Fulong Hu

Fulong Hu

Auto-generated profile, based on publicly available information

Fulong Hu

Huazhong University of Science and Technology

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
28 January 2025 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
FHFulong Hu
Fulong Hu
HZHai-Tao Zhang
Hai-Tao Zhang
BXBowen Xu
Bowen Xu
ZHZhe Hu
Zhe Hu
In this note, a detective matrix-based distributed algorithm is proposed to address a distributed minimum-time consensus prediction problem for discrete-time high-order multi-agent systems (MASs). Therein, each agent predicts the consensus value merely using the minimum length of individual and/or neighboring successive position time series. Compared to most existing algorithms that could only predict constant consensus values for first-order linear MASs, the present method could predict consensus manifolds for high-order linear MASs as well, which could be time-varying. Finally, both the effectiveness and superiority of the proposed distributed minimum-time consensus algorithm are substantiated by numerical simulations.

18 March 2024 in IEEE Transactions on Control of Network Systems
Verified
Journal Article
Closed access
FHFulong Hu
Fulong Hu
HZHai-Tao Zhang
Hai-Tao Zhang
YTYang Tang
Yang Tang
In this study, discrete-time high-order linear dynamics of multi-agent systems (MASs) is considered. A distributed minimal-time deadbeat consensus prediction (MDCP) algorithm is proposed that allows each agent to calculate the consensus value of an MAS merely by using the shortest intermittent information series of its own and its neighbors. The challenge of MDCP lies in revealing the relationship between the consensus item of state $\mathcal {Z}$ -transform and the annihilating polynomial of matrix pair with intermittent information. Sufficient conditions are derived to guarantee the feasibility of the present MDCP. Finally, both the effectiveness and superiority of the proposed MDCP are substantiated by numerical simulations.

17 July 2025 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
FHFulong Hu
Fulong Hu
HZHai-Tao Zhang
Hai-Tao Zhang
BXBowen Xu
Bowen Xu
JWJun Wang
Jun Wang
A hybrid self-supervised Koopman deep learning algorithm has been developed to learn the Koopman operator for nonlinear multi-agent systems (MASs) using partial state information. In contrast, most existing Koopman operator-learning methods rely on full state series, which is infeasible for most general nonlinear networked systems or multi-agent systems (MASs), as each node/agent only has access to its neighbor(s). Therein, a nonlinear encoder is designed as an observer function to lift the nonlinear state into a high-dimensional Hilbert space. In this lifted linear space, a linear networked model is constructed to predict future states. A corresponding nonlinear decoder, serving as the inverse of the encoder, retrieves the original nonlinear states. This algorithm could distill the linear features from the partial state information of nonlinear MASs, transforming complex, hard-to-predict nonlinear dynamics into high-dimensional linear systems. Accordingly, the retrieved linear feature can serve as an interface for other calculations, which can then be decoded back to the original nonlinear states. Theoretical derivation guarantees the feasibility of the present distributed Koopman operator-learning (DKOL). Extensive numerical simulations demonstrate its effectiveness and superiority.

1 January 2026 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
RSRan Shi
Ran Shi
HZHai-Tao Zhang
Hai-Tao Zhang
JLJialuo Li
Jialuo Li
FHFulong Hu
Fulong Hu
YHYifan Hu
Yifan Hu
JZJiayu Zou
Jiayu Zou
In this article, a heterogeneous multiagent pursuit-evasion (MPE) differential gaming problem is addressed. Therein, the pursuers aim to cooperatively capture the sole escaping evader. The theoretical analytical challenge lies in designing the Nash-minmax gaming strategy for such MPE games under directed graphs with external disturbances. Intra-alliance cooperation (pursuers and their peer neighbors) is regarded as a nonzero-sum game, while interalliance confrontation (multiple pursuers versus one evader) is treated as another zero-sum game. To tackle this issue, a hierarchical gaming framework is established to solve the associated coupled Hamilton-Jacobi-Isaacs (HJI) equation and accordingly derive the associated distributed gaming protocol. Finally, both numerical simulations and lake-based multi-autonomous surface vehicle (ASV) gaming experiments are conducted to verify the effectiveness of the present MPE gaming strategy.

1 November 2026 in IEEE Transactions on Control Systems Technology
Verified
Journal Article
Closed access
RSRan Shi
Ran Shi
HZHai-Tao Zhang
Hai-Tao Zhang
JLJialuo Li
Jialuo Li
DDDongyi Dai
Dongyi Dai
FHFulong Hu
Fulong Hu
BLBin Liu
Bin Liu

23 December 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
FHFulong Hu
Fulong Hu
HZHai-Tao Zhang
Hai-Tao Zhang
CLChen Lv
Chen Lv
JWJun Wang
Jun Wang
A hybrid Koopman deep learning algorithm is developed to predict the final synchronization of networked nonlinear dynamics with different topologies merely using neighboring state information. This algorithm introduces a nonlinear encoder as an observable function that maps the nonlinear state into a high-dimensional Hilbert space. By this means, a networked linear model is established to predict the future state of multiple transformed linear systems in the lifted space. Meanwhile, a nonlinear decoder is constructed, as the inverse of the lifting function, to retrieve the original nonlinear states. The virtue of the present algorithm lies in distilling and merging the linear features of multiple different topologies solely from the individual and/or neighboring state series. Therefore, the final synchronization states are calculated within the encoded linear space and subsequently decoded to recover the synchronization of the original nonlinear systems. Compared to most existing relevant algorithms that could only predict consensus values for linear networks, the present method could predict the final synchronization state of networked nonlinear dynamics with varying backbones. Sufficient conditions are derived to guarantee the prediction capability of the distributed final synchronization prediction (DFSP). Extensive numerical simulations verify its effectiveness.