access icon free Gated branch neural network for mandatory lane changing suggestion at the on-ramps of highway

© The Institution of Engineering and Technology
Received 06/01/2018, Accepted 02/07/2018, Revised 30/03/2018, Published 30/07/2018

A gated branch neural network (GBNN) is proposed for modelling mandatory lane changing (MLC) behaviour at the on-ramps of highways. It provides a core algorithm for an MLC suggestion system for advanced driver assistance systems (ADAS), where the main challenge is the trade-off between computational speed and prediction accuracy for both non-merge and merge events. The GBNN algorithm employs a gated branch based on correlation analysis, scaled exponential linear units activation function, and adaptive moment estimation optimiser. The algorithm has been evaluated using the real-world dataset of U.S. Highway 101 and Interstate 80 from Federal Highway Administration's Next Generation Simulation (NGSIM). Input features are extracted from NGSIM and pre-processed by standardisation and principal component analysis. TensorFlow framework and Python are used as the development platform. Results show that the proposed GBNN algorithm with the Pearson correlation method has values of 97.7%, 96.3%, and 0.990 for non-merge accuracy, merge accuracy, and receiver operating characteristic score, respectively. It outperforms other traditional binary classifiers for MLC applications, and is more light-weight than a convolutional neural network (AlexNet) of deep learning algorithm. Owing to its compact architecture, the GBNN provides high accuracy and efficiency, demonstrating promising usage as an MLC suggestion system in ADAS.

Inspec keywords: learning (artificial intelligence); behavioural sciences computing; optimisation; traffic engineering computing; principal component analysis; neural nets; driver information systems

Other keywords: adaptive moment estimation optimiser; correlation analysis; on-ramps-of-highway; nonmerge event; NGSIM; U.S. Highway 101; nonmerge accuracy; gated branch neural network; GBNN algorithm; U.S. Interstate 80; ADAS; Python; deep learning algorithm; mandatory lane changing behaviour modelling; Pearson correlation method; receiver operating characteristic score; MLC behaviour modelling; mandatory lane changing suggestion; Federal Highway Administration Next Generation Simulation; real-world dataset; advanced driver assistance systems; merge accuracy; TensorFlow framework; MLC suggestion system; principal component analysis; scaled exponential linear units activation function; merge event

Subjects: Knowledge engineering techniques; Other topics in statistics; Traffic engineering computing; Social and behavioural sciences computing; Neural computing techniques; Optimisation techniques

