Fan Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fan Wu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Fang Zhao
Beijing University of Posts and Telecommunications
7 shared publications - Haiyong Luo
Institute of Computing Technology, Chinese Academy of Sciences
7 shared publications - Bokun Ning
School of Software Engineering, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Xile Gao
Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications - Yimin Xiao
School of Software Engineering, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications Bo Zhou
Yibin Tinno Communication Company, Ltd, Science and Innovation Center, Guoxing Avenue, Lingang Economic Development Zone, Sichuan Province, China
1 shared publication
Latest Publications
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (4) , 4504-4516
FEMASF: An SVD-Based Algorithm for Accurately Estimating the Mounting Angle and Scale Factor
Accurately estimating the position and attitude of vehicles is essential for intelligent transportation systems. The GNSS/INS integrated system offers precise navigation information. However, the system’s positioning errors may accumulate rapidly in challenging GNSS signal conditions. Odometer (ODO) and nonholonomic constraints (NHC) are commonly employed to mitigate the rapid accumulation of INS errors. Compensating for the mounting angles of INS and the scale factor of the odometer is necessary to fully exploit the potential of ODO/NHC. However, many studies employ Kalman filters with small mounting angle assumption, which limits their applicability for large mounting angles in practice. To accurately estimate the mounting angle of INS with any installation attitude, we propose a new algorithm called Fast Estimation of Mounting Angle and Scale Factor (FEMASF). FEMASF employs Singular Value Decomposition (SVD) to obtain a closed-form solution for the parameters. It also incorporates an enhanced Sage-Husa scheme, enhancing overall estimation accuracy by reducing the weight of outlier data through a forgetting factor. Extensive simulation experimental results demonstrate that our proposed FEMASF algorithm outperforms filter-based methods in terms of accuracy and convergence speed for large mounting angles. Specifically, for the -90∘ mounting angle, FEMASF achieves 0.45∘ angle error, while the velocity-based Kalman filter (VKF) fails to converge and the position-based Kalman filter (PKF) yields about 4∘ error. Furthermore, neither VKF nor PKF converges for the 120∘ mounting angle, whereas FEMASF exhibits only about 3.2∘ estimation error.
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (4) , 4504-4516
FEMASF: An SVD-Based Algorithm for Accurately Estimating the Mounting Angle and Scale Factor
Accurately estimating the position and attitude of vehicles is essential for intelligent transportation systems. The GNSS/INS integrated system offers precise navigation information. However, the system’s positioning errors may accumulate rapidly in challenging GNSS signal conditions. Odometer (ODO) and nonholonomic constraints (NHC) are commonly employed to mitigate the rapid accumulation of INS errors. Compensating for the mounting angles of INS and the scale factor of the odometer is necessary to fully exploit the potential of ODO/NHC. However, many studies employ Kalman filters with small mounting angle assumption, which limits their applicability for large mounting angles in practice. To accurately estimate the mounting angle of INS with any installation attitude, we propose a new algorithm called Fast Estimation of Mounting Angle and Scale Factor (FEMASF). FEMASF employs Singular Value Decomposition (SVD) to obtain a closed-form solution for the parameters. It also incorporates an enhanced Sage-Husa scheme, enhancing overall estimation accuracy by reducing the weight of outlier data through a forgetting factor. Extensive simulation experimental results demonstrate that our proposed FEMASF algorithm outperforms filter-based methods in terms of accuracy and convergence speed for large mounting angles. Specifically, for the -90∘ mounting angle, FEMASF achieves 0.45∘ angle error, while the velocity-based Kalman filter (VKF) fails to converge and the position-based Kalman filter (PKF) yields about 4∘ error. Furthermore, neither VKF nor PKF converges for the 120∘ mounting angle, whereas FEMASF exhibits only about 3.2∘ estimation error.
