Abstract
Conditional imitation learning provides an efficient framework for autonomous driving, in which a driving policy is learned from human demonstration via mapping from sensor data to vehicle controls, and the navigation command is added to make the driving policy controllable. Navigation command matching is the key to ensuring the controllability of the driving policy model. However, the vehicle control parameters output by the model may not coincide with navigation commands, which means that the model performs incorrect behavior. To address the mismatching problem, we propose a stochastic navigation command matching (SNCM) method. Firstly, we use a multi-branch convolutional neural network to predict actions. Secondly, to generate the probability distributions of actions that are used in SNCM, a memory mechanism is designed. The generated probability distributions are then compared with the prior probability distributions under each navigation command to get matching error. Finally, the loss function weighted by matching and demonstration error is backpropagated to optimize the driving policy model. The significant performance improvement of the proposed method compared with the related works has been verified on the CARLA benchmark.
This work is supported by the National Natural Science Foundation of China Projects 62036008.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Urmson, C., et al.: Autonomous driving in urban environments: boss and the urban challenge. J. Field Robot. 25(8), 425–466 (2008)
Montemerlo, M., et al.: Junior: the Stanford entry in the urban challenge. J. Field Robot. 25(9), 569–597 (2008)
Bohren, J., et al.: Little Ben: the Ben Franklin racing team’s entry in the 2007 Darpa urban challenge. J. Field Robot. 25(9), 598–614 (2008)
Bacha, A., et al.: Odin: team VictorTango’s entry in the Darpa urban challenge. J. Field Robot. 25(8), 467–492 (2008)
Liang, X., Wang, T., Yang, L., Xing, E.: CIRL: controllable imitative reinforcement learning for vision-based self-driving. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 604–620. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_36
Tai, L., Yun, P., Chen, Y., Liu, C., Ye, H., Liu, M.: Visual-based autonomous driving deployment from a stochastic and uncertainty-aware perspective. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2622–2628. IEEE (2019)
Cultrera, L., Seidenari, L., Becattini, F., Pala, P., Del Bimbo, A.: Explaining autonomous driving by learning end-to-end visual attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 340–341 (2020)
Pan, Y., Xue, J., Zhang, P., Ouyang, W., Fang, J., Chen, X.: Navigation command matching for vision-based autonomous driving. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 4343–4349. IEEE (2020)
Codevilla, F., Müller, M., López, A., Koltun, V., Dosovitskiy, A.: End-to-end driving via conditional imitation learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 4693–4700. IEEE (2018)
Bojarski, M., et al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)
Xu, H., Gao, Y., Yu, F., Darrell, T.: End-to-end learning of driving models from large-scale video datasets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2174–2182 (2017)
Osa, T., Pajarinen, J., Neumann, G., Bagnell, J.A., Abbeel, P., Peters, J.: An algorithmic perspective on imitation learning. arXiv preprint arXiv:1811.06711 (2018)
Pan, Y., et al.: Agile autonomous driving using end-to-end deep imitation learning. arXiv preprint arXiv:1709.07174 (2017)
Muller, U., Ben, J., Cosatto, E., Flepp, B., Cun, Y.L.: Off-road obstacle avoidance through end-to-end learning. In: Advances in Neural Information Processing Systems, pp. 739–746. Citeseer (2006)
Song, S., Hu, X., Yu, J., Bai, L., Chen, L.: Learning a deep motion planning model for autonomous driving. In: IEEE Intelligent Vehicles Symposium (IV), pp. 1137–1142. IEEE (2018)
Jiang, H., Chang, L., Li, Q., Chen, D.: Deep transfer learning enable end-to-end steering angles prediction for self-driving car. In: IEEE Intelligent Vehicles Symposium (IV), pp. 405–412. IEEE (2020)
Li, Z., Motoyoshi, T., Sasaki, K., Ogata, T., Sugano, S.: Rethinking self-driving: multi-task knowledge for better generalization and accident explanation ability. arXiv preprint arXiv:1809.11100 (2018)
Sauer, A., Savinov, N., Geiger, A.: Conditional affordance learning for driving in urban environments. In: Conference on Robot Learning, pp. 237–252 (2018)
Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: an open urban driving simulator. In: Conference on Robot Learning, pp. 1–16. PMLR (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Meng, X., Xue, J., Zhao, K., Li, G., Wu, M. (2022). Stochastic Navigation Command Matching for Imitation Learning of a Driving Policy. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13536. Springer, Cham. https://doi.org/10.1007/978-3-031-18913-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-18913-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18912-8
Online ISBN: 978-3-031-18913-5
eBook Packages: Computer ScienceComputer Science (R0)