The rapid development of autonomous vehicles (AVs) necessitates advanced safety measures to ensure reliable and secure operation in diverse environments. One crucial aspect of enhancing AV safety is the ability to accurately classify and predict the behavior of surrounding objects, such as other vehicles, pedestrians, cyclists, and static obstacles. This study focuses on developing a robust object behavior classification framework leveraging machine learning and deep learning techniques. By integrating sensor data from LiDAR, radar, and cameras, the proposed system processes real-time environmental information to identify and categorize object behaviors. The framework employs a combination of convolutional neural networks (CNNs) for image data processing and recurrent neural networks (RNNs) for sequential data analysis, ensuring precise behavior prediction. The research highlights the importance of feature extraction, data fusion, and model optimization in achieving high classification accuracy. Furthermore, the study addresses challenges related to dynamic environments, occlusions, and varying weather conditions, providing solutions to enhance the robustness of the classification system. The effectiveness of the proposed approach is validated through extensive simulations. Results demonstrate significant improvements in behavior prediction accuracy and response times, contributing to the overall safety and reliability of autonomous vehicles. This research underscores the critical role of advanced object behavior classification in the evolution of autonomous driving technologies, paving the way for safer and more efficient transportation systems.