Loyal Wingman Assessment: Social Navigation for Human-Autonomous Collaboration in Simulated Air Combat

TL;DR

This paper tackles the problem of safely integrating autonomous loyal wingmen into human-pilot air combat formations by introducing social navigation metrics. It defines five metrics: $M_1$–$M_3$ (naturalness) and $M_4$–$M_5$ (comfort), with the kinematic basis $M_n=\frac{1}{T}\sum_{t=0}^{T}{\left(\frac{d^n p(t)}{dt^n}\right)^2}$ and $n=1,2,3$, and $M_5$ incorporating TCPA-based collision risk. Validation is planned in high-fidelity simulations with military pilots, using post-trial questionnaires and the AsaPy toolkit to correlate metric values with perceived naturalness and comfort in CAP/DCA scenarios. The work aims to guide real-time autonomous behavior and learning-based approaches (e.g., behavior trees, reinforcement learning) to improve safety, effectiveness, and social compatibility in mixed human–autonomous air-operations.

Abstract

This study proposes social navigation metrics for autonomous agents in air combat, aiming to facilitate their smooth integration into pilot formations. The absence of such metrics poses challenges to safety and effectiveness in mixed human-autonomous teams. The proposed metrics prioritize naturalness and comfort. We suggest validating them through a user study involving military pilots in simulated air combat scenarios alongside autonomous loyal wingmen. The experiment will involve setting up simulations, designing scenarios, and evaluating performance using feedback from questionnaires and data analysis. These metrics aim to enhance the operational performance of autonomous loyal wingmen, thereby contributing to safer and more strategic air combat.

Figures (1)

• Figure 1: Human-wingman personal space metric depiction.