pith. sign in

arxiv: 1906.08834 · v2 · pith:NKITESZWnew · submitted 2019-06-20 · 💻 cs.LG · cs.RO· eess.SP· stat.ML

Deep Learning in the Automotive Industry: Recent Advances and Application Examples

Kanwar Bharat Singh , Mustafa Ali Arat This is my paper

Pith reviewed 2026-05-25 19:26 UTC · model grok-4.3

classification 💻 cs.LG cs.ROeess.SPstat.ML
keywords deep learningautomotiveADASautomated drivingvirtual sensingvehicle health monitoring
0
0 comments X

The pith

Deep learning is set to deliver performance gains for most advanced driver assistance systems in vehicles.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper surveys recent deep learning advances and maps them onto automotive use cases. It states that these techniques can improve functionality across most ADAS solutions. Four areas receive the strongest emphasis: virtual sensing for vehicle dynamics, vehicle inspection and health monitoring, automated driving, and data-driven product development. The authors also note associated challenges drawn from the cited work. A reader would follow the argument to see where the technology is expected to matter most in the near term.

Core claim

Deep learning is poised to offer gains in performance and functionality for most ADAS solutions, with virtual sensing for vehicle dynamics applications, vehicle inspection/health monitoring, automated driving, and data-driven product development expected to receive the most attention.

What carries the argument

The structured overview of deep learning models and their cited automotive applications, grouped by the four key areas.

If this is right

  • Virtual sensing can reduce reliance on physical hardware for vehicle dynamics monitoring.
  • Automated driving functions gain reliability through data-driven perception and control.
  • Vehicle health monitoring shifts toward continuous, model-based inspection rather than periodic checks.
  • Product development incorporates larger volumes of sensor data to guide design decisions.
  • ADAS solutions overall achieve higher performance levels once the cited techniques are integrated.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Industry roadmaps may prioritize the four highlighted areas when allocating deep learning resources.
  • Challenges noted in the review could guide targeted research on data quality or real-time constraints.
  • Integration of these methods may accelerate the shift from rule-based to learned components in production vehicles.
  • The overview suggests a feedback loop where automotive data collection further improves the models.

Load-bearing premise

The advances and applications described in the cited literature accurately represent the current state and near-term potential of deep learning in automotive settings.

What would settle it

A side-by-side real-world test showing that deep learning models deliver no measurable improvement over conventional methods in ADAS tasks such as emergency braking or lane keeping.

read the original abstract

One of the most exciting technology breakthroughs in the last few years has been the rise of deep learning. State-of-the-art deep learning models are being widely deployed in academia and industry, across a variety of areas, from image analysis to natural language processing. These models have grown from fledgling research subjects to mature techniques in real-world use. The increasing scale of data, computational power and the associated algorithmic innovations are the main drivers for the progress we see in this field. These developments also have a huge potential for the automotive industry and therefore the interest in deep learning-based technology is growing. A lot of the product innovations, such as self-driving cars, parking and lane-change assist or safety functions, such as autonomous emergency braking, are powered by deep learning algorithms. Deep learning is poised to offer gains in performance and functionality for most ADAS (Advanced Driver Assistance System) solutions. Virtual sensing for vehicle dynamics application, vehicle inspection/heath monitoring, automated driving and data-driven product development are key areas that are expected to get the most attention. This article provides an overview of the recent advances and some associated challenges in deep learning techniques in the context of automotive applications.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript is a survey paper providing an overview of recent advances in deep learning and their applications to the automotive industry. It states that deep learning models are being deployed across areas from image analysis to NLP, driven by data scale, compute, and algorithmic innovations, with significant potential for automotive uses including self-driving cars, ADAS functions like parking/lane-change assist and autonomous emergency braking. The central forward-looking claim is that deep learning is poised to offer gains in performance and functionality for most ADAS solutions, with key areas expected to receive the most attention being virtual sensing for vehicle dynamics, vehicle inspection/health monitoring, automated driving, and data-driven product development; the paper also notes associated challenges.

