个人信息
参与实验室科研项目
复杂环境下非完全信息博弈决策的智能基础模型研究
研究课题
人机共享控制中的非线性仲裁方法研究
学术成果
共撰写/参与撰写专利 0 项，录用/发表论文 3 篇，投出待录用论文3篇。
Journal Articles
-
UNA-SAC: An Uncertainty-Aware Nonlinear Arbitration Method for Human–AI Shared Control
Shuyue Jiang,
Yun-Bo Zhao ,
Yu Kang,
Fei Xie,
and Yun-Sheng Zhao
IEEE Trans. Artif. Intell.
2026
[doi]
[pdf]
-
Nonlinear Arbitration for AI-Powered Human-Machine Systems: A Fused Distributional Approach
Shuyue Jiang,
Yun-Bo Zhao ,
and Yaqing Zhou
2026
[Abs]
[doi]
[pdf]
Rapid advances in Artificial Intelligence (AI) technology have revolutionized the architecture of traditional humanmachine systems, giving rise to a new generation of AI-powered Human-Machine Systems in which machines are fundamentally driven by AI. This paper is the first to identify two major limitations of linear arbitration approaches in such systems: not only does their linear structure lead to degraded system performance, but the unbounded bias in AI decision-making can also result in dangerous arbitration outcomes. To address these issues, we propose a novel Fused Distributional Nonlinear Arbitration (FDNA) approach. By fusing the probability distributions of machine and human decisions, the proposed approach enhances arbitration safety while maintaining system performance. Through rigorous theoretical analysis, we demonstrate FDNA’s advantages in multipeak adaptability and robustness, and its effectiveness is further validated through comprehensive experiments.
-
A Dual Confidence Evaluation-Based Shared Control Approach for Human-Machine Collaboration
Yaqing Zhou,
Yun-Bo Zhao ,
Pengfei Li,
Xia Tian,
Shuyue Jiang,
and Yu Kang
Neurocomputing
2026
[Abs]
[doi]
[pdf]
Shared control has become a key strategy for enhancing the safety and adaptability of human-machine collaboration systems, particularly in complex and uncertain environments. However, existing rule-based and confidence-based authority allocation approaches often suffer from limited generalizability or excessive reliance on physiological signals, which hinders their practical deployment. This paper proposes a Dual Confidence-Based Shared Control (DC-SC) approach that enables dynamic and interpretable authority allocation by quantifying the decision confidence of both humans and machines. The human confidence model is constructed through a knowledge-task matching function that measures the cognitive alignment between the operator’s expertise and task difficulty, while the machine confidence model assesses decision reliability via an uncertainty-tolerance matching mechanism. These two types of confidence indicators are jointly used to construct a shared control policy, in which the fusion weights are dynamically adjusted using environmental feedback within a policy gradient optimization framework, thereby maximizing human-machine collaborative performance. Theoretical analysis validates the soundness of the confidence models, and experiments conducted in benchmark environments such as LunarLander and UAV path planning demonstrate that DC-SC significantly outperforms both reinforcement learning baselines and traditional shared control approaches in terms of policy performance and system safety.
博客文章