Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys

Chen, Long; Li, Yuchen; Huang, Chao; Li, Bai; Xing, Yang; Tian, Daxin; Li, Li; Hu, Zhongxu; Na, Xiaoxiang; Li, Zixuan; Teng, Siyu; Lv, Chen; Wang, Jinjun; Cao, Dongpu; Zheng, Nanning; Wang, Fei–Yue · 2022 · OpenAlex-citations

DOI: 10.1109/tiv.2022.3223131

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper presents a "Survey of Surveys" (SoS) addressing the rapid growth of autonomous driving (AD) and intelligent vehicles (IVs). The authors identify a gap in existing literature, noting that while numerous surveys cover specific technical tasks, they often lack systematic summaries, historical context, and broad perspectives on ethics and future directions. This work serves as Part 1 of a larger series, aiming to bridge past achievements with future research by categorizing milestones, summarizing datasets, and outlining ethical considerations. The methodology involves collecting and analyzing 122 survey articles published between 2017 and 2021. These papers are categorized into 14 sub-sections, including overall AD, perception (localization, object detection, scene understanding), planning, control, system hardware/software, communication, simulation, interpretability, human-machine interface (HMI), and special scenes. The authors also review key AD datasets, such as KITTI, Cityscapes, nuScenes, and ApolloScape, detailing their sensor configurations (LiDAR, vision, radar, GPS) and supported tasks (e.g., 3D object detection, semantic segmentation, end-to-end planning). Additionally, the paper synthesizes findings from ethical studies, including the "Moral Machine Experiment," to analyze normative, environmental, and business ethics. Key findings highlight the evolution of AD from early radio-operated vehicles in the 1920s to modern deep learning-based systems. The analysis reveals that perception and dynamic object detection are the most heavily surveyed areas, with significant advancements in sensor fusion and 3D detection. The dataset review indicates a trend toward larger, more diverse datasets covering complex scenarios like night driving and adverse weather. Regarding ethics, the paper summarizes that while normative ethics often focus on moral dilemmas like the trolley problem, there is growing consensus that realistic ethical frameworks should prioritize HMI, data privacy, and environmental impacts. The authors note that IVs may reduce emissions through optimized driving but could increase total vehicle miles traveled, leading to higher noise and electromagnetic field exposure. The significance of this work lies in its comprehensive overview of the AD landscape, providing a structured reference for researchers and newcomers. The authors propose future research directions, including improving perception robustness, developing safe planning under imperfect data, enhancing control systems for longitudinal and lateral dynamics, and narrowing the gap between virtual and real-world testing. They emphasize the need for scenario intelligence to standardize data descriptions and improve adaptability. By systematically organizing existing surveys and identifying bottlenecks in perception, planning, control, and ethics, this paper aims to guide the field toward achieving Level 5 autonomy and addressing the societal implications of intelligent vehicles.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• driverless ads

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Synthesis & Review: research agenda