Polynomial and Differential Networks for End-to-End Autonomous Driving

This study introduces a novel model for predicting control variables in end-to-end autonomous driving by leveraging polynomial and differential networks. Recent advancements in autonomous driving have predominantly focused on methods that incorporate additional supervisory data, such as attention me...

Full description

Saved in:
Bibliographic Details
Main Authors: Youngseong Cho, Kyoungil Lim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10971419/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850141392025681920
author Youngseong Cho
Kyoungil Lim
author_facet Youngseong Cho
Kyoungil Lim
author_sort Youngseong Cho
collection DOAJ
description This study introduces a novel model for predicting control variables in end-to-end autonomous driving by leveraging polynomial and differential networks. Recent advancements in autonomous driving have predominantly focused on methods that incorporate additional supervisory data, such as attention mechanisms and bird&#x2019;s-eye view images. However, these approaches are often hindered by issues related to computational efficiency and the high costs of data acquisition for real-world applications. In contrast, the proposed method enhances the performance by integrating polynomial and differential networks, facilitating efficient learning while accounting for the physical properties inherent in the data. The results of experiments conducted using the CARLA simulator demonstrate that the proposed model outperforms existing state-of-the-art approaches. The model weights and training code used in these experiments are available at <uri>https://github.com/choys0401/polydiff</uri>.
format Article
id doaj-art-7554c036b2d54ecba61a25ef6bbb60f6
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-7554c036b2d54ecba61a25ef6bbb60f62025-08-20T02:29:27ZengIEEEIEEE Access2169-35362025-01-0113694926949910.1109/ACCESS.2025.356266610971419Polynomial and Differential Networks for End-to-End Autonomous DrivingYoungseong Cho0https://orcid.org/0009-0004-9460-8849Kyoungil Lim1https://orcid.org/0000-0003-4829-2383Advanced Institutes of Convergence Technology, Suwon, Republic of KoreaAdvanced Institutes of Convergence Technology, Suwon, Republic of KoreaThis study introduces a novel model for predicting control variables in end-to-end autonomous driving by leveraging polynomial and differential networks. Recent advancements in autonomous driving have predominantly focused on methods that incorporate additional supervisory data, such as attention mechanisms and bird&#x2019;s-eye view images. However, these approaches are often hindered by issues related to computational efficiency and the high costs of data acquisition for real-world applications. In contrast, the proposed method enhances the performance by integrating polynomial and differential networks, facilitating efficient learning while accounting for the physical properties inherent in the data. The results of experiments conducted using the CARLA simulator demonstrate that the proposed model outperforms existing state-of-the-art approaches. The model weights and training code used in these experiments are available at <uri>https://github.com/choys0401/polydiff</uri>.https://ieeexplore.ieee.org/document/10971419/Autonomous drivingdeep learningend-to-end drivingimitation learning
spellingShingle Youngseong Cho
Kyoungil Lim
Polynomial and Differential Networks for End-to-End Autonomous Driving
IEEE Access
Autonomous driving
deep learning
end-to-end driving
imitation learning
title Polynomial and Differential Networks for End-to-End Autonomous Driving
title_full Polynomial and Differential Networks for End-to-End Autonomous Driving
title_fullStr Polynomial and Differential Networks for End-to-End Autonomous Driving
title_full_unstemmed Polynomial and Differential Networks for End-to-End Autonomous Driving
title_short Polynomial and Differential Networks for End-to-End Autonomous Driving
title_sort polynomial and differential networks for end to end autonomous driving
topic Autonomous driving
deep learning
end-to-end driving
imitation learning
url https://ieeexplore.ieee.org/document/10971419/
work_keys_str_mv AT youngseongcho polynomialanddifferentialnetworksforendtoendautonomousdriving
AT kyoungillim polynomialanddifferentialnetworksforendtoendautonomousdriving