東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Modeling Driver-Initiated Control Tr...

Kamaraj, Amudha V.

FindBook

Google Book

Amazon

博客來

Modeling Driver-Initiated Control Transitions in Automated Vehicles.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Modeling Driver-Initiated Control Transitions in Automated Vehicles./
作者:	Kamaraj, Amudha V.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	132 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Industrial engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31297868
ISBN:	9798382591148

Modeling Driver-Initiated Control Transitions in Automated Vehicles.
Kamaraj, Amudha V.

Modeling Driver-Initiated Control Transitions in Automated Vehicles. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 132 p.

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2024.

In future fully automated vehicles, continuous user engagement of the automated mode can minimize disruptions to the traffic flow caused by manual driving. Prior research indicates that distrust that stems from dissimilarities between automated and manual driving styles can be a barrier to reliance on automated modes. However, existing studies requiring constant driver monitoring may not align with future automated systems that allow non-driving related task engagement. This dissertation addresses this gap by investigating the interaction between driving style similarity, trust, and reliance in the context of non-driving related tasks (NDRTs) through simulator studies and a computational driver-vehicle interaction model. The first simulator study reaffirmed that driving style similarity positively affects trust in automation when drivers continuously monitor the system. The second simulator study then examined the relationship between driving style similarity, trust, and automation reliance (measured by time spent in automated mode). Half the drivers in the study engaged in NDRTs thereby intermittently monitoring the automation while the other half continuously monitored the automation. Drivers had the flexibility to switch between automated and manual modes, aiming to reach a destination within a time limit. Incentives and penalties were applied based on arrival time, speed limit adherence, and task completion. Statistical models indicate that driving style similarity and NDRT engagement independently positively impact trust in automation, while only NDRT engagement positively influences automation reliance.Statistical models that examined study results are limited in explaining decision-making mechanisms influencing behavior. To further our understanding of the decision-making processes that could lead to differences in reliance behavior, an evidence accumulation-based approach was employed. Model analysis revealed that drivers who continuously monitored automation were slower to accumulate evidence and required more evidence to decide to switch from automated to manual mode with the opposite trend observed in drivers engaged in NDRTs. This suggests that situational demands influenced decisions to switch from automated to manual mode. This underscores the importance of understanding decision-making strategies when designing future human-vehicle interactions as these decisions ultimately affect traffic flow.

ISBN: 9798382591148Subjects--Topical Terms:

526216
Industrial engineering.
Subjects--Index Terms:

Automated vehicles

Modeling Driver-Initiated Control Transitions in Automated Vehicles.
LDR:03623nmm a2200397 4500 001 2428154
005 20241210085419.5
006 m o d
007 cr#unu||||||||
008 261011s2024 ||||||||||||||||| ||eng d
020 $a 9798382591148
035 $a (MiAaPQ)AAI31297868
035 $a AAI31297868
040 $a MiAaPQ $c MiAaPQ
100 1 $a Kamaraj, Amudha V. $3 3815194
245 1 0 $a Modeling Driver-Initiated Control Transitions in Automated Vehicles.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 132 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisor: Lee, John D.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2024.
520 $a In future fully automated vehicles, continuous user engagement of the automated mode can minimize disruptions to the traffic flow caused by manual driving. Prior research indicates that distrust that stems from dissimilarities between automated and manual driving styles can be a barrier to reliance on automated modes. However, existing studies requiring constant driver monitoring may not align with future automated systems that allow non-driving related task engagement. This dissertation addresses this gap by investigating the interaction between driving style similarity, trust, and reliance in the context of non-driving related tasks (NDRTs) through simulator studies and a computational driver-vehicle interaction model. The first simulator study reaffirmed that driving style similarity positively affects trust in automation when drivers continuously monitor the system. The second simulator study then examined the relationship between driving style similarity, trust, and automation reliance (measured by time spent in automated mode). Half the drivers in the study engaged in NDRTs thereby intermittently monitoring the automation while the other half continuously monitored the automation. Drivers had the flexibility to switch between automated and manual modes, aiming to reach a destination within a time limit. Incentives and penalties were applied based on arrival time, speed limit adherence, and task completion. Statistical models indicate that driving style similarity and NDRT engagement independently positively impact trust in automation, while only NDRT engagement positively influences automation reliance.Statistical models that examined study results are limited in explaining decision-making mechanisms influencing behavior. To further our understanding of the decision-making processes that could lead to differences in reliance behavior, an evidence accumulation-based approach was employed. Model analysis revealed that drivers who continuously monitored automation were slower to accumulate evidence and required more evidence to decide to switch from automated to manual mode with the opposite trend observed in drivers engaged in NDRTs. This suggests that situational demands influenced decisions to switch from automated to manual mode. This underscores the importance of understanding decision-making strategies when designing future human-vehicle interactions as these decisions ultimately affect traffic flow.
590 $a School code: 0262.
650 4 $a Industrial engineering. $3 526216
650 4 $a Statistics. $3 517247
650 4 $a Automotive engineering. $3 2181195
650 4 $a Mechanical engineering. $3 649730
653 $a Automated vehicles
653 $a Automation reliance
653 $a Human factors
653 $a Traffic flow
653 $a Manual driving
690 $a 0546
690 $a 0548
690 $a 0463
690 $a 0540
710 2 $a The University of Wisconsin - Madison. $b Industrial Engineering. $3 2093809
773 0 $t Dissertations Abstracts International $g 85-11B.
790 $a 0262
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31297868