This paper introduces an AI-based Automatic Ground Collision Avoidance System (AGCAS) for advanced jet trainers. It utilizes a customized Soft Actor-Critic (SAC) algorithm, integrated with a custom Convolutional Neural Network (CNN) and hyperparameter optimization, to enhance safety and operational capabilities by effectively avoiding ground collisions within limited observation spaces.

This article introduces a pilot-activated recovery system (PARS) for advanced jet trainers that uses an advanced reinforcement learning (RL) architecture, specifically a Soft Actor-Critic (SAC) model, to improve operational efficiency and aircraft upset recovery while considering negative-g forces on the pilot. The system outperforms conventional control methods in expert evaluations.

This paper evaluates the use of AI-based reinforcement learning agents for developing an AI-assisted pilot training module for specific aircraft aerobatic maneuvers. It demonstrates that AI can learn and execute various complex maneuvers with a quality comparable to professional pilots, utilizing both real pilot data and artificially created trajectories.

This paper introduces a novel hardware-aware Neural Architecture Search (NAS) framework that integrates deployment-aligned low-precision training. This approach addresses the accuracy degradation caused by the mismatch between full-precision optimization and low-precision deployment on edge accelerators, particularly for spaceborne AI applications.

This paper proposes a novel pipeline that leverages large language models (LLMs) to derive legal driving requirements for autonomous vehicles (AVs) by grounding LLM reasoning in a traffic scenario taxonomy. The method significantly improves law-scenario matching and the accuracy of derived mandatory and prohibitive requirements, providing a solid foundation for lawful AV development and deployment.