With the rapid development of information technology, unmanned cluster has been widely used in reconnaissance, attack, communication relay and other fields. Unmanned cluster situation cognition has become one of the key factors to affect the overall battlefield trend and improve the combat efficiency. Accurate and real-time situation cognition plays an indispensable role in unmanned cluster cooperative control, mission execution and operational command and decision making. How to integrate multi-source sensor information, process heterogeneous data, and realize accurate situation awareness and prediction is the key to improve the combat effectiveness of unmanned cluster. Especially in the face of complex environment, how to integrate multi-dimensional information such as environmental information, enemy dynamics, and our intention to generate a comprehensive and reliable target situation map is an important problem that needs to be solved urgently in the field of unmanned cluster research. This paper systematically summarizes and summarizes the status quo of unmanned cluster situation cognition technology, deeply analyzes the advantages and limitations of existing methods, and prospects the future research direction in this field.