In order to drive safely and efficiently on public roads, autonomous vehicles
will have to understand the intentions of surrounding vehicles, and adapt their
own behavior accordingly. If experienced human drivers are generally good at
inferring other vehicles' motion up to a few second
本文提出了一种基于深度学习的,可以实时生成周围车辆未来轨迹序列的车辆轨迹预测技术。通过利用编码器 - 解码器结构和使用基于长短期记忆(LSTM)的编码器分析过去轨迹中的模式,使用 LSTM 解码器生成未来轨迹序列。使用束搜索技术从解码器的输出中保留 K 个局部最优解,产生 K 个最可能的轨迹候选项。在高速公路交通场景下进行的实验表明,所提出的方法的预测精度显著高于传统的轨迹预测技术。