期刊
IET INTELLIGENT TRANSPORT SYSTEMS
卷 14, 期 3, 页码 148-153出版社
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-its.2019.0299
关键词
road vehicles; Gaussian processes; road safety; encoding; object recognition; road traffic; traffic engineering computing; decoding; recurrent neural nets; interactive driving behaviour; multimodal vehicle trajectory prediction; mutual information; autonomous vehicles; driving intention; long short-term memory model; multimodal intention; data fusion encoder; multimodal decoder; multiLSTM; probabilistic prediction; NGSIM data set
资金
- National Natural Science Foundation of China automobile industry innovation and development joint fund project [U1664263]
- National Natural Science Foundation of China [51875302]
- National Key Research and Development Program [2018YFB1600501]
Autonomous vehicles need to have the ability to predict the motion of surrounding vehicles, which will help to avoid potential accidents and make the best decision to ensure safety and comfort. The interactions among vehicles and those between them and the uncertainty of driving intention make trajectory prediction a challenging task. This study presents a long short-term memory (LSTM) model for the task of trajectory prediction to account for both the mutual information and the multi-modal intention. The model consists of a data fusion encoder and a multi-modal decoder. The data fusion encoder summarises the mutual information by multi-LSTM with shared parameters and the multi-modal decoder generates trajectories based on driving intention. In addition, mixture density network is added to output a probabilistic prediction which improves the reliability of prediction results. NGSIM data set is used for training and testing. The results show that the proposed model can better capture the interactive driving behaviour and outperforms the state-of-the-art methods in root-weighted square error of displacement and velocity.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据