Sage Journals: Discover world-class research

Abstract

Objective

To explore the scope of available research and to identify research gaps on in-vehicle interventions for drowsiness that utilize driver monitoring systems (DMS).

Background

DMS are gaining popularity as a countermeasure against drowsiness. However, how these systems can be best utilized to guide driver attention is unclear.

Methods

A scoping review was conducted in adherence to PRISMA guidelines. Five electronic databases (ACM Digital Library, Scopus, IEEE Xplore, TRID, and SAE Mobilus) were systematically searched in April 2022. Original studies examining in-vehicle drowsiness interventions that use DMS in a driving context (e.g., driving simulator and driver interviews) passed the screening. Data on study details, state detection methods, and interventions were extracted.

Results

Twenty studies qualified for inclusion. Majority of interventions involved warnings (n = 16) with an auditory component (n = 14). Feedback displays (n = 4) and automation takeover (n = 4) were also investigated. Multistage interventions (n = 12) first cautioned the driver, then urged them to take an action, or initiated an automation takeover. Overall, interventions had a positive impact on sleepiness levels, driving performance, and user evaluations. Whether interventions effective for one type of sleepiness (e.g., passive vs. active fatigue) will perform well for another type is unclear.

Conclusion

Literature mainly focused on developing sensors and improving the accuracy of DMS, but not on the driver interactions with these technologies. More intervention studies are needed in general and for investigating their long-term effects.

Application

We list gaps and limitations in the DMS literature to guide researchers and practitioners in designing and evaluating effective safety systems for drowsy driving.

Keywords

fatigue sleep driver state detection countermeasures in-vehicle interventions

Introduction

Driver drowsiness is a significant traffic safety issue. Drowsiness, or sleepiness, refers to reduced alertness associated with reduced executive functioning, mental effort, and involuntary muscle inhibitions (APA Dictionary of Psychology, n.d.-a). Fatigue, often used interchangeably with drowsiness, is a broader term relating to tiredness and declined functioning due to physical exertion, stress, boredom, lack of sleep, or potential disorders (APA Dictionary of Psychology, n.d.-b). Drowsiness can lead to increased speed variability, increased standard deviation of lane position, fewer micro corrections of the steering wheel (see Liu et al., 2009; Sahayadhas et al., 2012 for a review on vehicle measures), increased percentage of eyelid closures (Sikander & Anwar, 2019), lower driver awareness and alertness towards hazards, and lower cognitive processing and reaction times (Smith et al., 2009). Annually, 328,000 crashes in the US, including 109,000 crashes with injuries and 6400 fatal crashes, are estimated to involve a drowsy driver (Tefft, 2012). An eyelid closure analysis of naturalistic driving data (SHRP2; the Strategic Highway Research Program 2) found drowsy driving in 8.8–9.5% of crashes recorded and in 10.6–10.8% of crashes reported to the police (Owens et al., 2018).

Drowsiness can be caused by a variety of factors, including low arousal, high workload, and sleep-related factors. Periods of low arousal can lead to sleepiness due to boredom, also known as passive fatigue (Chong & Baldwin, 2021; Desmond & Hancock, 2000). For example, long, monotonous rural roads with little traffic can pave the way for this type of sleepiness. Passive fatigue is a particular concern with the current and upcoming advanced driver assistance systems, since monitoring the road for prolonged periods without manually controlling the vehicle can make it challenging to stay awake and attentive to the road (Körber et al., 2015; Schömig et al., 2015). On the other hand, extended periods of high workload can exert prolonged activation of and load on the synapses in the brain leading to high oxygenation of the neurons, DNA, proteins, and lipids (Chong & Baldwin, 2021). To prevent any permanent damage, the body initiates sleep, and this state is often referred to as active fatigue. Lastly, sleep-related factors such as sleep deprivation and the circadian rhythm, which is regulated by time of day, can also influence sleepiness levels (Chong & Baldwin, 2021; May & Baldwin, 2009). Consequently, majority of sleep related fatalities are reported to occur in the early morning (4–6 a.m. and 6–9 a.m.) with a second peak in the late afternoon (3–6 p.m.), when drivers are lacking sleep or when there is a large dip in the alertness levels (Brown et al., 2020; Valdez, 2019).

Popular strategies to fight drowsiness while driving include consuming caffeine, opening the windows, stretching, and resting (Gershon et al., 2011). One study showed that having a chewing gum with 100 mg of caffeine improved driving performance within 10 min when drivers experienced drowsiness due to low arousal (Gastaldi et al., 2016). Maintaining a constant blood oxygen level provided through an oxygen mask (Takahashi et al., 2014) and stretching while driving (Jang et al., 2017) have also been shown to have potential benefits for reducing sleepiness. However, these benefits depend on whether the driver is aware of their impaired state and whether they are able or willing to use these strategies. Further, drivers can under- or overestimate their sleepiness levels (e.g., Gaspar & Carney, 2023). Thus, monitoring the driver state in real time can be valuable for initiating timely interventions like informing the driver or even engaging driving automation.

Driver drowsiness monitoring systems that use driver physiological data (e.g., heart rate, electroencephalography; EEG), behavioral data (e.g., eye-tracking), vehicle kinematics (e.g., speed), subjective measures (e.g., sleepiness scales), or a combination of these sources have gained large interest in the last two decades. Numerous studies were published, including many scoping and systematic reviews (Arakawa, 2021; Chowdhury et al., 2018; Lohani et al., 2019; Lu et al., 2022; Ngxande et al., 2017; Sahayadhas et al., 2012; Sikander & Anwar, 2019; Watling et al., 2021; Yusoff et al., 2017). The reviews highlight the ongoing need for research in driver state detection methods before their widespread deployment in vehicles (Watling et al., 2021). Yet, even if accurate state detection systems become available, questions on whether and how the detected state should be communicated to the driver and whether and how the vehicle should intervene in response to this high-risk state remain unanswered. For example, when the system detects that the driver is drowsy, would alerting the driver through auditory warnings be stimulating or startling? Instead, should the vehicle turn on the lane keeping system to avoid lane deviations? As the next step of driver monitoring, in-vehicle systems can initiate countermeasures such as feedback displays, warnings, or automation aids for safe driving once drowsiness is detected. These interventions could make the drivers aware of their impaired state, encourage taking breaks or alert them, and support them with safely operating the vehicle.

In this paper, we report a scoping review aimed to explore the extent of available research and research gaps on in-vehicle countermeasures that utilize driver drowsiness monitoring and that have been evaluated in a driving context (e.g., driving simulator, on-road studies, or driver interviews). The scoping review also aimed to consolidate available information on different factors that affect intervention outcomes (e.g., driver monitoring system performance, driving scenarios, and participant population) to guide future intervention designs.

Methods

Protocol and Registration

The scoping review was conducted and reported in adherence to Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) Extension for Scoping Reviews (Tricco et al., 2018). A search protocol was prepared before conducting the search (Supplementary Material). The search was conducted to cover both driver drowsiness and driver distraction as part of a larger research effort; the current paper presents our findings on driver drowsiness exclusively.

Search and Information Sources

Search concept, keywords, and strategy (Table 1) were developed by the authors (SA, BD), and modified based on feedback from an information specialist (TK). A systematic search on title, abstract, and keywords of peer-reviewed journal articles and conference papers was conducted on April 6 and 7, 2022 on five electronic databases: Association of Computing Machinery (ACM) Digital Library (ACM DL), Scopus, Institute of Electrical and Electronics Engineers (IEEE) Xplore, Transportation Research International Documentation (TRID), and Society of Automotive Engineers (SAE) Mobilus. Studies written in a language other than English were filtered out at the search stage; however, no time restrictions were set for publication date. The final search strategy is available in the Supplementary Material.

