Haibin Duan

dblp:25/3501 · DBLP profile ↗
← Back
67ranked-venue papers
14as first author
28since 2021 · last 2026
0000-0002-4926-3202ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 34 · 8 first-author · 10 since 2021Applied, interdisciplinary, general and emerging computing · 20 · 5 first-author · 8 since 2021Systems, architecture and hardware · 7 · 5 since 2021Human-computer interaction and ubiquitous computing · 4 · 1 first-author · 4 since 2021Databases, data management, data science and information retrieval · 2 · 1 since 2021
YearPublicationVenuePosition
2026 Many-objective virtual power plants resource scheduling based on evolutionary multifactorial optimization
Zhihua Cui, Haibin Duan, Jinjun Chen
Expert Syst. Appl.4
2026 Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
Shukun Xiong, Maoxun Yuan, Ranjie Duan, Qing Guo 0005, Haibin Duan, Xingxing Wei 0001
Int. J. Comput. Vis.8
2026 Disturbance-Rejection Prescribed Performance Control With Fixed-Time for High-Order Nonlinear Systems via Command Filter
abstract
This paper presents a fixed-time command-filtered backstepping control method for high-order nonlinear networked systems subject to input saturation. A fixed-time command filter is introduced to cope with the complexity explosion caused by the backstepping method. On this basis, the error compensation mechanism is used to eliminate the effect of filter error. Furthermore, input saturation and prescribed performance are considered to meet the actual engineering requirements. Subsequently, a fixed-time state-feedback controller is designed by combining the backstepping method and command filter. This designed controller not only has the advantages of conventional command-filtered backstepping control but also ensures fixed-time convergence characteristics. Finally, two examples are provided to illustrate its effectiveness.
Zhaoyu Zhang 0005, Mengzhen Huo, Haibin Duan
IEEE Trans Autom. Sci. Eng.4
2026 Bioinspired Homotopic Model Predictive Contouring Control for Fixed-Wing Unmanned Aerial Vehicle Swarm
abstract
The emergence of homotopic path planning and tracking has shown great promise for cooperative swarm control. However, existing implementations lack efficient mechanisms for homotopy-constrained path tracking. In this paper, a bioinspired homotopic model predictive contouring control (HMPCC) method is proposed for cooperative path tracking in a fixed-wing unmanned aerial vehicle (UAV) swarm. Inspired by the hunting behavior and hierarchical social dynamics of Harris’s hawks, our proposed strategy can guide the entire swarm along trajectories within the same homotopy class. It simultaneously optimizes the swarm’s path tracking progress, enabling tight coordination while maintaining high tracking precision. Furthermore, the HMPCC method significantly reduces intra-swarm communication demands and does not require real-time state information from each individual UAV. Comparative simulations demonstrate that our proposed HMPCC method outperforms some current methods in path tracking accuracy, lap time, and overall coordination.
Haibin Duan
IEEE Trans. Circuits Syst. I Regul. Pap.3
2026 Dynamic Event-Triggered Target Encirclement Control for Heterogeneous UAV/UGV Swarm Based on Finite-Time Distributed Target Observation
abstract
Target encirclement by heterogeneous swarms composed of uncrewed aerial vehicles (UAVs) and uncrewed ground vehicles (UGVs) represents a significant application in multi-agent cooperative operations. With the unified kinematic model for the air-ground heterogeneous multi-agent system (HMAS) established, a finite-time distributed target observer (FTDTO) is first developed to address the issue that not all individuals in the swarm can obtain complete target information. An extended state observer (ESO) is then designed to simultaneously estimate both the agent’s own state and external disturbances, effectively handling uncertainties arising from sensor measurement noise and nonlinear model dynamics. Furthermore, considering the inherent communication challenges and bandwidth limitations in complex air-ground cooperative networks, a dynamic event-triggered mechanism (DETM) is employed. Based on this DETM, an HMAS encirclement control law is developed with adaptive radius contraction capability to prevent target escape. Theoretical analysis demonstrates the stability of the proposed ESO, FTDTO, and control law, and shows that Zeno behavior can be avoided. Simulation experiments are conducted to compare the proposed method with existing approaches, verifying the effectiveness of the proposed method and the target tracking capability with adaptive encirclement formation.
Shiqi Gong, Haibin Duan, Lingchen You
IEEE Trans. Circuits Syst. I Regul. Pap.2
2026 Game-Based Human-Swarm Shared Formation Control Authority Transfer of Manned-Unmanned Aerial Team
Mengzhen Huo, Haibin Duan
IEEE Trans. Circuits Syst. I Regul. Pap.2
2026 Input-Constrained Visual Servoing Formation Control for Quadrotors Using Off-Policy Reinforcement Learning
abstract
In this article, an input-constrained visual servoing formation controller is proposed for multiple quadrotor systems operating without intervehicle communication or relative position measurements. The aerial formation control is achieved by formulating image-based leader-follower dynamics using a virtual camera framework and sphere-based image moments. An adaptive velocity observer is developed for the follower quadrotor to estimate the relative velocity with respect to the leader quadrotor in communication-free environments. Input-constrained visual servoing and attitude controllers are proposed using an off-policy reinforcement learning (RL) algorithm to handle visibility and attitude constraints, without relying on accurate system model parameters. The stability of the closed-loop system is theoretically analyzed, and the effectiveness of the proposed controller is demonstrated through case studies.
