融合动态风险图与多变量注意力机制的车辆轨迹预测模型
陈文强,冯琳越,王东丹,顾玉磊,赵轩

Vehicle trajectory prediction model integrating dynamic risk map and multivariate attention mechanism
Wenqiang CHEN,Linyue FENG,Dongdan WANG,Yulei GU,Xuan ZHAO
表 3 各模型在横、纵向意图预测上的RMSE对比
Tab.3 Comparison of RMSE across models for lateral and longitudinal intention prediction
数据集tp/sEh/mEz/m
STDANSTGAMTRGMASTDANSTGAMTRGMA
HighD10.070.030.020.120.070.05
HighD20.120.110.100.150.140.12
HighD30.240.230.190.240.220.20
HighD40.400.360.300.510.480.37
HighD50.520.470.411.141.040.70
NGSIM10.130.080.060.400.200.15
NGSIM20.230.200.160.980.750.58
NGSIM30.310.290.251.661.461.14
NGSIM40.380.370.342.542.371.84
NGSIM50.450.400.403.673.542.68