TABLE 1:

Search Concepts, Keywords, and Strategy

Search concept	Search keywords	Search strategy
Inattention	Fatigue, fatigued, sleepiness, sleep, sleepy, drowsiness, drowsy, distraction, distracted	fatigue* OR sleep* OR drows* OR distrac*
Driving	Vehicle, driving, drive, driver	driv* OR vehicl*
Countermeasure	Intervention, intervening, countermeasure, mitigation, mitigating, reduction, reducing	interven* OR mitigat* OR countermeasure OR reduc*

Eligibility Criteria

Search results were uploaded to the Covidence software, which is an online collaboration platform that manages and simplifies the screening and data extraction phases of a literature review (Covidence Systematic Review Software, Veritas Health Innovation, Melbourne, Australia, 2022). Before the title and abstract screening, a team of three researchers (SA, XT, and YW) had two 2-hour long training sessions to familiarize themselves with Covidence as well as the eligibility criteria (Table 2) and reviewed 20 title/abstracts together. After reviewing over 200 title/abstracts independently, the researchers discussed their progress in a follow-up meeting and concluded that the titles and abstracts at times omitted critical study details (e.g., many abstracts were not clear as to whether the interventions were evaluated). To not exclude potentially eligible papers, the criteria were relaxed to pass studies with either drowsiness detection systems or intervention systems mentioned in the title/abstract, instead of having them both, to full-text screening. Following these calibration sessions, the researchers independently completed the title and abstract screening. To ensure greater consistency, one researcher (SA) screened all studies, while the others (XT and YW) split the studies randomly. All studies were double screened, and all conflicts were resolved through consensus at the end of the title/abstract screening phase.

TABLE 2:

Eligibility Criteria for Title/Abstract and Full Text Screening

Inclusion Criteria	Exclusion Criteria
The study evaluates automotive in-vehicle interventions for driver drowsiness. An external system detects driver drowsiness based on a rule or an algorithm and accordingly initiates an intervention. The context is driving, including passenger and freight transportation (e.g., personal vehicles and trucks). The study is original (i.e., primary research). The study analyzes human participant data collected via experiments (e.g., simulator study and on-road study), or focus groups/interviews. The study is reported in English. Full text is available online.	The intervention is for impaired states due to alcohol or drug use. The study examines interventions that are not in-vehicle technology (e.g., regulations or road design elements like rumble strips) or interventions that do not use a driver state monitoring system (e.g., systems that block phone applications once driving is detected). The study examines interventions that are for safety but not directly related to drowsiness interventions (e.g., seatbelts). The study is not about driving (e.g., the setting is healthcare, aviation, surface mining). The study is a review, commentary, editorial, or gray literature. The study does not involve human participant data (e.g., data collected via computer simulations).

Inclusion Criteria

Exclusion Criteria

The study evaluates automotive in-vehicle interventions for driver drowsiness.
An external system detects driver drowsiness based on a rule or an algorithm and accordingly initiates an intervention.
The context is driving, including passenger and freight transportation (e.g., personal vehicles and trucks).
The study is original (i.e., primary research).
The study analyzes human participant data collected via experiments (e.g., simulator study and on-road study), or focus groups/interviews.
The study is reported in English.
Full text is available online.

The intervention is for impaired states due to alcohol or drug use.
The study examines interventions that are not in-vehicle technology (e.g., regulations or road design elements like rumble strips) or interventions that do not use a driver state monitoring system (e.g., systems that block phone applications once driving is detected).
The study examines interventions that are for safety but not directly related to drowsiness interventions (e.g., seatbelts).
The study is not about driving (e.g., the setting is healthcare, aviation, surface mining).
The study is a review, commentary, editorial, or gray literature.
The study does not involve human participant data (e.g., data collected via computer simulations).

Due to the large number of identified studies based on the relaxed eligibility criteria in the title/abstract screening stage, three additional researchers (MA, CS, and CZ) contributed to the full text screening. All three received an hour-long training on the general review protocol, and all six reviewers received a 2-hour long training on full text screening. In the following week, all reviewers screened a set of five preselected papers and discussed their decision-making process in a calibration session. Afterwards, all studies were double screened by two reviewers independently (SA or YW vs. XT, MA, CS, or CZ) in strict adherence to the criteria listed in Table 2. Later, conflicts were discussed among the two reviewers who screened them, with a third as a tie breaker when necessary.

Data Charting and Synthesis of Results

A data extraction form was developed by the authors (SA, BD) prior to the start of the search and revised for clarity after full text screening. The form was uploaded to Covidence where data extraction was performed by SA. All extracted data was later verified by XT for accuracy. Any disagreements were resolved through discussions. The form consisted of three themes: study details, driver state monitoring system, and intervention. Specific fields extracted under these themes are provided in Table 3. The researchers were allowed to take notes to extract relevant data that did not fit into the listed categories/subcategories. Risk of bias was not analyzed; however, we report and comment on study characteristics (e.g., sample size) that can inform the reader about potential biases associated with different sources. Data extracted was summarized using a narrative synthesis and in tabular forms, and trends were visualized with plots whenever possible. The raw extracted data is provided in the Supplementary Material.

TABLE 3:

Data Extraction Themes and Fields

	Themes
	Study Details	Driver State Monitoring System	Intervention
Data Extraction Fields	Study title List of authors Year of publication Country of study Publication type Funding sources/conflict of interest Study goal Study setting Driving scenarios/settings Driving automation levels (if applicable) Participant demographics Participant eligibility criteria Sample size	Monitored driver states State definitions/descriptions Methods used to induce states Detection apparatus (e.g., eye-trackers) Measures collected (e.g., blinks) Features utilized (e.g., average blink rate) Models or algorithms (e.g., decision trees, if-then rules) Performance metrics Outcomes of state detection (e.g., accuracy and sensitivity)	Intervention description Evaluation outcomes: effectiveness, usefulness, acceptance, validation

Results

Selection of Sources of Evidence

3252 studies were identified with the systematic search. 2520 studies were screened out in the title/abstract screening phase. The average agreement between reviewers was 93% for the title/abstract screening (SA-YW: 96%, Cohen’s Kappa: .89; SA-XT: 89%, Cohen’s Kappa: .72), and 85% between the six reviewers for the full-text screening (average Cohen’s Kappa = .75). Many studies were excluded in the full-text stage; majority of the studies, despite mentioning an intervention in their titles or abstracts, focused only on the advancement of state monitoring technologies (n = 303, e.g., testing new features/sensors/models to improve detection accuracy), or did not use a state detection system to initiate an intervention (n = 152). At the end, a total of 11 studies passed to the data extraction phase. Later, a relevant study was identified that was not found in the first search due to an excluded subject area. A secondary search was conducted, and a little over 1300 additional papers were screened for title and abstract. We identified eight more eligible studies (not indexed in the databases searched) in the references of these 12 papers, leading to a total of 20 studies included in the review. The screening flowchart is shown in Figure 1. Overall, twelve journal articles, six conference proceeding papers, and two technical reports were identified.

Figure 1.

PRISMA flow diagram.

Study Details and Sample Characteristics

Table 4 provides an overview of study details and sample characteristics. The studies evaluated interventions on a driving simulator (n = 15) or on real roads (n = 4), with one study utilizing both settings (Nishigaki & Shirakata, 2019). In addition, a driving simulator (Kundinger et al., 2021) and two on-road studies (Aidman et al., 2015; Kircher et al., 2009) supplemented their assessments with interviews and questionnaires, while Horberry et al. (2022) conducted interviews and workshops to design a warning system which was later evaluated on a driving simulator. Although publication years varied between 1998 and 2022, most of the studies were published in the last decade (n = 13). Participant demographics and sample sizes were limited (most studies’ sample size ranged from 14 to 47, while few studies had lower (less than 12) or higher (up to 358) sample sizes), which can drastically hinder the generalizability of the findings and their application in practice. Some studies did not state eligibility criteria for recruiting participants, and some did not provide information on the sample size or participant demographics (e.g., Chen et al., 2014; Nishigaki & Shirakata, 2019). Further, most driving simulator studies collected data from participants aged 21–30, with one study collecting data from college students with no valid driver’s license (Liu & Uang, 2010). In general, a greater number of males were recruited over females, with two studies collecting data only from males (Fairclough & Van Winsum, 2000; Wolkow et al., 2020).

