Reentry Glide Vehicle Intent Inference Method via Multidimensional Intention Fusion
Year: 2026
Type: article
Abstract: To address the challenge of predicting reentry glide vehicle attack intention in no-fly zone scenarios, this paper proposes a multidimensional intention fusion-based inference method. Firstly, the recursive formula for the posterior probability of the vehicle's intention is derived using Bayes' theorem. Secondly, the concepts of pseudo heading deviation angle and endpoint relative energy are introduced to formulate an intention cost function that incorporates both angular and energetic dimensions, and the corresponding likelihood probability is obtained by quantifying the cost of different intentions, which solves the problem that the traditional cost function cannot characterize the real intention of the vehicle in scenarios involving no-fly zones. Finally, a dynamically weighted multidimensional intention fusion model is proposed to deduce the vehicle's attack intent in the footprints. The simulation results show that the proposed method has a higher accuracy rate of intent inference compared to the existing methods.
Authors: Yangchao He, Jiong Li, Lei Shao, Chijun Zhou, Humin Lei
Institution: Air Force Engineering University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Award: G3140573612
OpenAlex ID: W7160498317