Xinning Yi, Hao Liu 0004, Haibin Duan, Jianbin Qiu
IEEE Trans. Cybern.3
2026 BPFNN: Bayesian Probabilistic Fuzzy Neural Networks for Uncertainty-Aware Clustering and Probabilistic Fuzzy Reasoning
abstract
This article introduces the Bayesian probabilistic fuzzy neural network (BPFNN), a unified architecture designed to overcome the challenges of conventional fuzzy clustering and neural networks in terms of uncertainty, noise, and interpretability. At its core, the Bayesian probabilistic fuzzy $C$ -means (BPFCMs) algorithm is employed to define the hidden-layer nodes, extending traditional FCM through non-Gaussian modeling and posterior inference via Markov chain Monte Carlo (MCMC). By combining Metropolis-Hastings (MHs) for membership updates with Gibbs sampling for parameter estimation, BPFCM yields probabilistic memberships that capture uncertainty in the antecedent rules more effectively than deterministic approaches. Since the hidden-layer activations represent only similarity values between inputs and cluster centers, the original input features are not directly preserved. To compensate, the hidden-to-output connections are formulated as linear functions of the input, ensuring recovery of discriminative information in the consequent rules. These functions are optimized using a generalized cross-entropy (GCE) objective, with iteratively reweighted least squares (IRLSs) employed for efficient and regularized updates. Extensive experiments on benchmark datasets and high-dimensional laser-induced breakdown spectroscopy (LIBS) spectral data confirm that BPFNN consistently surpasses both classical fuzzy systems and contemporary deep learning models, providing improved accuracy, robustness, and interpretability.
Haibin Duan, Zheng Wang 0057, Eun-Hu Kim, Zunwei Fu, Witold Pedrycz
IEEE Trans. Cybern.2
2026 Reinforcement Learning-Based Formation Control for Networked Fixed-Wing UAVs: Self-Triggered Observer-Feedforward-Feedback Design and Experiment
abstract
This article studies the robust optimal formation control problem of networked fixed-wing unmanned aerial vehicles (UAVs) under communication uncertainties and external disturbances. A learning-based observer–feedforward–feedback control framework is constructed. A resilient self-triggered (ST) observer is designed to estimate reference data while enabling intermittent communication under communication uncertainties. By integrating reference estimation with a backstepping technique, the cooperative formation control problem is reformulated as a robust optimal regulation problem. The robust optimal feedforward control law is learned via an off-policy reinforcement learning (RL) algorithm that exploits the collected internal system data and external disturbance inputs. The stability of the constructed closed-loop control system is guaranteed, and Zeno behavior in the ST rule is avoided. The effectiveness of the proposed approach is demonstrated through an experimental study of multiple fixed-wing UAVs.
Hao Liu 0004, Ziming Ren, Haibin Duan, Michael V. Basin
IEEE Trans. Syst. Man Cybern. Syst.3
2025 A prompting multi-task learning-based veracity dissemination consistency reasoning augmentation for few-shot fake news detection
Weiqiang Jin, Ningwei Wang, Tao Tao 0005, Mengying Jiang, Yebei Xing, Biao Zhao 0003, Haibin Duan, Guang Yang 0006
Eng. Appl. Artif. Intell.8
2025 Leader-Follower Formation Control via Fixed-Time Distributed Observer Over Directed Topology: Theories and Applications
abstract
The consensus control problem under a leader-follower formation scenario is investigated in this paper, where the interactive link is considered as directed topology. A fixed-time distributed observer (FDO) is proposed to estimate the states of the leader node, whose states are supposed to be accessible for only partial followers. Furthermore, a weighted consensus protocol (WCP) is deployed on unmanned aerial vehicles (UAV) to attain formation tracking. The fixed-time convergence of FDO is proved through Lyapunov theories. A comparative simulation is conducted with FDO against a typical linear observer and WCP against a conventional consensus protocol. The results depict that the faster convergence speed and lower formation tracking error can be reached by FDO and WCP. An outdoor experiment with an unmanned ground vehicle (UGV) as leader and three quadrotor UAVs as followers is performed to enhance the application of the proposed approach.
Zhaoyu Zhang 0005, Haibin Duan
IEEE Trans. Circuits Syst. I Regul. Pap.2
2025 Enclosing Control of UAV Swarm With Distributed Neighbor Selection and Finite-Time Observer in Three-Dimensional Environment
abstract
The control of unmanned aerial vehicle (UAV) swarm for enclosing a target in a three-dimensional (3D) environment presents significant challenges essential for collaborative hunting tasks. A novel enclosing control framework is presents to facilitate the enclosure of a dynamic target by a swarm comprising both informed and uninformed UAVs in this paper. Initially, a distributed neighbor selection strategy based on interaction state (DNS-IS) is developed to optimize communication links while preserving the connectivity for uninformed UAVs. Subsequently, a finite-time distributed target state observer (FTDTO) is designed to rapidly and accurately estimate the target state for each UAV, ensuring that uninformed UAVs achieve the same observational accuracy as informed ones. Furthermore, an enclosing control law utilizing artificial potential field functions is proposed to effectively guide the UAVs and stabilize the enclosing formation. Simulation results validate the effectiveness of the proposed DNS-IS, FTDTO and control law, demonstrating the framework’s ability to achieve and dynamically maintain the desired enclosing configuration around the target, thereby ensuring the operational accuracy of the swarm.
Mengzhen Huo, Haibin Duan
IEEE Trans. Circuits Syst. I Regul. Pap.3
2025 Invariant Ellipsoids Method for Homogeneous Leader-Following Consensus Control
abstract
The invariant ellipsoid methodology focuses on minimizing the invariant/attractive set for a linear control system subjects to bounded external disturbances. In this note, the invariant ellipsoid methodology is adapted to multiagent systems (MASs) by leveraging the generalized homogeneous control. A necessary and sufficient condition for the optimal rejection of external disturbances using a homogeneous control protocol is presented. Compared to linear control protocols, the generalized homogeneous approach yields faster convergence and enhanced accuracy. Theoretical results are validated by the numerical simulations of the multiagent system comprised of unicycle mobile robots (UMRs).
