AI-Enhanced Hybrid CFAR for 6G Integrated Sensing and Communication (ISAC)

The integration of radar sensing and wireless communication in sixth-generation (6 G) networks, known as Integrated Sensing and Communication (ISAC), introduces new challenges for real-time target detection in dynamic and heterogeneous environments. Traditional Constant False Alarm Rate (CFAR) detectors, while effective in controlled settings, exhibit limited adaptability under varying clutter and interference conditions common in 6 G. This work proposes an AI-enhanced hybrid CFAR framework that combines classical statistical detection methods with the adaptability of artificial intelligence. By leveraging machine learning techniques to dynamically adjust detection thresholds based on environmental features, the proposed approach aims to improve robustness, responsiveness, and accuracy. This ongoing research focuses on the architectural design and theoretical formulation of the hybrid CFAR model, with the goal of enabling intelligent, low-latency target detection in future ISAC-enabled $\mathbf{6 G}$ systems.