CHAPTER 5

Conclusion

This research project has addressed the critical need for strategic guidance in the application of AI within state and local DOTs. As the transportation landscape becomes increasingly complex, the integration of AI is pivotal in addressing a series of challenges, from improving safety and traffic congestion to enhancing organizational efficiency and customer service. The background analysis illuminated the growing reliance on AI to interpret events, automate decisions, and take actions within transportation systems. The influx of structured and unstructured data from diverse sources further emphasized the potential of AI applications in transforming the way DOTs manage and optimize their operations.

A comprehensive literature review, particularly drawing on the extensive resources from scientific journals and proceedings, as well as the TRB database, revealed a plethora of specific AI applications in transportation. However, the absence of strategic guidance left a gap in providing actionable insights for DOTs to develop policies and standards and foster a knowledgeable workforce.

The primary objective of this research was to bridge this gap by formulating a research roadmap that not only identifies but prioritizes the research needs crucial for equipping state and local DOTs with a profound understanding of AI. By engaging with the transportation community and building upon existing research, the roadmap serves as a guiding document to help DOTs discern activities suited for AI and explore the potential applications. This initiative aligns with the evolving trends in the transportation research landscape, fostering a comprehensive understanding of AI applications. The outcomes of this project are not only valuable to state and local DOTs but also extend their relevance to a broader spectrum of research organizations, promoting collaboration and coordination in advancing AI solutions within the transportation sector.

The literature review, encapsulated in Task 2, delved into a meticulous examination of AI trends in transportation over the last 11 years. Employing advanced techniques like topic modeling, this review synthesized insights from more than 60,000 technical articles, providing a nuanced understanding of the dependency and maturity of AI within the realm of transportation research.

Task 3, focused on summarizing recent practices in DOTs through stakeholder interviews, provided a valuable perspective on the ground realities of AI implementations. This included an in-depth analysis of active and completed research efforts at the state and local DOT level, offering tangible insights into the practical applications and challenges faced in the field. The analysis also shows the disparity in practice among different DOTs and their current priorities.

The workshops conducted in Task 4 played a pivotal role in facilitating knowledge transfer and planning. These sessions not only garnered feedback on current AI requirements in DOTs but also played a crucial role in the development and refinement of the research roadmap. Task 5 then synthesized the learning from all tasks, creating a detailed research need report and research problem statements that would ensure a holistic understanding of the insights gained throughout the project. The workshops also helped in shaping the research need report, prioritizing elements for the most effective outcome. As a result, we have developed 11 research problem statements, each focusing on key areas of development: (1) workforce development and infrastructure development, (2) readiness and evaluation of AI, (3) challenges in adopting AI, (4) current practices and prioritization, (5) external collaboration, and (6) equity, policy, and planning.

The culmination of the research effort resulted in seven distinct deliverables, each contributing uniquely to the overarching objectives. In essence, this research project contributes significantly to the ongoing

dialogue on AI in transportation, laying the groundwork for informed decision-making, innovation, and the continued evolution of state-of-the-art practices in the realm of transportation research and operations. The lessons learned and insights gained will undoubtedly shape the future trajectory of AI adoption, ultimately enhancing the efficiency, safety, and sustainability of transportation systems.