TABLE 4:

Study Details. Studies are Sorted in Alphabetic Order of First-Author Last Names

Study ID	Study Details				Drowsiness Detection System
Study ID	Publication Type	Setting	Sample Size	Sample Characteristics	Heart Rate	EEG	Eye-Tracking	Body-Tracking	Vehicle Kinematics	Performance Metrics
1. Aidman et al., 2015	Journal article	On-road Questionnaire	14^a	1 female (F) and 14 male (M) army reserve personnel Ages 21–59 (M = 41.3, SD = 11.1) Self-reported as frequent drivers			✓			Not reported
2. Baldwin et al., 2014	Journal article	Simulator	42	Drove at least once per month, held a valid licenseAges 18–29 (M = 22.3, SD = 3.4): 14F, 5MAges 60+ (M = 67.6, SD = 5.4): 12F, 11M					✓	Not reported
3. Berka et al., 2005	Conference proceeding	Simulator	11^a	6F, 8M, healthy individualsAverage age: 38.1 (SD = 11.8)		✓				Not reported
4. Chen et al., 2014	Journal article	Simulator	Exp 1: 21Exp 2: 10	No information			✓		✓	Not applicable
5. Fairclough & Van Winsum, 2000	Journal article	Simulator	18	18M; normal or corrected visionAverage age: 34.2 (SD = 9.9)Average driving experience: 16.5 years (SD = 10.7)Majority drove every day and had estimated annual mileage 9,000–24,000 km					✓	Not reported
6. Fitzharris et al., 2017	Journal article	On-road	358 trucks’ data over 5 years	Drivers from a large-scale freight transport company			✓	✓		Not reported
6. Fitzharris et al., 2017	Journal article	On-road	358 trucks’ data over 5 years	Drivers from a large-scale freight transport company			(+observer rating)			Not reported
7. Gaspar et al., 2017	Journal article	Simulator	Control: 24Discrete alarm: 24Multistage alarm: 24	Licensed adults, 50% F in each groupAge range: 21–34					✓	Accuracy ranged between 50% and 75%
8. Hayashi et al., 2021	Journal article	Simulator	5	1F, 4MAges 21–26 years	✓		✓	✓	✓	Accuracy = 55%False alarm = 45%
9. Heitmann et al., 2001	Conference proceeding	Simulator	TACT-I: 3TACT-II: 4	TACT-I: Ages 21-28TACT-II: Ages 25–32			✓	✓		Not applicable
9. Heitmann et al., 2001	Conference proceeding	Simulator	TACT-I: 3TACT-II: 4	TACT-I: Ages 21-28TACT-II: Ages 25–32			(Observer rating only)			Not applicable
10. Horberry et al., 2022	Journal article	Interviews,Workshops,Simulator	Interviews: 16Workshop 1: 8Workshop 2: 9User evaluation in simulator: 14	Interviews: 24–65-year-old truck drivers, average years driving: 19.4 (SD = 14.5), average experience with in-cab warning system: 18 months (n = 12)Workshop 1: 4 drivers, 2 trainers, 1 operations manager, 1 general administration managerWorkshop 2: 9 managers & senior supervisors of a trucking companyUser evaluation: 3F, 11M truck and car driversAverage age: 38.4, average years driving≈18	Not applicable					Not applicable
11. Kircher et al., 2009	Technical report	On-road,Questionnaire, interview	7	3F, 4MAverage age: 42 (SD = 10.9)Average years of licensure: 25 years (SD = 10.9)Average mileage in the last year: 36,000 km (SD = 14,840)Estimated total mileage: 500,000 km (SD = 242,585)			✓			Not reported
12. Kozak, et al., 2006	Conference proceeding	Simulator	32	Held a valid license			✓		✓	Not reported
13. Kundinger et al., 2021	Conference proceeding	Simulator,Questionnaire,Interview	25^a	Good health, no sleep disorders, held a valid licenseAges 20–25 (M = 22.5, SD = 1.88): 8F, 7MAges 65–70 (M = 66.60, SD = 1.84): 9F, 7M	✓(+ KSS)					Accuracy = 83%,F-measure: “awake” as positive class = .90; “drowsy” as positive class = .26
14. Liu & Uang, 2010	Journal article	Simulator	Exp 1: 50Exp 2: 50	College students, not color blindSafely completed a simulator test driveExp 1: 18F, 32M (6F, 12M with valid license). Average age: 22.1Exp 2: 16F, 34M (4F, 11M with valid license). Average age: 21.4					✓	Not reported
15. Nishigaki & Shirakata, 2019	Conference proceeding	Simulator (Exp 1 & 2)On-road (Exp 3)	Exp 1: 10Exp 2: 5Exp 3: 5	No information					✓	Exp 1: Accuracy = 93%, false alarm = 7%Exp 3: 13 false alarms in 90h of driving
16. Niu & Ma, 2022	Journal article	Simulator	30	6F, 24M college students and employeesAverage age: 25.5 (SD = 3.0), average years driving: 3.2 (SD = 1.8)Slept a max of 5h the night before			✓			Not reported
17. Saito et al., 2016	Journal article	Simulator	20	5F, 15M students, ages 20–24 (M = 22, SD = 1.19)Drove daily, held a valid license			✓	✓	✓	Accuracy = 27%, 88%, 100% for three different thresholds
17. Saito et al., 2016	Journal article	Simulator	20				(+observer rating)		✓	Accuracy = 27%, 88%, 100% for three different thresholds
18. Saito et al., 2020	Conference proceeding	Simulator	12^a	5F, 11M, ages 20–28Drove daily, held a valid license			✓	✓	✓	Not reported
18. Saito et al., 2020	Conference proceeding	Simulator	12^a	5F, 11M, ages 20–28Drove daily, held a valid license			(+observer rating)		✓	Not reported
19. Vincent et al., 1998	Technical report	Simulator	32	7F, 25M, recruited from universitiesMedian age: 22 (range: 17–38)All held a valid driver’s licenseNo experience participating in a driving study			✓(observer rating only)		✓(observer rating only)	Not applicable
20. Wolkow et al., 2020	Journal article	On-road	59^a	All male, average age: 39.0 (SD = 6.6)Sleep apnea: Yes = 6; No = 33, Unknown = 10	✓					Sensitivity = 6.25% for predicting harsh braking events and 1.46%, 2.19% and 2.92% for harsh accelerationSpecificity = 98.81 for harsh braking and 98.80%, 98.81%, 98.82% for harsh acceleration

^aNote that the total sample size does not match what is reported for sample characteristics as the study did not detail how data loss corresponded to sample characteristics.

Drowsiness Detection Methods and Performance Metrics

Overall, the majority of the studies focused on detecting only drowsiness (n = 17), while two studies also had distraction detection as part of the system evaluated (Horberry et al., 2022; Kircher et al., 2009) and one study had health monitoring (Hayashi et al., 2021). Studies varied in terms of the algorithms used for detecting drowsiness and the features utilized (i.e., numeric measures used in algorithm development, e.g., blink rates). Mostly eye-tracking (n = 11) and vehicle kinematics (n = 11) data was used to detect drowsiness. State detection was performed via observer ratings (Fitzharris et al., 2017; Heitmann et al., 2001; Saito et al., 2016, 2020; Vincent et al., 1998), threshold-based rules (Baldwin et al., 2014; Fairclough & Van Winsum, 2000; Heitmann et al., 2001; Liu & Uang, 2010; Nishigaki & Shirakata, 2019; Saito et al., 2016, 2020; Vincent et al., 1998; Wolkow et al., 2020), traditional statistical models (Aidman et al., 2015; Berka et al., 2005; Hayashi et al., 2021), or machine learning (Chen et al., 2014; Gaspar et al., 2017; Kundinger et al., 2021; Niu & Ma, 2022). Horberry et al. (2022) did not implement a detection system but instead built a human machine interface (HMI) prototype for a warning system. The prototype was designed based on interviews and workshops with users (e.g., truck drivers) and stakeholders (e.g., managers of trucking companies) and was assessed by users in a driving simulator. Table 4 lists the features and performance metrics used, which might impact driver acceptance or use of the systems.

