high cost of manual annotations remain critical challenges. This study aims to present BSSA-Net, a novel three-branch parallel architecture to effectively address these limitations and enhance pose estimation performance in real-world scenarios. Design/Methodology/Approach: BSSA-Net is a three-branch parallel architecture trained on synthetic data and designed to generalize to real datasets. It incorporates a semantic-aligned knowledge interaction to fuse RGB and point cloud features, a bi-scale information fusion mechanism to integrate temporal cues through hierarchical features and attention modules and a hybrid scope feature extraction strategy to strengthen 3D graph convolution. Each branch follows a three-stage process – primary deformation, precise deformation and pose estimation – while a novel self-supervised loss is introduced to enable knowledge transfer without requiring extensive real-world labels. Findings: Experiments conducted on CAMERA25 and REAL275 across synthetic-only, self-supervised and supervised learning settings demonstrate that BSSA-Net achieves state-of-the-art performance. Cross-dataset evaluations on Wild6D further confirm its robustness and generalization, particularly in synthetic-only and self-supervised scenarios. These results highlight the effectiveness of the proposed architecture in bridging the synthetic-to-real gap. Originality/Value: This work introduces a novel multi-branch framework that fuses multi-modal features and leverages self-supervised learning, reducing reliance on labeled data while improving generalization. It advances the field of category-level 6D pose estimation by providing a scalable and robust approach for robotic perception and manipulation, offering a foundation for future research and real-world applications.

31 August 2026 in Image and Vision Computing
Verified
Journal Article
Closed access
WZWenjun Zhu
Wenjun Zhu
HHHongsheng Han
Hongsheng Han
PSPeng Shan
Peng Shan
YYYang Yi
Yang Yi
MZMengyi Zhang
Mengyi Zhang
YMYimin Mu
Yimin Mu