This paper surveys artificial intelligence methods for modeling and simulating mixed automated and human traffic, addressing the limitations of existing simulation tools in accurately representing complex driving behaviors. It proposes a comprehensive taxonomy of AI methods, reviews evaluation protocols, and outlines future research directions to bridge the gap between transportation engineering and computer science.

This paper presents a semi-automated data annotation pipeline for large-scale, multimodal autonomous vehicle datasets, developed for the DARTS project. It combines AI-driven pre-annotation with human-in-the-loop verification and introduces a novel Correction Acceleration Ratio (CAR) metric, demonstrating significant reductions in annotation time while maintaining high quality.