Urban traffic congestion is a growing challenge faced by cities worldwide, resulting in economic losses, increased pollution, and reduced quality of life. Traditional traffic signal systems operate on pre-timed schedules that are often inadequate in responding to real-time traffic fluctuations. Artificial Intelligence (AI) offers a dynamic alternative through adaptive traffic signal control systems that respond to real-time traffic data, optimize flow, and reduce congestion. This paper explores the foundational technologies behind AI-based traffic signal control, focusing on machine learning algorithms, computer vision, and reinforcement learning. It presents use cases in dynamic signal timing, emergency vehicle prioritization, and multimodal traffic management. Case studies from smart cities globally demonstrate the effectiveness of AI in reducing congestion and travel time. Ethical considerations, including privacy, accessibility, and algorithmic fairness, are discussed alongside technical challenges such as sensor reliability, system scalability, and integration with legacy infrastructure. Future directions include the integration of connected vehicle data, edge computing, and decentralized traffic control systems. AI-driven adaptive signal control systems are key components of intelligent transportation networks, enabling more efficient, responsive, and sustainable urban mobility.