- 12 November 2024
- Published by Springer Nature
- p. 341-347
CAFGO: Confidence-Adaptive Factor Graph Optimization Algorithm for Fusion Localization
- 12 November 2024
- Published by Springer Nature
- p. 341-347
CAFGO: Confidence-Adaptive Factor Graph Optimization Algorithm for Fusion Localization
- 21 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 3104-3108
Optimizing GNSS/INS Integrated Navigation: A Deep Learning Approach for Error Compensation
This paper addresses challenges stemming from sensor manufacturing processes and technological constraints, such as nonlinear stochastic noise, leading to rapid INS positioning error divergence. To enhance the performance of GNSS/INS (Global Navigation Satellite System/Integrated Navigation Systems) integrated navigation methods, we propose an AI-based adaptive error compensation method. We introduce deep learning to correct INS computational errors, leveraging its precision modeling without strict noise assumptions. Our approach integrates filtering methods and deep learning approaches, avoiding the uncontrollable introduction of positioning errors inherent in end-to-end models' black-box mode. We design a novel deep model structure to improve generalization while reducing parameters and computational complexity. Validation is conducted using a vehicular navigation data acquisition platform, simulating scenarios of GNSS signal loss. Experimental results demonstrate a 77.70% improvement in recognition rates across different road segments compared to traditional methods based on Extended Kalman Filter, indicating significant practical value.
- 21 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 3104-3108
Optimizing GNSS/INS Integrated Navigation: A Deep Learning Approach for Error Compensation
This paper addresses challenges stemming from sensor manufacturing processes and technological constraints, such as nonlinear stochastic noise, leading to rapid INS positioning error divergence. To enhance the performance of GNSS/INS (Global Navigation Satellite System/Integrated Navigation Systems) integrated navigation methods, we propose an AI-based adaptive error compensation method. We introduce deep learning to correct INS computational errors, leveraging its precision modeling without strict noise assumptions. Our approach integrates filtering methods and deep learning approaches, avoiding the uncontrollable introduction of positioning errors inherent in end-to-end models' black-box mode. We design a novel deep model structure to improve generalization while reducing parameters and computational complexity. Validation is conducted using a vehicular navigation data acquisition platform, simulating scenarios of GNSS signal loss. Experimental results demonstrate a 77.70% improvement in recognition rates across different road segments compared to traditional methods based on Extended Kalman Filter, indicating significant practical value.
- Open Access
- 29 February 2024
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2024, 1-15
T-SPP: Improving GNSS Single-Point Positioning Performance Using Transformer-Based Correction
GNSS (global navigation satellite systems) technology enables high-precision single-point positioning (SPP) in open environments. However, the accuracy of GNSS positioning is significantly compromised in complex urban canyons due to signal obstructions and non-line-of-sight propagation errors. To address this challenge, we propose a GNSS displacement estimation algorithm. This method learns nonlinear dependencies between GNSS raw measurements and corresponding position changes, capturing dynamic and layered features in GNSS measurement data for displacement estimation. We introduce a denoising auto-encoder (DAE) to preprocess raw GNSS observations, reducing the impact of noise. The model simultaneously outputs estimated displacement and model confidence. The fusion process dynamically combines positioning results from the SPP algorithm and the D-Tran model, adaptively blending them to achieve accurate and optimal positioning estimation. This approach optimizes the accuracy of estimated positioning results while maintaining confidence in the estimation. Experimental results show a 61% reduction in root mean square error (RMSE) and 100% availability in urban canyon environments compared to traditional single-point positioning techniques.
- 29 February 2024
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2024, 1-15
Open AccessT-SPP: Improving GNSS Single-Point Positioning Performance Using Transformer-Based Correction
GNSS (global navigation satellite systems) technology enables high-precision single-point positioning (SPP) in open environments. However, the accuracy of GNSS positioning is significantly compromised in complex urban canyons due to signal obstructions and non-line-of-sight propagation errors. To address this challenge, we propose a GNSS displacement estimation algorithm. This method learns nonlinear dependencies between GNSS raw measurements and corresponding position changes, capturing dynamic and layered features in GNSS measurement data for displacement estimation. We introduce a denoising auto-encoder (DAE) to preprocess raw GNSS observations, reducing the impact of noise. The model simultaneously outputs estimated displacement and model confidence. The fusion process dynamically combines positioning results from the SPP algorithm and the D-Tran model, adaptively blending them to achieve accurate and optimal positioning estimation. This approach optimizes the accuracy of estimated positioning results while maintaining confidence in the estimation. Experimental results show a 61% reduction in root mean square error (RMSE) and 100% availability in urban canyon environments compared to traditional single-point positioning techniques.
