Abstract
End-to-end deep reinforcement learning [1] algorithms used in autonomous car field and trained on lane-keeping task achieve good results in roads that don’t require decision making but cannot deal with situations where getting driving direction is mandatory like choosing to turn left or right in an upcoming crossroads, deciding when to leave a traffic circle or toward which path/destination to go. In this paper we introduce a new Deep Reinforcement Learning model that enable to integrate guidance commands at test time as a complementary input that indicate the right direction, that we call Deep Reinforcement Learning with guidance (DRLG), we apply the DRLG architecture on two algorithms, the asynchronous advantage actor-critic A3C and the Deep Deterministic Policy Gradient algorithm DDPG. For the training and experimentations of the new model, we adopt the CARLA virtual environment, a High-fidelity realistic driving simulator as a testbed since leading driving tests in the real world turns out to be neither safe nor affordable in term of materials and requirements. The results of testing show that DDPG and A3C with Guidance (DDPGG and A3CG) models succeed on their driving task through roads/roundabouts, by being appropriately responsive to the external commands, which allow to the autonomous car to follow the indicated route and take the right turns.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Attia, A., Dayan, S.: Global overview of imitation learning (2018). arXiv:180106503 [cs]
Bansal, M., Krizhevsky, A., Ogale, A.: ChauffeurNet: learning to drive by imitating the best and synthesizing the worst (2018). arXiv:181203079 [cs]
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L.D., Monfort, M., Muller, U., Zhang, J., Zhang, X., Zhao, J., Zieba, K.: End to end learning for self-driving cars (2016). arXiv:160407316 [cs]
Celemin, C., Ruiz-del-Solar, J.: An interactive framework for learning continuous actions policies based on corrective feedback (2018). https://doi.org/10.1007/s10846-018-0839-z
Celemin, C., Ruiz-del-Solar, J., Kober, J.: A fast hybrid reinforcement learning framework with human corrective feedback (2019). https://doi.org/10.1007/s10514-018-9786-6
Chen, C., Seff, A., Kornhauser, A., Xiao, J.: DeepDriving: learning affordance for direct perception in autonomous driving. In: 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp. 2722–2730. IEEE (2015)
Codevilla, F., MĂĽller, M., LĂłpez, A., Koltun, V., Dosovitskiy, A.: End-to-end driving via conditional imitation learning (2017). arXiv:171002410 [cs]
Dosovitskiy, A., Koltun, V.: Learning to act by predicting the future (2016). arXiv:161101779 [cs]
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator (2017). arXiv:171103938 [cs]
Fenjiro, Y., Benbrahim, H.: Deep reinforcement learning overview of the state of the art. JAMRIS 12, 20–39 (2018). https://doi.org/10.14313/JAMRIS_3-2018/15
Fridman, L., Terwilliger, J., Jenik, B.: DeepTraffic: crowdsourced hyperparameter tuning of deep reinforcement learning systems for multi-agent dense traffic navigation (2018). arXiv:180102805 [cs]
Aghdam, H.H., Heravi, E.J.: Guide to convolutional neural networks a practical application to traffic-sign detection and classification. Springer
Henein, M., Kennedy, G., Ila, V., Mahony, R.: Simultaneous localization and mapping with dynamic rigid objects (2018). arXiv:180503800 [cs]
Javaid, A.: Understanding Dijkstra algorithm. SSRN Electron. J. (2013). https://doi.org/10.2139/ssrn.2340905
Kılıç, İ., Yazıcı, A., Yıldız, Ö., Özçelikors, M., Ondoğan, A.: Intelligent adaptive cruise control system design and implementation. In: 2015 10th SoSE Conference, pp 232–237 (2015)
Kocic, J., Jovicic, N., Drndarevic, V.: Driver behavioral cloning using deep learning (2018)
Pananurak, W., Thanok, S., Parnichkun, M.: pp. 1794–1799 (2009)
Pizarro, D., Mazo, M., Santiso, E., Marron, M., Jimenez, D., Cobreces, S., Losada, C.: Localization of mobile robots using odometry and an external vision sensor. Sensors 10, 3655–3680 (2010). https://doi.org/10.3390/s100403655
Pomerleau, D.A.: ALVINN: an autonomous land vehicle in a neural network. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems 1 (1989)
Reddy, S., Dragan, A.D., Levine, S.: Shared autonomy via deep reinforcement learning (2018). arXiv:180201744 [cs]
Rosencrantz, M., Gordon, G., Thrun, S.: Decentralized sensor fusion with distributed particle filters (2012). arXiv:12122493 [cs]
Ross, S., Gordon, G.J., Bagnell, J.A.: A reduction of imitation learning and structured prediction to no-regret online learning (2010). arXiv:10110686 [cs, stat]
Sanders, P., Schultes, D.: Engineering fast route planning algorithms. In: Proceedings of the 6th International Conference on Experimental Algorithms, pp. 23–36. Springer, Berlin (2007)
Sasiadek, J., Hartana, P.: Sensor data fusion using Kalman filter (2000)
Schratter, M., Bouton, M., Kochenderfer, M.J., Watzenig, D.: Pedestrian collision avoidance system for scenarios with occlusions (2019). arXiv:190411566 [cs]
Wymann, B., Dimitrakakis, C., Sumner, A., Espie, E., Guionneau, C.: TORCS: open racing car
Zou, Q., Jiang, H., Dai, Q., Yue, Y., Chen, L., Wang, Q.: Robust lane detection from continuous driving scenes using deep neural networks (2019). arXiv:190302193 [cs]
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Youssef, F., Houda, B. (2020). Applying External Guidance Commands to Deep Reinforcement Learning for Autonomous Driving. In: Ben Ahmed, M., Boudhir, A., Santos, D., El Aroussi, M., Karas, Ä°. (eds) Innovations in Smart Cities Applications Edition 3. SCA 2019. Lecture Notes in Intelligent Transportation and Infrastructure. Springer, Cham. https://doi.org/10.1007/978-3-030-37629-1_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-37629-1_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37628-4
Online ISBN: 978-3-030-37629-1
eBook Packages: EngineeringEngineering (R0)