Engineering · Literature

Research papers on Self-driving car safety

Recent and highly-cited academic work on self-driving car safety, gathered from Semantic Scholar, CrossRef and OpenAlex.

1. A survey of deep learning techniques for autonomous driving

   Sorin Mihai Grigorescu, Bogdan Trăsnea, Tiberiu Cocias, et al. · 2019 · Journal of Field Robotics · 1,794 citations

   Abstract The last decade witnessed increasingly rapid progress in self‐driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving. We start by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception‐planning‐action pipeline, where each

   Save this paper

2. Planning and Decision-Making for Autonomous Vehicles

   Wilko Schwarting, Javier Alonso–Mora, Daniela L. Rus · 2018 · Annual Review of Control Robotics and Autonomous Systems · 962 citations

   In this review, we provide an overview of emerging trends and challenges in the field of intelligent and autonomous, or self-driving, vehicles. Recent advances in the field of perception, planning, and decision-making for autonomous vehicles have led to great improvements in functional capabilities, with several prototypes already driving on our roads and streets. Yet challenges remain regarding guaranteed performance and safety under all driving circumstances. For instance, planning methods that provide safe and system-compliant performance in complex, cluttered environments while modeling the uncertain interaction with other traffic participants are required. Furthermore, new paradigms, su

   Save this paper

3. Can You Trust Autonomous Vehicles : Contactless Attacks against Sensors of Self-driving Vehicle

   Jian-Hao Liu · 2016 · 367 citations

   Save this paper

4. Driving to Safety: How Many Miles of Driving Would It Take to Demonstrate Autonomous Vehicle Reliability?

   Nidhi Kalra, Susan M. Paddock · 2016 · RAND Corporation eBooks · 305 citations

   How safe are autonomous vehicles? The answer is crucial for developing sound policies to govern their deployment. This report evaluates whether it is practical to test-drive autonomous vehicles to assess their safety. We find that it would take hundreds of millions of miles and sometimes hundreds of billions of miles of test-driving to provide clear statistical evidence of autonomous vehicle safety, suggesting it is not a practical approach.

   Save this paper

5. Safety of Autonomous Vehicles

   Jun Wang, Li Zhang, Yanjun Huang, et al. · 2020 · Journal of Advanced Transportation · 260 citations

   Autonomous vehicle (AV) is regarded as the ultimate solution to future automotive engineering; however, safety still remains the key challenge for the development and commercialization of the AVs. Therefore, a comprehensive understanding of the development status of AVs and reported accidents is becoming urgent. In this article, the levels of automation are reviewed according to the role of the automated system in the autonomous driving process, which will affect the frequency of the disengagements and accidents when driving in autonomous modes. Additionally, the public on-road AV accident reports are statistically analyzed. The results show that over 3.7 million miles have been tested for A

   Save this paper

6. A Safety Standard Approach for Fully Autonomous Vehicles

   Philip John Koopman, Uma D. Ferrell, Frank Fratrik, et al. · 2019 · Lecture notes in computer science · 102 citations

   Save this paper

7. Steering towards safe self-driving laboratories

   Shi Xuan Leong, Caleb E Griesbach, Rui Zhang, et al. · 2025 · Nature Reviews Chemistry · 57 citations

   The past decade has witnessed remarkable advancements in autonomous systems, such as automobiles that are evolving from traditional vehicles to ones capable of navigating complex environments without human intervention. Similarly, the rise of self-driving laboratories (SDLs), which leverage robotics and artificial intelligence to accelerate discovery, is driving a paradigm shift in scientific research. As SDLs evolve to expand the scope of chemical processes that can be performed, it is essential to bring safety to the forefront to ensure that the necessary safeguards are in place to mitigate against potential accidents that range from near-misses to catastrophic failures. This Perspective e

   Save this paper

8. Coverage based testing for V&V and Safety Assurance of Self-driving Autonomous Vehicles: A Systematic Literature Review

   Zaid Tahir, Rob Alexander · 2020 · IEEE International Conference on Artificial Intelligence Testing (AITest) · 45 citations

   Self-driving Autonomous Vehicles (SAVs) are gaining more interest each passing day by the industry as well as the general public. Tech and automobile companies are investing huge amounts of capital in research and development of SAVs to make sure they have a head start in the SAV market in the future. One of the major hurdles in the way of SAVs making it to the public roads is the lack of confidence of public in the safety aspect of SAVs. In order to assure safety and provide confidence to the public in the safety of SAVs, researchers around the world have used coverage-based testing for Verification and Validation (V&V) and safety assurance of SAVs. The objective of this paper is to investi

