A High-Feasibility Real-Time Trajectory-Planning Method for Parafoils Based on a Flexible Dynamic Model

Effective trajectory planning is critical for achieving precise autonomous navigation and safe landing of parafoil delivery systems. However, current parafoil trajectory planning still faces challenges in ensuring consistency between actual system behavior and algorithmic real-time performance. Due to the strong fluid–structure interaction (FSI) between the flexible canopy and airflow, traditional dynamic models based on point mass and rigid-body assumptions often lack aerodynamic accuracy. These models produce planned trajectories in simulation environments that are inconsistent with the actual system’s behavior and cannot directly provide an effective reference for airdrop experiments. Additionally, traditional planning methods require a significant amount of time to calculate complex dynamic models and generate fixed trajectories in advance. These methods not only fail to provide usable results in a short period of time, but also cannot prevent the accumulation of tracking errors by adjusting the target trajectory in real time. To address these issues, this paper proposes a flexible 8-degree-of-freedom (8-DOF) dynamic model based on the FSI method, utilizing the actual aerodynamic parameters of the canopy to achieve improved consistency with the behavior of the actual system. The Soft Actor–Critic (SAC) algorithm is then employed to achieve real-time trajectory planning for parafoil airdrop systems, addressing the real-time planning performance limitations of traditional algorithms. The airdrop experiments validate that the simulation trajectories generated using this model demonstrate higher consistency with actual flight trajectories, providing more accurate references for pre-flight trajectory optimization. Moreover, the proposed method enables real-time trajectory planning and dynamically adjusts target trajectories based on the current position and attitude of the parafoil, effectively mitigating the accumulation of errors.