References

    1. 1)
      • 32. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, arXiv Prepr. arXiv, 2015, (1409), p. 1556v6.
    2. 2)
      • 16. Zhao, Z., Chen, W., Wu, X., et al: ‘LSTM network: a deep learning approach for short-term traffic forecast’, IET Intell. Transp. Syst., 2017, 11, (2), pp. 68–75.
    3. 3)
      • 26. Kingma, D.P., Ba, J.: ‘Adam: a method for stochastic optimization’, arXiv Prepr., 2014, (arXiv:1412.6980v9), pp. 1–15.
    4. 4)
      • 19. Henclewood, D., Suh, W., Guin, A., et al: ‘Real-time data-driven traffic simulation for performance measure estimation’, IET Intell. Transp. Syst., 2016, 10, (8), pp. 562–571.
    5. 5)
      • 29. Lambert, F.: ‘Tesla has a new autopilot ‘2.5’ hardware suite with more computing power for autonomous driving’. Available at https://electrek.co/2017/08/09/tesla-autopilot-2-5-hardware-computer-autonomous-driving/, accessed March 2018.
    6. 6)
      • 25. ‘CS231n convolutional neural networks for visual recognition’. Available at http://cs231n.github.io/.
    7. 7)
      • 6. ‘FARS encyclopedia – vehicles involved in single- and two-vehicle fatal crashes by vehicle maneuve’, 2009. Available at https://www-fars.nhtsa.dot.gov/Vehicles/VehiclesAllVehicles.aspx.
    8. 8)
      • 20. Coifman, B., Li, L.: ‘A critical evaluation of the next generation simulation (NGSIM) vehicle trajectory dataset’, Transp. Res. Part B Methodol., 2017, 105, pp. 362–377.
    9. 9)
      • 1. Dey, K.C., Yan, L., Wang, X., et al: ‘A review of communication, driver characteristics, and controls aspects of cooperative adaptive cruise control (CACC)’, IEEE Trans. Intell. Transp. Syst., 2016, 17, (2), pp. 491–509.
    10. 10)
      • 30. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, NV, United States, 2012, pp. 1097–1105.
    11. 11)
      • 7. Talebpour, A., Mahmassani, H.S., Hamdar, S.H.: ‘Modeling lane-changing behavior in a connected environment: a game theory approach’, Transp. Res. Procedia, 2015, 7, pp. 420–440.
    12. 12)
      • 3. Kim, I.-H., Bong, J.-H., Park, J., et al: ‘Prediction of driver's intention of lane change by augmenting sensor information using machine learning techniques’, Sensors, 2017, 17, (6), p. 1350.
    13. 13)
      • 8. Morton, J., Wheeler, T.A., Kochenderfer, M.J.: ‘Analysis of recurrent neural networks for probabilistic modeling of driver behavior’, IEEE Trans. Intell. Transp. Syst., 2017, 18, (5), pp. 1289–1298.
    14. 14)
      • 27. Woods, K., Bowyer, K.W.: ‘Generating ROC curves for artificial neural networks’, IEEE Trans. Med. Imaging, 1997, 16, (3), pp. 329–337.
    15. 15)
      • 4. Flanigan, M., Majka, K., Blatt, A., et al: ‘Utility of advanced driver assistance systems and connected vehicle technologies for emergency medical services: emergency event use cases in an automated and connected transportation system’. Transportation Research Board 94th Annual Meeting, Washington, DC, United States, 2015, pp. 15–5113.
    16. 16)
      • 17. ‘Next Generation Simulation Fact Sheet’. Available at https://www.fhwa.dot.gov/publications/research/operations/06137/index.cfm.
    17. 17)
      • 12. Tang, J., Liu, F., Zhang, W., et al: ‘Lane-changes prediction based on adaptive fuzzy neural network’, Expert Syst. Appl., 2018, 91, pp. 452–463.
    18. 18)
      • 21. Géron, A.: ‘Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems’ (O'Reilly Media, Sebastopol, 2017, 1st edn.).
    19. 19)
      • 11. Li, K., Wang, X., Xu, Y., et al: ‘Lane changing intention recognition based on speech recognition models’, Transp. Res. Part C Emerg. Technol., 2016, 69, pp. 497–514.
    20. 20)
      • 28. Goodfellow, I., Bengio, Y., Courville, A.: ‘Deep learning’ (MIT press, Cambridge, MA, USA, 2016).
    21. 21)
      • 14. Dou, Y., Yan, F., Feng, D.: ‘Lane changing prediction at highway lane drops using support vector machine and artificial neural network classifiers’. IEEE/ASME Int. Conf. Adv. Intell. Mechatronics, AIM, Banff, Canada, 2016, September, (86), pp. 901–906.
    22. 22)
      • 10. Kumar, P., Perrollaz, M., Laugier, C., et al: ‘Learning-based approach for online lane change intention prediction’. IEEE Intelligent Vehicles Symp. (IV), Gold Coast, Australia, 2013, pp. 797–802.
    23. 23)
      • 15. Kim, J., Kim, J., Jang, G.-J., et al: ‘Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection’, Neural Netw., 2017, 87, pp. 109–121.
    24. 24)
      • 5. Gaikwad, V., Lokhande, S.: ‘Lane departure identification for advanced driver assistance’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (2), pp. 910–918.
    25. 25)
      • 24. Klambauer, G., Unterthiner, T., Mayr, A., et al: ‘Self-normalizing neural networks’, arXiv Prepr., 2017, (arXiv:1706.02515v5), pp. 1–102.
    26. 26)
      • 9. Bahram, M., Hubmann, C., Lawitzky, A., et al: ‘A combined model- and learning-based framework for interaction-aware maneuver prediction’, IEEE Trans. Intell. Transp. Syst., 2016, 17, (6), pp. 1538–1550.
    27. 27)
      • 2. Jeannin, J.B., Ghorbal, K., Kouskoulas, Y., et al: ‘A formally verified hybrid system for safe advisories in the next-generation airborne collision avoidance system’, Int. J. Softw. Tools Technol. Transf., 2017, 19, (6), pp. 717–741.
    28. 28)
      • 13. Hou, Y., Edara, P., Sun, C.: ‘Modeling mandatory lane changing using Bayes classifier and decision trees’, IEEE Trans. Intell. Transp. Syst., 2014, 15, (2), pp. 647–655.
    29. 29)
      • 23. Friedman, J., Hastie, T., Tibshirani, R.: ‘The elements of statistical learning’ (Springer-Verlag, New York, USA, 2001).
    30. 30)
      • 18. Monteil, J., Nantes, A., Billot, R., et al: ‘Microscopic cooperative traffic flow: calibration and simulation based on a next generation simulation dataset’, IET Intell. Transp. Syst., 2014, 8, (6), pp. 519–525.
    31. 31)
      • 22. James, G., Witten, D., Hastie, T., et al: ‘An introduction to statistical learning: with applications in R’ (Springer, Springer-Verlag, New York, USA, 2017, 2017 edn.).
    32. 32)
      • 31. Szegedy, C., Liu, W., Jia, Y., et al: ‘Going deeper with convolutions’. Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 1–9.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2018.5093
Loading

Related content

content/journals/10.1049/iet-its.2018.5093
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading