Selected work

Representative Papers

An Indoor Navigation System for the Visually Impaired based on UWB Positioning and D* Lite Path Planning Algorithm

Jul 17, 2026

This study addresses the challenge of enabling safe and autonomous indoor navigation for visually impaired individuals in GPS-denied environments. The authors propose an indoor navigation system that integrates centimeter-level accurate ultra-wideband (UWB) positioning with the D* Lite dynamic path planning algorithm. By leveraging UWB for high-precision real-time localization and employing D* Lite to rapidly replan optimal paths in response to dynamic obstacles, the system significantly enhances both the responsiveness and robustness of navigation. Experimental results demonstrate that the proposed approach achieves low latency and high reliability, effectively supporting visually impaired users in navigating complex indoor spaces safely and flexibly.

0 citationsRead paper

Discovery of connectivity-trainability trade-off of IQP Circuits for Hamiltonian Optimization

Jun 23, 2026

This study investigates the performance and trainability of Instantaneous Quantum Polynomial-time (IQP) circuits in Hamiltonian optimization tasks, with a focus on how circuit architecture influences optimization capability. Through systematic numerical experiments and theoretical analysis, the authors evaluate training efficacy across IQP circuits with varying connectivity structures. They uncover and quantify, for the first time, a trade-off between connectivity and trainability: while higher connectivity enhances expressive power, it also exacerbates vanishing gradients, thereby hindering optimization efficiency; in contrast, moderately connected architectures facilitate more reliable convergence to low-energy states. These findings highlight the critical role of circuit topology in variational quantum optimization and offer practical guidance for designing scalable and trainable quantum algorithms.

0 citationsRead paper

Statistical Firefly Algorithm for Truss Topology Optimization

Jan 18, 2026

This study addresses the high computational cost and low search efficiency commonly encountered in truss topology optimization by proposing an enhanced firefly algorithm integrated with a statistical hypothesis testing mechanism. The method leverages historical movement information of individual solutions to statistically evaluate and select potentially effective search directions, thereby avoiding redundant structural reanalyses. Without altering the original algorithmic framework, this approach significantly reduces computational overhead. Experimental results on multiple classical truss benchmark problems demonstrate that the proposed method achieves comparable solution quality while substantially decreasing the number of objective function evaluations, leading to markedly improved optimization efficiency.

0 citationsRead paper

Real-time Recognition of Human Interactions from a Single RGB-D Camera for Socially-Aware Robot Navigation

Sep 29, 2025

Existing robot navigation systems often neglect human social cues, resulting in unnatural interactions and compromised safety. This paper proposes a real-time, socially aware navigation method based on a single RGB-D camera. First, 3D human pose estimation extracts individual body configurations; then, a computationally efficient spatial group modeling approach—integrating Principal Component Analysis (PCA) with the shoelace formula—precisely identifies interaction directions and participant regions. The entire pipeline is implemented end-to-end within the ROS 2 framework. Evaluated in dynamic social environments, the method achieves high-accuracy social interaction recognition with an average per-frame processing time of approximately 4 ms, enabling deployment on resource-constrained embedded platforms. The source code is publicly released. This work establishes a novel paradigm for lightweight, scalable, and socially compliant robotic navigation.

0 citationsRead paper

Two-Stage Swarm Intelligence Ensemble Deep Transfer Learning (SI-EDTL) for Vehicle Detection Using Unmanned Aerial Vehicles

Sep 09, 2025

To address low detection accuracy and poor generalization in multi-vehicle detection from UAV imagery, this paper proposes a two-stage deep transfer learning ensemble framework optimized via swarm intelligence. Methodologically, it constructs a heterogeneous feature-decision dual-layer ensemble model by integrating three Faster R-CNN variants with five transfer classifiers; whale optimization algorithm (WOA) is employed for automated hyperparameter search, and a weighted averaging strategy enhances detection balance. The entire framework is implemented in MATLAB R2020b with parallel computing support. Experimental evaluation on the AU-AIR dataset demonstrates that the proposed method significantly outperforms existing state-of-the-art approaches, achieving a 5.3% improvement in mean average precision (mAP) while maintaining high precision and recall. Results confirm its robustness and generalization capability in small-object and densely populated scenarios.