Although the accuracy and false alarm rates can significantly impact the use of state detection systems, classification performance metrics were generally not reported (n = 10). With those that did (n = 6), accuracy rates varied greatly between 27% and 100%. Due to this large range and small number of studies, no association between algorithm performance and type or number of features was observed. For example, Hayashi et al. (2021) used heart rate, eye-tracking, body-tracking, and vehicle kinematics, but reported low accuracy (55%). On the other hand, Nishigaki and Shirakata (2019) used only vehicle kinematics data and reported 93% accuracy. This large variability might be due to small sample sizes (n = 5 participants) used in both studies. Relaxing thresholds helped achieve 100% accuracy in Saito et al. (2016); however, it may have also increased false alarm rates, which may lead to disuse. Further, no connections could be made between detection measures (e.g., EEG and heart rate) and user evaluations (e.g., driver acceptance).

Performance measures were not applicable in four of the studies as detected states were not compared to a ground truth. Performance measure calculations were not relevant in Horberry et al. (2022), as they conducted interviews and workshops for developing design principles for a warning system. Heitmann et al. (2001) and Vincent et al. (1998) used observer ratings only to monitor drowsiness; these papers were included in the review as we considered them to simulate a driver monitoring system. An accuracy measure was also not applicable in Chen et al. (2014): although a probabilistic neural network-based drowsiness detection system was described, the experiment was conducted only with alert drivers, which did not require detecting states.

Drowsiness Types and Induction Methods

Seven studies induced drowsiness through low arousal (i.e., passive fatigue) from continuously driving on monotonous roads in the simulator for long durations (Fairclough & Van Winsum, 2000; Hayashi et al., 2021; Kundinger et al., 2021; Liu & Uang, 2010; Nishigaki & Shirakata, 2019; Saito et al., 2016, 2020). Durations varied from 30 to 120 min, although 30-min drives were not sufficient in inducing drowsiness with some participants (Nishigaki & Shirakata, 2019). Saito et al. (2016) observed extreme drowsiness with 13 participants, out of which four fell completely asleep within three 30-minute drives. Only one study created active fatigue conditions with a secondary task for extended durations (90 mins) while driving in the simulator (Baldwin et al., 2014).

Type of sleepiness was unclear in six studies (30%). In particular, with naturalistic studies, researchers did not have access to or control over driving times, road conditions, or time of drives (Aidman et al., 2015; Fitzharris et al., 2017; Kircher et al., 2009; Wolkow et al., 2020). Further, Chen et al. (2014) and Horberry et al. (2022) did not test their systems with sleepy drivers.

Lack of sleep was investigated in five driving simulator studies (Berka et al., 2005; Gaspar et al., 2017; Heitmann et al., 2001; Kozak et al., 2006; Niu & Ma, 2022) and one on-road study (Vincent et al., 1998). Three of these studies scheduled long overnight drives (4–5-hour drives starting at 10 p.m. onwards) with participants awake for more than 14 hr (Berka et al., 2005; Gaspar et al., 2017; Vincent et al., 1998). In Heitmann et al. (2001), the experimental drives were scheduled as multiple trials (each around 30–50 mins) overnight either from 1 to 8 a.m. or from 10 p.m. to 9 a.m. Participants in Kozak et al. (2006) were awake for 23 hr before a three-hour experimental drive at 6 a.m. (without caffeine after 6 p.m. the day before). Niu and Ma (2022) restricted participants’ sleep the night before to at most 5 hr before a 30-min experimental drive. Berka et al. (2005) and Vincent et al. (1998) also reported that some drivers did not show drowsiness levels to trigger the warning systems.

Interventions and Outcomes

A variety of interventions were tested across studies as visualized in Figure 2 and described in Table 5. Figure 2 aims to guide researchers and designers to address the gaps in intervention design, while considering whether an intervention is appropriate for different reasons of drowsiness (Chong & Baldwin, 2021).

Figure 2.

Bubble chart showing the distribution of studies based on their drowsiness and intervention types (highest level is shown). Size of the bubbles indicate the number of studies. Lighter colored bubbles show single stage interventions while darker colored bubbles indicate multistage interventions. The numbers inside the bubbles correspond to study IDs.

TABLE 5:

