1.Transformer Networks for Trajectory Forecasting
没有考虑人与人之间的交互 。
2.Vehicle Trajectory Prediction Using LSTMs With Spatial–Temporal Attention Mechanisms
从可解释性的角度出发,算出了权重
3.Vehicle Trajectory Prediction Method Coupled With Ego Vehicle Motion Trend Under Dual
Attention Mechanism
改进:输入多了本车的预测轨迹