Data-driven and Empirical Research for Emerging Mixed Traffic of Automated Vehicles and Human-driven Vehicles

Motivation and Objectives:

Data-driven research is considered critical for understanding the dynamics of mixed traffic flow, interactive behaviors of Automated Vehicles (AVs) and human-driven vehicles (HDVs), as well as the impact of AVs on traffic safety and efficiency. Emerging datasets, especially real-world empirical data, allow researchers to investigate what could happen in the future mixed traffic. However, several challenges are still hampering data-driven research, e.g., the generalization capability problem of modeling, the unfamiliarity of the research community with advanced data processing and analysis tools, and the absence of collaboration between the research community and the Original Equipment Manufacturers (OEMs).

To address the challenges, this workshop aims to push forward the data-driven and empirical research for the upcoming mixed traffic by:

• Providing a unique opportunity for knowledge sharing by gathering together notable researchers in the domain and experts from the leading data collecting and vehicle automation companies.

• Showcasing the emerging datasets, their formats, and structure, and discuss their limitations, and challenges for the current research.

• Validating state-of-the-art modeling methods and assumptions, with mixed traffic flow datasets.

• Identifying the current research gaps and future directions, as well as the opportunities for creating synergy between data-driven and theory-driven research.

Participants of this workshop will have the opportunity to communicate with other dataset users face to face. The goals are to share best practices, discuss common problems that have not been addressed, and gain insights on future research directions, so as to stay ahead of the curve. Additionally, a dataset list with detailed summaries together with tools and tips for analyzing the data will be shared with the participants after the workshop.

Topics of Interest:

Interested researchers are invited to submit their papers on the relevant research topics including but not limited to:

1. State-of-the-art AV-related Datasets

2. Data collection, processing, managing, and publishing

3. Mixed traffic status prediction (long/medium/short term)

4. Behavioral modeling and interaction in mixed traffic

5. Role of artificial intelligence in data-driven research for mixed traffic

6. Impact evaluation methods of mixed traffic

7. Empirical evaluation of different vehicle automation levels

8. Safety impacts of vehicle automation in mixed traffic

9. Traffic flow impacts and string stability in mixed traffic

10. Driving behavioral adaptation in mixed traffic

11. Energy consumption/demand in mixed traffic

12. Assumptions and simulation models for mixed traffic

13. Policies, regulations, and codes of practice

Agenda