Autonomous Driving | Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction

Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction

提出了一种基于U-Net architecture和注意力的循环网络框架，增加了语义信息来预测轨迹终点。提出的算法在公开数据集SDD, inD, ETH/UCY上部分取得了SOTA的成绩，还简化了模型。

1 Introduction

Levels of multi-agent learning in autonomous driving

总结