Siyuan Wang 0018, Haibin Duan, Min Li 0088, Andrei Polyakov 0001, Gang Zheng 0002
IEEE Trans. Cybern.2
2025 Corrections to "Robust Classification via Interval Type-2 Fuzzy C-Means and Gradient Boosting"
abstract
Original Article: Robust Classification via Interval Type-2 Fuzzy C-Means and Gradient Boosting, IEEE Transactions on Fuzzy Systems, vol. 33, no. 9, pp. 3103–3117, Sept. 2025. doi:10.1109/TFUZZ.2025.3583051.
Haibin Duan, Zheng Wang 0057, Eun-Hu Kim, Zunwei Fu, Witold Pedrycz
IEEE Trans. Fuzzy Syst.2
2025 Robust Classification via Interval Type-2 Fuzzy C-Means and Gradient Boosting
abstract
This article introduces the Bayesian probabilistic fuzzy neural network (BPFNN), designed to overcome the limitations of Fuzzy C-Means (FCM) clustering, which struggles with uncertainty, noise, nonlinearity, and interpretability. Additionally, it addresses the shortcomings of traditional objective functions, such as mean squared error (MSE), which fail to capture the complexities inherent in high-dimensional and uncertain datasets. The BPFNN framework integrates Bayesian probabilistic modeling with advanced fuzzy clustering techniques, utilizing a non-Gaussian probability density function to better represent data uncertainties. A hybrid Markov chain Monte Carlo strategy, combining Metropolis-Hastings for membership updates and Gibbs sampling for cluster parameter estimation, is employed to effectively model uncertainty. For the learning of connection weights, the generalized cross-entropy loss function is applied, and the iteratively reweighted least squares algorithm is used to update the weights, allowing for a more precise quantification of the divergence between predicted and ground truth labels. Experimental evaluations on several benchmark datasets, as well as a high-dimensional laser-induced breakdown spectroscopy (LIBS) spectral dataset, demonstrate that the proposed BPFNN significantly outperforms both traditional methods and State-of-the-Art techniques in terms of classification accuracy and robustness. Notably, BPFNN achieves an average accuracy improvement of 3.2% over conventional models on benchmark datasets, with a 5.3% improvement on the LIBS dataset, highlighting its substantial advancement in the field.
Haibin Duan, Zheng Wang 0057, Eun-Hu Kim, Zunwei Fu, Witold Pedrycz
IEEE Trans. Fuzzy Syst.2
2025 Replanning-Oriented Framework for Efficient Real-Time Decision-Making in Multi-UAV Systems
abstract
Efficient real-time decision-making for long-term multiple unmanned aerial vehicles (multi-UAV) missions in geo-distributed environments requires an integrated approach to manage dynamic task demands. We propose a hierarchical dual-layer decision-making framework for multi-UAV mission replanning. The upper layer optimizes multi-UAV deployment using the density-constrained K-medoids clustering and simulated annealing algorithm, achieving globally optimal solutions. The lower layer addresses task assignment via the goal-oriented belief space multiagent reinforcement learning algorithm, which leverages updated belief distributions to mitigate sparse reward and enhance training efficiency. Coordination between the two layers ensures comprehensive coverage of predefined demands while adapting to dynamic events. The effectiveness of the proposed methods is validated through a real-world case study using the 911 call dataset from city emergency services.
Xingshuo Hai, Longyan Tan, Qiang Feng 0003, Haibin Duan, Changyun Wen
IEEE Trans. Ind. Informatics4
2025 Distributed Cooperative Control of Human-UAV Swarm Based on State Observation
abstract
This article proposes an integrated framework for unmanned aerial vehicles (UAVs) cooperative control, combining advanced distributed control strategies with human–swarm interaction mechanisms to address obstacle avoidance scenarios. First, distributed controllers are designed to explicitly account for observer errors. Specifically, first-order and high-order control barrier functions (CBFs), integrated with the bounded-error observer, are proposed and theoretically validated. These CBFs impose constraints on the control inputs to guarantee system safety during the entire operation. Second, a three-tier human–UAV swarm interaction architecture is introduced, enabling comprehensive human intervention across different operational levels. To verify the effectiveness and practicality of the proposed method, simulation experiments are conducted in a target tracking and rescue scenario. The integrated observer–controller design demonstrates superior performance over conventional approaches, exhibiting enhanced obstacle avoidance capabilities and robust disturbance rejection. The three-tier framework can effectively coordinate human–UAV swarm interaction and improve the efficiency of the swarm mission.
Hangxuan He, Mengzhen Huo, Haibin Duan
IEEE Trans. Syst. Man Cybern. Syst.3
2024 Heterogeneous UAV Swarm Task Allocation via Hierarchy Tolerance Pigeon-Inspired Optimization
abstract
The task allocation of unmanned aerial vehicle (UAV) swarm is one of the practical problems for UAV's application and serves as the premise for tackling swarm's complex missions. By establishing a heterogeneous swarm task allocation problem featuring three types of UAVs, constraints such as UAV types, flight time and task execution sequence are considered. An objective function considering flight distance and task time of various types of UAVs is designed. Inspired by the hierarchical interaction behavior of pigeons, the hierarchical structure strategy is proposed and combined with the basic pigeon-inspired optimization (PIO) to improve the population's exploration ability. Simultaneously, the finite tolerance strategy is implemented to prevent individuals from falling into local optima due to inefficient explorations. Accordingly, hierarchy tolerance PIO (HTPIO) algorithm is proposed. Through comparing with other three algorithms across benchmark functions and two examples of swarm task allocation problem, HTPIO obtains the best results on more than half of benchmark functions and all examples. It is proved that HTPIO can effectively deal with complex optimization problems without increasing computational consumption and ensures the population always maintains a strong optimization ability throughout the process.
