Fengqing Hu

Fengqing Hu

Auto-generated profile, based on publicly available information

Fengqing Hu

Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
11 July 2019 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
LCLu Chao
Lu Chao
FHFengqing Hu
Fengqing Hu
DCDongpu Cao
Dongpu Cao
JGJianwei Gong
Jianwei Gong
YXYang Xing
Yang Xing
ZLZirui Li
Zirui Li
Driver model adaptation (DMA) provides a way to model the target driver when sufficient data are not available. Traditional DMA methods running at the model level are restricted by the specific model structures and cannot make full use of the historical data. In this paper, a novel DMA framework based on transfer learning (TL) is proposed to deal with the adaptation of driver models in lane-changing scenarios at the data level. Under the proposed DMA framework, a new TL approach named DTW-LPA that combines dynamic time warping (DTW) and local Procrustes analysis (LPA) is developed. Using the DTW, the relationship between the datasets for different drivers can be found automatically. Based on this relationship, the LPA can transfer the data in the historical dataset to the dataset of a newly-involved driver (target driver). In this way, sufficient data can be obtained for the target driver. After the data transferring process, a proper modeling method, such as the Gaussian mixture regression (GMR), can be applied to train the model for the target driver. Data collected from a driving simulator and realistic driving scenes are used to validate the proposed method in various experiments. Compared with the GMR-only and GMR-MAP methods, the DTW-LPA shows better performance on the model accuracy with much lower predicting errors in most cases.

15 May 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
LCLu Chao
Lu Chao
FHFengqing Hu
Fengqing Hu
DCDongpu Cao
Dongpu Cao
JGJianwei Gong
Jianwei Gong
YXYang Xing
Yang Xing
ZLZirui Li
Zirui Li
Considering the difficulty and high cost of collecting sufficient data in the real world, driving simulators are used in many studies as an alternative data source, which can provide a much easier and safer way to collect driver data. However, because of the inherent differences between the virtual and real world, the recognition model for driving behaviour trained using simulation-based data cannot fit the real driving scenes well. To fill the gap between simulation and real data, a knowledge transfer framework is proposed in this paper. Two transfer learning (TL) methods namely semi-supervised manifold alignment (SMA) and kernel manifold alignment (KEMA) are used in the proposed framework to map the data collected from the virtual and real worlds to one latent common manifold. A typical lane-changing scenario is taken into account for a case study. Three classifiers are trained on the latent manifold and used to do the lane-changing behaviour recognition in the real world. In this way, sufficient simulation data are transferred to supplement the training set with few labelled real data, and thus improve the performance of behaviour recognition in the real world. Compared with the traditional methods without knowledge transfer, classifiers combined with TL can reduce the error rate of recognition from around 30% (when only the real data are used) or higher than 50% (when only the simulation data are used) to as low as 11%.

1 May 2024 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
Yan WangYan Wang
Yan Wang
FHFengqing Hu
Fengqing Hu
CTCheng Tian
Cheng Tian
PLPanshuo Li
Panshuo Li
Hailong HuangHailong Huang
Hailong Huang
CHChao Huang
Chao Huang
Sideslip angle and vehicle velocity are crucial for both traditional and autonomous vehicles. They play essential roles in chassis stability control, as well as in tasks such as path planning and tracking control. However, these states cannot be directly measured by onboard sensors, therefore various vehicle state estimation algorithms have been developed. Most of these algorithms assume that the noise characteristics are known, ignoring the impact of missing measurement data, and cannot simultaneously handle the effects of colored noise and white noise. To address these issues, we propose a fault-tolerant extended Kalman filter network (FTEKFNet), which integrates both physics-based and data-driven methods for vehicle state estimation. Based on the Fault Tolerant Extended Kalman Filter (FTEKF) iterative framework, a pre-trained artificial neural network is utilized to directly predict the Kalman gain, and it is combined with FTEKF to form FTEKFNet. Experimental results under different conditions demonstrate that FTEKFNet can simultaneously deal with unknown noise and data loss problems and has good adaptability to color noise. The estimation performance of the proposed algorithm is better than the traditional FTEKF and EKF methods.

4 February 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
FHFengqing Hu
Fengqing Hu
XFXiaowen Fu
Xiaowen Fu
Hailong HuangHailong Huang
Hailong Huang
Safety is of vital importance to transportation cyber-physical systems (T-CPS). With the deeper integration of automated vehicles (AVs) in road traffic, safe control algorithms for AVs have become a crucial demand for maintaining the overall safety of T-CPS. One of the major concerns with respect to the DRL-based cyber systems of AVs is the lack of safety guarantees, which may cause physical collisions. Safe reinforcement learning (SRL) is a promising way to enhance the safety performance of traditional DRL. However, current SRL methods are designed in a time-triggered (TT) paradigm, where the controller is uniformly triggered in the time domain. Despite the safety enhancement, this TT-SRL paradigm lacks data efficiency in safety-critical scenarios, and most importantly, still cannot guarantee safety during the intervals between time steps. The main objective of this paper is to address the safety issue of the existing TT-SRL methods while improving the data efficiency by proposing an event-triggered SRL (ET-SRL) framework. In the proposed method, safety is guaranteed by designing an additional safe controller to correct the unsafe actions generated by DRL. Event-triggered control barrier functions (CBFs) are used to provide safety constraints in a discrete manner. A state and dynamics synchronization module is also designed to estimate model uncertainties considering both the state dynamics and the input dynamics. The proposed method is trained and applied in simulated car-following experiments. The effectiveness of the proposed method is demonstrated by comparison to both DRL-based and model-based baselines in both artificial safety-critical scenarios and a real trajectory dataset.

1 January 2026 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
DHDong Hu
Dong Hu
FHFengqing Hu
Fengqing Hu
Lidong YangLidong Yang
Lidong Yang
CHChao Huang
Chao Huang