Novel trajectory prediction algorithms for hypersonic gliding vehicles based on maneuver mode on-line identification and intent inference

Abstract

Aiming at the trajectory prediction problem in hypersonic glide vehicle defense, novel trajectory prediction algorithms based on maneuver mode on-line identification and intent inference are proposed. For solving the maneuver mode identification and modeling problems, the auto-regressive method is introduced to reveal the hidden internal law in the historical tracking data and present the parametric model of the maneuver mode, thereby realizing the accurate trajectory prediction. To deal with the maneuver mode mutation problem, a novel intent inference based long-term trajectory prediction algorithm is proposed: firstly, the cost function of maneuver intent is constructed reasonably. Then, to solve the vehicle’s intent recursive calculation problem, the recurrence formula of the vehicle’s intent is derived based on Bayesian estimation theory, and the vehicle’s reachable region rapid resolution and discretization methods are proposed. Finally, the vehicle’s state recursive formula is derived with Bayesian estimation theory, and the trajectory prediction problem is transformed into the probability prediction problem of the vehicle appearing in a specific region. To avoid the large calculation problem in long-term trajectory prediction, the random sampling shooting method is adopted. The proposed trajectory prediction algorithms are combined to are combined to realize complementary advantages and provide as much valuable prediction information as possible for the defender. The simulation results show that the proposed trajectory prediction algorithms share high prediction accuracy and applicability.