This article explores the progress made in the creation of a pilot activated recovery system (PARS) for advanced jet trainers that utilizes artificial intelligence (AI) in an effort to enhance operational efficiency. The PARS model employs an advanced reinforcement learning (RL) architecture, incorporating a cutting-edge soft-actor critic (SAC) model and hyper-parameter optimization methods. Negative-g punishments and other handcrafted features remarked upon by control engineers and domain experts regarding PARS are also taken into account by the system. When evaluated by them, the AI model's behavior is deemed more desirable than that of conventional control methods.
@article{arxiv.2604.24355,
title = {An Aircraft Upset Recovery System with Reinforcement Learning},
author = {Mahir Demir and Atahan Cilan and Seyyid Osman Sevgili and Özgün Can Yürütken and Ümit Can Bekar},
journal= {arXiv preprint arXiv:2604.24355},
year = {2026}
}