Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles

Martin Sigl; Andreas Lebherz; Christoph Schutz; Sebastian Wagner; Daniel Watzenig

doi:10.1109/ICCVE52871.2022.9742719

Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles

Martin Sigl, Andreas Lebherz, Christoph Schutz, Sebastian Wagner, Daniel Watzenig

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

Abstract

Virtual tests are used increasingly to assess automated driving. They are generally based on ground truth information. The perception process of automated vehicles with sensors provides a shifted, erroneous view of the environment. Within the virtual assessment process of automated driving, it is necessary to restore this sensor view for the automated driving function to ensure realistic testing. This paper presents two approaches to derive models that are able to recreate these perception errors. Both approaches are evaluated regarding their overall performance to emulate the sensor view of automated vehicles. They are able to create models that significantly reduce the difference between ground truth and an automated vehicle's sensor view of the environment. The resulting models can be used to improve the virtual assessment process.

Original language	English
Title of host publication	ICCVE 2022 - IEEE International Conference on Connected Vehicles and Expo
Publisher	Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9781665416870
DOIs	https://doi.org/10.1109/ICCVE52871.2022.9742719
Publication status	Published - 2022
Event	2022 IEEE International Conference on Connected Vehicles and Expo: ICCVE 2022 - Florida Polytechnic University, Hybrider Event, United States Duration: 7 Mar 2022 → 9 Mar 2022 https://iccve2022.org/

Conference

Conference	2022 IEEE International Conference on Connected Vehicles and Expo
Abbreviated title	ICCVE 2022
Country/Territory	United States
City	Hybrider Event
Period	7/03/22 → 9/03/22
Internet address	https://iccve2022.org/

Keywords

Autonomous Vehicles
Deep Learning
linear time invariant element
LSTM
Sensor Errors
Sensor Models
Sensor Systems
Simulation
Vehicle Detection

ASJC Scopus subject areas

Computer Science Applications
Automotive Engineering
Safety, Risk, Reliability and Quality
Control and Optimization

Access to Document

10.1109/ICCVE52871.2022.9742719

Cite this

Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles. / Sigl, Martin; Lebherz, Andreas; Schutz, Christoph et al.
ICCVE 2022 - IEEE International Conference on Connected Vehicles and Expo. Institute of Electrical and Electronics Engineers, 2022.

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

Sigl, M, Lebherz, A, Schutz, C, Wagner, S & Watzenig, D 2022, Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles. in ICCVE 2022 - IEEE International Conference on Connected Vehicles and Expo. Institute of Electrical and Electronics Engineers, 2022 IEEE International Conference on Connected Vehicles and Expo, Hybrider Event, Florida, United States, 7/03/22. https://doi.org/10.1109/ICCVE52871.2022.9742719

@inproceedings{eb70bc0ad0ab468abb8d2403f36fd4c9,

title = "Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles",

abstract = "Virtual tests are used increasingly to assess automated driving. They are generally based on ground truth information. The perception process of automated vehicles with sensors provides a shifted, erroneous view of the environment. Within the virtual assessment process of automated driving, it is necessary to restore this sensor view for the automated driving function to ensure realistic testing. This paper presents two approaches to derive models that are able to recreate these perception errors. Both approaches are evaluated regarding their overall performance to emulate the sensor view of automated vehicles. They are able to create models that significantly reduce the difference between ground truth and an automated vehicle's sensor view of the environment. The resulting models can be used to improve the virtual assessment process.",

keywords = "Autonomous Vehicles, Deep Learning, linear time invariant element, LSTM, Sensor Errors, Sensor Models, Sensor Systems, Simulation, Vehicle Detection",

author = "Martin Sigl and Andreas Lebherz and Christoph Schutz and Sebastian Wagner and Daniel Watzenig",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Connected Vehicles and Expo : ICCVE 2022, ICCVE 2022 ; Conference date: 07-03-2022 Through 09-03-2022",

year = "2022",

doi = "10.1109/ICCVE52871.2022.9742719",

language = "English",

booktitle = "ICCVE 2022 - IEEE International Conference on Connected Vehicles and Expo",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

url = "https://iccve2022.org/",

}

TY - GEN

T1 - Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles

AU - Sigl, Martin

AU - Lebherz, Andreas

AU - Schutz, Christoph

AU - Wagner, Sebastian

AU - Watzenig, Daniel

PY - 2022

Y1 - 2022

N2 - Virtual tests are used increasingly to assess automated driving. They are generally based on ground truth information. The perception process of automated vehicles with sensors provides a shifted, erroneous view of the environment. Within the virtual assessment process of automated driving, it is necessary to restore this sensor view for the automated driving function to ensure realistic testing. This paper presents two approaches to derive models that are able to recreate these perception errors. Both approaches are evaluated regarding their overall performance to emulate the sensor view of automated vehicles. They are able to create models that significantly reduce the difference between ground truth and an automated vehicle's sensor view of the environment. The resulting models can be used to improve the virtual assessment process.

AB - Virtual tests are used increasingly to assess automated driving. They are generally based on ground truth information. The perception process of automated vehicles with sensors provides a shifted, erroneous view of the environment. Within the virtual assessment process of automated driving, it is necessary to restore this sensor view for the automated driving function to ensure realistic testing. This paper presents two approaches to derive models that are able to recreate these perception errors. Both approaches are evaluated regarding their overall performance to emulate the sensor view of automated vehicles. They are able to create models that significantly reduce the difference between ground truth and an automated vehicle's sensor view of the environment. The resulting models can be used to improve the virtual assessment process.

KW - Autonomous Vehicles

KW - Deep Learning

KW - linear time invariant element

KW - LSTM

KW - Sensor Errors

KW - Sensor Models

KW - Sensor Systems

KW - Simulation

KW - Vehicle Detection

UR - http://www.scopus.com/inward/record.url?scp=85128216322&partnerID=8YFLogxK

U2 - 10.1109/ICCVE52871.2022.9742719

DO - 10.1109/ICCVE52871.2022.9742719

M3 - Conference paper

AN - SCOPUS:85128216322

BT - ICCVE 2022 - IEEE International Conference on Connected Vehicles and Expo

PB - Institute of Electrical and Electronics Engineers

T2 - 2022 IEEE International Conference on Connected Vehicles and Expo

Y2 - 7 March 2022 through 9 March 2022

ER -

Comparing a Linear Filter with a ML-based Approach for Modeling Perception Errors of Automated Vehicles

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this