   Save this paper

9. Review of Learning-Based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps Between Self-Driving and Traffic Congestion

   Hao Zhou, Jorge A. Laval, Anye Zhou, et al. · 2019 · Transportation Research Record · 45 citations

   Self-driving technology companies and the research community are accelerating the pace of use of machine learning longitudinal motion planning (mMP) for autonomous vehicles (AVs). This paper reviews the current state of the art in mMP, with an exclusive focus on its impact on traffic congestion. The paper identifies the availability of congestion scenarios in current datasets, and summarizes the required features for training mMP. For learning methods, the major methods in both imitation learning and non-imitation learning are surveyed. The emerging technologies adopted by some leading AV companies, such as Tesla, Waymo, and Comma.ai, are also highlighted. It is found that: (i) the AV indust

   Save this paper

10. Machine vision-based autonomous road hazard avoidance system for self-driving vehicles

    Cheng-Qun Qiu, Hao Tang, Yucheng Yang, et al. · 2024 · Scientific Reports · 38 citations

    The resolution of traffic congestion and personal safety issues holds paramount importance for human’s life. The ability of an autonomous driving system to navigate complex road conditions is crucial. Deep learning has greatly facilitated machine vision perception in autonomous driving. Aiming at the problem of small target detection in traditional YOLOv5s, this paper proposes an optimized target detection algorithm. The C3 module on the algorithm’s backbone is upgraded to the CBAMC3 module, introducing a novel GELU activation function and EfficiCIoU loss function, which accelerate convergence on position loss lbox, confidence loss lobj, and classification loss lcls, enhance image learning c

    Save this paper

11. Advancements and challenges in achieving fully autonomous self-driving vehicles

    V. Satya, R. Kosuru, Ashwin Kavasseri Venkitaraman · 2023 · World Journal of Advanced Research and Reviews · 37 citations

    This article presents a review and analysis of the prospects of achieving full-length autonomous driving, a concept that has long been a dream of humans. Although the automotive industry has made significant progress in many areas, creating fully automated vehicles (level 5) has remained a challenge. This paper examines some companies that are already racing to achieve this feat, such as Tesla, Google's Waymo, and Uber, and the challenges they face, such as ensuring safety and reliability while also dealing with complex and expensive technology. The article highlights the issues that must be addressed when discussing fully automated vehicles, such as legal and regulatory frameworks, public a

    Save this paper

12. How to Guarantee Driving Safety for Autonomous Vehicles in a Real-World Environment: A Perspective on Self-Evolution Mechanisms

    Shuo Yang, Yanjun Huang, Li Li, et al. · 2024 · IEEE Intelligent Transportation Systems Magazine · 24 citations

    A succession of accidents shows that production vehicles with autonomous driving systems do not work safely in real-world environments, especially when facing unseen scenarios. Therefore, how to ensure that autonomous systems drive more safely becomes a challenge. Thanks to the self-learning ability of human beings, human drivers can gradually learn how to drive from a driving test with typical and finite scenarios to the real world with infinite ones. Analogically, it is believed that accidents can be largely reduced once the designed autonomous vehicles are endowed with a self-learning ability to adapt to the unseen and then to infinite scenarios in the real world. Accordingly, this work p

    Save this paper

13. Road traffic safety assessment in self-driving vehicles based on time-to-collision with motion orientation.

    F. M. Ortiz, Matteo Sammarco, Marcin Detyniecki, et al. · 2023 · Accident; analysis and prevention · 22 citations

    Traffic conflict analysis based on Surrogate Safety Measures (SSMs) helps to estimate the risk level of an ego-vehicle interacting with other road users. Nonetheless, risk assessment for autonomous vehicles (AVs) is still incipient, given that most of the AVs are currently prototypes and current SSMs do not directly apply to autonomous driving styles. Therefore, to assess and quantify the potential risk arising from AV interactions with other road users, this study introduces the TTCmo (Time-to-Collision with motion orientation), a metric that considers the yaw angle of conflicting objects. In fact, the yaw angle represents the orientation of the other road users and objects detected by the

