The DOI matches its Crossref record; 218 of the 230 references it cites were found in a registry or an index.
A Survey of Deep Learning Applications to Autonomous Vehicle Control
Open accessAbstract
Designing a controller for autonomous vehicles capable of providing adequate performance in all driving scenarios is challenging due to the highly complex environment and inability to test the system in the wide variety of scenarios which it may encounter after deployment. However, deep learning methods have shown great promise in not only providing excellent performance for complex and non-linear control problems, but also in generalising previously learned rules to new scenarios. For these reasons, the use of deep learning for vehicle control is becoming increasingly popular. Although important advancements have been achieved in this field, these works have not been fully summarised. This paper surveys a wide range of research works reported in the literature which aim to control a vehicle through deep learning methods. Although there exists overlap between control and perception, the focus of this paper is on vehicle control, rather than the wider perception problem which includes tasks such as semantic segmentation and object detection. The paper identifies the strengths and limitations of available deep learning methods through comparative analysis and discusses the research challenges in terms of computation, architecture selection, goal specification, generalisation, verification and validation, as well as safety. Overall, this survey brings timely and topical information to a rapidly evolving field relevant to intelligent transportation systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This includes historical signals and inappropriately proxied measures that make ML systems vulnerable to reproducing past discrimination against under-represented groups (e.g. in contexts such as job hiring and criminal justice), or propagating abusive content [46,67].”
From A Survey of Data Quality Requirements That Matter in ML Development Pipelines (2023) · cites this paper as [46]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This includes historical signals and inappropriately proxied measures that make ML systems vulnerable to reproducing past discrimination against under-represented groups (e.g. in contexts such as job hiring and criminal justice), or propagating abusive content [46,67].”
From A Survey of Data Quality Requirements That Matter in ML Development Pipelines (2023) · cites this paper as [46]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“in fields such as image classification and speech recognition [24]–[26].”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“Then, the neural network was trained with three different optimisation algorithms to update the network weights, namely Stochastic Gradient Descent (SGD) [90], Adam [91], and Nesterov’s Accelerated Gradient (NAG) [92].”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2014) · Cited by 33,419
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 1×
“deep learning enables developers to describe the desired behaviour and teach the system to perform well and generalise to new environments through learning [43]–[47].”
BackgroundReinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 25,268
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Neural networks for pattern recognition
Bishop, C. (1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,537 · cited 1×
“work and to terminate training can result in overfitting to the validation set. Therefore an additional independent set, known as testing set, is required for the evaluation of the network performance [186]. The testing set is only used to test the final network to confirm its performance and generalisation capabilities.…”
MethodSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“in fields such as image classification and speech recognition [24]–[26].”
BackgroundAre we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897
Research works printed but not linked: 26
- ripley, 1996, Artificial Neural Networks
- schalkoff, 1997, Artificial Neural Networks
- ng, 2004, Feature selection, L1 vs. L2 regularization, and rotational invariance, Proc 21st Int Conf Mach Learn (ICML), 78
- 10.1126/science.153.3731.34 · DOI · Paper page
- barron, 2009, Parallelizing Reinforcement Learning
- abraham, 2017, Consumer Interest in Automation Preliminary Observations Exploring a Year’s Change
- knight, 2016, An Ambitious Plan to Build a Self-Driving Borg
- 2016, Cooperative Intelligent Transportation Systems—Research Theme Analysis Report
- 2017, Consumer Acceptance of Autonomous Vehicles
- bosankic, 2017, How consumers’ Perception of Autonomous Cars Will Influence Their Adoption
- sevchuk, 2016, Hyperparameter Optimization for Neural Networks
- raffel, 2015, Neural Network Hyperparameters
- 2018, Global status report on road safety 2018
- 2019, Waymo open dataset An autonomous driving dataset
- 2018, Udacity Self-Driving Car Dataset
- 2018, Autonomous car development platform from nvidia drive px2
- williams, 1987, Reinforcement learning connectionist systems
- 2018, Cyclone V—Overview
- 2018, Evolution of the Eye
- 0, CarSim
- nguyen, 2015, Deep neural networks are easily fooled, Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), 427
- 2017, 2016 road safety statistics What is behind the figures
- 2017, 2016 Fatal Motor Vehicle Crashes Overview
- maurer, 2016, Autonomous Driving
- 2017, Research on the Impacts of Connected and Autonomous Vehicles (CAVs) on Traffic Flow Summary Report
- 2019, The Open Racing Car Simulator
Cited by
Sorted by citations
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Ahmad, K., Maabreh, M., Ghaly, M., Khan, K., Qadir, J., & Al-Fuqaha, A. (2022) · Computer Science Review · doi:10.1016/j.cosrev.2021.100452 · Cited by 291
“…autonomous cars where one of the key responsibilities of the AI module is continuous monitoring of the surrounding environment and the prediction of di ff erent events, which generally involves the detection and recognition of various objects such as pedestrians, vehicles, and roadside objects [38].”
BackgroundA Survey of Deep RL and IL for Autonomous Driving Policy Learning
Zhu, Z., & Zhao, H. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3134702 · Cited by 260
“References [4] addresses the deep learning techniques for AD with a focus on perception and control, while [32] addresses control only.”
BackgroundMachine learning for next-generation intelligent transportation systems: A survey
Yuan, T., Da Rocha Neto, W., Rothenberg, C. E., Obraczka, K., Barakat, C., & Turletti, T. (2022) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4427 · Cited by 179
“…works include [6-16], which focus on specific aspects of ITS, such as vehicular networks [7], vehicle detection [8-10], safety of vehicular ad-hoc network (VANET) [6, 15], VANET performance optimization [16], autonomous vehicle control [13], and Deep Reinforcement Learning (DRL) for 6G VANETs [14].”
Elallid, B. B., Benamar, N., Hafid, A. S., Rachidi, T., & Mrani, N. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.03.013 · Cited by 179
“Kuutti et al. (2020) discussed DL methods for controlling AVs and its promising performance in complex scenarios.”
Metadata
- Authors
- Kuutti, S., Bowden, R., Jin, Y., Barber, P., & Fallah, S.
- Affiliations
- University of Surrey (GB)
- Jaguar Land Rover (United Kingdom) (GB)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2021-02
- Volume
- 22
- Issue
- 2
- Pages
- 712-733
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W2995697759
- Cited by
- 96
- References
- 230
- Citations by year
- 2026: 12 · 2025: 7 · 2024: 16 · 2023: 21 · 2022: 14 · 2021: 21
- FWCI
- 5.64
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Surrey Research Insight Open Access (The University of Surrey) (submittedVersion)
- PUB – Publications at Bielefeld University (Bielefeld University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.K.-Engineering and Physical Sciences Research Council (EP/R512217/1)
- Jaguar Land Rover
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Automotive Engineering › Vehicle Dynamics and Control Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- autonomous vehicles, vehicle control, deep learning control, verification and validation, safety, goal specification, intelligent transportation systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
