基于GCN和CIL的端到端自动驾驶换道方法

doi:10.19562/j.chinasae.qcgc.2023.12.013

Abstract

Abstract:

For the lane change of autonomous driving， to solve the problems of unstable output and difficulty to extract dynamic interactive scene feature in conventional end-to-end method， an end-to-end learning method for autonomous lane change based on graph convolutional network （GCN） and conditional imitation learning （CIL） is proposed in this paper. Firstly， the dynamic interactive information of driving scenarios is aggregated in the form of graph-structured data. Secondly， the driving behavior instructions that the ego vehicle should take are output through GCN， which is then combined with CIL. The driving instructions output by GCN are taken as high-level commands for guiding CIL， and are finally mapped to underlying control actions of the vehicle with other perception data to complete autonomous lane change without collision. Experimental verification is carried out on CARLA simulation platform. The experimental results prove that the performance of this method is better than that of conventional end-to-end method， and it has better success rate and generalization performance.

Key words: intelligent vehicle, end-to-end driving, lane change, conditional imitation learning, graph convolutional network

Lü Yanzhi,Chao Wei,Yuanhao He. An End-to-End Lane Change Method for Autonomous Driving Based on GCN and CIL[J].Automotive Engineering, 2023, 45(12): 2310-2317.

Figures/Tables 9

References 20

1	MILANES V， LLORCA D F， VILLAGRA J， et al. Intelligent automatic overtaking system using vision for vehicle detection［J］. Expert Systems with Applications， 2012， 39（3）：3362-3373.
2	FLETCHER L， TELLER S， OLSON E， et al. The MIT-cornell collision and why it happened［J］. Journal of Field Robotics， 2009， 25（10）：775-807.
3	YURTSEVER E， LAMBERT J， CARBALLO A， et al. A survey of autonomous driving： common practices and emerging technologies［J］. IEEE Access， 2020， 8： 58443-58469.
4	PEREZ J， MILANES V， ONIEVA E， et al. Longitudinal fuzzy control for autonomous overtaking［C］. 2011 IEEE International Conference on Mechatronics. IEEE， 2011： 188-193.
5	LIU T， TANG X， ZHANG J， et al. Reinforcement learning-enabled decision-making strategies for a vehicle-cyber-physical-system in connected environment［J］. arXiv preprint arXiv：， 2020.
6	BOJARSKI M， DEL TESTA D， DWORAKOWSKI D， et al. End to end learning for self-driving cars［J］. arXiv preprint arXiv：， 2016.
7	ZHU L， HE Y， YU F R， et al. Communication-based train control system performance optimization using deep reinforcement learning［J］. IEEE Transactions on Vehicular Technology， 2017， 66（12）： 10705-10717.
8	KENDALL A， HAWKE J， JANZ D， et al. Learning to drive in a day［C］. 2019 International Conference on Robotics and Automation （ICRA）. IEEE， 2019： 8248-8254.
9	MIRCHEVSKA B， PEK C， WERLING M， et al. High-level decision making for safe and reasonable autonomous lane changing using reinforcement learning［C］. 2018 21st International Conference on Intelligent Transportation Systems （ITSC）. IEEE， 2018： 2156-2162.
10	ENGLERT P， PARASCHOS A， PETERS J， et al. Model-based imitation learning by probabilistic trajectory matching［C］. 2013 IEEE International Conference on Robotics and Automation. IEEE， 2013： 1922-1927.
11	GIUSTI A， GUZZI J， CIREŞAN D C， et al. A machine learning approach to visual perception of forest trails for mobile robots［J］. IEEE Robotics and Automation Letters， 2015， 1（2）： 661-667.
12	ZHANG J， CHO K. Query-efficient imitation learning for end-to-end simulated driving［C］. Proceedings of the AAAI Conference on Artificial Intelligence， 2017.
13	CODEVILLA F， MÜLLER M， LÓPEZ A， et al. End-to-end driving via conditional imitation learning［C］. 2018 IEEE international conference on robotics and automation （ICRA）. IEEE， 2018： 4693-4700.
14	MEI X， SUN Y， CHEN Y， et al. Autonomous navigation through intersections with graph convolutional networks and conditional imitation learning for self-driving cars［J］. arXiv preprint arXiv：， 2021.
15	POMERLEAU D A. Alvinn： an autonomous land vehicle in a neural network［J］. Advances in Neural Information Processing Systems， 1988， 1.
16	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks［J］. Advances in Neural Information Processing Systems， 2015， 28.
17	MANEN S， GYGLI M， DAI D， et al. Pathtrack： fast trajectory annotation with path supervision［C］. Proceedings of the IEEE International Conference on Computer Vision， 2017： 290-299.
18	KIPF T N， WELLING M. Semi-supervised classification with graph convolutional networks［J］. arXiv preprint arXiv：， 2016.
19	DOSOVITSKIY A， ROS G， CODEVILLA F， et al. CARLA： an open urban driving simulator［C］. Conference on Robot Learning. PMLR， 2017： 1-16.
20	KINGMA D P， BA J. Adam： a method for stochastic optimization［J］. arXiv preprint arXiv：， 2014.

