Military vehicle requirements continue to evolve rapidly in all AVT domains (air, space, sea, ground).

To keep pace with the needs of the Alliance, the time and effort to develop next-generation military vehicles and weapon systems need to be significantly reduced, while simultaneously diminishing problems occurring late in the system development.

Meeting these needs requires new and advanced capabilities for quick, accurate and thorough assessment of the design and operational spaces and reliable optimisation processes of platforms’ design.

AVT recently completed several assessments of this need.

Previous AVT efforts (AVT-092, AVT-093, AVT-237, AVT-331) have consistently shown that there is design benefit to coupling more engineering disciplines, at higher levels of fidelity, earlier in the development.

Machine Learning / Artificial Intelligence (ML/AI) has the potential to introduce higher accuracy from the earliest stages of the design process, improving and accelerating vehicle design.

However, the best ways to apply ML/AI in the design pipeline are as yet unknown.

The main objectives of the Research Specialists' Meeting are:

To identify and extend the state of the art of Machine Learning/Artificial Intelligence (ML/AI) methods for vehicle design, investigating how ML/AI can enable faster, more accurate, and more reliable design processes, from conceptual, through preliminary, to detailed design.

Both experts in ML/AI development and in vehicle design are invited to discuss methods and applications of ML/AI across the military vehicle space, exchanging information across disciplines, addressing current capabilities and applications as well as needs and gaps.

Topics to be covered:

• Supervised, unsupervised, and reinforcement learning for vehicle design;
• ML/AI enabled simulation-driven design, including multidisciplinary design optimization and optimization under uncertainty;
• Physics-informed ML/AI approaches, transfer learning, and approaches for the use of already available experimental and computational data;
• Data sources, types, sample sizes, and data reliability for typical design applications and the interdependence of ML/AI and data generation for vehicle design;
• Multi-fidelity and multi-source information fusion approaches to vehicle design;
• Review of the state of the art on ML/AI for vehicle design, comparison of methods, current gaps and limitations, best

The focus of the Research Specialists' Meeting will be on design methodologies for sea, air, space, and land platforms, but contributions regarding generic tools and techniques and best practice from other domains are also appreciated.

All details about deadlines and abstract submission are provided in the document "AVT-411-RSM-CfP" on the right side below the map.