Significance. If the cited literature is representative, this survey consolidates existing work on deep learning applications in automotive settings and identifies high-impact areas, which could serve as a useful entry point for researchers bridging ML and automotive engineering. No machine-checked proofs, reproducible code, or parameter-free derivations are present, as expected for an overview paper.

major comments (1)
  1. [Abstract] Abstract: The forward-looking claim that deep learning 'is poised to offer gains in performance and functionality for most ADAS solutions' and that the listed key areas 'are expected to get the most attention' is load-bearing for the paper's central contribution but rests entirely on the accuracy of the cited works without any explicit critical synthesis, quantitative benchmarks, or discussion of failure modes from those works.
minor comments (2)
  1. [Abstract] Abstract: Typo in 'vehicle inspection/heath monitoring' (should be 'health').
  2. The manuscript would benefit from a summary table listing the main application areas, representative citations, and claimed benefits to improve readability and allow quick comparison across the surveyed domains.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our survey manuscript. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The forward-looking claim that deep learning 'is poised to offer gains in performance and functionality for most ADAS solutions' and that the listed key areas 'are expected to get the most attention' is load-bearing for the paper's central contribution but rests entirely on the accuracy of the cited works without any explicit critical synthesis, quantitative benchmarks, or discussion of failure modes from those works.

    Authors: The manuscript is a survey whose abstract statements synthesize trends from the cited literature reviewed in the body of the paper, which discusses applications, performance gains reported in prior work, and associated challenges. We agree that the abstract could more clearly signal its reliance on existing studies rather than presenting new synthesis. In revision we will adjust the abstract wording to be more measured, explicitly tie the claims to the reviewed literature, and reference the challenges section. We will not add new quantitative benchmarks or original failure-mode analyses, as these lie outside the scope of a survey paper that consolidates rather than generates primary evaluations. revision: partial

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a survey/overview of existing literature on deep learning in automotive applications. It presents no original derivations, equations, fitted parameters, or technical claims that could reduce to self-defined inputs or self-citations. All forward-looking statements are explicitly tied to cited external works, with no internal load-bearing steps that match any of the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities because the paper is a survey of existing work rather than a technical derivation or new model.

pith-pipeline@v0.9.0 · 5740 in / 1005 out tokens · 27722 ms · 2026-05-25T19:26:00.021736+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

79 extracted references · 79 canonical work pages · 10 internal anchors

  1. [1]

    Gradient-based learning applied to document recognition,

    Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998, doi: 10.1109/5.726791

    work page doi:10.1109/5.726791 1998

  2. [2]

    Backpropagation applied to handwritten zip code recognition,

    Y. LeCun et al., "Backpropagation applied to handwritten zip code recognition," Neural Computation, vol. 1, no. 4, pp. 541–551, Dec. 1989, doi: 10.1162/neco.1989.1.4.541

    work page doi:10.1162/neco.1989.1.4.541 1989

  3. [3]

    The past, present, and future of machine learning APIs,

    A. Cetinsoy, F. J. Martin, J. A. Ortega, and P. Petersen, "The past, present, and future of machine learning APIs," in JMLR: Workshop Conf. Proc., 2016, pp. 43–49

    work page 2016

  4. [4]

    Chollet and J

    F. Chollet and J. J. Allaire, Deep Learning with R . Greenwich, CT, USA: Manning Publications Company, 2018

    work page 2018

  5. [5]

    An in -depth look at Google’s first Tensor Processing Unit (TPU),

    K. Sato, C. Young, and D. Patterson, "An in -depth look at Google’s first Tensor Processing Unit (TPU)," Google Cloud Big Data and Machine Learning Blog, 2017

    work page 2017

  6. [6]

    ImageNet: A large -scale hierarchical image database,

    J. Deng, W. Dong, R. Socher, L. Li, L. Kai, and F.-F. Li, "ImageNet: A large -scale hierarchical image database," in IEEE Conf. Comp. Vision Pattern Recognition , Jun. 2009, pp. 248–255

    work page 2009

  7. [7]

    Goodfellow, Y

    I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. MIT Press, 2016

    work page 2016

  8. [8]

    ROS: An open-source robot operating system,

    M. Quigley et al., "ROS: An open-source robot operating system," in ICRA Workshop on Open Source Software , 2009

    work page 2009

  9. [9]

