• Leonardo reported R&D results from the FAIR Innovation Grant, targeting autonomous systems for complex scenarios, including intelligent drones, radar data fusion.
• Work advanced safe, constrained reinforcement learning for autonomous drone navigation, including a drone-chasing use case designed to exceed typical research benchmarks.
• Radar AI development added explainability tools to improve model transparency, supported software to cut design costs, reduced energy use by lowering detection thresholds.
• Multimodal foundation-model research expanded techniques to improve dataset quality, diversity to manage data quantity-versus-quality trade-offs in vision-language training.
• Federated learning work improved training on continuous, non-IID data across privacy-constrained clients, aiming for more efficient models without sharing sensitive data.

Disclaimer: This news brief was created by Public Technologies (PUBT) using generative artificial intelligence. While PUBT strives to provide accurate and timely information, this AI-generated content is for informational purposes only and should not be interpreted as financial, investment, or legal advice. Leonardo S.p.A. published the original content used to generate this news brief on August 06, 2026, and is solely responsible for the information contained therein.