arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.06338cs.LG
收藏

基于LSTM编解码器结构的车辆轨迹序列到序列预测

Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture

Hanyang University(汉阳大学)

Seong Hyeon Park, ByeongDo Kim, Chang Mook Kang, Chung Choo Chung, Jun Won Choi

摘要:

本文提出了一种基于深度学习的车辆轨迹预测技术,可以实时的生成周围车辆的未来轨迹序列。我们采用编码器-解码器架构,该架构使用基于长短期记忆(LSTM)的编码器来分析过去轨迹中潜在的模式,并使用基于LSTM的解码器来生成未来轨迹序列。该结构通过采用波束搜索技术在占用栅格地图上产生$K$最可能的轨迹候选,该波束搜索技术保持来自解码器输出的$K$局部最佳候选。高速公路交通场景的实验表明,该方法的预测精度显着高于传统的轨迹预测技术。

英文摘要:

In this paper, we propose a deep learning based vehicle trajectory prediction technique which can generate the future trajectory sequence of surrounding vehicles in real time. We employ the encoder-decoder architecture which analyzes the pattern underlying in the past trajectory using the long short-term memory (LSTM) based encoder and generates the future trajectory sequence using the LSTM based decoder. This structure produces the $K$ most likely trajectory candidates over occupancy grid map by employing the beam search technique which keeps the $K$ locally best candidates from the decoder output. The experiments conducted on highway traffic scenarios show that the prediction accuracy of the proposed method is significantly higher than the conventional trajectory prediction techniques.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