0 citationsRead paper

Recent publications

Latest Papers

An Indoor Navigation System for the Visually Impaired based on UWB Positioning and D* Lite Path Planning Algorithm

Jul 17, 2026

This study addresses the challenge of enabling safe and autonomous indoor navigation for visually impaired individuals in GPS-denied environments. The authors propose an indoor navigation system that integrates centimeter-level accurate ultra-wideband (UWB) positioning with the D* Lite dynamic path planning algorithm. By leveraging UWB for high-precision real-time localization and employing D* Lite to rapidly replan optimal paths in response to dynamic obstacles, the system significantly enhances both the responsiveness and robustness of navigation. Experimental results demonstrate that the proposed approach achieves low latency and high reliability, effectively supporting visually impaired users in navigating complex indoor spaces safely and flexibly.

0 citationsRead paper

Discovery of connectivity-trainability trade-off of IQP Circuits for Hamiltonian Optimization

Jun 23, 2026

This study investigates the performance and trainability of Instantaneous Quantum Polynomial-time (IQP) circuits in Hamiltonian optimization tasks, with a focus on how circuit architecture influences optimization capability. Through systematic numerical experiments and theoretical analysis, the authors evaluate training efficacy across IQP circuits with varying connectivity structures. They uncover and quantify, for the first time, a trade-off between connectivity and trainability: while higher connectivity enhances expressive power, it also exacerbates vanishing gradients, thereby hindering optimization efficiency; in contrast, moderately connected architectures facilitate more reliable convergence to low-energy states. These findings highlight the critical role of circuit topology in variational quantum optimization and offer practical guidance for designing scalable and trainable quantum algorithms.

0 citationsRead paper

Statistical Firefly Algorithm for Truss Topology Optimization

Jan 18, 2026

This study addresses the high computational cost and low search efficiency commonly encountered in truss topology optimization by proposing an enhanced firefly algorithm integrated with a statistical hypothesis testing mechanism. The method leverages historical movement information of individual solutions to statistically evaluate and select potentially effective search directions, thereby avoiding redundant structural reanalyses. Without altering the original algorithmic framework, this approach significantly reduces computational overhead. Experimental results on multiple classical truss benchmark problems demonstrate that the proposed method achieves comparable solution quality while substantially decreasing the number of objective function evaluations, leading to markedly improved optimization efficiency.

0 citationsRead paper

Real-time Recognition of Human Interactions from a Single RGB-D Camera for Socially-Aware Robot Navigation

Sep 29, 2025

Existing robot navigation systems often neglect human social cues, resulting in unnatural interactions and compromised safety. This paper proposes a real-time, socially aware navigation method based on a single RGB-D camera. First, 3D human pose estimation extracts individual body configurations; then, a computationally efficient spatial group modeling approach—integrating Principal Component Analysis (PCA) with the shoelace formula—precisely identifies interaction directions and participant regions. The entire pipeline is implemented end-to-end within the ROS 2 framework. Evaluated in dynamic social environments, the method achieves high-accuracy social interaction recognition with an average per-frame processing time of approximately 4 ms, enabling deployment on resource-constrained embedded platforms. The source code is publicly released. This work establishes a novel paradigm for lightweight, scalable, and socially compliant robotic navigation.

0 citationsRead paper

Two-Stage Swarm Intelligence Ensemble Deep Transfer Learning (SI-EDTL) for Vehicle Detection Using Unmanned Aerial Vehicles

Sep 09, 2025

To address low detection accuracy and poor generalization in multi-vehicle detection from UAV imagery, this paper proposes a two-stage deep transfer learning ensemble framework optimized via swarm intelligence. Methodologically, it constructs a heterogeneous feature-decision dual-layer ensemble model by integrating three Faster R-CNN variants with five transfer classifiers; whale optimization algorithm (WOA) is employed for automated hyperparameter search, and a weighted averaging strategy enhances detection balance. The entire framework is implemented in MATLAB R2020b with parallel computing support. Experimental evaluation on the AU-AIR dataset demonstrates that the proposed method significantly outperforms existing state-of-the-art approaches, achieving a 5.3% improvement in mean average precision (mAP) while maintaining high precision and recall. Results confirm its robustness and generalization capability in small-object and densely populated scenarios.

0 citationsRead paper