The role of driver models in testing highly-automated driving: a survey
Abstract: A particular challenge in the development of highly-automated driving functions is the validation of these systems. A possible approach to cope with the validation effort is the use of simulations. Thereby, simulators can be used in various aspects of the validation process. For a meaningful application of simulators, individual aspects of reality are replaced by models. Based on an analysis of the different use cases, the various driver models from the state-of-art will be examined in this article with regard to their conceptual suitability for safeguarding highly automated driving functions.
Eine besondere Herausforderung bei der Entwicklung hoch-automatisierter Fahrfunktionen ist die Validierung dieser Systeme. Ein möglicher Ansatz, den Validierungsaufwand zu meistern, ist der Einsatz von Simulationen. Hierbei können Simulatoren für verschiedene Aspekte des Validierungs-Prozesses verwendet werden. Um verwendbare Ergebnisse zu erhalten, müssen die einzelnen Aspekte der Realität dabei durch entsprechende Modelle abgebildet werden. Basierend auf einer Analyse verschiedener Anwendungsfälle für Simulationen, werden in diesem Beitrag verschiedene Klassen von Modellen für das menschliche Fahrverhalten hinsichtlich ihrer An-wendbarkeit im Rahmen der simulativen Absicherung evaluiert.
- Weitere Titel
-
Die Rolle von Fahrermodellen für das Testen hoch-automatisierter Fahrfunktionen: Eine Übersicht
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
The role of driver models in testing highly-automated driving: a survey ; volume:71 ; number:1 ; year:2023 ; pages:16-27 ; extent:11
Automatisierungstechnik ; 71, Heft 1 (2023), 16-27 (gesamt 11)
- Urheber
- DOI
-
10.1515/auto-2022-0097
- URN
-
urn:nbn:de:101:1-2023011213040784023059
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:22 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Lemmer, Markus
- Schwab, Stefan
- Hohmann, Sören
Ähnliche Objekte (12)
Exploring Driver Responses to Authoritative Control Interventions in Highly Automated Driving
Drivers’ Individual Design Preferences of Takeover Requests in Highly Automated Driving
Trust in highly automated driving
Driver mental states detection during highly automated driving by decoding brain signals
Driver’s non-driving postures in automated driving: Modeling, assessment, and countermeasure
Modeling driver-vehicle interaction in automated driving
HAVEit: DLR makes highly automated driving sustainable
Macroscopic Safety Requirements for Highly Automated Driving
Personality Openness Predicts Driver Trust in Automated Driving
Evaluation criteria for scenario-based testing of highly automated railway driving-decision-making systems
Supporting take-over situations in highly automated driving
Highly precise MEMS gyroscopes for fully automated driving
Exploring Driver Responses to Authoritative Control Interventions in Highly Automated Driving
Drivers’ Individual Design Preferences of Takeover Requests in Highly Automated Driving
Trust in highly automated driving
Driver mental states detection during highly automated driving by decoding brain signals
Driver’s non-driving postures in automated driving: Modeling, assessment, and countermeasure
Modeling driver-vehicle interaction in automated driving
HAVEit: DLR makes highly automated driving sustainable
Macroscopic Safety Requirements for Highly Automated Driving
Personality Openness Predicts Driver Trust in Automated Driving
Evaluation criteria for scenario-based testing of highly automated railway driving-decision-making systems
Supporting take-over situations in highly automated driving
Highly precise MEMS gyroscopes for fully automated driving
Exploring Driver Responses to Authoritative Control Interventions in Highly Automated Driving
Drivers’ Individual Design Preferences of Takeover Requests in Highly Automated Driving
Trust in highly automated driving
Driver mental states detection during highly automated driving by decoding brain signals
Driver’s non-driving postures in automated driving: Modeling, assessment, and countermeasure
Modeling driver-vehicle interaction in automated driving
HAVEit: DLR makes highly automated driving sustainable
Macroscopic Safety Requirements for Highly Automated Driving
Personality Openness Predicts Driver Trust in Automated Driving
Evaluation criteria for scenario-based testing of highly automated railway driving-decision-making systems
Supporting take-over situations in highly automated driving