Scholarlink

<p>The research presents a Hybrid Fuzzy–Predictive Co-Regulation Model (HF-PCM) as a solution for enhancing adaptive human–system interaction within virtual environments. The framework uses a Sugeno-type fuzzy inference system together with Model Predictive Control (MPC) to manage uncertainty and facilitate adaptive decision-making during dynamic interaction situations. The system processes human interaction inputs through fuzzy reasoning which interprets their behavioral states before the system uses these states in the predictive control layer to achieve system stability and responsiveness. The model uses multiple optimization objectives to achieve tracking accuracy and control effort and interaction consistency while maintaining efficient human-system coordination. The system maintains stability and safe operation through its constraint-aware control mechanism together with theoretical stability principles which enable it to perform reliably across different operational conditions. The experimental results show major improvements that reached an RMS error of 0.089 and system stability of 0.92 and a cooperation index of 0.88. The analysis reveals that HF-PCM provides better results than separate fuzzy and MPC systems because it delivers higher accuracy and better response times together with enhanced interaction capabilities. The framework provides a solution for real-time human–AI collaboration in immersive environments which scales and provides interpretable results while supporting advanced interactive control applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and Optimization of Human-AI Collaborative Control Systems for Interactive Spatial Narratives in Virtual Reality

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月24日

查看全文
  • Han Yan,
  • Sijia Hao,
  • Jingyi Zhang,
  • Tuhao Huang

摘要

The research presents a Hybrid Fuzzy–Predictive Co-Regulation Model (HF-PCM) as a solution for enhancing adaptive human–system interaction within virtual environments. The framework uses a Sugeno-type fuzzy inference system together with Model Predictive Control (MPC) to manage uncertainty and facilitate adaptive decision-making during dynamic interaction situations. The system processes human interaction inputs through fuzzy reasoning which interprets their behavioral states before the system uses these states in the predictive control layer to achieve system stability and responsiveness. The model uses multiple optimization objectives to achieve tracking accuracy and control effort and interaction consistency while maintaining efficient human-system coordination. The system maintains stability and safe operation through its constraint-aware control mechanism together with theoretical stability principles which enable it to perform reliably across different operational conditions. The experimental results show major improvements that reached an RMS error of 0.089 and system stability of 0.92 and a cooperation index of 0.88. The analysis reveals that HF-PCM provides better results than separate fuzzy and MPC systems because it delivers higher accuracy and better response times together with enhanced interaction capabilities. The framework provides a solution for real-time human–AI collaboration in immersive environments which scales and provides interpretable results while supporting advanced interactive control applications.