Trajectory of Prediction of Immediate Surroundings for Autonomous Vehicles Using Hierarchical Deep Learning Model

Pei Yun Hsu, Mei Lin Huang, Hsin Han Chiang*

*Corresponding author for this work

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

Abstract

A predicting model based on long-short-term-memory (LSTM) and gated recurrent unit (GRU) is proposed to assist autonomous vehicles (AVs) to drive safely. To understand the behaviors of surroundings under a mixed scene of vehicles, bicycles, and pedestrians, the proposed model can predict the future trajectory of each object with models constructed by GRU. Since different objects have diverse behaviors, this paper applies different models to different categories for vehicles, pedestrians, and cyclists. For each object, the proposed model considers three observed trajectories with different time steps as the input data to predict a more accurate future trajectory. The proposed model is verified and compared with LSTM and GRU on KITTI dataset in the conducted experiments.

Original languageEnglish
Title of host publication2nd IEEE Eurasia Conference on IOT, Communication and Engineering 2020, ECICE 2020
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages263-266
Number of pages4
ISBN (Electronic)9781728180601
DOIs
Publication statusPublished - 2020 Oct 23
Event2nd IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2020 - Yunlin, Taiwan
Duration: 2020 Oct 232020 Oct 25

Publication series

Name2nd IEEE Eurasia Conference on IOT, Communication and Engineering 2020, ECICE 2020

Conference

Conference2nd IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2020
Country/TerritoryTaiwan
CityYunlin
Period2020/10/232020/10/25

Keywords

  • autonomous vehicles (AVs)
  • deep learning
  • GRU
  • trajectory prediction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Biomedical Engineering
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Instrumentation

Fingerprint

Dive into the research topics of 'Trajectory of Prediction of Immediate Surroundings for Autonomous Vehicles Using Hierarchical Deep Learning Model'. Together they form a unique fingerprint.

Cite this