Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding. This revolutionary force offers the most promising path yet toward solving one of engineering’s grandest challenges: achieving reliable, fully autonomous driving, particularly the pursuit of Level 5 autonomy. This survey delivers a comprehensive and critical synthesis of the emerging role of GenAI across the autonomous driving stack. We delve into the frontier applications of GenAI in image, LiDAR, trajectory, occupancy, and video generation, as well as LLM-guided reasoning and decision-making. We categorize practical applications, such as end-to-end driving strategies and closed-loop simulations. We identify key obstacles and possibilities such as comprehensive generalization across rare cases, evaluation, safety, and onboard deployment. By unifying these threads, the survey provides a forward-looking reference for researchers, engineers, and policymakers navigating the convergence of generative AI and advanced autonomous mobility. An actively maintained repository of cited works is available at https://github.com/taco-group/GenAI4AD.
Yuping Wang, Shuo Xing, Cui Can et al.· ACM Computing Surveys· 56 citations· ⚡2
Demand-responsive transit (DRT) has emerged as a flexible mobility solution for addressing service blind spots in areas underserved by conventional public transportation. However, empirical research on DRT demand estimation remains limited, especially in the context of regional heterogeneity and zero-inflated demand. This study proposes a data-driven DRT demand estimation framework using operational records from two contrasting regions in Incheon, South Korea. Yeongjongdo is a tourism- and airport-oriented area with a high floating population and strong temporal variability, while Geomdan New Town is a residential district with relatively stable travel patterns. A grid-based origin–destination (O–D) modeling structure was employed, incorporating spatial variables such as land use, population dynamics, facility distribution, and public transport accessibility. Multiple region-specific machine learning models were developed and evaluated to estimate planning-oriented mean daily demand for each O–D-hour. A comparative analysis of alternative model configurations showed that the appropriate model structure varied according to regional demand conditions. In Yeongjongdo, the proposed two-stage model, which combines demand-occurrence classification and conditional regression, achieved the best overall performance, with a test MAE of 0.0022 and RMSE of 0.0105. These values represented reductions of 37.1% and 42.0%, respectively, relative to the strongest direct regression benchmarks. In contrast, direct regression was more effective in Geomdan New Town, achieving a test MAE of 0.0071 and RMSE of 0.0190. These results indicate that the relative performance of direct regression and two-stage prediction may vary across regional demand contexts.
Yunji Jang, Eun Hak Lee, Jiho Yeo et al.· Scientific Reports· 0 citations