Under the context of non-dyadic human–machine interaction in intelligent coal mines, this study investigates the impact of different dyadic collaboration modes on Team Situation Awareness (TSA). Based on a simulated coal mine monitoring task, the experiment compares four working modes—Individual Operation, Supervised Operation, Cooperative Operation, and Divided-task Operation—across tasks of varying complexity. TSA was assessed using both objective (SAGAT) and subjective (SART) measures, alongside parallel evaluations of task performance and workload (NASA-TLX). The results demonstrate that, compared to Individual or Supervised Operation, both Cooperative and Divided-task Operation significantly enhance TSA and task performance. Cooperative Operation improves information integration and comprehension, while Divided-task Operation enhances response efficiency by enabling focused attention on role-specific demands. Moreover, dyadic collaboration reduces cognitive workload, with the task-sharing mode showing the lowest cognitive and temporal demands. The findings indicate that clear task structuring and real-time information exchange can alleviate cognitive bottlenecks and promote accurate environmental perception. Theoretically, this study extends the application of non-dyadic interaction theory to intelligent coal mine scenarios and empirically validates a “Collaboration Mode–TSA–Performance” model. Practically, it provides design implications for adaptive collaboration frameworks in high-risk, high-complexity industrial systems, highlighting the value of dynamic role allocation in optimizing cognitive resource utilization and enhancing operational safety.