Exploring the benefits of conversing with a digital voice assistant during automated driving: A parametric duration model of takeover time

Mahajan, Kirti; Large, David R.; Burnett, Gary; Velaga, Nagendra R.

doi:10.1016/j.trf.2021.03.012

Cited by 32 publications

(11 citation statements)

References 72 publications

(111 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 6-second sequence of glances was used by Fridman et al [108] to predict the driver state. Likewise, Mahajan et al [240] analyzed glance behavior (e.g., frequency) regarding situation awareness before takeover requests (TORs). Besides, longer eye movement sequences can be used, which we found to be mainly implicit input for predictive algorithms.…”

Section: Input Modalitiesmentioning

confidence: 99%

“…For example, Benedetto et al [32] measured pupil diameter, blink rate, and blink duration to assess the driver's mental workload and inform accident prevention systems. Likewise, Mahajan et al [240] measured pupil diameter and blink frequency to assess the changed driver alertness due to automation and the TOR performance. However, we did not find any driver assistance systems already built into vehicles, such as drowsiness detection using visual input, which could be due to the set time range (2011-2021).…”

Section: Input Modalitiesmentioning

confidence: 99%

“…Our synthesis showed that input modalities were mainly sensed via vehicle sensors located in the front. For example, cameras for visual input, such as gaze [116], blinking [240], or pupil dilation [240], or kinesthetic input, such as gesture [81], facial expression [153], or head movement [314]. Similarly, microphones were placed in the front to sense auditory input (e.g., speech [245] or humming [111]).…”

Section: Interaction Locationsmentioning

confidence: 99%

See 2 more Smart Citations

A Design Space for Human Sensor and Actuator Focused In-Vehicle Interaction Based on a Systematic Literature Review

Jansen

Colley

Rukzio

2022

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

Automotive user interfaces constantly change due to increasing automation, novel features, additional applications, and user demands. While in-vehicle interaction can utilize numerous promising modalities, no existing overview includes an extensive set of human sensors and actuators and interaction locations throughout the vehicle interior. We conducted a systematic literature review of 327 publications leading to a design space for in-vehicle interaction that outlines existing and lack of work regarding input and output modalities, locations, and multimodal interaction. To investigate user acceptance of possible modalities and locations inferred from existing work and gaps unveiled in our design space, we conducted an online study (N=48). The study revealed users' general acceptance of novel modalities (e.g., brain or thermal activity) and interaction with locations other than the front (e.g., seat or table). Our work helps practitioners evaluate key design decisions, exploit trends, and explore new areas in the domain of in-vehicle interaction.

show abstract

Section: Input Modalitiesmentioning

confidence: 99%

Section: Input Modalitiesmentioning

confidence: 99%

Section: Interaction Locationsmentioning

confidence: 99%

See 1 more Smart Citation

A Design Space for Human Sensor and Actuator Focused In-Vehicle Interaction Based on a Systematic Literature Review

Jansen

Colley

Rukzio

2022

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

show abstract

“…As errors in these situations may directly impact the resulting decisions, this could lead to subsequent errors of high impact. Already the interpretation and analysis, as well as the direct control of human-machine interactions, in economic, healthcare, or transportation relevant environments is dependent on smart processes based on machine-learning and cognitive architectures (Dojchinovski et al, 2019;Gruzauskas et al, 2020;Mahajan et al, 2021;Valaskova et al, 2021;Sri Suvetha et al, 2022). As these methods are employed to reduce the possibilities and impact of economic crisis, an erroneous implementation could be devastating.…”

Section: Introductionmentioning

confidence: 99%

Acoustic-Based Automatic Addressee Detection for Technical Systems: A Review

Siegert

Weißkirchen²,

Wendemuth³

2022

Front. Comput. Sci.

View full text Add to dashboard Cite

ObjectiveAcoustic addressee detection is a challenge that arises in human group interactions, as well as in interactions with technical systems. The research domain is relatively new, and no structured review is available. Especially due to the recent growth of usage of voice assistants, this topic received increased attention. To allow a natural interaction on the same level as human interactions, many studies focused on the acoustic analyses of speech. The aim of this survey is to give an overview on the different studies and compare them in terms of utilized features, datasets, as well as classification architectures, which has so far been not conducted.MethodsThe survey followed the Preferred Reporting Items for Systematic reviews and Meta-Analysis (PRISMA) guidelines. We included all studies which were analyzing acoustic and/or acoustic characteristics of speech utterances to automatically detect the addressee. For each study, we describe the used dataset, feature set, classification architecture, performance, and other relevant findings.Results1,581 studies were screened, of which 23 studies met the inclusion criteria. The majority of studies utilized German or English speech corpora. Twenty-six percent of the studies were tested on in-house datasets, where only limited information is available. Nearly 40% of the studies employed hand-crafted feature sets, the other studies mostly rely on Interspeech ComParE 2013 feature set or Log-FilterBank Energy and Log Energy of Short-Time Fourier Transform features. 12 out of 23 studies used deep-learning approaches, the other 11 studies used classical machine learning methods. Nine out of 23 studies furthermore employed a classifier fusion.ConclusionSpeech-based automatic addressee detection is a relatively new research domain. Especially by using vast amounts of material or sophisticated models, device-directed speech is distinguished from non-device-directed speech. Furthermore, a clear distinction between in-house datasets and pre-existing ones can be drawn and a clear trend toward pre-defined larger feature sets (with partly used feature selection methods) is apparent.

show abstract

“…Outputting facial expressions and speech is a fundamental capability of in-vehicle robots. Several studies have shown that robot facial expressions and speech have additional positive effects on driving safety [ 8 , 9 ]. Many studies have shown that multimodal warnings in cars are more beneficial for driving safety than unimodal warnings [ 10 , 11 ], both for manual [ 11 , 12 ] and highly automated [ 13 ] vehicles.…”

Section: Introductionmentioning

confidence: 99%

Multimodal Warnings Design for In-Vehicle Robots under Driving Safety Scenarios

Wang

Liu

et al. 2022

Sensors

View full text Add to dashboard Cite

In case of dangerous driving, the in-vehicle robot can provide multimodal warnings to help the driver correct the wrong operation, so the impact of the warning signal itself on driving safety needs to be reduced. This study investigates the design of multimodal warnings for in-vehicle robots under driving safety warning scenarios. Based on transparency theory, this study addressed the content and timing of visual and auditory modality warning outputs and discussed the effects of different robot speech and facial expressions on driving safety. Two rounds of experiments were conducted on a driving simulator to collect vehicle data, subjective data, and behavioral data. The results showed that driving safety and workload were optimal when the robot was designed to use negative expressions for the visual modality during the comprehension (SAT 2) phase and speech at a rate of 345 words/minute for the auditory modality during the comprehension (SAT 2) and prediction (SAT 3) phases. The design guideline obtained from the study provides a reference for the interaction design of driver assistance systems with robots as the interface.

show abstract

Exploring the benefits of conversing with a digital voice assistant during automated driving: A parametric duration model of takeover time

Cited by 32 publications

References 72 publications

A Design Space for Human Sensor and Actuator Focused In-Vehicle Interaction Based on a Systematic Literature Review

A Design Space for Human Sensor and Actuator Focused In-Vehicle Interaction Based on a Systematic Literature Review

Acoustic-Based Automatic Addressee Detection for Technical Systems: A Review

Multimodal Warnings Design for In-Vehicle Robots under Driving Safety Scenarios

Contact Info

Product

Resources

About