Descriptions of Interventions and Their Outcomes

ID	Intervention Types	Description	Outcomes
ID	Intervention Types	Description	Sleepiness	Driving Performance	Others
13	Feedback display	Closed/open eyes illustrations to show drowsy/nondrowsy states displayed on the center console.			The system was easy to understand, useful, exciting.Higher perceived usefulness, attitude, and intention in older drivers compared to young drivers
1	Multistage feedback + warning system (auditory)	Level 1—Visual display: A 50 × 80 mm² monochrome LCD screen on the left of dashboard shows sleepiness levels determined by Johns Drowsiness scale (JDS; 0–10). If JDS<4.5 for 5minutes, display blacked out (turned back on if touched).Level 2—Level 1 + auditory warning: Same display as level 1 + beeping sounds when 4.5≤JDS<5.0 and JDS≥5.0.	↓
6	Multistage warning system (auditory, vibratory)	Level 1—Auditory and vibratory warning: “Fatigue detected” voice message or an auditory tone depending on the vehicle. Vibrations issued at 1 Hz for 4 s at the base of the seat.Level 2—Level 1 + feedback to transportation company + fatigue management plan: Notification sent to company’s dispatch center. They advise the driver to take a rest or to swap drivers.	↓	↑
11	Multistage warning system (auditory, visual)	Level 1 (slightly drowsy)—Visual + auditory warning: “Drowsy?” text + discreet beep for 15 s or until a button was pressed. Repeated after 30 minutes (earliest) if drowsiness did not improve.Level 2 (drowsy)—Visual + auditory warning: “You are drowsy” text + discreet beep + a voice recording: “You are too tired to drive” every minute until drowsiness improved or the button was pressed. Repeated after 5 minutes (earliest) if drowsiness did not improve.Level 3 (very drowsy)—Visual + auditory warning: “You will fall asleep soon” text + loud beep + a voice recording: “You are dangerously tired. Stop soon!” every minute until drowsiness improved or the button was pressed. Repeated after 5 minutes (earliest) if drowsiness did not improve.			Generally positive opinions of the system6/7 said they would want to have the system in their car
20	Warning system (auditory, vibratory) + fatigue break procedure	When drowsiness was detected or felt by the driver:Auditory and vibratory warnings issued from a wrist-worn heart rate measurement device.Fatigue break procedure: The driver to (1) find a safe parking spot or a rest area within 10 km, (2) complete a fatigue log and record subjective sleepiness, (3) contact the haulier, evaluate fitness to drive, and follow their advice, (4) take a 35-minute break.	↓	↑	Poor compliance to the fatigue break procedure
10	Multistage warning system (auditory, visual, vibratory)	Level 1—Cautionary warning: Alerting tone + spoken message “caution fatigue” + amber coffee cup on the windscreen as a head up display (HUD) + intermittent seat vibration.Level 2—Urgent warning: Louder, more urgent tone + spoken message “danger fatigue!” + larger, flashing red coffee cup on the windscreen as HUD + continuous seat vibration.			Users accepted the design, found it useful, effective, not likely to excessively interfere with other in-cab systems, and not overly likely to overload or startle. Users noticed and correctly understood different design elements
3	Multistage warning system (auditory)	Auditory alarms with 6 unique sounds, with an increasing urgency.The three most urgent alarms were played for 2 s.If no drowsiness within 20 consecutive seconds, it was reset to the least urgent sound.	↓(marginal)	↑(trends)	Perceived helpfulness in maintaining alertness ↑
7	Single- versus Multistage warning system(Auditory- visual, vibratory, all three combined	Single stage (discrete) alarm: a Yellow coffee cup sign; a 2-tone chime; a double vibration pulse on the left and right side of the driver seat bottomThree-stage alarm (in increasing order): White, yellow, red coffee cup; single beep, 2-tone chime, loud repeating beep (3 s); single vibration pulse, double pulse, repeating pulse.	ns	↑
9	Warning system (vibratory)	In-seat vibration system (TACT): (1) random signals and (2) signals initiated by experimenters based on sleep indicators (e.g., eye closures).	↓	↑
12	Warning system (auditory, visual, vibratory)	HMI-1: Steering wheel torque communicating appropriate steering wheel angle to return to the lane.HMI-2: HMI-1 + Rumble strip sound recording (vehicle driving over rumble strips on an interstate highway with 65 mph).HMI-3: HMI-1 + steering wheel vibration (15 Hz vibrations with 2 Nm peak amplitude for 1.5 s).HMI-4: HMI-1 + HUD (a flashing red LED strip on instrument panel, reflected on windshield within driver’s field of view).		↑	Helpfulness and acceptability ↑ (HMI-2 & HMI-3 compared to HMI-1 & HMI-4)
16	Warning system (auditory)	Alarm levels to prepare drowsy drivers 5 s or 10 s before a takeover request: Low (2 kHz, 60 dB, 2 s), medium (2.5 kHz, 70 dB, 3 s), high (3 kHz, 80 dB, 4 s).		↑	Subjective ratings ↑Glance behavior ↑
19	Warning system (auditory) + breaks	An auditory tone was presented to the driver when fatigue was detected by the observer.Drivers were allowed to take breaks when they felt the need, or they had to take a 15 min break if they hit traffic cones along the track placed at 200 m intervals on the median lane line.	ns		No impact on drivers’ decision to take breaks
2	Warning system (auditory)	Verbal (“danger”) and nonverbal (1000 Hz tone) forward collision warnings.		↑
5	Multistage feedback display + warning system (auditory)	Two visual display types (3F vs. 9F) with voice warnings; Updated every 30 s.Normative performance: Green lightModerate impairment: amber light + “Warning. You are showing symptoms of impairment.”Severe impairment: Red light + “You are highly impaired. Please take a break.”3F: 3 colored lights versus 9F: A dial with 3 colored sections, each further divided into three.	ns	↑	Perceived usefulness ↑Slightly higher perceived accuracy with 9F display compared to 3FNo impact on drivers’ decision to take breaks
14	Multistage warning system (auditory)	Auditory alarms: Drowsiness ratings calculated using Matthews & Desmond’s fatigue rating scales (thresholds determined by guidelines).Rating >20, beep 3 s, stop 3 s; repeat for 1 min.Rating >50, beep 3 s, stop 3 s; repeat for 3 min.Rating >80, beep continually until rating <50.	↓ (marginal)		Subjective ratings of boredom and sleepiness ↓Sensitivity (d’) in detecting signs ↑
15	Multistage feedback display + warning system (visual, vibratory)	Attention levels continuously presented in four discrete levels.Level 1—Visual display + visual warning: Attention level reaches the second lowest level: a message displayed for 6 s: “Attention level low. Time for a break” + white coffee cup icon.Level 2—Visual display + visual and vibratory warning: Attention level reaches the lowest level: a message displayed “Time for a break” + red coffee cup icon + steering wheel vibrations for a short duration.	↓
8	Multistage warning (auditory) + control transition system	A confidence level (CL) index is calculated.CL<50: normal state; system continues monitoring the driver.50≤CL<100: cautious state; system verbally confirms state with driver:Driver rejects: continue monitoring.Driver confirms: Urge the driver to stop and renavigate to the closest parking area.No response within 3.7 s: System starts beeping.No response within the next 0.8 s: extremely dangerous state; emergency brake.CL ≥100: dangerous state; emergency brake.			Workload, evaluated via NASA-TLX: ns
17	Multistage control transition	Level 1—Partial control transition: When a lane departure is predicted due to drowsiness, partial control (α%) is applied to keep the vehicle inside but at the edge of the lane.Level 2—Complete control transition: If no response within 5 s, the driver is assumed to be inattentive. The remaining (100-α)% control is implemented to bring the vehicle to lane center. Deactivated if steering wheel torque input>3 Nm.		↑
18	Multistage control transition	Level 1—Partial control transition: Same as above.Level 2—Complete control transition: Same as above.Level 3—Emergency brake: If no response within the next 10 s, the vehicle stopped.		↑
4	Automation setting change	A driver oriented adaptive cruise control that changes its range keeping style based on drowsiness levels: Reduced headway distance for alert, and increased headway distance for drowsy drivers.	ns	↑	Driver acceptance ↑

Note. Arrows indicate increase (↑) and decrease (↓) in given metrics, while ns indicates no significant change.

Most common interventions were auditory warning systems (n = 14). Some studies integrated a combination of strategies like displays and warnings in Nishigaki and Shirakata (2019). Some interventions were presented to the driver in a multistage approach (n = 12): the first stage informed or cautioned the driver, and then the second stage either urged the driver to take an action (e.g., warnings) or initiated a complete automation takeover.

Feedback systems

Interventions that displayed alertness states fell under this category (Aidman et al., 2015; Fairclough & Van Winsum, 2000; Kundinger et al., 2021; Nishigaki & Shirakata, 2019). Three studies continuously displayed driver states (Fairclough & Van Winsum, 2000; Kundinger et al., 2021; Nishigaki & Shirakata, 2019), while in Aidman et al. (2015), the display was designed to disappear if the risk levels were low for 5 min, which was calculated based on Johns Drowsiness Scale (JDS; a regression model of blink rates and velocity). An auditory alarm rang once the risk levels surpassed a certain threshold. Nishigaki and Shirakata (2019) and Fairclough and Van Vinsum (2000) implemented similar multistage auditory warning systems on top of the state display. Aidman et al. (2015) and Nishigaki and Shirakata (2019) reported reduced sleepiness, while Fairclough and Van Vinsum (2000) found significant improvements in driving performance (steering wheel movement velocity and lateral position). Three studies did not examine the impact of feedback displays alone (Aidman et al., 2015; Fairclough & Van Winsum, 2000; Nishigaki & Shirakata, 2019). Participants in Kundinger et al. (2021) found the display useful and easy to understand. In general, the impact of state feedback displays on driving performance or drowsiness needs further investigation.

Warning systems

Most of the studies (n = 16) incorporated at least one type of warning with visual, auditory, tactile modalities, or a combination of these. Generally, warning systems reduced sleepiness (Aidman et al., 2015; Berka et al., 2005; Fitzharris et al., 2017; Heitmann et al., 2001; Liu & Uang, 2010; Nishigaki & Shirakata, 2019; Wolkow et al., 2020) and improved driving performance (Baldwin et al., 2014; Berka et al., 2005; Fairclough & Van Winsum, 2000; Fitzharris et al., 2017; Gaspar et al., 2017; Heitmann et al., 2001; Kozak et al., 2006; Niu & Ma, 2022; Wolkow et al., 2020). Participants perceived drowsiness warning systems as helpful with high user acceptance (Berka et al., 2005; Fairclough & Van Winsum, 2000; Kozak et al., 2006), as positive, not disturbing, but unnecessary at times (Kircher et al., 2009), and as effective without causing interference with other in-cabin warning systems or overloading or startling (Horberry et al., 2022). On the other hand, participants in Vincent et al. (1998) disregarded the alarms by the warning system.

