The field of road safety is witnessing significant advancements with the integration of artificial intelligence and machine learning techniques. Researchers are focusing on developing predictive models that can identify high-risk areas and predict accident rates, enabling proactive decision-making for policymakers and transportation authorities. Furthermore, the use of deep learning architectures is being explored for vision-based traffic accident anticipation, demonstrating promising results in detecting potential accidents. Additionally, innovative systems are being developed to detect road anomalies such as potholes and cracks, providing real-time notifications to drivers and authorities. Noteworthy papers in this area include the development of a Geographical Random Forest model to investigate robotaxi crash severity, which found that spatially localized machine learning outperforms regular machine learning in predicting crash severity. Another notable paper presented a comprehensive review of deep learning advances in vision-based traffic accident anticipation, highlighting opportunities for future research in multimodal data fusion and self-supervised learning.