Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods

Semih Beycimen; Dmitry Ignatyev; Argyrios Zolotas

doi:10.1109/MFI55806.2022.9913844

Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods

Semih Beycimen, Dmitry Ignatyev, Argyrios Zolotas

Cranfield University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a study of end-to-end methods for predicting autonomous vehicle navigation parameters. Image-based and Image & Lidar points-based end-to-end models have been trained under Nvidia learning architectures as well as Densenet-169, Resnet-152 and Inception-v4. Various learning parameters for autonomous vehicle navigation, input models and pre-processing data algorithms i.e. image cropping, noise removing, semantic segmentation for image data have been investigated and tested. The best ones, from the rigorous investigation, are selected for the main framework of the study. Results reveal that the Nvidia architecture trained Image & Lidar points-based method offers the better results accuracy rate-wise for steering angle and speed.

Original language	English
Title of host publication	2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665460262
DOIs	https://doi.org/10.1109/MFI55806.2022.9913844
Publication status	Published - 2022
Externally published	Yes
Event	2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022 - Bedford, United Kingdom Duration: 20 Sept 2022 → 22 Sept 2022

Publication series

Name	IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems
Volume	2022-September

Conference

Conference	2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022
Country/Territory	United Kingdom
City	Bedford
Period	20/09/22 → 22/09/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Access to Document

10.1109/MFI55806.2022.9913844

Cite this

Beycimen, S., Ignatyev, D., & Zolotas, A. (2022). Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods. In 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022 (IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems; Vol. 2022-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MFI55806.2022.9913844

Beycimen, Semih ; Ignatyev, Dmitry ; Zolotas, Argyrios. / Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods. 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems).

@inproceedings{63d493a6148f40e687983d6a9e11cc02,

title = "Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods",

abstract = "This paper presents a study of end-to-end methods for predicting autonomous vehicle navigation parameters. Image-based and Image & Lidar points-based end-to-end models have been trained under Nvidia learning architectures as well as Densenet-169, Resnet-152 and Inception-v4. Various learning parameters for autonomous vehicle navigation, input models and pre-processing data algorithms i.e. image cropping, noise removing, semantic segmentation for image data have been investigated and tested. The best ones, from the rigorous investigation, are selected for the main framework of the study. Results reveal that the Nvidia architecture trained Image & Lidar points-based method offers the better results accuracy rate-wise for steering angle and speed.",

author = "Semih Beycimen and Dmitry Ignatyev and Argyrios Zolotas",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022 ; Conference date: 20-09-2022 Through 22-09-2022",

year = "2022",

doi = "10.1109/MFI55806.2022.9913844",

language = "English",

series = "IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022",

address = "United States",

}

Beycimen, S, Ignatyev, D & Zolotas, A 2022, Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods. in 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, vol. 2022-September, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022, Bedford, United Kingdom, 20/09/22. https://doi.org/10.1109/MFI55806.2022.9913844

Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods. / Beycimen, Semih; Ignatyev, Dmitry; Zolotas, Argyrios.
2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems; Vol. 2022-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods

AU - Beycimen, Semih

AU - Ignatyev, Dmitry

AU - Zolotas, Argyrios

PY - 2022

Y1 - 2022

N2 - This paper presents a study of end-to-end methods for predicting autonomous vehicle navigation parameters. Image-based and Image & Lidar points-based end-to-end models have been trained under Nvidia learning architectures as well as Densenet-169, Resnet-152 and Inception-v4. Various learning parameters for autonomous vehicle navigation, input models and pre-processing data algorithms i.e. image cropping, noise removing, semantic segmentation for image data have been investigated and tested. The best ones, from the rigorous investigation, are selected for the main framework of the study. Results reveal that the Nvidia architecture trained Image & Lidar points-based method offers the better results accuracy rate-wise for steering angle and speed.

AB - This paper presents a study of end-to-end methods for predicting autonomous vehicle navigation parameters. Image-based and Image & Lidar points-based end-to-end models have been trained under Nvidia learning architectures as well as Densenet-169, Resnet-152 and Inception-v4. Various learning parameters for autonomous vehicle navigation, input models and pre-processing data algorithms i.e. image cropping, noise removing, semantic segmentation for image data have been investigated and tested. The best ones, from the rigorous investigation, are selected for the main framework of the study. Results reveal that the Nvidia architecture trained Image & Lidar points-based method offers the better results accuracy rate-wise for steering angle and speed.

UR - http://www.scopus.com/inward/record.url?scp=85140987336&partnerID=8YFLogxK

U2 - 10.1109/MFI55806.2022.9913844

DO - 10.1109/MFI55806.2022.9913844

M3 - Conference contribution

AN - SCOPUS:85140987336

T3 - IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems

BT - 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022

Y2 - 20 September 2022 through 22 September 2022

ER -

Beycimen S, Ignatyev D, Zolotas A. Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods. In 2022 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems). doi: 10.1109/MFI55806.2022.9913844

Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this