Only three studies compared different modalities of warnings (Gaspar et al., 2017; Kozak et al., 2006; Nishigaki & Shirakata, 2019). Kozak et al. (2006) and Nishigaki and Shirakata (2019) found that adding vibrations to steering wheel torque and to auditory warnings improved driving performance and time until sleepiness, respectively. Moreover, Kozak et al. (2006) showed that steering wheel torque combined with vibratory warnings was better than torque alone, and torque with a head up display. Gaspar et al. (2017), on the other hand, did not find a significant difference on the outcomes when auditory-visual, haptic, and their combination were compared.

Overall, the variation in measurements and the limited number of studies restrict drawing larger conclusions on drowsiness warning systems, but the existing findings are promising.

Automation systems

Four studies triggered automation when the monitoring system detected drowsiness. Automation upon detecting sleepiness were operationalized in two ways: (1) automation changed its behavior (Chen et al., 2014; Saito et al., 2016, 2020) or (2) automation took over complete control (Hayashi et al., 2021; Saito et al., 2016, 2020). In three of these studies, the systems improved driving performance (Chen et al., 2014; Saito et al., 2016, 2020), while Hayashi et al. (2021) reported trends of increased, but statistically nonsignificant, mental workload. Further, how or when to inform the driver about a control transition and when to perform the transition were not investigated in any of the four studies, which could impact driver acceptance and use of the system. Although Chen et al. (2014) reported good acceptance of the driver-oriented adaptive cruise control that they tested, these opinions belonged only to alert drivers and not to drowsy drivers or those transitioning to drowsiness. More research is needed on the design of the control transitions with sleepy drivers.

Despite the benefits, sudden changes in automation can be startling, confusing, and annoying for the driver, especially in case of false detection of sleepiness. It might also be dangerous, especially in an impaired state. Three of the studies attempted to address the false alarm issue by gradually giving automation control (Saito et al., 2016, 2020), or by getting verbal confirmation from the driver (Hayashi et al., 2021). In Saito et al. (2016, 2020), a partial control transition was performed to keep the vehicle within the lane when drowsiness was first detected. If the driver failed to interfere within 10 s, automation took over lateral control completely to bring the vehicle to the lane center. Finally, if this second stage got activated twice within 30 s, the vehicle assumed that the driver was sleepy and stopped itself. In Hayashi et al. (2021), the driver was asked to verbally confirm whether the detected drowsiness was correct within 3.7 s before the system activated control transition. Due to the small sample size (5 drivers), detection rates were low (55%, Table 4), but false alarms were rectified by driver’s verbal corrections of the detected states. Although not statistically significant, compared to a “No” response, “Yes” was associated with greater mental demand (evaluated through NASA-TLX), which might reflect drivers’ struggle to keep awake. This verbal confirmation might also momentarily improve alertness in passive fatigue states. Moreover, whether the time allowances (e.g., 10 s and 3.7 s) for the driver to intervene before control transitions were adequate need further testing.

Compatibility of design choices with sleepiness types and demographics

Overall, many interventions (n = 7) targeted passive fatigue (Figure 2), whereas active and sleep-related fatigue were not investigated for feedback and automation systems. For passive fatigue, the feedback and warning systems were associated with reduced sleepiness (Fairclough & Van Winsum, 2000; Nishigaki & Shirakata, 2019), improved driving performance (Fairclough & Van Winsum, 2000), good subjective ratings (Fairclough & Van Winsum, 2000; Kundinger et al., 2021; Liu & Uang, 2010), and improved signal detection sensitivity (Liu & Uang, 2010). Similarly, automation systems improved vehicle control in three studies (Hayashi et al., 2021; Saito et al., 2016, 2020). However, it is unclear whether the use of automation would exacerbate passive fatigue as the driver is expected to monitor automation instead of driving actively. None of the latter three studies assessed changes in sleepiness levels after control transition. Further research is needed to understand the impacts of automation interventions on drowsiness levels and its further consequences on the use of and reliance on automation.

All six studies that induced drowsiness through lack of sleep tested a warning system, and five of them reported that driving performance improved (Gaspar et al., 2017; Heitmann et al., 2001; Kozak et al., 2006; Niu & Ma, 2022) or showed marginal improvement (Berka et al., 2005). Two studies reported positive subjective ratings (Kozak et al., 2006; Niu & Ma, 2022). With the warning systems, sleepiness levels marginally decreased (Berka et al., 2005), or remained the same (Gaspar et al., 2017; Vincent et al., 1998). In Vincent et al. (1998), participants were allowed to take breaks (napping was not allowed) when they wished, and the results show that the sleepiness levels first reduced after a break but increased back to the prebreak levels after around 12 min of driving. In the same study, the intervention group had significantly higher drowsiness levels before taking a break compared to their baseline levels and compared to the control group before they took a break. This finding might indicate behavioral adaptations to warnings in which drivers, even if they are sleepier, might think they are fit to drive for longer until they receive a warning.

More than half of the studies incorporated a multistage approach. Interview participants in Horberry et al. (2022) mentioned single stage warnings to be startling and potentially dangerous and preferred multistage warnings. Gaspar et al. (2017) found a significant decrease in lane departures due to drowsiness when a multistage warning system was used as opposed to a single warning. Although other included studies did not investigate the differences in the effectiveness between single and multistage warnings, both type of warnings were found to be effective through multiple measures, including improved sleepiness and driving performance.

Lastly, even though sample demographics across studies were limited, age differences were observed in the effectiveness of warning and feedback systems (Baldwin et al., 2014; Kundinger et al., 2021), with older drivers (65+) benefiting from drowsiness interventions more compared to younger drivers (18–29 or 20–25 year olds, respectively). Warnings helped older drivers reduce crashes (Baldwin et al., 2014). Older drivers found the feedback system in Kundinger et al. (2021) exciting, useful, and easy to understand, and had higher intentions to use the system, especially during long drives at night, compared to younger drivers. The impact of drowsiness interventions on different demographic groups needs to be examined further. How these factors would impact the efficacy of automation interventions is also unknown.

Discussion

This scoping review identified studies which evaluated in-vehicle interventions featuring driver state detection systems for mitigating drowsiness. The popularity of drowsiness detection systems has increased in the last decade, likely due to technological advancements and increased availability of sensors and computational resources. Although overall findings showed positive impact of interventions on sleepiness levels, driving performance, and user evaluations, more research is still needed to understand the effectiveness of such systems and how best to design them. Many studies were excluded from this review due to not implementing an intervention after detecting drowsiness (n = 303) or not evaluating the interventions (n = 94). Much of the relevant research focused on developing and implementing new technology or sensors and improving the accuracy of detection models, but not on how drivers would interact with these technologies.

The drowsiness detection systems utilized in these studies used mainly five categories of features: EEG, heart rate, eye-tracking, body-tracking, and vehicle kinematics. Although a variety of physiological measures (e.g., breathing or sweat response) are commonly utilized in the driver drowsiness detection literature (see Chowdhury et al., 2018; Lohani et al., 2019; Sahayadhas et al., 2012; Sikander & Anwar, 2019; Watling et al., 2021), interventions identified in this review utilized only heart rate and EEG. The use of other physiological measures is yet to be explored for interventions.