实验方法	实验场景	实验次数	成功率/%	碰撞率/%	最优换道概率/%	平均偏移距离/m
IL（MLP）	简单	25	72	28	77.8	0.539 1
IL（MLP）	复杂	75	37.3	62.7	57.1	0.622 4
IL（GCN）	简单	25	80	20	80	0.525 8
IL（GCN）	复杂	75	48	52	58.3	0.611 7
MLP-CIL	简单	25	88	12	81.8	0.405 3
MLP-CIL	复杂	75	72	28	68.5	0.513 7
GCN-CIL （本文的方法）	简单	25	100	0	100	0.303 4
GCN-CIL （本文的方法）	复杂	75	94.7	5.3	87.3	0.339 6

[1]	Shurui Guan,Keqiang Li,Junyu Zhou,Jia Shi,Weiwei Kong,Yugong Luo. A Cooperative Lane Change Strategy for Intelligent Connected Vehicles Oriented to Mandatory Lane Change Scenarios [J]. Automotive Engineering, 2024, 46(2): 201-210.
[2]	Jianping Hao,Yanzhao Su,Zhihua Zhong,Jin Huang. Service-Oriented Architecture and Service Scheduling Mechanism for Intelligent Vehicles [J]. Automotive Engineering, 2023, 45(9): 1563-1572.
[3]	Gaoshi Zhao,Long Chen,Yingfeng Cai,Yubo Lian,Hai Wang,Qingchao Liu,Chenglong Teng. Trajectory Prediction Technology Integrating Complex Network and Memory-Augmented Network [J]. Automotive Engineering, 2023, 45(9): 1608-1616.
[4]	Lin Hu,Gen Li,Fang Wang,Miao Lin,Ning Wu. Research on Test Scenarios of Passenger Cars and Two-Wheelers at Intersections Based on CIDAS Accident Data [J]. Automotive Engineering, 2023, 45(8): 1417-1427.
[5]	Qihui Hu,Yingfeng Cai,Hai Wang,Long Chen,Zhaozhi Dong,Qingchao Liu. Heterogeneous Multi-object Trajectory Prediction Method Based on Hierarchical Graph Attention [J]. Automotive Engineering, 2023, 45(8): 1448-1456.
[6]	Shiju Pan, Jianshi Li, Hua Li, Jingtao Lou, Youchun Xu. Path Following Method of Intelligent Vehicles Based on Feedback Pure Tracking Method [J]. Automotive Engineering, 2023, 45(7): 1134-1144.
[7]	Jun Li, Wei Zhou, Shuang Tang. Lane Change and Obstacle Avoidance Trajectory Planning of Intelligent Vehicle Based on Adaptive Fitting [J]. Automotive Engineering, 2023, 45(7): 1174-1183.
[8]	Zixian Li,Shiju Pan,Yuan Zhu,Binbing He,Youchun Xu. Semi-active Suspension Control for Intelligent Vehicles Based on State Feedback and Preview Feedforward [J]. Automotive Engineering, 2023, 45(5): 735-745.
[9]	Xiang Gao,Long Chen,Xinye Wang,Xiaoxia Xiong,Yicheng Li,Yuexia Chen. Intelligent Vehicle Driving Risk Assessment Method Based on Trajectory Prediction [J]. Automotive Engineering, 2023, 45(4): 588-597.
[10]	Jie Hu,Qi Zhu,Ruipeng Chen,Minchao Zhang,Zhihao Zhang,Haoyan Liu. Global Path Planning of Intelligent Vehicle with Must-Pass Nodes [J]. Automotive Engineering, 2023, 45(3): 350-360.
[11]	Shiju Pan,Yongle Li,Zixian Li,Binbing He,Yuan Zhu,Youchun Xu. Path Following Method of Intelligent Vehicles Based on Improved Pure Tracking [J]. Automotive Engineering, 2023, 45(1): 1-8.
[12]	Shulian Zhao,Fei Lai,Keqiang Li,Tao Chen,Zhangjie Meng,Yichao Tang,Siyu Wu,Haodong Tian. Research on Intelligent Vehicle Test Method Based on Digital Twin Technology [J]. Automotive Engineering, 2023, 45(1): 42-51.
[13]	Wenbo Shao,Jun Li,Yuxin Zhang,Hong Wang. Key Technologies to Ensure the Safety of the Intended Functionality for Intelligent Vehicles [J]. Automotive Engineering, 2022, 44(9): 1289-1304.
[14]	Zihao Wang,Yingfeng Cai,Hai Wang,Long Chen,Xiaoxia Xiong. Surrounding Multi-Target Trajectory Prediction Method Based on Monocular Visual Motion Estimation [J]. Automotive Engineering, 2022, 44(9): 1318-1326.
[15]	Wang Liang,Zhaobo Qin,Liang Chen,Yougang Bian,Manjiang Hu. Longitudinal Control Method of Intelligent Vehicles Based on the Improved BP Neural Network [J]. Automotive Engineering, 2022, 44(8): 1162-1172.

An End-to-End Lane Change Method for Autonomous Driving Based on GCN and CIL

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 20

Related Articles 15

Metrics

Comments

Recommended 10