Investigating Users’ Preferences in Adaptive Driving Styles for Level 2 Driving Automation

Zahra Sajednia; Kumar Akash; Zhaobo Zheng; Teruhisa Misu; Miaomiao Dong; Vidya Krishnamoorthy; Kimberly Martinez; Keertana Sureshbabu; Gaojian Huang

doi:10.1145/3543174.354608

Investigating Users’ Preferences in Adaptive Driving Styles for Level 2 Driving Automation

Zahra Sajednia, Kumar Akash, Zhaobo Zheng, Teruhisa Misu, Miaomiao Dong, Vidya Krishnamoorthy, Kimberly Martinez, Keertana Sureshbabu, Gaojian Huang

Honda Research Institute USA, Inc.

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

Abstract

Users prefer different styles (more defensive or aggressive) for their autonomous vehicle (AV) to drive. This preference depends on multiple factors including user’s trust in AV and the scenario. Understanding users’ preferred driving style and takeover behavior can assist in creating comfortable driving experiences. In this driving simulator study, participants were asked to interact with L2 driving automation with different driving style adaptations. We analyze the effects of different AV driving style adaptations on users’ survey responses. We propose linear and generalized linear mixed effect models for predicting the user’s preference and takeover actions. Results suggest that trust plays an important role in determining users’ preferences and takeover actions. Also, the scenario, pressing brakes, and AV’s aggressiveness level are among the main factors correlated with users’ preferences. The results provide a step toward developing human-aware driving automation that can implicitly adapt its driving style based on the user’s preference.

Original language	American English
Title of host publication	Proceeding of 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2022)
Pages	162-170
DOIs	https://doi.org/10.1145/3543174.354608
State	Published - Sep 2002
Externally published	Yes

Access to Document

10.1145/3543174.354608

Cite this

Sajednia, Z., Akash, K., Zheng, Z., Misu, T., Dong, M., Krishnamoorthy, V., Martinez, K., Sureshbabu, K., & Huang, G. (2002). Investigating Users’ Preferences in Adaptive Driving Styles for Level 2 Driving Automation. In Proceeding of 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2022) (pp. 162-170) https://doi.org/10.1145/3543174.354608

Investigating Users’ Preferences in Adaptive Driving Styles for Level 2 Driving Automation. / Sajednia, Zahra; Akash, Kumar; Zheng, Zhaobo et al.
Proceeding of 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2022). 2002. p. 162-170.

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

Sajednia, Z, Akash, K, Zheng, Z, Misu, T, Dong, M, Krishnamoorthy, V, Martinez, K, Sureshbabu, K & Huang, G 2002, Investigating Users’ Preferences in Adaptive Driving Styles for Level 2 Driving Automation. in Proceeding of 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2022). pp. 162-170. https://doi.org/10.1145/3543174.354608

@inproceedings{37e24f8797f84384896c3b7b702ae740,

title = "Investigating Users{\textquoteright} Preferences in Adaptive Driving Styles for Level 2 Driving Automation",

abstract = "Users prefer different styles (more defensive or aggressive) for their autonomous vehicle (AV) to drive. This preference depends on multiple factors including user{\textquoteright}s trust in AV and the scenario. Understanding users{\textquoteright} preferred driving style and takeover behavior can assist in creating comfortable driving experiences. In this driving simulator study, participants were asked to interact with L2 driving automation with different driving style adaptations. We analyze the effects of different AV driving style adaptations on users{\textquoteright} survey responses. We propose linear and generalized linear mixed effect models for predicting the user{\textquoteright}s preference and takeover actions. Results suggest that trust plays an important role in determining users{\textquoteright} preferences and takeover actions. Also, the scenario, pressing brakes, and AV{\textquoteright}s aggressiveness level are among the main factors correlated with users{\textquoteright} preferences. The results provide a step toward developing human-aware driving automation that can implicitly adapt its driving style based on the user{\textquoteright}s preference.",

author = "Zahra Sajednia and Kumar Akash and Zhaobo Zheng and Teruhisa Misu and Miaomiao Dong and Vidya Krishnamoorthy and Kimberly Martinez and Keertana Sureshbabu and Gaojian Huang",

year = "2002",

month = sep,

doi = "10.1145/3543174.354608",

language = "American English",

pages = "162--170",

booktitle = "Proceeding of 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2022)",

}

TY - GEN

T1 - Investigating Users’ Preferences in Adaptive Driving Styles for Level 2 Driving Automation

AU - Sajednia, Zahra

AU - Akash, Kumar

AU - Zheng, Zhaobo

AU - Misu, Teruhisa

AU - Dong, Miaomiao

AU - Krishnamoorthy, Vidya

AU - Martinez, Kimberly

AU - Sureshbabu, Keertana

AU - Huang, Gaojian

PY - 2002/9

Y1 - 2002/9

N2 - Users prefer different styles (more defensive or aggressive) for their autonomous vehicle (AV) to drive. This preference depends on multiple factors including user’s trust in AV and the scenario. Understanding users’ preferred driving style and takeover behavior can assist in creating comfortable driving experiences. In this driving simulator study, participants were asked to interact with L2 driving automation with different driving style adaptations. We analyze the effects of different AV driving style adaptations on users’ survey responses. We propose linear and generalized linear mixed effect models for predicting the user’s preference and takeover actions. Results suggest that trust plays an important role in determining users’ preferences and takeover actions. Also, the scenario, pressing brakes, and AV’s aggressiveness level are among the main factors correlated with users’ preferences. The results provide a step toward developing human-aware driving automation that can implicitly adapt its driving style based on the user’s preference.

AB - Users prefer different styles (more defensive or aggressive) for their autonomous vehicle (AV) to drive. This preference depends on multiple factors including user’s trust in AV and the scenario. Understanding users’ preferred driving style and takeover behavior can assist in creating comfortable driving experiences. In this driving simulator study, participants were asked to interact with L2 driving automation with different driving style adaptations. We analyze the effects of different AV driving style adaptations on users’ survey responses. We propose linear and generalized linear mixed effect models for predicting the user’s preference and takeover actions. Results suggest that trust plays an important role in determining users’ preferences and takeover actions. Also, the scenario, pressing brakes, and AV’s aggressiveness level are among the main factors correlated with users’ preferences. The results provide a step toward developing human-aware driving automation that can implicitly adapt its driving style based on the user’s preference.

U2 - 10.1145/3543174.354608

DO - 10.1145/3543174.354608

M3 - Conference contribution

SP - 162

EP - 170

BT - Proceeding of 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI 2022)

ER -