Pedestrian trajectory prediction for autonomous vehicle by integrating IA-LSTM and MSFM

Hao Chen, Chongfeng Wei, Yinhua Liu, Chuan Hu, Jushou Lu, Xi Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, pedestrian trajectory prediction is systematically explored by integrating the Intention-Attention-Long Short Term Memory Network (IA-LSTM) and Modified Social Force Model (MSFM). Firstly, a novel IA-LSTM is developed for pedestrian trajectory prediction, pedestrian intention (waiting/crossing), pedestrian-pedestrian interactions and pedestrian-vehicle interactions are considered. Secondly, a MSFM is proposed for pedestrian trajectory prediction, the influences of other pedestrians, vehicles and crosswalk boundary are taken into account. Finally, an integrated model based on the IA-LSTM and MSFM is developed. Moreover, traffic data is collected at an un- signalized crosswalk, and the parameters of the MSFM are calibrated by proposing the use of Maximum Likelihood Estimation (MLE). The experimental results indicate that the integrated model surpasses the existing methods, and the prediction accuracy is improved by more than 19%, which inspires confidence in the application of the integrated model in the autonomous vehicle field to enhance the safety of pedestrians.
Original languageEnglish
Title of host publicationProceedings of the 7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350340488
ISBN (Print)9798350340495
DOIs
Publication statusPublished - 25 Jan 2024
Event7th CAA International Conference on Vehicular Control and Intelligence 2023 - Changsha, China
Duration: 27 Oct 202329 Oct 2023

Conference

Conference7th CAA International Conference on Vehicular Control and Intelligence 2023
Abbreviated titleCVCI 2023
Country/TerritoryChina
CityChangsha
Period27/10/202329/10/2023

Fingerprint

Dive into the research topics of 'Pedestrian trajectory prediction for autonomous vehicle by integrating IA-LSTM and MSFM'. Together they form a unique fingerprint.

Cite this