The field of autonomous vehicles is moving towards improving safety and efficiency in complex traffic environments. Researchers are focusing on developing innovative methods to reduce crash rates, enhance travel efficiency, and improve interaction with human-driven vehicles. Notable advancements include the use of real-time traffic data to dynamically reroute vehicles, extending naturalistic projection to multimodal behavior scenarios, and quantifying consensus across safety, interaction quality, and traffic performance. Noteworthy papers include:

• A study on Waymo's Rider-Only crash rates, which found a statistically significant lower crashed vehicle rate compared to human benchmarks.
• A proposed coordinated routing approach for enhancing bus timeliness and travel efficiency in mixed-traffic environments, which demonstrated significant improvements in transit reliability and CAV operational performance.
• A method for extending naturalistic projection to multimodal behavior scenarios, which provides a higher degree of fidelity in data-driven modeling of naturalistic behavior.
• A consensus-aware AV behavior analysis, which highlighted the need for AV models that explicitly balance multi-dimensional performance in mixed-traffic environments.
• A CV-based max-pressure control method, which significantly reduces vehicle delays compared to both actuated control and conventional MP control across various CV penetration rates.