To ensure the safe and reasonable passage of intelligent driving vehicles through uncontrolled intersections, a sequential decision-making method based on the Level-K game model was proposed. Firstly, the initial classification of vehicle reasoning levels was conducted through trajectory prediction and correlation analysis among vehicles. On this basis, the concept of sequential priority was introduced into the improved Level-K game framework to construct decision-making model for uncontrolled intersections. Secondly, to reduce unnecessary interactions among vehicles and lower the computational complexity of the decision-making model, a game start and end discrimination mechanism was proposed to dynamically screen the objects participating in the game. Meanwhile, to ensure the safety of the decision-making, a rectangular vehicle model was proposed to assess the collision risk of vehicles. Finally, the effectiveness of the proposed method was verified through experiments. The results show that the interactive decision-making method proposed can effectively avoid potential collision risks and enable intelligent driving vehicles to pass through intersections safely and reasonably.
HangP, LvC, XingY, et al. Human-like decision making for autonomous driving: a noncooperative game theoretic approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(4): 2076-2087.
[2]
ChuH Q, GuoL L, YanY J, et al. Self-learning optimal cruise control based on individual car-following style[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(10): 6622-6633.
GaoZhen-hai, SunTian-jun, HeLei. Causal inference-based decision making for longitudinal autonomous driving of vehicles[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(5): 1392-1404.
[5]
ChoiE H. Crash factors in intersection-related crashes: an on-scene perspective[R]. Washington, DC: US Dept of Transportation, National Highway Traffic Safety Administration,2010.
[6]
ShiraziM S, MorrisB T. Looking at intersections: A survey of intersection monitoring, behavior and safety analysis of recent studies[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 18(1): 4-24.
ZhuBing, JiaShi-zheng, ZhaoJian, et al. Sequential game-based human-like decision-making for autonomous vehicles considering subjective cognition[J]. Automotive Engineering, 2025, 47(1): 13-22.
[9]
LiN, YaoY, KolmanovskyI, et al. Game-theoretic modeling of multi-vehicle interactions at uncontrolled intersections[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(2): 1428-1442.
[10]
TianR, LiN, KolmanovskyI, et al. Game-theoretic modeling of traffic in unsignalized intersection network for autonomous vehicle control verification and validation[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(3): 2211-2226.
[11]
JiaS Z, ZhangY X, LiX, et al. Interactive decision-making with switchable game modes for automated vehicles at intersections[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(11): 11785-11799.
[12]
SankarG S, HanK. Adaptive robust game-theoretic decision making strategy for autonomous vehicles in highway[J]. IEEE Transactions on Vehicular Technology, 2020, 69(12): 14484-14493.
[13]
ChengJ, MeiX D, LiuM. Forecast-MAE: self-supervised pre-training for motion forecasting with masked autoencoders[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision,Paris, France, 2023: 8679-8689.
[14]
VaswaniA, ShazeerN, ParmarN, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30: 6000-6010.
[15]
LinT Y, DollárP, GirshickR, et al. Feature pyramid networks for object detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017: 2117-2125.
[16]
QiC R, SuH, MoK, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017: 652-660.
[17]
HeK M, ChenX L, XieS N, et al. Masked autoencoders are scalable vision learners[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022: 16000-16009.