- Open Access
- 31 March 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (7) , 1691
Towards Predicting the Measurement Noise Covariance with a Transformer and Residual Denoising Autoencoder for GNSS/INS Tightly-Coupled Integrated Navigation
The tightly coupled navigation system is commonly used in UAV products and land vehicles. It adopts the Kalman filter to combine raw satellite observations, including the pseudorange, pseudorange rate and Doppler frequency, with the inertial measurements to achieve high navigational accuracy in GNSS-challenged environments. The accurate estimation of measurement noise covariance can ensure the quick convergence of the Kalman filter and the accuracy of the navigation results. Existing tightly coupled integrated navigation systems employ either constant noise covariance or simple noise covariance updating methods, which cannot accurately reflect the dynamic measurement noises. In this article, we propose an adaptive measurement noise estimation algorithm using a transformer and residual denoising autoencoder (RDAE), which can dynamically estimate the covariance of measurement noise. The residual module is used to solve the gradient degradation problem. The DAE is adopted to learn the essential characteristics from the noisy ephemeris data. By introducing the attention mechanism, the transformer can effectively learn the time and space dependency of long-term ephemeris data, and thus dynamically adjusts the noise covariance with the predicted factors. Extensive experimental results demonstrate that our method can achieve sub-meter positioning accuracy in the outdoor open environment. In a GNSS-degraded environment, our proposed method can still obtain about 3 m positioning accuracy. Another test on a new dataset also confirms that our proposed method has reasonable robustness and adaptability.
- 31 March 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (7) , 1691
Open AccessTowards Predicting the Measurement Noise Covariance with a Transformer and Residual Denoising Autoencoder for GNSS/INS Tightly-Coupled Integrated Navigation
The tightly coupled navigation system is commonly used in UAV products and land vehicles. It adopts the Kalman filter to combine raw satellite observations, including the pseudorange, pseudorange rate and Doppler frequency, with the inertial measurements to achieve high navigational accuracy in GNSS-challenged environments. The accurate estimation of measurement noise covariance can ensure the quick convergence of the Kalman filter and the accuracy of the navigation results. Existing tightly coupled integrated navigation systems employ either constant noise covariance or simple noise covariance updating methods, which cannot accurately reflect the dynamic measurement noises. In this article, we propose an adaptive measurement noise estimation algorithm using a transformer and residual denoising autoencoder (RDAE), which can dynamically estimate the covariance of measurement noise. The residual module is used to solve the gradient degradation problem. The DAE is adopted to learn the essential characteristics from the noisy ephemeris data. By introducing the attention mechanism, the transformer can effectively learn the time and space dependency of long-term ephemeris data, and thus dynamically adjusts the noise covariance with the predicted factors. Extensive experimental results demonstrate that our method can achieve sub-meter positioning accuracy in the outdoor open environment. In a GNSS-degraded environment, our proposed method can still obtain about 3 m positioning accuracy. Another test on a new dataset also confirms that our proposed method has reasonable robustness and adaptability.
- 20 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 70 (11) , 11404-11418
Residual Attention Network-Based Confidence Estimation Algorithm for Non-Holonomic Constraint in GNSS/INS Integrated Navigation System
Nowadays, the availability of accurate vehicle position becomes more and more indispensable. The GNSS/INS (Global Navigation Satellite Systems/Inertial Navigation System) is currently the most widely-used integrated navigation scheme for land vehicles, which is capable of provide high-accuracy and continuous positioning results in the open-sky environments. However, under the GNSS-denied conditions, the existing GNSS/INS integrated system often fails to provide reliable positioning results due to various and nonlinear errors contained in the MEMS (Micro-Electro-Mechanical System) IMU (Inertial Measurement Unit) measurements. To improve the positioning accuracy during GNSS outage, deep learning has been introduced into the GNSS/INS integrated system in recent years. In this paper, we propose a residual attention network-based confidence (i.e., measurement noise covariance) estimation algorithm for non-holonomic constraint in GNSS/INS integrated navigation system, which adopts a residual attention network to dynamically estimate the noise covariance of the pseudo-observation (i.e., non-holonomic constraint) for optimal Kalman filtering (KF) fusion. To emphasize the more representative features with larger weights for accurate noise covariance estimation, we introduce an attention mechanism to automatically assign proper weights to the learned features according to their contributions. We evaluate our proposed method on three practical road datasets and compare it with other seven methods including the traditional KF, Pure INS, KF with three deep learning networks, K-means, and the Input-Delayed Neural Networks based method. Extensive experimental results demonstrate that our proposed RA-NHC bounds the errors associated with velocities and achieves reasonable accuracy improvement in position and velocity estimation.