    TensorFlow: A sys tem for large -scale machine learning,

    M. Abadi et al., "TensorFlow: A sys tem for large -scale machine learning," in OSDI'16 Proc. 12th USENIX Conf. Operating Syst. Design Implementation, 2016

    work page 2016

  10. [10]

    Chollet, "Keras," 2015

    F. Chollet, "Keras," 2015

    work page 2015

  11. [11]

    Scalable and accurate deep learning with electronic health records,

    A. Rajkomar et al., "Scalable and accurate deep learning with electronic health records," npj Digital Med., vol. 1, no. 1, p. 18, May 2018, doi: 10.1038/s41746-018-0029-1

    work page doi:10.1038/s41746-018-0029-1 2018

  12. [12]

    Just one autonomous car will use 4,000 GB of data/day

    P. Nelson, "Just one autonomous car will use 4,000 GB of data/day." https://www.networkworld.com/article/3147892/one- autonomous-car-will-use-4000-gb-of-dataday.html (accessed Mar. 04, 2019)

    work page arXiv 2019

  13. [13]

    Imagenet classification with deep convolutional neural networks,

    A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Adv. Neural Inform. Process. Syst., 2012, pp. 1097– 1105. 13

    work page 2012

  14. [14]

    Convolutional neural networks,

    A. Ng, "Convolutional neural networks," Deep Learning Specialization, Coursera

    work page

  15. [15]

    How to train tensorflow models using GPUs,

    K. Savitsina, "How to train tensorflow models using GPUs," 04-Oct-2017, 2017

    work page 2017

  16. [16]

    Caffe: Convolutional architecture for fast feature embedding,

    Y. Jia et al., "Caffe: Convolutional architecture for fast feature embedding," in Proc. 22nd ACM Int. Conf. Multimedia, Nov. 2014, pp. 675–678

    work page 2014

  17. [17]

    Theano: new features and speed improvements

    F. Bastien et al. , "Theano: New features and speed improvements," arXiv preprint arXiv:1211.5590, 2012

    work page internal anchor Pith review Pith/arXiv arXiv 2012

  18. [18]

    CNTK: Microsoft's open - source deep -learning toolkit,

    F. Seide and A. Agarwal, "CNTK: Microsoft's open - source deep -learning toolkit," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery Data Mining , Aug. 2016, p. 2135

    work page 2016

  19. [19]

    Introduction to pytorch,

    N. Ketkar, "Introduction to pytorch," in Deep Learning with Python, Springer, 2017, pp. 195–208

    work page 2017

  20. [20]

    Deep learning,

    Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436 –44, May 2015, doi: 10.1038/nature14539

    work page doi:10.1038/nature14539 2015

  21. [21]

    ImageNet large scale visual recognition challenge,

    O. Russakovsky et al. , "ImageNet large scale visual recognition challenge," Int. J. Comput. Vision, vol. 115, no. 3, pp. 211–252, Dec. 2015, doi: 10.1007/s11263-015- 0816-y

    work page doi:10.1007/s11263-015- 2015

  22. [22]

    A survey on transfer learning,

    S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345– 1359, Oct. 2010, doi: 10.1109/TKDE.2009.191

    work page doi:10.1109/tkde.2009.191 2010

  23. [23]

    Medsker and L

    L. Medsker and L. C. Jain, Recurrent neural networks: Design and applications. USA: CRC Press, 1999

    work page 1999

  24. [24]

    Very Deep Convolutional Networks for Large-Scale Image Recognition

    K. Simonyan and A. Zisserman, "Very deep convolutional networks for large -scale image recognition," arXiv preprint arXiv:1409.1556, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  25. [25]

    Deep residual learning for image recognition,

    K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in IEEE Conf. Comput. Vision Pattern Recognition (CVPR), Jun. 2016, pp. 770- 778, doi: 10.1109/CVPR.2016.90

    work page doi:10.1109/cvpr.2016.90 2016

  26. [26]

