Abstract
The decision and control module plays a key role for autonomous driving, which is responsible for generating appropriate control commands that navigate the autonomous vehicles safely and efficiently. Existing decision and control modules for automated vehicles are mainly using a rule-based hand-engineered approach. Although working well in a number of specialized scenarios, such method shows its limitation when dealing with highly automated driving tasks such as dense urban scenarios. Recent advances in artificial intelligence have inspired a line of works about self-learning based decision and control, which enable self-reinforcement of the control policy to potentially super-human performance. In this chapter, we will introduce how to appropriately apply such techniques to automated vehicles. The chapter will begin with the motivations and basics, followed by the key challenges and recent achievements of self-learning decision and control for automated vehicles, focusing on the following key aspects: scalability, performance, interpretability, mixed-model, and emergency handling.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bojarski M, Yeres P, Choromanska A, Choromanski K, Firner B, Jackel L, Muller U (2017) Explaining how a deep neural network trained with end-to-end learning steers a car. arXiv preprint arXiv:1704.07911
Chen J, Li SE, Tomizuka M (2021) Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning. IEEE Trans Intell Transp Syst
Chen J, Wang Z, Tomizuka M (2018) Deep hierarchical reinforcement learning for autonomous driving with distinct behaviors. In: 2018 IEEE intelligent vehicles symposium (IV). IEEE, pp 1239–1244
Chen J, Yuan B, Tomizuka M (2019) Model-free deep reinforcement learning for urban autonomous driving. In: 2019 IEEE intelligent transportation systems conference (ITSC). IEEE, pp 2765–2771
Duan J, Guan Y, Li SE, Ren Y, Sun Q, Cheng B (2021) Distributional soft actor-critic: off-policy reinforcement learning for addressing value estimation errors. IEEE Trans Neural Netw Learn Syst
Duan J, Li SE, Guan Y, Sun Q, Cheng B (2020) Hierarchical reinforcement learning for self-driving decision-making without reliance on labelled driving data. IET Intell Transp Syst 14(5):297–305
Duan J, Yu D, Li SE, Wang W, Ren Y, Lin Z, Cheng B (2021) Fixed-dimensional and permutation invariant state representation of autonomous driving. arXiv preprint arXiv:2105.11299
Emuna R, Borowsky A, Biess A (2020) Deep reinforcement learning for human-like driving policies in collision avoidance tasks of self-driving cars. arXiv preprint arXiv:2006.04218
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning. PMLR, pp 1126–1135
Fujimoto S, van Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477
Gu Z, Yang Y, Duan J, Li SE, Chen J, Cao W, Zheng S (2021) Belief state separated reinforcement learning for autonomous vehicle decision making under uncertainty. In: 2021 IEEE 24th international conference on intelligent transportation systems (ITSC), pp 1–7
Guan Y, Li SE, Duan J, Li J, Ren Y, Sun Q, Cheng B (2019) Direct and indirect reinforcement learning. Int J Intell Syst
Guan Y, Li SE, Duan J, Wang W, Cheng B (2018) Markov probabilistic decision making of self-driving cars in highway with random traffic flow: a simulation study. J Intell Connected Veh
Guan Y, Ren Y, Li SE, Sun Q, Luo L, Li K (2020) Centralized cooperation for connected and automated vehicles at intersections by proximal policy optimization. IEEE Trans Veh Technol 69(11):12597–12608
Guan Y, Ren Y, Sun Q, Li SE, Ma H, Duan J, Dai Y, Cheng B (2021) Integrated decision and control: towards interpretable and computationally efficient driving intelligence. arXiv preprint arXiv:2103.10290
Guo J, Kurup U, Shah Mohak (2019) Is it safe to drive? An overview of factors, metrics, and datasets for driveability assessment in autonomous driving. IEEE Trans Intell Transp Syst 21(8):3135–3151
Haarnoja T, Tang H, Abbeel P, Levine S (2017) Reinforcement learning with deep energy-based policies. In: Proceedings of the 34th international conference on machine learning, vol 70, pp 1352–1361. (JMLR-organization)
Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290
Haarnoja T, Zhou A, Hartikainen K, Tucker G, Ha S, Tan J, Kumar V, Zhu H, Gupta A, Abbeel P et al (2018) Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905
Hafner D, Lillicrap T, Fischer I, Villegas R, Ha D, Lee H, Davidson J (2018) Learning latent dynamics for planning from pixels. arXiv preprint arXiv:1811.04551
Hafner D, Lillicrap T, Fischer I, Villegas R, Ha D, Lee H, Davidson J (2019) Learning latent dynamics for planning from pixels. In: International conference on machine learning, pp 2555–2565. PMLR
Hou L, Xin L, Li SE, Cheng B, Wang W (2019) Interactive trajectory prediction of surrounding road users for autonomous driving using structural-LSTM network. IEEE Trans Intell Transp Syst 21(11):4615–4625