    Save this paper

14. Real-time combined safety-mobility assessment using self-driving vehicles collected data.

    Ahmed Kamel, Tarek Sayed, M. Kamel · 2024 · Accident; analysis and prevention · 16 citations

    The study presents a real-time safety and mobility assessment approach using data generated by autonomous vehicles (AVs). The proposed safety assessment method uses Bayesian hierarchical spatial random parameter extreme value model (BHSRP), which can handle the limited availability and uneven distribution of conflict data and accounts for unobserved spatial heterogeneity. The approach estimates two real-time safety metrics: the risk of crash (RC) and return level (RL), using Time-To-Collision (TTC) as conflict indicator. Additionally, a Risk Exposure (RE) index was developed to reflect the risk of an individual vehicle to travel through a corridor. In parallel, the mobility of corridor were

    Save this paper

15. Autonomous Lateral Maneuvers for Self-Driving Vehicles in Complex Traffic Environment

    Zhaolun Li, Jing-Jing Jiang, Wen-Hua Chen, et al. · 2023 · IEEE Transactions on Intelligent Vehicles · 15 citations

    Autonomous driving functions have gained great interests from both academia and industry over the years. This paper proposes a Model Predictive Control based method to generate a safe and feasible trajectory for the ego vehicle to perform various lateral maneuvers and to produce optimized control inputs to guide the ego vehicle through a mixed traffic environment with both human drivers and autonomous vehicle. A novel reference speed generation function is proposed to automatically adjust the position of the ego vehicle before the initiation of any lateral maneuvers. After a proper gap is selected, the lateral maneuver initiation function with an add-on threshold function is introduced to en

    Save this paper

16. Robust Multi‐Agent Reinforcement Learning Against Adversarial Attacks for Cooperative Self‐Driving Vehicles

    Chu-Yao Wang, Zi-Wei Wang, Nabil Aouf · 2025 · IET Radar, Sonar & Navigation · 11 citations

    Multi‐agent deep reinforcement learning (MARL) for self‐driving vehicles aims to address the complex challenge of coordinating multiple autonomous agents in shared road environments. MARL creates a more stable system and improves vehicle performance in typical traffic scenarios compared to single‐agent DRL systems. However, despite its sophisticated cooperative training, MARL remains vulnerable to unforeseen adversarial attacks. Perturbed observation states can lead one or more vehicles to make critical errors in decision‐making, triggering chain reactions that often result in severe collisions and accidents. To ensure the safety and reliability of multi‐agent autonomous driving systems, thi

    Save this paper

17. Toward AI-Powered Edge Intelligence for Object Detection in Self-Driving Cars: Enhancing IoV Efficiency and Safety

    Imran Ahmed, Misbah Ahmad, Muftooh Ur Rehman Siddiqi, et al. · 2025 · IEEE Internet of Things Journal · 10 citations

    In the rapidly advancing field of intelligent transportation systems, integrating artificial intelligence (AI) with edge computing presents a promising way to enhance the safety and efficiency of the Internet of Vehicles (IoV). This study explores and presents a deep learning-based object detection model within an edge computing framework which aims to facilitate real time object detection in self driving cars. Using an urban traffic scenarios-based dataset, our research shows the ability of the model to accurately detect and classify various objects important for autonomous driving. The YOLOv8 model is used in this work due to its optimal balance between accuracy and computational efficienc

    Save this paper

18. From Human to Autonomous Driving: A Method to Identify and Draw Up the Driving Behaviour of Connected Autonomous Vehicles

    Giandomenico Caruso, Mohammad Kia Yousefi, Lorenzo Mussone · 2022 · Vehicles · 9 citations

    The driving behaviour of Connected and Automated Vehicles (CAVs) may influence the final acceptance of this technology. Developing a driving style suitable for most people implies the evaluation of alternatives that must be validated. Intelligent Virtual Drivers (IVDs), whose behaviour is controlled by a program, can test different driving styles along a specific route. However, multiple combinations of IVD settings may lead to similar outcomes due to their high variability. The paper proposes a method to identify the IVD settings that can be used as a reference for a given route. The method is based on the cluster analysis of vehicular data produced by a group of IVDs with different setting

    Save this paper

19. Human-Centric Role in Self-Driving Vehicles: Can Human Driving Perception Change the Flavor of Safety Features?

    B. Mrazovac, M. Bjelica · 2023 · IEEE Intelligent Transportation Systems Magazine · 6 citations

    Autonomous vehicles are expected to generate significant revenues for the global economy in the next decade. Recently, industry experts warned that autonomous vehicles are losing momentum. Self-driving is stalling. Fusing human sentiment and driving perception into a holistic approach to the development of human-centric autonomous vehicles could regain the market’s trust. In this article, we try to explain why the traditional approach to self-driving vehicles, which focuses only on perfecting vehicle performance, sends engineers back to the whiteboard.