    Going deeper with convolutions,

    C. Szegedy et al., "Going deeper with convolutions," in IEEE Conf. Comput. Vision and Pattern Recognition (CVPR), Jun . 2015, pp. 1 –9, doi: 10.1109/CVPR.2015.7298594

    work page doi:10.1109/cvpr.2015.7298594 2015

  27. [27]

    SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

    F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, "Squeezenet: Alexnet -level accuracy with 50x fewer parameters and< 0.5 mb model size," arXiv preprint arXiv:1602.07360, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  28. [28]

    Untersuchungen z u dynamischen neuronalen Netzen,

    S. Hochreiter, "Untersuchungen z u dynamischen neuronalen Netzen," Diploma, Technische Universität München, vol. 91, no. 1, 1991

    work page 1991

  29. [29]

    Long short -term memory,

    S. Hochreiter and J. Schmidhuber, "Long short -term memory," Neural Computation, vol. 9, no. 8, pp. 1735 – 1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735

    work page doi:10.1162/neco.1997.9.8.1735 1997

  30. [30]

    Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

    K. Cho et al. , "Learning phrase representations using RNN encoder -decoder for statistical machine translation," arXiv preprint arXiv:1406.1078, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  31. [31]

    Literature review and fundamental approaches for vehicl e and tire state estimation,

    K. B. Singh, M. A. Arat, and S. Taheri, "Literature review and fundamental approaches for vehicl e and tire state estimation," Veh. Syst. Dynamics, pp. 1–23, Nov. 2018, doi: 10.1080/00423114.2018.1544373

    work page doi:10.1080/00423114.2018.1544373 2018

  32. [32]

    Development of a road condition observer for the “vehicle motion control

    T. Raste, P. Lauer, and B. Hartmann, "Development of a road condition observer for the “vehicle motion control” project," in XXXVII. Int. μ -Symp. 2018 Bremsen - Fachtagung, 2018, pp. 127–-141

    work page 2018

  33. [33]

    Development and experimental evaluation of a slip angle estimator for vehicle stability control,

    D. Piyabongkarn, R. Rajamani, J. A. Grogg, and J. Y. Lew, "Development and experimental evaluation of a slip angle estimator for vehicle stability control," IEEE Trans. Control Syst. Technol., vol. 17, n o. 1, pp. 78 –88, Jan. 2009, doi: 10.1109/TCST.2008.922503

    work page doi:10.1109/tcst.2008.922503 2009

  34. [34]

    Vehicle dynamic state estimation: State of the art schemes and perspectives,

    H. Guo, D. Cao, H. Chen, C. Lv, H. Wang, and S. Yang, "Vehicle dynamic state estimation: State of the art schemes and perspectives," IEEE/CAA J. Automat. Sinica, vol. 5, no. 2, pp. 418 –431, Ma r. 2018, doi: 10.1109/JAS.2017.7510811

    work page doi:10.1109/jas.2017.7510811 2018

  35. [35]

    A deep learning based virtual sensor for vehicle sideslip angle estimation: Experimental results,

    J. Ghosh, A. Tonoli, and N. Amati, "A deep learning based virtual sensor for vehicle sideslip angle estimation: Experimental results," SAE Technical Paper, 0148–7191, 2018

    work page 2018

  36. [36]

    A hybrid approach to side -slip angle estimation with recurrent neural networks and kinematic vehicle models,

    T. Gräber, S. Lupberger, M. Unter reiner, and D. Schramm, "A hybrid approach to side -slip angle estimation with recurrent neural networks and kinematic vehicle models," IEEE Tran. Intell. Veh., vol. 4, no. 1, pp. 39–47, Mar. 2019, doi: 10.1109/TIV.2018.2886687

    work page doi:10.1109/tiv.2018.2886687 2019

  37. [37]

    Estimation of vehicle sideslip, tire force and wheel cornering stiffness,

    G. Baffet, A. Charara, and D. Lechner, "Estimation of vehicle sideslip, tire force and wheel cornering stiffness," Control Eng. Practice, vol. 17, no. 11, pp. 1255 –1264, Nov. 2009, doi: 10.1016/j.conengprac.2009.05.005

    work page doi:10.1016/j.conengprac.2009.05.005 2009

  38. [38]