Haibin Duan, Yongbin Sun
CEC2
2024 DisCo-FEND: Social Context Veracity Dissemination Consistency-Guided Case Reasoning for Few-Shot Fake News Detection
Weiqiang Jin, Ningwei Wang, Tao Tao 0005, Mengying Jiang, Biao Zhao 0003, Haibin Duan, Guang Yang 0006
WISE (5)8
2024 UAV swarm air combat maneuver decision-making method based on multi-agent reinforcement learning and transferring
Haibin Duan
Sci. China Inf. Sci.3
2024 Three-Dimension Cluster Space Formation Control of Manned/Unmanned Aerial Team Subject to Input Constraint
abstract
Using the heterogeneous manned/unmanned aerial team in a dynamic environment offers a lot of benefits, but one needs an efficient system to coordinate their behavior. This article provides a three-dimension cluster space formation control method to allow one operator on the manned aircraft to supervise and control multiple unmanned systems simultaneously. In this method, the UAV swarm is regarded as an entity with specified cluster space states. Through this method, the cluster space commands issued by the operator could be converted to the UAV pose states. Via the combination of four designed cluster space commands, the heterogeneous team could complete the complex formation transformation in three-dimension space. To execute the commands from operators under the input constraint, the unmanned system utilizes the damping discrete time optimal control law to converge to the desired pose states. To validate the effectiveness of the proposed cluster space formation control method, experiments are conducted on both numerical simulations and platforms.
Mengzhen Huo, Haibin Duan
IEEE Trans. Ind. Informatics2
2024 Adaptive Learning Control for a Quadrotor Unmanned Aerial Vehicle Landing on a Moving Ship
abstract
The shipboard landing problem of a quadrotor without prior knowledge of the ship is investigated in this article. The relative motion model of the quadrotor and the ship is established and transformed into an affine form for the landing controller design. To improve the adaptability to different ships, a neuron-adaptive neural network is adopted to estimate the model uncertainties caused by unknown ship parameters, and the disturbance observer is developed to measure the lumped disturbance, including the external disturbances and the approximation error. Moreover, a novel backstepping integral evolution sliding mode controller is developed for the relative position, and nonsingular fast terminal sliding mode control is adopted for others. Combined with the auxiliary systems, the input saturation and filter errors are considered in the closed-loop system. The theoretical analysis illustrates that the states of the relative motion system are guaranteed to be bounded. The simulation examples demonstrate the effectiveness and advantages of the proposed method.
Yang Yuan 0006, Haibin Duan
IEEE Trans. Ind. Informatics2
2024 Distributed Robust Learning Control for Multiple Unmanned Surface Vessels With Fixed-Time Prescribed Performance
abstract
This article investigates the distributed formation control problem for multiple unmanned surface vessels (USVs) with model uncertainties, exogenous disturbance, and input saturation. First, a distributed finite-time sliding mode observer is developed to obtain the desired trajectory of each USV. Then, a second-order differentiable continuous fixed-time prescribed performance function is applied to reconstruct the error model based on the reference signal. In addition, the unknown part and disturbance are simultaneously handled by the composite learning control method as well as input saturation, where the acrlong NN, disturbance observer, auxiliary system, and nonsingular fast terminal sliding mode technique are integrated. Moreover, it is proved that the formation error converges to a small neighbor of the origin in a finite time. Finally, the computational simulation examples are conducted to validate the feasibility and effectiveness of the proposed method.
Haibin Duan, Yang Yuan 0006, Zhigang Zeng
IEEE Trans. Syst. Man Cybern. Syst.1
2023 Hawk-Pigeon Game Tactics for Unmanned Aerial Vehicle Swarm Target Defense
abstract
Unmanned aerial vehicle (UAV) swarm target defense is a crucial and practical issue about group decision-making and cooperative control in multiagent systems. Hawk-pigeon game architecture is presented in this article to guide UAV swarm target defense. Firstly, a 6-degree-of-freedom UAV model is employed, and the control command converter is derived, which could be widely used in the transformation from the second-order integrator model to the 6-DOF UAV model. Moreover, the attack tactics and pursuit strategies of the defender UAVs are proposed inspired by the hawk's hunting mechanism, and the dynamic model of the attacker UAVs is formulated inspired by pigeon group homing behavior. Furthermore, the victory zone of the hawk-pigeon game is analyzed using the time of interception and explicitly exhibited in isochrones means. The proposed method is scalable and adaptive, adopting distributed decision-making to support large-scale UAV swarm engagement. Finally, comparative experiments in different scenarios demonstrate the effectiveness of the proposed method over state-of-the-art target-attacker-defender game methods on the win rate, the number of captures, and activity time.
