REAL-TIME OBJECT DETECTION AND COLLISION AVOIDANCE IN IOT-ENABLED AUTONOMOUS VEHICLES

Abstract

The growing demand for autonomous vehicles (AVs) has fueled extensive research in real-time object detection and collision avoidance, with IoT-enabled technologies playing a vital role in ensuring safe navigation. This study examines the integration of IoT-based sensor networks, artificial intelligence (AI), and edge computing to enhance AV perception and decision-making in dynamic environments. Key sensor technologies, including LiDAR, radar, ultrasonic sensors, and cameras, are analyzed for their effectiveness in detecting and classifying pedestrians, vehicles, and obstacles in real time. AI-driven techniques such as convolutional neural networks (CNNs), deep reinforcement learning, and sensor fusion algorithms are explored for improving object detection accuracy and predictive collision avoidance. Additionally, the role of Vehicle-to-Everything (V2X) communication is discussed, highlighting its significance in enabling AVs to interact with other vehicles, infrastructure, and pedestrians to anticipate hazards. Edge computing and 5G connectivity are also emphasized as critical enablers for reducing processing latency and improving system responsiveness. Despite these advancements, challenges persist, including sensor reliability in adverse weather, computational efficiency, cybersecurity risks, and the need for large-scale infrastructure deployment. This study identifies emerging solutions, such as AI-powered adaptive learning models, blockchain for secure data exchange, and energy-efficient edge computing frameworks, as promising avenues for overcoming these challenges. By leveraging IoT-enabled infrastructure and advanced AI methodologies, AVs can achieve improved situational awareness, reduced collision risks, and enhanced road safety. Future research will focus on optimizing sensor fusion techniques, enhancing computational efficiency, and developing robust security frameworks to ensure the reliability and scalability of AV systems.