Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module

Yuru Li; Dongliang Duan; Chen Chen; Xiang Cheng; Liuqing Yang

doi:10.1109/WCNC45663.2020.9120722

Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module

Yuru Li, Dongliang Duan, Chen Chen, Xiang Cheng, Liuqing Yang

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

Abstract

For autonomous driving of unmanned vehicles in intelligent transportation systems, multi-vehicle cooperative perception supported by vehicular networks can greatly improve the accuracy and reliability of the perception decisions. Currently, the perception decisions for a single vehicle are mostly provided by neural networks. Therefore, in order to fuse the perception decisions from multiple vehicles, the credibility of the neural network outputs needs to be studied. Among various factors, the environment is one of the most important affecting vehicles' perception decisions. In this paper, we propose a new evaluation criteria for the neural networks used in the perception module of unmanned vehicles. This criterion is termed as Environmental Sensitivity (ES), indicates the sensitivity of the network to environmental changes. We design an algorithm to quantitatively measure the ES value of different perception networks based on the extracted features. Experimental results show that our algorithm can well capture the sensitivity of the network in different environments and the ES values will be helpful to the subsequent decision fusion process.

Original language	English (US)
Title of host publication	2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728131061
DOIs	https://doi.org/10.1109/WCNC45663.2020.9120722
State	Published - May 2020
Externally published	Yes
Event	2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Seoul, Korea, Republic of Duration: May 25 2020 → May 28 2020

Publication series

Name	IEEE Wireless Communications and Networking Conference, WCNC
Volume	2020-May
ISSN (Print)	1525-3511

Conference

Conference	2020 IEEE Wireless Communications and Networking Conference, WCNC 2020
Country/Territory	Korea, Republic of
City	Seoul
Period	5/25/20 → 5/28/20

Bibliographical note

Funding Information:
This work was in part supported by the Ministry National Key Research and Development Project under Grant 2017YFE0121400, Guandong Key R&D Project under Grant 2019B010153003, the open research fund of Key Laboratory of Wireless Sensor Network & Communication under Grant 2017003, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, and the National Science Foundation under Grants CNS-1932413 and CNS-1932139.

Publisher Copyright:
© 2020 IEEE.

Keywords

Environmental sensitivity
decision fusion
multi-vehicle cooperative perception
vehicular network

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1109/WCNC45663.2020.9120722

Find It

Find It at U of M Libraries

Cite this

Li, Y., Duan, D., Chen, C., Cheng, X., & Yang, L. (2020). Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module. In 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings Article 9120722 (IEEE Wireless Communications and Networking Conference, WCNC; Vol. 2020-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WCNC45663.2020.9120722

Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module. / Li, Yuru; Duan, Dongliang; Chen, Chen et al.
2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9120722 (IEEE Wireless Communications and Networking Conference, WCNC; Vol. 2020-May).

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

Li, Y, Duan, D, Chen, C, Cheng, X & Yang, L 2020, Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module. in 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings., 9120722, IEEE Wireless Communications and Networking Conference, WCNC, vol. 2020-May, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020, Seoul, Korea, Republic of, 5/25/20. https://doi.org/10.1109/WCNC45663.2020.9120722

Li Y, Duan D, Chen C, Cheng X, Yang L. Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module. In 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9120722. (IEEE Wireless Communications and Networking Conference, WCNC). doi: 10.1109/WCNC45663.2020.9120722

@inproceedings{1a38ff96f30f4f04910e34ec4f50eac9,

title = "Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module",

abstract = "For autonomous driving of unmanned vehicles in intelligent transportation systems, multi-vehicle cooperative perception supported by vehicular networks can greatly improve the accuracy and reliability of the perception decisions. Currently, the perception decisions for a single vehicle are mostly provided by neural networks. Therefore, in order to fuse the perception decisions from multiple vehicles, the credibility of the neural network outputs needs to be studied. Among various factors, the environment is one of the most important affecting vehicles' perception decisions. In this paper, we propose a new evaluation criteria for the neural networks used in the perception module of unmanned vehicles. This criterion is termed as Environmental Sensitivity (ES), indicates the sensitivity of the network to environmental changes. We design an algorithm to quantitatively measure the ES value of different perception networks based on the extracted features. Experimental results show that our algorithm can well capture the sensitivity of the network in different environments and the ES values will be helpful to the subsequent decision fusion process.",