Kahn G, Villaflor A, Pong V, Abbeel P, Levine S (2017) Uncertainty-aware reinforcement learning for collision avoidance. arXiv preprint arXiv:1702.01182
Kim J, Canny J (2017) Interpretable learning for self-driving cars by visualizing causal attention. In Proceedings of the IEEE international conference on computer vision, pp. 2942–2950
Kong Y, Guan Y, Duan J, Li SE, Sun Q, Nie B (2021) Decision-making under on-ramp merge scenarios by distributional soft actor-critic algorithm. arXiv preprint arXiv:2103.04535
Krishnan RG, Shalit U, Sontag D (2015) Deep kalman filters. arXiv preprint arXiv:1511.05121
Lee AX, Nagabandi A, Abbeel P, Levine S (2019) Stochastic latent actor-critic: deep reinforcement learning with a latent variable model. arXiv preprint arXiv:1907.00953
Levine S (2018) Reinforcement learning and control as probabilistic inference: tutorial and review. arXiv preprint arXiv:1805.00909
Li G, Li SE, Cheng B, Green P (2017) Estimation of driving style in naturalistic highway traffic using maneuver transition probabilities. Transp Res Part C Emerg Technol 74:113–125
Li Shengbo, Li Keqiang, Rajamani Rajesh, Wang Jianqiang (2010) Model predictive multi-objective vehicular adaptive cruise control. IEEE Trans Control Syst Technol 19(3):556–566
Li SE (2020) Reinforcement learning and control. Tsinghua University: Lecture Notes. http://www.idlab-tsinghua.com/thulab/labweb/publications.html
Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971
Lu X-Y, Wang J, Li SE, Zheng Y (2014) Multiple-vehicle longitudinal collision mitigation by coordinated brake control. Math Probl Eng 2014
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529
Mu Y, Li SE, Liu C, Sun Q, Nie B, Cheng B, Peng B (2020) Mixed reinforcement learning with additive stochastic uncertainty. arXiv preprint arXiv:2003.00848
Yao Mu, Baiyu Peng, Ziqing Gu, Shengbo Eben Li, Chang Liu, Bingbing Nie, Jianfeng Zheng, and Bo Zhang. Mixed reinforcement learning for efficient policy optimization in stochastic environments. In: 2020 20th international conference on control, automation and systems (ICCAS). IEEE, pp 1212–1219
Peng B, Mu Y, Duan J, Guan Y, Li SE, Chen J (2021) Separated proportional-integral lagrangian for chance constrained reinforcement learning. arXiv preprint arXiv:2102.08539
Peng B, Mu Y, Guan Y, Li SE, Yin Y, Chen J (2020) Model-based actor-critic with chance constraint for stochastic system. arXiv preprint arXiv:2012.10716 2020
Ren Y, Duan J, Li SE, Guan Y, Sun Q (2020) Improving generalization of reinforcement learning with minimax distributional soft actor-critic. In: 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC). IEEE, pp 1–6
Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: International conference on machine learning, pages 1889–1897
Shengbo LI, Yang G, Lian HOU, Hongbo GAO , Jingliang DUAN , Shuang LIANG , WANG Yu, CHENG Bo, LIÂ Keqiang, REN Wei et al (2019) Key technique of deep neural network and its applications in autonomous driving. J Autom Saf Energy 10(2):119
Sutton RS, Szepesvári C, Geramifard A, Bowling MP (2012) Dyna-style planning with linear function approximation and prioritized sweeping. arXiv preprint arXiv:1206.3285
Urmson C, Anhalt J, Bagnell D, Baker C, Bittner R, Clark MN, Dolan J, Duggins D, Galatali T, Geyer C et al (2008) Autonomous driving in urban environments: boss and the urban challenge. J Field Robot 25(8):425–466
Wen L, Duan J, Li SE, Xu S, Peng H (2020) Safe reinforcement learning for autonomous vehicles through parallel constrained policy optimization. In: 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC). IEEE, pp 1–7
Xin L, Kong Y, Li SE, Chen J, Guan Y, Tomizuka M, Cheng B (2021) Enable faster and smoother spatio-temporal trajectory planning for autonomous vehicles in constrained dynamic environment. Proc Inst Mech Eng Part D J Autom Eng 235(4):1101–1112
Yin Y, Li SE, Li K, Yang J, Ma F (2020) Self-learning drift control of automated vehicles beyond handling limit after rear-end collision. Transp Saf Environ 2(2):97–105
Zhang F, Gonzales J, Li SE, Borrelli F, Li K (2018) Drift control for cornering maneuver of autonomous vehicles. Mechatronics 54:167–174
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Chen, J., Duan, J., Guan, Y., Sun, Q., Yin, Y., Li, S.E. (2023). Self-learning Decision and Control for Highly Automated Vehicles. In: Murphey, Y.L., Kolmanovsky, I., Watta, P. (eds) AI-enabled Technologies for Autonomous and Connected Vehicles. Lecture Notes in Intelligent Transportation and Infrastructure. Springer, Cham. https://doi.org/10.1007/978-3-031-06780-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-06780-8_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06779-2
Online ISBN: 978-3-031-06780-8
eBook Packages: EngineeringEngineering (R0)