Developing a Highly Automated Driving Scenario to Investigate User 
Intervention: When Things Go Wrong

Faltaous, S; Machulla, T; Baumann, M; Chuang, L

doi:10.1145/3131726.3131766

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

このアイテムの新しいバージョンが利用可能です:
https://pure.mpg.de/pubman/item/item_2551883_2

詳細要約

公開

会議論文

Developing a Highly Automated Driving Scenario to Investigate User Intervention: When Things Go Wrong

MPS-Authors

/persons/resource/persons216488

Faltaous, S
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84065

Machulla, T
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Research Group Multisensory Perception and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83861

Chuang, L
Project group: Cognition & Control in Human-Machine Systems, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

Link
(全文テキスト（全般）)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Faltaous, S., Machulla, T., Baumann, M., & Chuang, L. (2017). Developing a Highly Automated Driving Scenario to Investigate User Intervention: When Things Go Wrong. In Adjunct Proceedings (pp. 67-71). New York, NY, USA: ACM Press.

引用: https://hdl.handle.net/21.11116/0000-0000-C38D-5

要旨

Current levels of vehicle automation (i.e., SAE-L2) require users to be vigilant and to intervene when automated vehicles fail to perform appropriately. In this work, we developed a scenario for investigating how humans respond, in the absence of notifications for system failure. In order to develop better notifications to elicit user intervention, it is necessary to first understand how humans would intervene, even without the aid of in-vehicle notifications. We provide a description of how this is implemented in a driving simulator using Unity, a game engine. In addition, we report preliminary results. Overall, we found that participants were more aroused and cautious under conditions of low environment visibility, even though visibility had no bearing on the likelihood of vehicle automation to fail. We present recommendations for how the current scenario could be improved for subsequent research.