GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction

Predicting the future trajectories of pedestrians on the road is an important task for autonomous driving. The pedestrian trajectory prediction is affected by scene paths, pedestrian’s intentions and decision-making, which is a multi-modal problem. Relying solely on historical coordinates...

Full description

Saved in:
Bibliographic Details
Main Authors: Amar Fadillah, Ching-Lin Lee, Zhi-Xuan Wang, Kuan-Ting Lai
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11079594/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706433251115008
author Amar Fadillah
Ching-Lin Lee
Zhi-Xuan Wang
Kuan-Ting Lai
author_facet Amar Fadillah
Ching-Lin Lee
Zhi-Xuan Wang
Kuan-Ting Lai
author_sort Amar Fadillah
collection DOAJ
description Predicting the future trajectories of pedestrians on the road is an important task for autonomous driving. The pedestrian trajectory prediction is affected by scene paths, pedestrian’s intentions and decision-making, which is a multi-modal problem. Relying solely on historical coordinates pedestrian data represents the most straightforward method for pedestrian trajectory prediction. Nevertheless, the accuracy achieved by this method is limited, primarily because it fails to account for the crucial scene paths impacting the pedestrian. Instead of predicting the future trajectory directly, we propose to use scene context and observed trajectory to predict the goal points first, and then reuse the goal points to predict the future trajectories. By leveraging the information from scene context and observed trajectory, the uncertainty can be limited to a few target areas, which represent the “goals” of the pedestrians. In this paper, we propose GoalNet, a new trajectory prediction neural network based on the goal areas of a pedestrian. Our network can predict both pedestrian’s trajectories and bounding boxes. The overall model is efficient and modular, and its outputs can be changed according to the usage scenario. Experimental results show that GoalNet significantly improves the previous state-of-the-art performance by 48.7% on the JAAD and 40.8% on the PIE dataset.
format Article
id doaj-art-210f601daffa49d4bcfef670bbab4e57
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-210f601daffa49d4bcfef670bbab4e572025-08-20T03:16:12ZengIEEEIEEE Access2169-35362025-01-011313253713254610.1109/ACCESS.2025.358881211079594GoalNet: Goal Areas Oriented Pedestrian Trajectory PredictionAmar Fadillah0https://orcid.org/0009-0001-2979-9325Ching-Lin Lee1https://orcid.org/0009-0006-4613-6423Zhi-Xuan Wang2Kuan-Ting Lai3https://orcid.org/0000-0002-8497-1562Department of Electronic Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Electronic Engineering, National Taipei University of Technology, Taipei, TaiwanDepartment of Artificial Intelligence Technology, National Taipei University of Technology, Taipei, TaiwanDepartment of Electronic Engineering, National Taipei University of Technology, Taipei, TaiwanPredicting the future trajectories of pedestrians on the road is an important task for autonomous driving. The pedestrian trajectory prediction is affected by scene paths, pedestrian’s intentions and decision-making, which is a multi-modal problem. Relying solely on historical coordinates pedestrian data represents the most straightforward method for pedestrian trajectory prediction. Nevertheless, the accuracy achieved by this method is limited, primarily because it fails to account for the crucial scene paths impacting the pedestrian. Instead of predicting the future trajectory directly, we propose to use scene context and observed trajectory to predict the goal points first, and then reuse the goal points to predict the future trajectories. By leveraging the information from scene context and observed trajectory, the uncertainty can be limited to a few target areas, which represent the “goals” of the pedestrians. In this paper, we propose GoalNet, a new trajectory prediction neural network based on the goal areas of a pedestrian. Our network can predict both pedestrian’s trajectories and bounding boxes. The overall model is efficient and modular, and its outputs can be changed according to the usage scenario. Experimental results show that GoalNet significantly improves the previous state-of-the-art performance by 48.7% on the JAAD and 40.8% on the PIE dataset.https://ieeexplore.ieee.org/document/11079594/Pedestrianstrajectory predictionfuture trajectories
spellingShingle Amar Fadillah
Ching-Lin Lee
Zhi-Xuan Wang
Kuan-Ting Lai
GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction
IEEE Access
Pedestrians
trajectory prediction
future trajectories
title GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction
title_full GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction
title_fullStr GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction
title_full_unstemmed GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction
title_short GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction
title_sort goalnet goal areas oriented pedestrian trajectory prediction
topic Pedestrians
trajectory prediction
future trajectories
url https://ieeexplore.ieee.org/document/11079594/
work_keys_str_mv AT amarfadillah goalnetgoalareasorientedpedestriantrajectoryprediction
AT chinglinlee goalnetgoalareasorientedpedestriantrajectoryprediction
AT zhixuanwang goalnetgoalareasorientedpedestriantrajectoryprediction
AT kuantinglai goalnetgoalareasorientedpedestriantrajectoryprediction