Abstract
This study looks at the facilitation of computer vision and machine learning, which helps Autonomous vehicles (AVs) make pertinent decisions before entering a roundabout. A deep learning-based decision-making system (DBDM) is proposed in order to make a correct “Enter” or “Wait” decision when an AV enters a roundabout. In this regard, videos of human drivers negotiating different normal roundabouts, differing in terms of size, are employed alongside a range of different learning algorithms (e.g. VGG-16, Resnet-50 and Xception). In total, 130 videos captured at normal roundabouts were used to test the models, and VGG-16 performed best with an accuracy rate of 92.57% comparing with pervious work (GBIPA-SC-NR), thus suggesting that the proposed DBDM method can be applied effectively for AVs.
Supported by Loughborough University.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adler, B., Xiao, J., Zhang, J.: Autonomous exploration of urban environments using unmanned aerial vehicles. J. Field Robot. 31(6), 912–939 (2014)
Gonzalez, D., Pérez, J., Milanés, V.: Parametric-based path generation for automated vehicles at roundabouts. Expert Syst. Appl. 71, 332–341 (2017)
Gritschneder, F., Hatzelmann, P., Thom, M., Kunz, F., Dietmayer, K.: Adaptive learning based on guided exploration for decision making at roundabouts. In 2016 IEEE Intelligent Vehicles Symposium (IV), pp. 433–440. IEEE (2016)
Hassannejad, H., Medici, P., Cardarelli, E., Cerri, P.: Detection of moving objects in roundabouts based on a monocular system. Expert Syst. Appl. 42(9), 4167–4176 (2015)
Liu, C., et al.: Beyond pixels: exploring new representations and applications for motion analysis. PhD Thesis, Massachusetts Institute of Technology (2009)
Okumura, B., et al.: Challenges in perception and decision making for intelligent automotive vehicles: a case study. IEEE Trans. Intell. Veh. 1(1), 20–32 (2016)
Rodrigues, M., McGordon, A., Gest, G., Marco, J.: Autonomous navigation in interaction-based environments—a case of non-signalized roundabouts. IEEE Trans. Intell. Veh. 3(4), 425–438 (2018)
Wang, W., Meng, Q., Chung, P.W.H.: Camera based decision making at roundabouts for autonomous vehicles. In 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 1460–1465. IEEE (2018)
Wang, W., Nguyen, Q.A., Ma, W., Wei, J., Chung, P.W.H., Meng, Q.: Multi-grid based decision making at roundabout for autonomous vehicles. In: 2019 IEEE International Conference of Vehicular Electronics and Safety (ICVES), pp. 1–6. IEEE (2019)
Ziegler, J., et al.: Making bertha drive—an autonomous journey on a historic route. IEEE Intell. Transp. Syst. Mag. 6(2), 8–20 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, W., Jiang, L., Lin, S., Fang, H., Meng, Q. (2020). Deep Learning-Based Decision Making for Autonomous Vehicle at Roundabout. In: Mohammad, A., Dong, X., Russo, M. (eds) Towards Autonomous Robotic Systems. TAROS 2020. Lecture Notes in Computer Science(), vol 12228. Springer, Cham. https://doi.org/10.1007/978-3-030-63486-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-63486-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63485-8
Online ISBN: 978-3-030-63486-5
eBook Packages: Computer ScienceComputer Science (R0)