Wan-ying Ruan, Yongbin Sun, Haibin Duan
IEEE Trans. Ind. Informatics4
2023 A Novel Framework to Generate Synthetic Video for Foreground Detection in Highway Surveillance Scenarios
abstract
Foreground detection (FD) plays an important role in the domain of video surveillance for highway. The design of advanced FD algorithms requires large-scale and diverse video dataset. However, collecting and labeling real dataset is still time-consuming, labor-intensive, and highly subjective. To address this issue, we first use computer graphics (CG) to clone real highway scenarios (HS) and generate synthetic multi-challenge video datasets, called “Synthetic-HS (CG)”, automatically labeled with accurate pixel-level ground truth. The Synthetic-HS (CG) dataset contains eight imaging condition sequences for computer vision research. Then, we design an image translation (IT) model that translates source domain (Synthetic-HS (CG)) to target domain (real). This model uses skip connections and attention module to generate realistic synthetic images “Synthetic-HS (IT)”. We use publicly available Synthetic-HS in combination with the corresponding real video sequence to conduct experiments. The experiment results suggest that: 1) The Synthetic-HS (CG) dataset enables us to provide precise quantitative evaluation of the drawbacks of foreground detection methods 2) The realistic Synthetic-HS (IT) images can be used to promote the visual perception in highway video surveillance.
Xuan Li 0006, Haibin Duan, Bingzi Liu, Xiao Wang 0002, Fei-Yue Wang 0001
IEEE Trans. Intell. Transp. Syst.2
2023 A Novel Scenarios Engineering Methodology for Foundation Models in Metaverse
abstract
Foundation models are used to train a broad system of general data to build adaptations to new bottlenecks. Typically, they contain hundreds of billions of hyperparameters that have been trained with hundreds of gigabytes of data. However, this type of black-box vulnerability places foundation models at risk of data poisoning attacks that are designed to pass on misinformation or purposely introduce machine bias. Moreover, ordinary researchers have not been able to completely participate due to the rise in deployment standards. This study introduces the theoretical framework of scenarios engineering (SE) for building accessible and reliable foundation models in metaverse, namely, “SE-enabled foundation models in metaverse.” Particularly, the research framework comprises a six-layer architecture (infrastructure layer, operation layer, knowledge layer, intelligence layer, management layer, and interaction layer), which can provide controllability, trustworthiness, and interactivity for the foundation models in metaverse. This creates closed-loop, virtual–real, and human–machine environments that provides the best indices and goals for the foundation models, which allows us to fully validate and calibrate the corresponding models. Then, examples of use cases from the automotive industry are listed to provide transparency on the possible use and benefits of our approach. Finally, the open research topics of related frameworks are discussed.
Xuan Li 0006, Yonglin Tian, Peijun Ye 0001, Haibin Duan, Fei-Yue Wang 0001
IEEE Trans. Syst. Man Cybern. Syst.4
2022 Distributed game strategy for unmanned aerial vehicle formation with external disturbances and obstacles
abstract
We investigate a distributed game strategy for unmanned aerial vehicle (UAV) formations with external disturbances and obstacles. The strategy is based on a distributed model predictive control (MPC) framework and Levy flight based pigeon inspired optimization (LFPIO). First, we propose a non-singular fast terminal sliding mode observer (NFTSMO) to estimate the influence of a disturbance, and prove that the observer converges in fixed time using a Lyapunov function. Second, we design an obstacle avoidance strategy based on topology reconstruction, by which the UAV can save energy and safely pass obstacles. Third, we establish a distributed MPC framework where each UAV exchanges messages only with its neighbors. Further, the cost function of each UAV is designed, by which the UAV formation problem is transformed into a game problem. Finally, we develop LFPIO and use it to solve the Nash equilibrium. Numerical simulations are conducted, and the efficiency of LFPIO based distributed MPC is verified through comparative simulations.
Yang Yuan 0006, Sida Luo, Haibin Duan
Frontiers Inf. Technol. Electron. Eng.4
2022 Biological eagle eye-based method for change detection in water scenes
Xuan Li 0006, Haibin Duan, Jingchun Li, Fei-Yue Wang 0001
Pattern Recognit.2
2020 A cascade adaboost and CNN algorithm for drogue detection in UAV autonomous aerial refueling
Haibin Duan
Neurocomputing2
2020 A multi-objective pigeon-inspired optimization approach to UAV distributed flocking among obstacles
HuaXin Qiu 0001, Haibin Duan
Inf. Sci.2
2020 Multi-UAV obstacle avoidance control via multi-objective social learning pigeon-inspired optimization
abstract
We propose multi-objective social learning pigeon-inspired optimization (MSLPIO) and apply it to obstacle avoidance for unmanned aerial vehicle (UAV) formation. In the algorithm, each pigeon learns from the better pigeon but not necessarily the global best one in the update process. A social learning factor is added to the map and compass operator and the landmark operator. In addition, a dimension-dependent parameter setting method is adopted to improve the blindness of parameter setting. We simulate the flight process of five UAVs in a complex obstacle environment. Results verify the effectiveness of the proposed method. MSLPIO has better convergence performance compared with the improved multi-objective pigeon-inspired optimization and the improved non-dominated sorting genetic algorithm.
Wan-ying Ruan, Haibin Duan
Frontiers Inf. Technol. Electron. Eng.2
2020 Limit-Cycle-Based Mutant Multiobjective Pigeon-Inspired Optimization
abstract
This article presents a limit-cycle-based mutant multiobjective pigeon-inspired optimization (PIO). In this algorithm, the limit-cycle-based mechanism is devised to consider the factors that affect the flight of pigeons to simplify the multiobjective PIO algorithm. The mutant mechanism is incorporated to strengthen the exploration capability in the evolutionary process. Additionally, the application of the dual repository makes the nondominated solutions stored and selected to guide the flight of pigeons. Attributed to the limit-cycle-based mutant mechanisms, this algorithm not only obtains the faster convergence speed and higher accuracy but also improves its population diversity. To confirm the universal application of this algorithm, theoretical analysis of the convergence is discussed in this article. Finally, comparative experiments of our proposed algorithm and other five multiobjective methods are conducted to verify the accuracy, efficiency, and convergence stability of the proposed algorithm.
Haibin Duan, Mengzhen Huo, Yuhui Shi 0001
IEEE Trans. Evol. Comput.1
2019 Hybrid ISMC-PIO and Receding Horizon Control for UAVs Formation
abstract
Unmanned aerial vehicles (UAVs) formation can achieve considerable missions. Control strategy plays an important role in UAVs formation. In this paper, a receding horizon control (RHC) for UAVs formation based on independent search and multi-area convergence pigeon-inspired optimization (ISMC-PIO) is proposed. To minimize the cost value for measuring UAVs formation process, the modified pigeon-inspired optimization (PIO) is utilized by converting the RHC parameters and performance index for UAVs formation problem to a global optimization problem. PIO is a novel bioinspired algorithm. However, basic PIO has the disadvantages of slower convergence speed and falling into local optimum easily. The modified PIO has faster convergence rate and global search ability by importing independent search factor and multi-area convergence strategy. Numerous experiments are implemented to prove that the ISMC-PIO can converge quickly and obtain a better cost value.
Haibin Duan
CEC2
2019 Binocular Pose Estimation for UAV Autonomous Aerial Refueling via Brain Storm Optimization
abstract
Autonomous aerial refueling (AAR) is a crucial technique of unmanned aerial vehicles (UAVs) to push the fuel limits and play a great role in both civilian and military domains. This paper presents an accurate and robust binocular pose estimation algorithms optimized by brain storm optimization (BSO), which is developed from a robust non-iterative solution of PnP (RPnP). In this algorithm, BSO is employed to select the best rotation axis in RPnP. A large quantity of contrastive simulation experiments has been conducted to verify the proposed algorithm. Furthermore, this work built an aerial verification platform for vision-based AAR. A tanker UAV and a receiver UAV were applied to implement AAR. The real-time visual measuring system includes feature extraction and pose estimation. Several state-of-the-art pose estimation algorithms and the proposed method (which refers to BSO-BPnP) have been tested in the aerial verification platform. Adequate comparative trials and detailed analyses are given in this paper.
Yuhui Shi 0001, Haibin Duan
CEC6
2019 Advancements in pigeon-inspired optimization and its variants
Haibin Duan, HuaXin Qiu 0001
Sci. China Inf. Sci.1
2019 Unmanned aerial systems coordinate target allocation based on wolf behaviors
Haibin Duan, HuaXin Qiu 0001, Tianjie Zhang, Daifeng Zhang, Mengzhen Huo, Yankai Shen
Sci. China Inf. Sci.1
2019 Live-fly experimentation for pigeon-inspired obstacle avoidance of quadrotor unmanned aerial vehicles
Mengzhen Huo, Haibin Duan, Daifeng Zhang, HuaXin Qiu 0001
Sci. China Inf. Sci.2
2019 Affine formation control for heterogeneous multi-agent systems with directed interaction networks
Yang Xu 0018, Dongyu Li, Yancheng You, Haibin Duan
Neurocomputing5
2018 Drogue Detection for Autonomous Aerial Refueling Based on Adaboost and Convolutional Neural Networks
Haibin Duan
ICONIP (4)3
2018 Automatic salient object sequence rebuilding for video segment analysis
Haibin Duan, Zejian Yuan, Nanning Zheng 0001
Sci. China Inf. Sci.2
2018 Social-class pigeon-inspired optimization and time stamp segmentation for multi-UAV cooperative path planning
Daifeng Zhang, Haibin Duan
Neurocomputing2
2018 An adaptive optimal-Kernel time-frequency representation-based complex network method for characterizing fatigued behavior using the SSVEP-based BCI system
Zhongke Gao, Wei-Dong Dang, Yuxuan Yang 0001, Haibin Duan, Guanrong Chen
Knowl. Based Syst.6
2017 Three-Dimensional Path Planning for Uninhabited Combat Aerial Vehicle Based on Predator-Prey Pigeon-Inspired Optimization in Dynamic Environment
abstract
Three-dimension path planning of uninhabited combat aerial vehicle (UCAV) is a complicated optimal problem, which mainly focused on optimizing the flight route considering the different types of constrains under complex combating environment. A novel predator-prey pigeon-inspired optimization (PPPIO) is proposed to solve the UCAV three-dimension path planning problem in dynamic environment. Pigeon-inspired optimization (PIO) is a new bio-inspired optimization algorithm. In this algorithm, map and compass operator model and landmark operator model are used to search the best result of a function. The prey-predator concept is adopted to improve global best properties and enhance the convergence speed. The characteristics of the optimal path are presented in the form of a cost function. The comparative simulation results show that our proposed PPPIO algorithm is more efficient than the basic PIO, particle swarm optimization (PSO), and different evolution (DE) in solving UCAV three-dimensional path planning problems.
Haibin Duan
IEEE ACM Trans. Comput. Biol. Bioinform.2
2016 Convergence analysis of brain storm optimization algorithm
abstract
Brain storm optimization (BSO) algorithm is a new kind of swarm intelligence algorithm, which is inspired by collective behavior of human beings. In this paper, a Markov model for brain storm optimization algorithm is derived. The model gives the theoretical probability of the occurrence of each possible population as the number of generation count goes to infinity. Using the Markov model, the convergence of the brain storm optimization is analyzed.
Haibin Duan, Yuhui Shi 0001
CEC2
2016 Hot-Redundancy CPCI Measurement and Control System Based on Probabilistic Neural Networks
Xiaoguang Hu, Guofeng Zhang 0002, Haibin Duan
ISNN4
2016 A binocular vision-based UAVs autonomous aerial refueling platform
Haibin Duan, Qinan Luo
Sci. China Inf. Sci.1
2016 Echo State Networks With Orthogonal Pigeon-Inspired Optimization for Image Restoration
abstract
In this paper, a neurodynamic approach for image restoration is proposed. Image restoration is a process of estimating original images from blurred and/or noisy images. It can be considered as a mapping problem that can be solved by neural networks. Echo state network (ESN) is a recurrent neural network with a simplified training process, which is adopted to estimate the original images in this paper. The parameter selection is important to the performance of the ESN. Thus, the pigeon-inspired optimization (PIO) approach is employed in the training process of the ESN to obtain desired parameters. Moreover, the orthogonal design strategy is utilized in the initialization of PIO to improve the diversity of individuals. The proposed method is tested on several deteriorated images with different sorts and levels of blur and/or noise. Results obtained by the improved ESN are compared with those obtained by several state-of-the-art methods. It is verified experimentally that better image restorations can be obtained for different blurred and/or noisy instances with the proposed neurodynamic method. In addition, the performance of the orthogonal PIO algorithm is compared with that of several existing bioinspired optimization algorithms to confirm its superiority.
Haibin Duan
IEEE Trans. Neural Networks Learn. Syst.1
2015 Elitist Chemical Reaction Optimization for Contour-Based Target Recognition in Aerial Images
abstract
Target recognition for aerial images is an important research issue in remote sensing applications. Many feature-based recognition methods have been introduced for target recognition. Nevertheless, these methods have their limitations when considering the large amount of data provided by satellite imagery. In this paper, we explore several techniques for target recognition in aerial images with a contour matching approach. Contours in our approach are detected by a contour grouping strategy and described by edge potential function, which provides an attraction field for edges with similar curves. In this sense, target recognition can be formulated as an optimization problem. An improved chemical reaction optimization (CRO) algorithm is proposed in this paper to deal with the target matching problem. Experimental results demonstrate the robustness and high efficiency of our approach over the state-of-the-art evolutionary algorithms, which include the original CRO, predator-prey biogeography-based optimization, an improved version of brain storm optimization, artificial bee colony, quantum-behaved particle swarm optimization, a self-adaptive differential evolution algorithm, and stud genetic algorithm. In addition, several case studies regarding remote sensing are also presented. The results show that the proposed method is capable of improving the application ability of recognizing target in aerial images.
Haibin Duan, Lu Gan 0006
IEEE Trans. Geosci. Remote. Sens.1
2014 Improved Biogeography-Based Optimization approach to secondary protein prediction
abstract
In recent years, many bio-inspired computation algorithms have been proposed to solve constraint problems. Biogeography-Based Optimization (BBO) is one of these newly proposed optimization algorithms. As a new way to solve complicated optimization problems, BBO has a quick convergence. In this paper, we proposed an improved BBO for solving protein structure prediction problems. Comparative experiments with standard BBO and differential evolution algorithm (DE) are also conducted, and the results demonstrate this improved BBO approach performs better in solving these complicated protein prediction problems.
Junsong Fan, Haibin Duan, Guangming Xie
IJCNN2
2014 Biologically adaptive robust mean shift algorithm with Cauchy predator-prey BBO and space variant resolution for unmanned helicopter formation
Xiaohua Wang 0003, Haibin Duan
Sci. China Inf. Sci.2
2014 Dual tree complex wavelet transform approach to copy-rotate-move forgery detection
YunJie Wu, Haibin Duan, Linna Zhou
Sci. China Inf. Sci.3
2014 Imperialist competitive algorithm optimized artificial neural networks for UCAV global path planning
Haibin Duan, Linzhi Huang
Neurocomputing1
2013 Quadrotor Flight Control Parameters Optimization Based on Chaotic Estimation of Distribution Algorithm
Pei Chu, Haibin Duan
ISNN (2)2
2013 Parameters identification of UCAV flight control system based on predator-prey particle swarm optimization
Haibin Duan, Yaxiang Yu
Sci. China Inf. Sci.1
2012 Artificial Bee Colony approach to parameters optimization of Pulse Coupled Neural Networks
abstract
Artificial Bee Colony (ABC) algorithm is a kind of newly developed bio-inspired intelligence. In this paper, we conduct a investigation on bees' behaviors when seeking for food, and a method for optimizing parameters has been developed. By using this algorithm, we can obtain the best solution to many problems. Pulse Coupled Neural Networks (PCNN) is a kind of algorithm widely used in image processing. The current model of PCNN has several shortcomings, such as losing basic details of the original images. ABC algorithm is adopted to search the best value of PCNN parameters. In this way, the image can be enhanced to the fullest extent. Experimental results verified the feasibility and effectiveness of our proposed approach.
Kehan Gao, Haibin Duan, Zhuoshu Li
INDIN2
2012 A cooperative approach to multiple UAVs searching for moving targets based on a hybrid of virtual force and receding horizon
abstract
This paper addresses the problem of multiple Unmanned Aerial Vehicles (UAVs) cooperative searching for several moving targets with a hybrid method, which is named VFRH. This method is a combination of the virtual force method and the receding horizon method. Its main idea is that the virtual force method is used to help the receding horizon method improve searching efficiencies and reduce the computational burdens. The cooperative tactics based on VFRH is subsequently proposed to make the search more effective for multiple UAVs. At last, performance of multi-UAV cooperatively searching for hidden targets based on VFRH shows the promising results.
