Many-vs-Many Missile Guidance via Virtual Targets

TL;DR

This work addresses many-vs-many missile guidance under target uncertainty by replacing direct target assignment with a centralized VT-based strategy. Virtual targets are generated from a Normalizing Flows–based probabilistic trajectory predictor and clustered into $n$ distinct hypotheses, which interceptors pursue via Zero-Effort-Miss guidance in midcourse and Proportional Navigation in endgame. Monte Carlo simulations show that the VT approach matches or slightly exceeds straight-line baselines when $n=m$ and significantly outperforms them when $n>m$, demonstrating that probabilistic, diverse trajectory hypotheses leverage numerical superiority to improve interception probability. The method offers a scalable, data-driven way to handle target uncertainty and multi-agent engagements, with practical implications for robust missile defense design in high-interceptor-count scenarios.

Abstract

This paper presents a novel approach to many-vs-many missile guidance using virtual targets (VTs) generated by a Normalizing Flows-based trajectory predictor. Rather than assigning n interceptors directly to m physical targets through conventional weapon target assignment algorithms, we propose a centralized strategy that constructs n VT trajectories representing probabilistic predictions of maneuvering target behavior. Each interceptor is guided toward its assigned VT using Zero-Effort-Miss guidance during midcourse flight, transitioning to Proportional Navigation guidance for terminal interception. This approach treats many-vs-many engagements as many-vs-distribution scenarios, exploiting numerical superiority (n > m) by distributing interceptors across diverse trajectory hypotheses rather than pursuing identical deterministic predictions. Monte Carlo simulations across various target-interceptor configurations (1-6 targets, 1-8 interceptors) demonstrate that the VT method matches or exceeds baseline straight-line prediction performance by 0-4.1% when n = m, with improvements increasing to 5.8-14.4% when n > m. The results confirm that probabilistic VTs enable effective exploitation of numerical superiority, significantly increasing interception probability in many-vs-many scenarios.

Figures (5)

• Figure 1: Comparison of the prediction of virtual target trajectories (Fig. \ref{['fig:pdf']}--\ref{['fig:virtual_targets']}) and straight-line predictions (Fig. \ref{['fig:dynamic_model']}--\ref{['fig:straight_line_prediction']}).
• Figure 2: Overview of the proposed many-vs-many missile guidance approach using virtual targets.
• Figure 3: Example of a many-vs-many missile guidance scenario with $m=2$ targets and $n=5$ interceptors, where the current past and predicted interceptor trajectories are shown in lighter colored solid and dashed lines, respectively, and the virtual target trajectories are shown in darker colored dashed lines and the past physical target trajectories in black solid lines.
• Figure 4: Example of a many-vs-many missile guidance scenario with $m=2$ targets and $n=5$ interceptors, where the current past and predicted interceptor trajectories are shown in lighter colored solid and dashed lines, respectively, and the virtual target trajectories are shown in darker colored dashed lines and the past physical target trajectories in black solid lines.
• Figure 5: Successful interceptions for the proposed approach and the baseline approach for different numbers of targets $m$ and interceptors $n$ in $n_{\mathrm{MC}}=1,000$ Monte Carlo runs.