- 20 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 70 (11) , 11404-11418
Residual Attention Network-Based Confidence Estimation Algorithm for Non-Holonomic Constraint in GNSS/INS Integrated Navigation System
Nowadays, the availability of accurate vehicle position becomes more and more indispensable. The GNSS/INS (Global Navigation Satellite Systems/Inertial Navigation System) is currently the most widely-used integrated navigation scheme for land vehicles, which is capable of provide high-accuracy and continuous positioning results in the open-sky environments. However, under the GNSS-denied conditions, the existing GNSS/INS integrated system often fails to provide reliable positioning results due to various and nonlinear errors contained in the MEMS (Micro-Electro-Mechanical System) IMU (Inertial Measurement Unit) measurements. To improve the positioning accuracy during GNSS outage, deep learning has been introduced into the GNSS/INS integrated system in recent years. In this paper, we propose a residual attention network-based confidence (i.e., measurement noise covariance) estimation algorithm for non-holonomic constraint in GNSS/INS integrated navigation system, which adopts a residual attention network to dynamically estimate the noise covariance of the pseudo-observation (i.e., non-holonomic constraint) for optimal Kalman filtering (KF) fusion. To emphasize the more representative features with larger weights for accurate noise covariance estimation, we introduce an attention mechanism to automatically assign proper weights to the learned features according to their contributions. We evaluate our proposed method on three practical road datasets and compare it with other seven methods including the traditional KF, Pure INS, KF with three deep learning networks, K-means, and the Input-Delayed Neural Networks based method. Extensive experimental results demonstrate that our proposed RA-NHC bounds the errors associated with velocities and achieves reasonable accuracy improvement in position and velocity estimation.
- 16 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-13
Predicting the Noise Covariance With a Multitask Learning Model for Kalman Filter-Based GNSS/INS Integrated Navigation
In the recent years, the availability of accurate vehicle position becomes more urgent. The global navigation satellite systems/inertial navigation system (GNSS/INS) is the most used integrated navigation scheme for land vehicles, which utilizes the Kalman filter (KF) to optimally fuse GNSS measurement and INS prediction for accurate and robust localization. However, the uncertainty of the process noise covariance and the measurement noise covariance has a significant impact on Kalman filtering performance. Traditional KF-based integrated navigation methods configure the process noise covariance and measurement noise covariance with predefined constants, which cannot adaptively characterize the various and dynamic environments, and obtain accurate and continuous positioning results under complex environments. To obtain accurate and robust localization results under various complex and dynamic environments, in this article, we propose a novel noise covariance estimation algorithm for the GNSS/INS-integrated navigation using multitask learning model, which can simultaneously estimate the process noise covariance and measurement noise covariance for the KF. The predicted multiplication factors are used to dynamically scale process noise covariance matrix and measurement noise covariance matrix respectively according to the inputs of raw inertial measurement. Extensive experiments are conducted on our collected practical road data set under three typical complex urban scenarios, such as, avenues, viaducts, and tunnels. Experimental results demonstrate that compared with the traditional KF-based integrated navigation algorithm with predefined fixed settings, our proposed method reduces 77.13% positioning error.
- 16 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-13
Predicting the Noise Covariance With a Multitask Learning Model for Kalman Filter-Based GNSS/INS Integrated Navigation
In the recent years, the availability of accurate vehicle position becomes more urgent. The global navigation satellite systems/inertial navigation system (GNSS/INS) is the most used integrated navigation scheme for land vehicles, which utilizes the Kalman filter (KF) to optimally fuse GNSS measurement and INS prediction for accurate and robust localization. However, the uncertainty of the process noise covariance and the measurement noise covariance has a significant impact on Kalman filtering performance. Traditional KF-based integrated navigation methods configure the process noise covariance and measurement noise covariance with predefined constants, which cannot adaptively characterize the various and dynamic environments, and obtain accurate and continuous positioning results under complex environments. To obtain accurate and robust localization results under various complex and dynamic environments, in this article, we propose a novel noise covariance estimation algorithm for the GNSS/INS-integrated navigation using multitask learning model, which can simultaneously estimate the process noise covariance and measurement noise covariance for the KF. The predicted multiplication factors are used to dynamically scale process noise covariance matrix and measurement noise covariance matrix respectively according to the inputs of raw inertial measurement. Extensive experiments are conducted on our collected practical road data set under three typical complex urban scenarios, such as, avenues, viaducts, and tunnels. Experimental results demonstrate that compared with the traditional KF-based integrated navigation algorithm with predefined fixed settings, our proposed method reduces 77.13% positioning error.