Zhanchen Zhu

Zhanchen Zhu

Auto-generated profile, based on publicly available information

Zhanchen Zhu

Department of Data Science and AI, Monash University, Melbourne, VIC, Australia

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 October 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SZShuning Zhang
Shuning Zhang
EWErshen Wang
Ershen Wang
ZZZhanchen Zhu
Zhanchen Zhu
JYJingyi Yi
Jingyi Yi
YWYongkang Wang
Yongkang Wang
EKEnze Kuai
Enze Kuai
UWB positioning has become an important branch of indoor localization technology, which has high accuracy in the ideal state but is easily affected by the environment and other factors. To address the accuracy enhancement challenges of indoor UWB positioning across various conditions, a versatile UKF-FNN-RIC algorithm is proposed, leveraging the unscented Kalman filter (UKF), feedforward neural network (FNN), and redundant information correction (RIC). Firstly, various existing UWB positioning algorithms are analyzed, the redundant information in the UWB solution model is studied in depth, and the relationship between the redundant information and the measurement vectors is clarified, thus the error correction algorithm of gradient descent of redundant information is proposed, and the data meets the pre-conditions of its application through UKF and FNN transforms. The UKF-FNN-RIC algorithm is proposed in TOA scenarios. Finally, simulation experiments and practical experiments are carried out for two-way ranging (TWR) TOA scenario, which show that the algorithm in the paper can greatly improve the accuracy and robustness. The accuracy of fixed-point in the practical experiment reaches millimeter level, the accuracy of track determination reaches centimeter level, and the algorithms can be easily migrated to other positioning systems.