Abstract
While optimization-based approaches still enjoy mainstream appeal in solving motion planning and control problems, learning-based approaches have become increasingly popular with recent developments in artificial intelligence. Even though current state-of-the-art learning-based approaches to planning and control have their limitations, we feel they will become extremely important in the future and that, as technical trends, they should not be overlooked. More particularly, reinforcement learning has been widely used in solving problems that take place in the form of rounds or time steps with stepwise guiding information such as rewards. Therefore, it has been experimented with as a methodology to solve different levels of autonomous driving planning and control problems. We thus conclude that reinforcement learning-based planning and control will gradually become a viable solution to autonomous driving planning and control problems or at least become a necessary complement to current optimization approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Shai, S-S., Ben-Zrihem, N., Cohen, A., and Shashua, A. 2016. Long-term Planning by Short-term Prediction. arXiv preprint arXiv:1602.01580. 143, 145, 156
Gómez, M., González, R. V., MartÃnez-MarÃn T., Meziat D., and Sánchez S. 2012. Optimal motion planning by reinforcement learning in autonomous mobile vehicles. Robotica, 30(2), pp. 159–70. DOI: https://doi.org/10.1017/S0263574711000452. 143, 145, 155
Shalev-Shwartz, S., Shammah, S., and Shashua, A. 2016. Safe, Multi-agent, Reinforcement Learning for Autonomous Driving. arXiv preprint arXiv:1610.03295. 143, 144, 154
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller M. 2013. Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602. 151
Katrakazas, C., Quddus, M., Chen, W-H., and Deka, L. 2015. Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions. Elsevier Transporation Research Park C: Emerging Technologies, 60, pp. 416‒442 DOI: 10.1016/j.trc.2015.09.011. 143
Paden, B., Cap, M., Yong, S. Z., Yershow, D., and FrazzoloE. 2016. A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Transactions on Intelligent Vehicles, 1(1), pp. 33–55. DOI: https://doi.org/10.1109/TIV.2016.2578706. 143
Sutton, R. S. and Barto, A. G. 1998. Reinforcement Learning: An Introduction. Cambridge: MIT Press. 147
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., and Zhang, X. 2016. End to End Learning for Self-driving Cars. arXiv preprint arXiv:1604.07316. 143, 153
Geng, X., Liang, H., Yu, B., Zhao, P., He, L., and Huang, R. 2017. A scenario-adaptive driving behavior prediction approach to urban autonomous driving. Applied Sciences, 7(4), p. 426. DOI: https://doi.org/10.3390/app7040426. 143, 144
SAE Levels of Driving Automation. https://www.sae.org/misc/pdfs/automated_driving.pdf. 144
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., and Kavukcuoglu, K. 2016. Asynchronous methods for deep reinforcement learning. In International Conference on Machine Learning (pp. 1928‒1937). 152
https://github.com/awjuliani/DeepRL-Agents/blob/master/A3C-Doom.ipynb.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Liu, S., Li, L., Tang, J., Wu, S., Gaudiot, JL. (2020). Reinforcement Learning-Based Planning and Control. In: Creating Autonomous Vehicle Systems. Synthesis Lectures on Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-031-01805-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-01805-3_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-00677-7
Online ISBN: 978-3-031-01805-3
eBook Packages: Synthesis Collection of Technology (R0)eBColl Synthesis Collection 7eBColl Synthesis Collection 10