In addition, detection performance was mostly not reported, and the reported metrics varied largely. Although other driver state detection studies have shown that adding different types of features (i.e., data fusion) can improve detection accuracy and reduce false alarm rates (e.g., He et al., 2022; Koo et al., 2015), no relationship between the type of measures used for detecting drowsiness (e.g., eye closure) and the resulting algorithm performance (e.g., accuracy) could be ascertained in this review. These metrics are typically reported in the operator state detection research, yet they seem to be omitted when the focus has been on intervention design and testing rather than algorithm development. Detection accuracy levels have a direct influence on intervention outcomes like effectiveness and acceptance. For example, false alarms can lead to confusion, annoyance, and system disuse and users might ignore the alarms and rely on their expected probability of events (Bliss et al., 1995; Parasuraman & Riley, 1997). One possible reason for the omission of accuracy rates might be due to the challenges of establishing a drowsiness ground truth. However, eye closure metrics, EEG data, and observer ratings (Kundinger et al., 2020; Wierwille & Ellsworth, 1994) have been used widely in the literature to identify the ground truth for drowsiness. Similarly, studies have utilized tools like Karolinska Sleepiness Scale (Åkerstedt & Gillberg, 1990) to collect subjective ratings from participants directly.

Overall, design and testing of interventions for different sleepiness types need more research. It is not clear whether an intervention that is effective for one type of sleepiness will perform well for another type. For example, the driver might need extra stimulation with passive fatigue, and decreased stimulation for active fatigue. In the case of lack of sleep, for example, drowsy drivers might need to be supported with advanced driver assistance systems for safely keeping within lane, while this countermeasure might worsen passive fatigue conditions. Further, benefits established in the general alarm literature may not apply directly to the drowsy driving context, as drowsiness occurs due to physiological changes that might impact vigilance and the recovery process (see Chong & Baldwin, 2021 for a detailed review).

Feedback displays that present the detected driver alertness levels have been implemented alone (Kundinger et al., 2021) or in conjunction with warnings (Aidman et al., 2015; Nishigaki & Shirakata, 2019). Such feedback systems can let drivers take appropriate measures and prepare for any further actions from the vehicle (e.g., control transitions), but may also lead to visual clutter. An example of a good strategy to prevent clutter is to dim the display when the driver is not sleepy (Aidman et al., 2015). The trade-off between providing information and display clutter is yet to be explored for drowsiness interventions.

Warnings were the most common intervention type tested, communicating when the driver needed to take a break (Fairclough & Van Winsum, 2000; Fitzharris et al., 2017; Kircher et al., 2009; Vincent et al., 1998; Wolkow et al., 2020) in addition to guiding drivers’ attention to the roadway (e.g., Niu & Ma, 2022). The impact of different modalities is not clear; however, combining modalities might be best to help drivers to notice the warning. Two studies showed that the best combination was auditory and tactile modalities (Kozak et al., 2006; Nishigaki & Shirakata, 2019), with Gaspar et al. (2017) not finding any differences across auditory and haptic modalities and their combination. In the general drowsiness intervention literature (without a state detection system), sounds combined with vibrations were associated with reduced sleepiness compared to no alarms (e.g., Zhao et al., 2012). Potential startling, annoyance, alarm fatigue, or system deactivation with the long-term use of these alarms must be also considered (Marshall et al., 2007; Wilken et al., 2017). As observed in Vincent et al. (1998), drivers might adapt to and over-trust warnings; drivers were observed to let their drowsiness progress further before taking breaks, and the authors reported that the alarms were disregarded by the drivers. Such behavioral adaptations to interventions need further research.

Although control transition strategies can be beneficial in reducing crashes, stopping the vehicle can be abrupt and confusing, especially in cases of false drowsiness detection. To alleviate the negative impact of false alarms, validation steps can be incorporated, such as asking the driver whether they are sleepy as was done in Hayashi et al. (2021), or giving the control to the vehicle gradually as was done in Saito et al. (2016, 2020). However, the relevant design choices were not sufficiently studied. For example, in Hayashi et al. (2021), if drivers did not respond within 3.7 s, the vehicle navigated itself to the nearest parking area, while in Saito et al. (2020), this time was 10 s. The time for control transition might be insufficient in cases when the driver is drowsy or distracted or when the noise levels are high, which may lead to unauthorized control transition.

Majority of the warning interventions utilized multistage warnings to communicate the urgency of the alarms. Both single and multistage interventions showed positive impact on sleepiness, driving performance, and other relevant measures, but only one study compared the two (Gaspar et al., 2017). In this study, the frequency of lane departures due to drowsiness was lower with the multistage warnings than with single stage warnings. It must also be noted that two-stage warning systems were preferred by drivers over single-stage systems; participants in Horberry et al. (2022) found single stage warnings to be startling and potentially dangerous. Both Aidman et al. (2015) and Nishigaki and Shirakata (2019) showed that integrating different modalities in the second stage of their intervention helped with reducing sleepiness. Despite the limited empirical evidence, benefits such as reducing confusion or surprise can be expected with a multistage approach. As well, incorporating multiple modalities at different stages might help communicate urgency, but more research is needed.

Although distractions generally have negative effects in driving, they can be effective strategies for mitigating low arousal states leading to drowsiness. Atchley et al. (2014) showed that strategically timed verbal tasks were effective in improving driving performance and attention to road. Verbal interactions with the vehicle can also lessen passive fatigue symptoms, by imposing mental stimulation (Hayashi et al., 2021). For example, a similar cognitive task was found to be helpful in alleviating the effects of sleep inertia (i.e., impaired cognitive performance after waking up; Hilditch & McHill, 2019) in automated driving tested in a driving simulator study (Wörle et al., 2020).

Future Research Directions

Given the limited but emerging nature of the field, this review helped identify important gaps for future research. First, a large gap exists in understanding intervention efficacy with respect to different types of drowsiness. For example, automation strategies might worsen the passive sleep symptoms by further reducing the physical and cognitive stimulation. On the other hand, automation that allows drivers to sleep for a certain amount of time can address lack of sleep, especially when the driver loses their ability to control the vehicle, in which case sleep inertia needs to be addressed.

In terms of assessing interventions, studies have mostly used sleepiness or driving performance as metrics, while user evaluations of technology and its acceptance were not utilized as much. One critical element that is missing in the literature is determining the best thresholds and parameters for triggering interventions (e.g., time to control transition) for higher user acceptance. In addition to this approach, qualitative research methods (e.g., interviews) can provide useful insights to guide user-centric design. The impact of differences in demographics (e.g., age, professional vs. nonprofessional drivers) on user acceptance has also not been adequately studied.

False alarms can drastically impact the use of drowsiness mitigation systems. Although false alarms are mostly irritating, they can also be dangerous, especially with startling warnings or control transitions. Sudden changes in vehicle control can also create discomfort or motion sickness for passengers. Further studies are needed to explore the performance of these systems under false alarm conditions and to develop potential mitigation strategies similar to Saito et al. (2016, 2020) and Hayashi et al. (2021).

Another critical gap is whether driver overreliance on an automation system can alter their decision to sleep on the road. Even without such interventions in current vehicles, drivers have been reported to intentionally sleep on the road with existing advanced driver assistance systems (Casaletto, 2022; Fitzsimons, 2021; Little & Armstrong, 2021). These systems need to be designed to build driver mental models to support appropriate reliance. Lastly, long term impacts of any of these interventions (feedback, warning, and automation) have not been investigated.

Limitations

Given the limited number of studies, their generally small sample sizes, and the large variability across studies in objectives, designs, collected measures (e.g., heart rate vs. lane deviation), and outcome variables (e.g., sleepiness vs. driving performance), we were limited in our ability to generalize or aggregate findings. The studies screened in this review are limited to those that were published until April 7, 2022, when the search was conducted, to those that included the search keywords in their title, abstract, or keywords, and finally to those that were indexed in the databases searched and the reference lists of the included articles.

Conclusions

This paper explored in-vehicle driver drowsiness interventions that utilize driver state detection. It identified the critical research gaps in the emerging field of drowsiness monitoring and mitigation. Large efforts are being placed in improving detection accuracies. However, how we can best utilize these systems to guide driver attention for improved road safety is unclear, and how intervention outcomes might vary under different drowsiness types remains unexplored. More studies are needed to evaluate interventions, not only for their technical performance, but also for human-vehicle interactions such as potential for confusion, annoyance, and overreliance. Further, the variety in drowsiness measures and outcomes, limitations in sample size and demographical representations, and insufficient study details limit aggregation of existing findings.

