Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-agent Reinforcement Learning for Cooperative Lane Changing of Connected and Autonomous Vehicles in Mixed Traffic (2111.06318v2)

Published 11 Nov 2021 in cs.LG and cs.MA

Abstract: Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL), a powerful data-driven control method, has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic network (MA2C) is developed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is proposed to incorporate fuel efficiency, driving comfort, and safety of autonomous driving. Comprehensive experimental results, conducted under three different traffic densities and various levels of human driver aggressiveness, show that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety and driver comfort.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Trans. Intell. Veh., 1(1):33–55, 2016.
  2. Minimizing the disruption of traffic flow of automated vehicles during lane changes. IEEE Trans. Intell. Transp. Syst., 16(3):1249–1258, 2015.
  3. A cooperative lane change model for connected and automated vehicles. IEEE Access, 8:54940–54951, 2020.
  4. Autonomous driving using safe reinforcement learning by incorporating a regret-based human lane-changing decision model. In American Control Conference (ACC), pages 4355–4361, 2020.
  5. Continuous control for automated lane change behavior based on deep deterministic policy gradient algorithm. In IEEE Intelligent Vehicles Symposium (IV), pages 1454–1460, 2019.
  6. Efficient motion planning for automated lane change based on imitation learning and mixed-integer optimization. In 23rd International Conference on Intelligent Transportation Systems (ITSC), pages 1–6, 2020.
  7. Harmonious lane changing via deep reinforcement learning. IEEE Trans. Intell. Transp. Syst., 2021.
  8. A cooperative control framework for CAV lane change in a mixed traffic environment. CoRR, abs/2010.05439, 2020.
  9. Automated speed and lane change decision making using deep reinforcement learning. In Wei-Bin Zhang, Alexandre M. Bayen, Javier J. Sánchez Medina, and Matthew J. Barth, editors, 21st International Conference on Intelligent Transportation Systems (ITSC), pages 2148–2155, 2018.
  10. Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nat., 575(7782):350–354, 2019.
  11. Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans. Intell. Transp. Syst., 21(3):1086–1095, 2020.
  12. Efficient large-scale fleet management via multi-agent deep reinforcement learning. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1774–1783, 2018.
  13. Safe, multi-agent, reinforcement learning for autonomous driving. CoRR, abs/1610.03295, 2016.
  14. Multi-agent graph reinforcement learning for connected automated driving. In Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
  15. Leveraging the capabilities of connected and autonomous vehicles and multi-agent reinforcement learning to mitigate highway bottleneck congestion. CoRR, abs/2010.05436, 2020.
  16. Praveen Palanisamy. Multi-agent connected autonomous driving using deep reinforcement learning. In International Joint Conference on Neural Networks (IJCNN), pages 1–7, 2020.
  17. Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles. Comput. Aided Civ. Infrastructure Eng., 36(7):838–857, 2021.
  18. Lane change algorithm for autonomous vehicles via virtual curvature method. Journal of advanced Transportation, 43(1):47–70, 2009.
  19. If, when, and how to perform lane change maneuvers on highways. IEEE Intell. Transp. Syst. Mag., 8(4):68–78, 2016.
  20. Lane change maneuvers for automated vehicles. IEEE Intell. Transp. Syst. Mag., 18(5):1087–1096, 2016.
  21. Attention-based hierarchical deep reinforcement learning for lane change behaviors in autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 137–145, 2019.
  22. A drl-based multiagent cooperative control framework for CAV networks: a graphic convolution Q network. CoRR, abs/2010.05437, 2020.
  23. Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic. CoRR, abs/2105.05701, 2021.
  24. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations (ICLR), 2017.
  25. Playing atari with deep reinforcement learning. CoRR, abs/1312.5602, 2013.
  26. Matthijs TJ Spaan. Partially observable markov decision processes. In Reinforcement Learning, pages 387–414. Springer Verlag, 2012.
  27. Asynchronous methods for deep reinforcement learning. In International conference on machine learning (ICML), pages 1928–1937, 2016.
  28. Parameter sharing reinforcement learning architecture for multi agent driving behaviors. CoRR, abs/1811.07214, 2018.
  29. Longitudinal position control for highway on-ramp merging: A multi-agent approach to automated driving. In 22nd IEEE Intelligent Transportation Systems Conference (ITSC), pages 3461–3468, 2019.
  30. B-GAP: behavior-guided action prediction for autonomous navigation. CoRR, abs/2011.03748, 2020.
  31. Multi-agent reinforcement learning for networked system control. In 8th International Conference on Learning Representations (ICLR), 2020.
  32. Reinforcement learning: An introduction. MIT press, 2018.
  33. Congested traffic states in empirical observations and microscopic simulations. Physical Review E, 62:1805–1824, 2000.
  34. Connectivity statistics of store-and-forward intervehicle communication. IEEE Trans. Intell. Transp. Syst., 11(1):172–181, 2010.
  35. Edouard Leurent. An environment for autonomous driving decision-making. https://github.com/eleurent/highway-env, 2018.
  36. Foundations of deep reinforcement learning: theory and practice in Python. Addison-Wesley Professional, 2019.
  37. Towards safe control of continuum manipulator using shielded multiagent reinforcement learning. IEEE Robotics Autom. Lett., 6(4):7461–7468, 2021.
  38. Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett, editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NeurIPS), pages 5279–5288, 2017.
  39. Proximal policy optimization algorithms. CoRR, abs/1707.06347, 2017.
  40. Trust region policy optimization. In International conference on machine learning (ICML), pages 1889–1897, 2015.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Wei Zhou (308 papers)
  2. Dong Chen (218 papers)
  3. Jun Yan (247 papers)
  4. Zhaojian Li (60 papers)
  5. Huilin Yin (14 papers)
  6. Wanchen Ge (1 paper)
Citations (61)
View on Semantic Scholar