Pilot perception modelling for carrier landing based on Multi-source fuzzy information fusion

Abstract

Carrier-based aircraft landing requires pilots to rapidly integrate heterogeneous cues from the improved Fresnel lens optical landing system, height deviation relative to the reference glide path and the correction trend of height error under strong disturbances and severe time pressure. Such concurrent information processing may lead to perceptual overload and delayed control response. To address this issue, this paper proposes a multi-source information fusion method for pilot perception modelling during carrier-based aircraft landing. First, optical deviation, height deviation and the correction rate of height deviation are fuzzified to construct a unified perceptual feature space. Then, a Bayesian regularised neural network is developed to establish the nonlinear mapping between these inputs and a defuzzified pilot perception proxy index generated by the fuzzy inference system. The results show that the proposed model achieves higher prediction accuracy than conventional regression models and reveals the dominant contribution of height-related information in the perception process. The proposed method provides an interpretable proxy-state representation for pilot-state-aware modelling and offers a potential perceptual basis for future human–machine shared control in carrier-based aircraft landing.