Trajectory prediction for intelligent vehicles using spatial‐attention mechanism. Issue 13 (6th January 2021)

• Record Type: Journal Article
• Authors: Yan, Jun; Peng, Zifeng; Yin, Huilin; Wang, Jie; Wang, Xiao; Shen, Yuesong; Stechele, Walter; Cremers, Daniel
• Is Part Of: IET intelligent transport systems. Volume 14:Issue 13(2020)
• Page Start: 1855
• Page End: 1863
• Publication Date: 2021-01-06
• Subjects: road vehicles -- learning (artificial intelligence) -- traffic engineering computing -- mean square error methods -- decoding; trajectory prediction -- intelligent vehicles -- spatial‐attention mechanism -- autonomous vehicles -- safe trajectory -- interaction aware prediction methods -- previous trajectories -- sequence‐to‐sequence prediction problem -- LSTM encoder–decoder framework -- context attention -- lane attention -- Spatial‐attention mechanisms -- selective‐attention mechanism -- prediction accuracy; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2020.0274
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : It is of great interest for autonomous vehicles to predict the trajectory of other vehicles when planning a safe trajectory. To accurately predict the trajectory of the target vehicle, the interaction between vehicles must be considered. Interaction aware prediction methods track the previous trajectories of both the target vehicle and its surrounding vehicles. In this study, the authors consider trajectory prediction as a sequence‐to‐sequence prediction problem. They tackle this problem with an LSTM encoder–decoder framework. Moreover, they propose two spatial‐attention mechanisms to account for the interaction between vehicles, i.e. context attention and lane attention. Spatial‐attention mechanisms adopt the selective‐attention mechanism of human drivers. They choose context vectors to help the model understand the surrounding environment better and thus improve its prediction accuracy. They evaluate the authors' methods on the highD data set recorded in German highways with root mean squared error metric. Their experimental results show superior performance to other state‐of‐the‐art methods. Code is available at https://github.com/momo1986/Spatial‐attention .