keywords = "Environmental sensitivity, decision fusion, multi-vehicle cooperative perception, vehicular network",

author = "Yuru Li and Dongliang Duan and Chen Chen and Xiang Cheng and Liuqing Yang",

note = "Funding Information: This work was in part supported by the Ministry National Key Research and Development Project under Grant 2017YFE0121400, Guandong Key R&D Project under Grant 2019B010153003, the open research fund of Key Laboratory of Wireless Sensor Network & Communication under Grant 2017003, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, and the National Science Foundation under Grants CNS-1932413 and CNS-1932139. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 ; Conference date: 25-05-2020 Through 28-05-2020",

year = "2020",

month = may,

doi = "10.1109/WCNC45663.2020.9120722",

language = "English (US)",

series = "IEEE Wireless Communications and Networking Conference, WCNC",

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

booktitle = "2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings",

}

TY - GEN

T1 - Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module

AU - Li, Yuru

AU - Duan, Dongliang

AU - Chen, Chen

AU - Cheng, Xiang

AU - Yang, Liuqing

N1 - Funding Information: This work was in part supported by the Ministry National Key Research and Development Project under Grant 2017YFE0121400, Guandong Key R&D Project under Grant 2019B010153003, the open research fund of Key Laboratory of Wireless Sensor Network & Communication under Grant 2017003, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, and the National Science Foundation under Grants CNS-1932413 and CNS-1932139. Publisher Copyright: © 2020 IEEE.

PY - 2020/5

Y1 - 2020/5

N2 - For autonomous driving of unmanned vehicles in intelligent transportation systems, multi-vehicle cooperative perception supported by vehicular networks can greatly improve the accuracy and reliability of the perception decisions. Currently, the perception decisions for a single vehicle are mostly provided by neural networks. Therefore, in order to fuse the perception decisions from multiple vehicles, the credibility of the neural network outputs needs to be studied. Among various factors, the environment is one of the most important affecting vehicles' perception decisions. In this paper, we propose a new evaluation criteria for the neural networks used in the perception module of unmanned vehicles. This criterion is termed as Environmental Sensitivity (ES), indicates the sensitivity of the network to environmental changes. We design an algorithm to quantitatively measure the ES value of different perception networks based on the extracted features. Experimental results show that our algorithm can well capture the sensitivity of the network in different environments and the ES values will be helpful to the subsequent decision fusion process.

AB - For autonomous driving of unmanned vehicles in intelligent transportation systems, multi-vehicle cooperative perception supported by vehicular networks can greatly improve the accuracy and reliability of the perception decisions. Currently, the perception decisions for a single vehicle are mostly provided by neural networks. Therefore, in order to fuse the perception decisions from multiple vehicles, the credibility of the neural network outputs needs to be studied. Among various factors, the environment is one of the most important affecting vehicles' perception decisions. In this paper, we propose a new evaluation criteria for the neural networks used in the perception module of unmanned vehicles. This criterion is termed as Environmental Sensitivity (ES), indicates the sensitivity of the network to environmental changes. We design an algorithm to quantitatively measure the ES value of different perception networks based on the extracted features. Experimental results show that our algorithm can well capture the sensitivity of the network in different environments and the ES values will be helpful to the subsequent decision fusion process.

KW - Environmental sensitivity

KW - decision fusion

KW - multi-vehicle cooperative perception

KW - vehicular network

UR - http://www.scopus.com/inward/record.url?scp=85087275950&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85087275950&partnerID=8YFLogxK

U2 - 10.1109/WCNC45663.2020.9120722

DO - 10.1109/WCNC45663.2020.9120722

M3 - Conference contribution

AN - SCOPUS:85087275950

T3 - IEEE Wireless Communications and Networking Conference, WCNC

BT - 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020

Y2 - 25 May 2020 through 28 May 2020

ER -

Environmental Sensitivity Evaluation of Neural Networks in Unmanned Vehicle Perception Module

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this