TY - GEN
T1 - Multi-Vehicles Decision-Making in Interactive Highway Exit
T2 - 17th IEEE Conference on Industrial Electronics and Applications, ICIEA 2022
AU - Gao, Xin
AU - Luan, Tian
AU - Li, Xueyuan
AU - Liu, Qi
AU - Li, Zirui
AU - Yang, Fan
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In the research of driverless decision-making, most of the current research is aimed at following, changing lanes, overtaking, and other scenarios. In this paper, algorithms and reward functions are designed to solve decision-making problems in interactive environments. An interaction and stochastic high-speed exit scenario of human-driven vehicles and autonomous vehicles (AVs) is designed. The features of the graph are directly extracted from the surrounding environment information of AVs by using the graph convolutional neural network (GCN). The steering angle and longitudinal acceleration are output through the neural network module. In addition, an exponentially increasing reward function based on driving purpose, traffic efficiency, driving comfort, and safety is designed. Moreover, this paper uses two algorithms, Graph Convolutional Deep Q-learning Network (GCN-DQN) and Graph Convolutional Double Deep Q-learning Network (GCN-DDQN), to train the driverless decision model and compare them with each other. According to simulation results, by adjusting the weight value in the reward function, the system can realize different control targets. Meanwhile, the decision-making model trained by GCN-DDQN has better performance under strong interactive random scenes than the GCN-DQN method.
AB - In the research of driverless decision-making, most of the current research is aimed at following, changing lanes, overtaking, and other scenarios. In this paper, algorithms and reward functions are designed to solve decision-making problems in interactive environments. An interaction and stochastic high-speed exit scenario of human-driven vehicles and autonomous vehicles (AVs) is designed. The features of the graph are directly extracted from the surrounding environment information of AVs by using the graph convolutional neural network (GCN). The steering angle and longitudinal acceleration are output through the neural network module. In addition, an exponentially increasing reward function based on driving purpose, traffic efficiency, driving comfort, and safety is designed. Moreover, this paper uses two algorithms, Graph Convolutional Deep Q-learning Network (GCN-DQN) and Graph Convolutional Double Deep Q-learning Network (GCN-DDQN), to train the driverless decision model and compare them with each other. According to simulation results, by adjusting the weight value in the reward function, the system can realize different control targets. Meanwhile, the decision-making model trained by GCN-DDQN has better performance under strong interactive random scenes than the GCN-DQN method.
KW - GCN-DDQN
KW - GCN-DQN
KW - Solid interactive random scenes
KW - autonomous vehicles
KW - decision-making
KW - reward function
UR - http://www.scopus.com/inward/record.url?scp=85146840596&partnerID=8YFLogxK
U2 - 10.1109/ICIEA54703.2022.10005925
DO - 10.1109/ICIEA54703.2022.10005925
M3 - Conference contribution
AN - SCOPUS:85146840596
T3 - ICIEA 2022 - Proceedings of the 17th IEEE Conference on Industrial Electronics and Applications
SP - 534
EP - 539
BT - ICIEA 2022 - Proceedings of the 17th IEEE Conference on Industrial Electronics and Applications
A2 - Xie, Wenxiang
A2 - Gao, Shibin
A2 - He, Xiaoqiong
A2 - Zhu, Xing
A2 - Huang, Jingjing
A2 - Chen, Weirong
A2 - Ma, Lei
A2 - Shu, Haiyan
A2 - Cao, Wenping
A2 - Jiang, Lijun
A2 - Shu, Zeliang
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 16 December 2022 through 19 December 2022
ER -