    Save this paper

20. Exploring the impact of display types of information about autonomous driving in semi-autonomous vehicles on drivers’ situation awareness and take-over performance under different driving scenarios

    Cheng-Min Zhou, Yuxuan Luo, Jake Kaner · 2025 · PLOS One · 6 citations

    With the advent of the era of autonomous driving, designing an effective and appropriate autonomous driving information display is crucial for ensuring driving safety. Head-up Display (HUD) is regarded as a promising way for presenting in-vehicle information in the future. This study conducted a simulation experiment to explore the impacts of three types of autonomous driving information displays on HUD on Situation Awareness (SA) and take-over performance, while considering the complexity of different driving scenarios. The experiment used in this study adopted a Latin square experimental design and employed an integrated eye-tracking technology with self-reporting and the Situation Awarene

    Save this paper

21. A Reliability Analysis of Self-Driving Vehicles: Evaluating the Safety and Performance of Autonomous Driving Systems

    Aneesh Pradeep, Mironshokh Bakoev, Nazokat Akhroljonova · 2023 · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · 5 citations

    Self-driving cars are a ground-breaking invention with the potential to revolutionize the transportation sector. As technology develops, it is more crucial than ever to guarantee the dependability of self-driving cars. The dependability analysis of self-driving cars is the main topic of this research article. The multiple levels of automation in self-driving cars and their accompanying reliability requirements are covered in the first section of the study. Afterwards, it examines the many parts of a self-driving car system, such as the perception, decision-making, and control subsystems, and talks about the dependability issues that each of these parts faces. The paper ends by highlighting t

    Save this paper

22. Shadow Testing in Autonomous Vehicles : A Novel Approach to Validating Full Self-Driving AI Systems

    Revanth Pathuri · 2024 · International Journal of Scientific Research in Computer Science, Engineering and Information Technology · 4 citations

    As autonomous vehicles progress towards widespread deployment, ensuring the reliability and safety of Full Self-Driving (FSD) AI systems remains a critical challenge. This article presents a comprehensive analysis of shadow testing, an innovative approach to validating new FSD AI models in real-world conditions without compromising user safety. We examine the methodology of deploying new AI models in "shadow mode," where they process live sensory data alongside the operational system but do not control the vehicle. This approach enables the collection of valuable performance metrics and the identification of edge cases while mitigating risks associated with direct deployment. Our study demon

    Save this paper

23. Investigation of driver preference for a user-centred design of decision systems in autonomous vehicles, part I: preferences for binary self-driving modes

    Hyowon Lee, Yovela Murzello, M. Nabipour, et al. · 2024 · Theoretical Issues in Ergonomics Science · 4 citations

    Abstract As autonomous vehicles (AV) are becoming more pervasive in transportation, it is important to consider drivers’ perceptions of these vehicles. The existing research has investigated taking over AV control, its safety and acceptance. However, the preferences for self-driving in multiple traffic situations have not been extensively investigated. In Part I, we aim to bridge these gaps by investigating such preferences in high and low traffic complexities. Eighty-eight participants in North America were recruited. They viewed video recordings of driving in the city of Toronto, the regional municipality of Waterloo and highways to answer survey questions. Their responses regarding percep

    Save this paper

24. Economic benefit, challenges, and perspectives for the application of Autonomous technology in self-driving vehicles

    Runzhu Xiao · 2023 · Highlights in Science, Engineering and Technology · 4 citations

    With the development and innovation of state-of-art autonomous driving technology, the feasibility of autonomous technology application in self-driving vehicles has become a social interest. Despite the several energy and economic advantages brought by autonomous driving, the safety, technic, and ethical issues are still of concern. Thus, this paper has carefully evaluated the feasibility of self-driving applications regarding the above aspects. Suggestions are also provided accordingly for further technology evolution. The results show that autonomous driving has greater benefits, but there is still room to fill in the legal and technical aspects. The benefits mainly include freeing up driv

    Save this paper