    Vehicle sideslip estimation: A kinematic based approach,

    D. Selmanaj, M. Corno, G. Panzani, and S. M. Savaresi, "Vehicle sideslip estimation: A kinematic based approach," Control Eng. Practice, vol. 67, pp. 1–12, Oct. 2017, doi: 10.1016/j.conengprac.2017.06.013

    work page doi:10.1016/j.conengprac.2017.06.013 2017

  39. [39]

    Vehicle sideslip angle estimation based on tire model adaptation,

    K. B. Singh, "Vehicle sideslip angle estimation based on tire model adaptation," Electronics, vol. 8, no. 2, p. 199, Feb. 2019, doi: 10.3390/electronics8020199

    work page doi:10.3390/electronics8020199 2019

  40. [40]

    Slip-based tire-road friction estimation,

    F. Gustafsson, "Slip-based tire-road friction estimation," Automatica, vol. 33, no. 6, pp. 1087–1099, Jun. 1997, doi: 10.1016/S0005-1098(97)00003-4

    work page doi:10.1016/s0005-1098(97)00003-4 1997

  41. [41]

    Friction coefficient measurement for autonomous winter road maintenance,

    G. Erdogan, L. Alexander, and R. Rajamani, "Friction coefficient measurement for autonomous winter road maintenance," Veh. Syst. Dynamics, vol. 47, no. 4, pp. 497–512, Mar. 2009, doi: 10.1080/00423110802220554

    work page doi:10.1080/00423110802220554 2009

  42. [42]

    Robust estimation of road frictional coefficient,

    C. Ahn, H. Peng, and H. E. Tseng, "Robust estimation of road frictional coefficient," IEEE Trans. Control Syst. Technol., vol. 21, no. 1, pp. 1 –13, Jan. 2013, doi: 10.1109/TCST.2011.2170838

    work page doi:10.1109/tcst.2011.2170838 2013

  43. [43]

    Estimation of tire –road friction coefficient and its application in chassis control systems,

    K. B. Singh and S. Taheri, "Estimation of tire –road friction coefficient and its application in chassis control systems," Syst. Sci. Control Eng., vol. 3, no. 1, pp. 39–61, 2015, doi: 10.1080/21642583.2014.985804

    work page doi:10.1080/21642583.2014.985804 2015

  44. [44]

    Detecting ro ad surface wetness from audio: A deep learning approach,

    I. Abdić et al. , "Detecting ro ad surface wetness from audio: A deep learning approach," in 23rd Int. Conf. Pattern Recognition (ICPR), Dec. 2016, pp. 3458–3463, doi: 10.1109/ICPR.2016.7900169

    work page doi:10.1109/icpr.2016.7900169 2016

  45. [45]

    Jonnarth, Camera-based friction estimation with deep convolutional neural networks

    A. Jonnarth, Camera-based friction estimation with deep convolutional neural networks. Uppsala Universitet, 2018

    work page 2018

  46. [46]

    Machine learning models for road surface and friction estimation using front -camera images,

    S. Roychowdhury, M. Zhao, A. Wallin, N. Ohlsson, and M. Jonasson, "Machine learning models for road surface and friction estimation using front -camera images," in Int. Joint Conf. Neural Networks (IJCNN), 2018

    work page 2018

  47. [47]

    Assessment of deep convolutional neural networks for road surface classification,

    M. Nolte, N. Kister, and M. Maurer, "Assessment of deep convolutional neural networks for road surface classification," arXiv preprint arXiv:1804.08872, 2018

    work page arXiv 2018

  48. [48]

    Densely connected convolutional networks,

    G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in IEEE Conf. Comput. Vision and Pattern Recognition (CVPR) , Jul . 2017, pp. 2261 –2269, doi: 10.1109/CVPR.2017.243

    work page doi:10.1109/cvpr.2017.243 2017

  49. [49]

    Disrupting vehicle inspection using deep learning,

    I. Bogomolny, "Disrupting vehicle inspection using deep learning," Tel Aviv, 2018

    work page 2018

  50. [50]

