基于时空特征与交互关系建模的换道意图预测
高帅帅,魏诚,惠飞,张竟成,宋汉辰

Lane-changing intention prediction based on spatiotemporal feature and interaction modeling
Shuaishuai GAO,Cheng WEI,Fei HUI,Jingcheng ZHANG,Hanchen SONG
表 3 输入长度为1.5 s时不同模型的性能对比
Tab.3 Performance comparison of different models with 1.5 s input length
模型类别$ P $/%$ R $/%F1 /%$ {A}_{\text{cc}} $/%
Social-LSTM
(模型A)
LK85.7890.7788.2091.64
LLC94.6192.1393.36
RLC95.0792.0393.53
ST-GCN(模型B)LK91.0493.8192.4194.86
LLC97.4194.6095.98
RLC96.3296.1796.25
Transformer(模型C)LK96.6993.3494.9896.71
LLC97.4698.5397.99
RLC96.0098.2797.12
GATv2(模型D)LK72.3077.3574.7480.39
LLC83.6284.0683.84
RLC86.2279.7682.87
Transformer-GATv2
(模型E)
LK96.3796.1796.2797.52
LLC98.2898.6498.46
RLC97.9097.7597.82