Xinjie Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xinjie Xiao has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Bo Shen
Donghua University
2 shared publications - Huashan Liu
School of Information and Intelligent Science, Donghua University, Shanghai, China
2 shared publications - Huan Zhang
School of Information Engineering, Guangdong University of Technology, Guangzhou, China
1 shared publication - Lianghui Li
College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China
1 shared publication - Lieyu Tian
Guangzhou Marine Geological Survey, Guangzhou 511458, China
1 shared publication Xiangjian Li
Donghua University
1 shared publication
Latest Publications
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (3) , 2186-2197
Rapid Generalization of Motion Planning for Robot Manipulator Among Locally Changed Environments
As is known, the problem of making a trained deep reinforcement learning (DRL) model to adapt to a new environment different from where it trains remains open. In this article, DRL-based techniques are investigated and deployed for the robotic motion planning task in locally changed environments. First, a dynamic-entropy actor-critic is proposed to automatically adjust the coefficient of the entropy cluster to enable the agent to efficiently learn the potentially optimal policy. Second, a tutoring-guiding mechanism is established to heuristically explore and sufficiently exploit valuable experience. Third, a mechanism consisting of progressive planner and inverse kinematics mapper is designed to cope with localized changes in the environment, which enables the robot manipulator to rapidly adapt to the newly changed environment. Finally, experimental results have verified the superior performance of the proposed approaches.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (3) , 2186-2197
Rapid Generalization of Motion Planning for Robot Manipulator Among Locally Changed Environments
As is known, the problem of making a trained deep reinforcement learning (DRL) model to adapt to a new environment different from where it trains remains open. In this article, DRL-based techniques are investigated and deployed for the robotic motion planning task in locally changed environments. First, a dynamic-entropy actor-critic is proposed to automatically adjust the coefficient of the entropy cluster to enable the agent to efficiently learn the potentially optimal policy. Second, a tutoring-guiding mechanism is established to heuristically explore and sufficiently exploit valuable experience. Third, a mechanism consisting of progressive planner and inverse kinematics mapper is designed to cope with localized changes in the environment, which enables the robot manipulator to rapidly adapt to the newly changed environment. Finally, experimental results have verified the superior performance of the proposed approaches.
- 17 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
Underwater Image Enhancement via Adaptive Bi-Level Color-Based Adjustment
Underwater images often exhibit severe color distortions and reduced contrast due to light absorption and scattering, presenting substantial challenges for image enhancement techniques. To address these challenges, this paper presents BCTA-Net, an adaptive bi-level color-based network specifically engineered to enhance the quality of underwater images by addressing distortions in dynamic and complex environments. The network integrates content-aware global and local restoration strategies. On a local scale, a color-aware attention mechanism is proposed which employs color histograms to adaptively correct non-uniform color distortions and enhance local color fidelity. Additionally, a triple attention module restores spatially varying local details in a content-aware manner, improving clarity and texture precision of enhancement. These elements are combined into a dual-branch architecture aimed at reducing local contrast, color fidelity, and detail precision issues. On a global scale, contrastive learning focused on background lightness corrects color distortions due to uneven illumination. The integration of these components results in a lightweight, dynamic global-local model with robust generalization capabilities across various underwater scenarios, as demonstrated by comprehensive experiments that show significant performance improvements over existing methods.
- 17 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
Underwater Image Enhancement via Adaptive Bi-Level Color-Based Adjustment
Underwater images often exhibit severe color distortions and reduced contrast due to light absorption and scattering, presenting substantial challenges for image enhancement techniques. To address these challenges, this paper presents BCTA-Net, an adaptive bi-level color-based network specifically engineered to enhance the quality of underwater images by addressing distortions in dynamic and complex environments. The network integrates content-aware global and local restoration strategies. On a local scale, a color-aware attention mechanism is proposed which employs color histograms to adaptively correct non-uniform color distortions and enhance local color fidelity. Additionally, a triple attention module restores spatially varying local details in a content-aware manner, improving clarity and texture precision of enhancement. These elements are combined into a dual-branch architecture aimed at reducing local contrast, color fidelity, and detail precision issues. On a global scale, contrastive learning focused on background lightness corrects color distortions due to uneven illumination. The integration of these components results in a lightweight, dynamic global-local model with robust generalization capabilities across various underwater scenarios, as demonstrated by comprehensive experiments that show significant performance improvements over existing methods.