    Deep learning based car damage classification,

    K. Patil, M. Kulkarni, A. Sriraman, and S. Karande, "Deep learning based car damage classification," in 16th IEEE Int. Conf. Machine Learning Appl. (ICMLA) , Dec. 2017, pp. 50–54, doi: 10.1109/ICMLA.2017.0-179

    work page doi:10.1109/icmla.2017.0-179 2017

  51. [51]

    UVeye Vehicle Inspection Systems - Smart Mobility,

    "UVeye Vehicle Inspection Systems - Smart Mobility,” UVeye - Vehicle inspection systems." https://www.uveye.com/smart-mobility/ (accessed Feb. 25, 2019)

    work page 2019

  52. [52]

    An Anti-fraud System for Car Insurance Claim Based on Visual Evidence

    P. Li, B. Shen, and W. Dong, "An anti -fraud system for car insurance claim based on visual evidence," arXiv preprint arXiv:1804.11207, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  53. [53]

    Driving with Data: Modeling and Forecasting Vehicle Fleet Maintenance in Detroit

    J. Gardner et al. , "Driving with data: Modeling and forecasting vehicle fleet maintenance in Detroit," arXiv preprint arXiv:1710.06839, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  54. [54]

    Anomaly detection in automobile control network data with long short-term memory networks,

    [54] A. Taylor, S. Leblanc, and N. Japkowicz, "Anomaly detection in automobile control network data with long short-term memory networks," in IEEE Int. Conf. Data Sci. Adv. Anal. (DSAA) , Oct. 2016 , pp. 130 –139, doi: 10.1109/DSAA.2016.20

    work page doi:10.1109/dsaa.2016.20 2016

  55. [55]

    New GM feature monitors vehicle functions, warns of required maintenance

    "New GM feature monitors vehicle functions, warns of required maintenance." http://asq.org/qualitynews/qnt/execute/displaySetup?ne wsID=21750 (accessed Feb. 25, 2019)

    work page 2019

  56. [56]

    Tire defects classification using convolution architecture for fast feature embedding,

    Y. Zhang, X. Cui, Y. Liu, and B. Yu, "Tire defects classification using convolution architecture for fast feature embedding," Int. J. Computational Intell. Syst., vol. 11, no. 1, pp. 1056 –1066, Ja n. 2018, doi: 10.2991/ijcis.11.1.80

    work page doi:10.2991/ijcis.11.1.80 2018

  57. [57]

    Applying neural networks for tire pressure monitoring systems,

    A. Kost, "Applying neural networks for tire pressure monitoring systems," Masters thesis, California Polytechnic State Univ., California, 2018

    work page 2018

  58. [58]

    Diagnosis of electric vehicle batteries using recurrent neural networks,

    G. You, S. Park, and D. Oh, "Diagnosis of electric vehicle batteries using recurrent neural networks," IEEE Trans. Ind. Electron., vol. 64, no. 6, pp. 4885 –4893, Jun. 2017, doi: 10.1109/TIE.2017.2674593

    work page doi:10.1109/tie.2017.2674593 2017

  59. [59]

    End to End Learning for Self-Driving Cars

    M. Bojarski et al., "End to end learning for self -driving cars," arXiv preprint arXiv:1604.07316, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  60. [60]

    End -to-end learning of driving models from large -scale video datasets,

    H. Xu, Y. Gao, F. Yu, and T. Darrell, "End -to-end learning of driving models from large -scale video datasets," in Proc. IEEE Conf. Comput. Vision Pattern Recognition, 2017

    work page 2017

  61. [61]

    End-to-end deep learning for driver distraction recognition,

    A. Koesdwiady, S. M. Bedawi, C. Ou, and F. Karray, "End-to-end deep learning for driver distraction recognition," in Image Anal. Recognition, 2017

    work page 2017

  62. [62]

    Wikipedia

    A. Ng, "Wikipedia." 08-Feb-2019

    work page 2019

  63. [63]

    Autonomous Car Development Platform | NVIDIA DRIVE AGX

    "Autonomous Car Development Platform | NVIDIA DRIVE AGX." https://www.nvidia.com/en-us/self- driving-cars/drive-platform/ (accessed Feb. 26, 2019)

    work page 2019

  64. [64]

