Abstract: Maritime equipment group gaming (MEGG) provides a critical framework for analyzing strategy interactions among groups of maritime equipment engaged in complex maritime operations, such as adversarial simulation, maritime traffic, and maritime rescue. The equipment groups typically include manned and unmanned vessels, carrier-based aircraft, and other similar assets, and the strategy interactions examined in MEGG primarily involve confrontation, competition, and cooperation. First, the survey clarifies the concept of maritime equipment group gaming by distinguishing it from related paradigms such as population games and swarm intelligence. This conceptual clarification helps lay the groundwork for subsequent classification and analysis. Next, the survey reviews typical MEGG task scenarios, including adversarial simulation, maritime traffic, and maritime rescue. Each of these scenarios presents distinct operational challenges and objectives within the MEGG framework. The survey then classifies the basic types of MEGG approaches. Specifically, MEGG approaches are categorized along multiple dimensions: game modes confrontation, competition, cooperation, and mixed), game scope (intra-group, inter-group, and dual-level), equipment heterogeneity (single-class and cross-class systems), and intelligence levels (from non-intelligent to intelligent systems). Second, the survey reviews technological progress in two main categories: non-intelligent and intelligent MEGGs. For non-intelligent MEGG, classical methods such as Lanchester's laws, population game theory, and crowd simulation models are reviewed. For intelligent MEGG, the survey reviews the MEGG approaches based on traditional machine learning (including decision support, scheduling, planning, simulation, prediction) and multi-agent reinforcement learning (focusing on adversarial simulation, task planning, and so on). Finally, the survey summarizes current challenges in MEGG research and proposes six promising directions: a human-machine integrated intelligent decision-making framework for gaming, trustworthiness and interpretability of intelligent gaming models, deep reasoning for maritime missions using large-scale models, hierarchical collaborative gaming mechanisms for intelligent agents; a standardized management system for heterogeneous intelligent agent clusters, and high-fidelity gaming systems enhanced by cross-domain expert knowledge. These directions collectively provide structured and actionable guidance for future research in this emerging and significant field.