蒋舒悦 周雅情 题为 “Nonlinear Arbitration for AI-Powered Human-Machine Systems: A Fused Distributional Approach” 的论文已被《IEEE Transactions on Human-Machine Systems》接受发表。该论文摘要如下：

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.