    26262: road vehicles -functional safety, International Standard ISO/FDIS,

    ISO, "26262: road vehicles -functional safety, International Standard ISO/FDIS," 2011

    work page 2011

  65. [65]

    An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software

    R. Salay, R. Queiroz, and K. Czarnecki, "An analysis of ISO 26262: Using machine learning safely in automotive software," arXiv preprint arXiv:1709.02435, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  66. [66]

    BD D100K: A diverse driving video database with scalable annotation tooling,

    F. Yu et al. , "BD D100K: A diverse driving video database with scalable annotation tooling," arXiv preprint arXiv:1805.04687, 2018

    work page arXiv 2018

  67. [67]

    nuScenes dataset

    "nuScenes dataset." https://www.nuscenes.org/ (accessed Feb. 26, 2019)

    work page 2019

  68. [68]

    Apollo s cape

    "Apollo s cape." http://apolloscape.auto/ (accessed Feb. 26, 2019)

    work page 2019

  69. [69]

    Introducing AVS, an open standard for autonomous vehicle visualization from uber,

    "Introducing AVS, an open standard for autonomous vehicle visualization from uber," Uber Engineering Blog. https://eng.uber.com/avs-autonomous-vehicle- visualization/ (accessed Feb. 26, 2019)

    work page 2019

  70. [70]

    An Analysis of Deep Neural Network Models for Practical Applications

    A. Canziani, A. Paszke, and E. Culurciello, "An analysis of deep neural network models for practical applications," arXiv preprint arXiv:1605.07678, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  71. [71]

    DeepXplore: Automated whitebox testing of deep learning systems,

    K. Pei, Y. Cao, J. Yang, and S. Jana, "DeepXplore: Automated whitebox testing of deep learning systems," in Proc. 26th Symp. Operating Syst. Principles, Oct., 2017, pp. 1–18

    work page 2017

  72. [72]

    DeepTest: automated testing of deep -neural-network-driven autonomous cars,

    Y. Tian, K. Pei, S. Jana, and B. Ray, "DeepTest: automated testing of deep -neural-network-driven autonomous cars," in Proc. 40th Int. Conf. Software Eng., May-Jun. 2018, pp. 303–314

    work page 2018

  73. [73]

    DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing

    M. Zhang, Y. Zhang, L. Zhang, C. Liu, and S. Khurshid, "DeepRoad: GAN -based metamorphic autonomous driving system testing," arXiv preprint arXiv:1802.02295, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  74. [74]

    Squeezenext: Hardware-aware neural network design,

    A. Gholami et al., "Squeezenext: Hardware-aware neural network design," in IEEE Conf. Comput. Vision Pattern Recognition Workshops, 2018

    work page 2018

  75. [75]

    Forrest Iandola, CEO of DeepScale

    DeepScale AI, "Forrest Iandola, CEO of DeepScale." Tips and Tricks for Developing Smaller Neural Nets

    work page

  76. [76]

    Co-Design of deep neural nets and neural net accelerators for embedded vision applications

    DeepScale AI, "Co-Design of deep neural nets and neural net accelerators for embedded vision applications."

    work page

  77. [77]

    Perception systems for autonomous vehicles using efficient deep neural networks,

    "Perception systems for autonomous vehicles using efficient deep neural networks," GetLink.pro. https://getlink.pro/youtube/perception-systems-for- autonomous-vehicles-using-efficient-deep-neural- networks (accessed Mar. 03, 2019)

    work page 2019

  78. [78]

    Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1,

    M. Courbariaux, I. Hu bara, D. Soudry, R. El -Yaniv, and Y. Bengio, “Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1,” ArXiv Prepr. ArXiv160202830, 2016

    work page 2016

  79. [79]

    5 Of The Largest Car Recalls In History,

    B. DeMeter, “5 Of The Largest Car Recalls In History,” Investopedia, 22 -May-2012. [Online]. Available: https://www.investopedia.com/slide-show/car-recalls/. [Accessed: 14-Jun-2019]. AUTHOR BIOGRAPHIES KANWAR BHARAT SINGH is currently a Principal Engineer at the Goodyear Tire and Rubber Co. He received his M.S. degree in Mechanical Engineering from Virgin...

    work page 2012