Manned-Unmanned Teaming

Zhixiang Kong, Quanbo Ge, Chengsheng Pan

The U.S. military continuously innovates its combat theories, proposing new styles of warfare such as multi-domain joint operations and mosaic operations. The form of warfare is shifting from network-centric warfare towards intelligent warfare. Intelligent warfare emphasises decentralised forces and intelligent coordination, with a typical example being manned/unmanned teaming systems. This article first reviews the development history and trends of manned/unmanned teaming systems in the U.S. military. It then elaborates on the new challenges in intelligent networking posed by manned/unmanned teaming operations at the levels of networks, links, and nodes. Finally, based on these challenges, it proposes a limited centralised manned/unmanned intelligent command architecture, providing insights for the construction of next generation manned/unmanned teaming systems on the future battlefield for our military.

Dominik Künzel, Vivien Wuwer, Gunar Roth, Axel Schulte

In our contribution, we investigate the impact of different modalities for tasking unmanned vehicles in Manned-Unmanned Teaming (MUM-T) scenarios. As pilots have to manage unmanned assets from the cockpit, human-machine interaction becomes critical to mission success. In this study we assessed the touch and voice modalities in a helicopter simulator, measuring workload, usability, and mission efficiency. It has been shown that voice interaction reduces workload and improves usability, as well as mission performance, while touch input remains valuable as a backup. The findings underline the need for improved interaction design in future MUM-T systems to enhance safety and mission efficiency in high-demand flight environments.

Tanya S. Paul, Daniel Lafond, Pierre-Yves Benzakine

The integration of autonomous systems and artificial intelligence (AI) is reshaping Air Dominance in Future Combat Air Systems (FCAS) by enhancing manned-unmanned teaming (MUM-T). This research presents STAR (Sharing Tasks with Autonomous Resources), a system for managing MUM-T operations within Command and Control (C2), utilizing multi-modal sensor-fusion data. STAR enables AI-driven task allocation to improve mission efficiency based on interdependence and capacities of human and autonomous agents. A human-in-the loop simulation with ten participants in a Threat Detection mission demonstrated the system's ability to optimize task allocation. Seven supervised machine learning models, were trained and tested with the highest accuracy being the Extreme Gradient Boosting (XGBoost), which achieved 89% in predicting the best collaboration mode among autonomous search (Scout), escort (Guardian), shared tasking (Collaborative), human-controlled (Follow), and backup (Request Back-up). This approach enhances interoperability within MUM-T and facilitates resource coordination across agents. STAR may also become a new COI (Community of Interest) service for FCAS, as an enabler for dynamic tasking using FCAS data during mission execution.

Vivien Wuwer, Dominik Künzel, Axel Schulte

This study examines the impact of different tasking modalities - touch versus voice - on pilot performance in manned-unmanned teaming (MUM-T) mission scenarios. MUM-T operations place high cognitive and operational demands on military helicopter pilots, requiring simultaneous control of their own aircraft and coordination of unmanned aerial vehicles (UAVs). A simulator study was conducted analyzing subjective workload, head-down time, pilot flight behavior, and autopilot usage. Although pilots subjectively reported that voice tasking reduced head-down time and supported better flight performance, objective measurements showed only minor improvements or inconsistent results. Over 75 % head-down time was recorded across all conditions. Voice input alone does not notably mitigate visual demands. Task complexity, training, and context play a critical role. The findings underline the need for improved interaction design and more reliable flight automation in future MUM-T systems to enhance safety and mission efficiency in high-demand flight environments.

Stuart Michelson, Charles Domercant

ABSTRACT Manned Unmanned Teaming (MUMT) is fast becoming a critical capability for maintaining operational superiority and overmatch against near peer competitors. However, there is presently no concept of MUMT behaviors in Model Based Systems Engineering (MBSE) analyses. Such a concept is needed in order to capture and understand the increasingly complex interactions between humans and machines that will govern system behavior on the battlefield. This manuscript describes an effort that sought to identify and roadmap the development of the MUMT requirements necessary to build into the next generation of functional MBSE models that lead to sustainable autonomous (semi or full with MUMT) military operations. Three scenarios spanning the unmanned systems domain incorporating current state of practice and envisioning increased autonomy were used as the basis for developing a generalizable MBSE expression of MUMT behavior.