Zhuoning Dong, Haibin Duan
INDIN4
2010 Receding horizon control for multi-UAVs close formation control based on differential evolution
Xiangyin Zhang, Haibin Duan, Yaxiang Yu
Sci. China Inf. Sci.2
2010 Template matching using chaotic imperialist competitive algorithm
Haibin Duan, Chunfang Xu, Senqi Liu, Shan Shao
Pattern Recognit. Lett.1
2010 Artificial bee colony (ABC) optimized edge potential function (EPF) approach to target recognition for low-altitude aircraft
Chunfang Xu, Haibin Duan
Pattern Recognit. Lett.2
2010 Meta-heuristic intelligence based image processing
Frances Yu, Haibin Duan
Pattern Recognit. Lett.2
2009 Hybrid Game Theory and D-S Evidence Approach to Multiple UCAVs Cooperative Air Combat Decision
Haibin Duan
ISNN (3)2
2009 An Improved Quantum Evolutionary Algorithm with 2-Crossovers
Zhihui Xing, Haibin Duan, Chunfang Xu
ISNN (1)2
2008 UCAV path planning based on Ant Colony Optimization and satisficing decision algorithm
abstract
Path planning of uninhabited combat air vehicle (UCAV) is a complicated global optimum problem. Ant colony optimization (ACO) algorithm was originally presented under the inspiration during collective behavior study results on real ant system, and it has strong robustness and easy to combine with other methods in optimization. In this paper, we propose a hybrid ACO with satisficing decision algorithm for solving the UCAV path planning in complicated combat field environments. When ant chooses the next node from the current candidate path nodes, the acceptance function and rejection function in satisficing decision are calculated. In this way, the efficiency of global optimization can be greatly improved. The detailed realization procedure for this hybrid approach is also presented. Series experimental comparison results show the proposed hybrid method is more effective and feasible in the UCAV path planning than the basic ACO model.
Haibin Duan, Yaxiang Yu, Rui Zhou 0003
IEEE Congress on Evolutionary Computation1
2008 DEACO: Hybrid Ant Colony Optimization with Differential Evolution
abstract
Ant Colony Optimization (ACO) algorithm is a novel meta-heuristic algorithm for the approximate solution of combinatorial optimization problems that has been inspired by the foraging behavior of real ant colonies. ACO has strong robustness and easy to combine with other methods in optimization, but it has the shortcomings of stagnation that limits the wide application to the various areas. In this paper, a hybrid ACO with Differential Evolution (DE) algorithm was proposed to overcome the above-mentioned limitations, and this algorithm was named DEACO. Considering the importance of ACO pheromone trail for ants exploring the candidate paths, DE was applied to optimize the pheromone trail in the basic ACO model. In this way, a reasonable pheromone trail between two neighboring cities can be formed, so as to lead the ants to find out the optimum tour. The proposed algorithm is tested with the Traveling Salesman Problem (TSP), and the experimental results demonstrate that the proposed DEACO is a feasible and effective ACO model in solving complex optimization problems.
Xiangyin Zhang, Haibin Duan, Jiqiang Jin
IEEE Congress on Evolutionary Computation2
2008 Air robot path planning based on Intelligent Water Drops optimization
abstract
Path planning of air robot is a complicated global optimum problem. Intelligent water drops (IWD) algorithm is newly presented under the inspiration of the dynamic of river systems and the actions that water drops do in the rivers, and it is easy to combine with other methods in optimization. In this paper, we propose an improved IWD optimization algorithm for solving the air robot path planning problems in various environments. The water drops can act as an agent in searching the optimal path. The detailed realization procedure for this novel approach is also presented. Series experimental comparison results show the proposed IWD optimization algorithm is more effective and feasible in the air robot path planning than the basic IWD model.
Haibin Duan, Senqi Liu, Xiujuan Lei
IJCNN1
2007 Experimental study of the adjustable parameters in basic ant colony optimization algorithm
abstract
Ant Colony Optimization(ACO) algorithm was originally presented under the inspiration during collective behavior study results on real ant system, and it has strong robustness and easy to combine with other methods in optimization. Although basic ACO algorithm for the heuristic solution of hard combinational optimization problems enjoy a rapidly growing popularity, but little research is conducted on the optimum configuration strategy for the adjustable parameters in the ACO algorithm. In order to deeply study the optimum configuration strategy for the adjustable parameters in the ACO algorithm, an effective Matlab GUI(Graphical User Interface) based ACO simulation platform is developed in this paper. In order to investigate the relative strengths and weaknesses of these adjustable parameters, series of experiments on EIL51TSP are conducted on the developed ACO simulation platform. On the basis of the experimental results presented above, a novel effective “three-step” optimum configuration strategy for the adjustable parameters in basic ACO algorithm is drawn. This “three-step” optimum configuration strategy for the adjustable parameters in basic ACO algorithm is also beneficial to the application and development of ACO algorithm in various kinds of optimization problems.
Haibin Duan, Guanjun Ma, Senqi Liu
IEEE Congress on Evolutionary Computation1
2007 Novel Hybrid Approach for Fault Diagnosis in 3-DOF Flight Simulator Based on BP Neural Network and Ant Colony Algorithm
abstract
In the 3-DOF(degree-of-freedom) flight simulator system, the relations between observed information and fault causes are very complicated. Based on the description of the basic principle of the ant colony algorithm, a novel hybrid approach for fault diagnosis in 3-DOF flight simulator is proposed in this paper, which is based on BP(back propagation) neural network and ant colony algorithm. Combining with rough set theory, ant colony algorithm is used to compute the reductions of the decision table. Then, the condition attributes of decision table are regarded as the input nodes of BP neural network and the decision attributes are regarded as the output nodes of BP neural network correspondingly. Experiments demonstrate that the proposed hybrid approach could achieve a fairly good performance, yield good prediction accuracy of the prediction errors
Haibin Duan, Xiufen Yu, Guanjun Ma
SIS1