Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction

This paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interac...

Full description

Saved in:
Bibliographic Details
Main Author: Zikai Zhang
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7538
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060332853100544
author Zikai Zhang
author_facet Zikai Zhang
author_sort Zikai Zhang
collection DOAJ
description This paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interactions. Our primary objective is to evaluate the generalizability of the proposed model across diverse training and testing datasets. Through extensive experiments, we investigate how varying data distributions—such as different road configurations and recording times—impact the model’s prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction.
format Article
id doaj-art-5a23f185c98940ed95a69dbafc4eced6
institution DOAJ
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-5a23f185c98940ed95a69dbafc4eced62025-08-20T02:50:36ZengMDPI AGSensors1424-82202024-11-012423753810.3390/s24237538Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory PredictionZikai Zhang0Department of Computer Science, Durham University, Stockton Rd, Durham DH1 3LE, UKThis paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interactions. Our primary objective is to evaluate the generalizability of the proposed model across diverse training and testing datasets. Through extensive experiments, we investigate how varying data distributions—such as different road configurations and recording times—impact the model’s prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction.https://www.mdpi.com/1424-8220/24/23/7538machine learningdomain generalizationdriving behaviormotion forecastingtrajectory prediction
spellingShingle Zikai Zhang
Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction
Sensors
machine learning
domain generalization
driving behavior
motion forecasting
trajectory prediction
title Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction
title_full Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction
title_fullStr Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction
title_full_unstemmed Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction
title_short Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction
title_sort exploring round dataset for domain generalization in autonomous vehicle trajectory prediction
topic machine learning
domain generalization
driving behavior
motion forecasting
trajectory prediction
url https://www.mdpi.com/1424-8220/24/23/7538
work_keys_str_mv AT zikaizhang exploringrounddatasetfordomaingeneralizationinautonomousvehicletrajectoryprediction