Key Points

Much of the research on driver drowsiness monitoring focused on developing and implementing new technology or sensors and improving the accuracy of detection models, but not on how drivers would interact with these technologies.

Drowsiness interventions that utilize state monitoring systems have been found effective in reducing sleepiness, driving performance, and acceptance. However, only a limited number of studies performed evaluations and further research is needed.

Warnings were tested the most; followed by automation control transition and feedback displays. The impact of intervention design on different sleepiness types (e.g., passive fatigue) has not been investigated.

More studies are needed to investigate the long-term effects of these interventions as well as their unintended effects like overreliance on automation, worsened drowsiness, or annoyance and dangers due to false alarms.

Supplemental Material

Supplemental Material - Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review

Supplemental Material for Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review by Suzan Ayas, Birsen Donmez, and Tang Xing in Human Factors

Supplemental Material

Supplemental Material - Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review

Supplemental Material for Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review by Suzan Ayas, Birsen Donmez, and Tang Xing in Human Factors

Supplemental Material

Supplemental Material - Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review

Supplemental Material for Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review by Suzan Ayas, Birsen Donmez, and Tang Xing in Human Factors

Supplemental Material

Supplemental Material - Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review

Supplemental Material for Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review by Suzan Ayas, Birsen Donmez, and Tang Xing in Human Factors

Footnotes

Acknowledgments

This work was supported by the National Sciences and Engineering Research Council of Canada (NSERC) through the Discovery [RGPIN-2016–05580] and the Canada Research Chair Programs. We would like to thank Teruko Kishibe for their feedback on the study protocol and Yihan Wang, Mohamed Abdelwahab, Cole Stotland, and Claire Zhang for their help with the screening phases.

Author Contributions

The authors confirm contribution to the paper as follows: study conception and design: S. Ayas, B. Donmez; data collection: S. Ayas, X. Tang; analysis and interpretation of results: S. Ayas, X. Tang, B. Donmez; draft manuscript preparation: S. Ayas, B. Donmez. All authors reviewed the results and approved the final version of the manuscript.

ORCID iDs

Suzan Ayas

Birsen Donmez

Xing Tang

Supplemental Material

Supplemental material for this article is available online.

Author Biographies

Suzan Ayas is a PhD candidate at the University of Toronto, Department of Mechanical & Industrial Engineering. She received her MASc degree in industrial engineering from the University of Toronto in 2019 and her BSc in industrial engineering from Bogazici University in 2017.

Birsen Donmez is a professor at the University of Toronto, Department of Mechanical & Industrial Engineering, and is the Canada Research Chair in Human Factors and Transportation. She received her PhD in industrial engineering from the University of Iowa in 2007.

Xing Tang is a PhD candidate in Industrial Design at Northwestern Polytechnical University, China. He received his MS degree in industrial design engineering from the Southwest University of Science and Technology, in 2019.

References

Aidman

Chadunow

Johnson

Reece

(2015). Real-time driver drowsiness feedback improves driver alertness and self-reported driving performance. Accident Analysis & Prevention, 81, 8–13. https://doi.org/10.1016/j.aap.2015.03.041

Åkerstedt

T.,

Gillberg

(1990). Subjective and objective sleepiness in the active individual. International Journal of Neuroscience, 52(1–2), 29–37. https://doi.org/10.3109/00207459008994241

APA Dictionary of Psychology . (n.d.-a). https://dictionary.apa.org/drowsiness

APA Dictionary of Psychology . (n.d.-b). https://dictionary.apa.org/fatigue

Arakawa

(2021). A review of heartbeat detection systems for automotive applications. Sensors, 21(18), 6112. https://doi.org/10.3390/s21186112

Atchley

Chan

Gregersen

(2014). A strategically timed verbal task improves performance and neurophysiological alertness during fatiguing drives. Human Factors, 56(3), 453–462. https://doi.org/10.1177/0018720813500305

Baldwin

C. L.

May

J. F.

Parasuraman

(2014). Auditory forward collision warnings reduce crashes associated with task-induced fatigue in young and older drivers. International Journal of Human Factors and Ergonomics, 3(2), 107–121. https://doi.org/10.1504/IJHFE.2014.067804

Berka

Levendowski

D. J.

Westbrook

Davis

Lumicao

M. N.

Olmstead

R. E.

Popovic

Zivkovic

V. T.

Ramsey

C. K.

(2005). Implementation of a closed-loop real-time EEG-based drowsiness detection system: Effects of feedback alarms on performance in a driving simulator. In 1st International Conference on Augmented Cognition (pp. 151–170) Las Vegas, NV.

Bliss

J. P.

Gilson

R. D.

Deaton

J. E.

(1995). Human probability matching behaviour in response to alarms of varying reliability. Ergonomics, 38(11), 2300–2312. https://doi.org/10.1080/00140139508925269

10.

Brown

Vanlaar

W. G.

Robertson

R. D.

(2020). Fatigue-related fatal collisions in Canada, 2000-2016. Traffic Injury Research Foundation.

11.

Casaletto

(2022, September 2). Locals react after man caught allegedly asleep in autopilot Tesla. City News. https://toronto.citynews.ca/

12.

Chen

Dai

Luo

(2014). Investigation of a driver-oriented adaptive cruise control system. International Journal of Vehicle Design, 66(1), 20–42. https://doi.org/10.1504/IJVD.2014.064371

13.

Chong

S. D.,

Baldwin

C. L.

(2021). The origins of passive, active, and sleep-related fatigue. Frontiers in Neuroergonomics, 2, 765322. https://doi.org/10.3389/fnrgo.2021.765322

14.

Chowdhury

Shankaran

Kavakli

Haque

M. M.

(2018). Sensor applications and physiological features in drivers’ drowsiness detection: A review. IEEE Sensors Journal, 18(8), 3055–3067. https://doi.org/10.1109/JSEN.2018.2807245

15.

Covidence systematic review software, Veritas Health Innovation, Melbourne, Australia . (2022). Covidence. https://www.covidence.org/

16.

Desmond

P. A.,

Hancock

P. A.

(2000). Active and passive fatigue states. In Stress, workload, and fatigue (pp. 455–465). https://doi.org/10.1201/b12791-3.1

17.

Fairclough

S. H.,

Van Winsum

(2000). The influence of impairment feedback on driver behavior: A simulator study. Transportation Human Factors, 2(3), 229–246. https://doi.org/10.1207/STHF0203_4

18.

Fitzharris

Liu

Stephens

A. N.

Lenné

M. G.

(2017). The relative importance of real-time in-cab and external feedback in managing fatigue in real-world commercial transport operations. Traffic Injury Prevention, 18(sup1), S71–S78. https://doi.org/10.1080/15389588.2017.1306855

19.

Fitzsimons

(2021, May 18). Tesla driver slept as car was going over 80 mph on Autopilot, Wisconsin officials say. NBC News. https://www.nbcnews.com/

20.

Gaspar

J. G.

Brown

T. L.

Schwarz

C. W.

Lee

J. D.

Kang

Higgins

J. S.

(2017). Evaluating driver drowsiness countermeasures. Traffic Injury Prevention, 18(sup1), S58–S63. https://doi.org/10.1080/15389588.2017.1303140

21.

Gaspar

J. G.,

Carney

(2023). Drowsiness and decision making during long drives: A driving simulation study [Technical Report]. AAA Foundation for Traffic Safety. https://aaafoundation.org/drowsiness-and-decision-making-during-long-drives-a-driving-simulation-study/

22.

Gastaldi

Rossi

Hadas

Fasan

Keren

Mulatti

(2016). Caffeinated chewing gum as countermeasure to drivers’ passive task-related fatigue caused by monotonous roadway. Transportation Research Record: Journal of the Transportation Research Board, 2602(1), 26–34. https://doi.org/10.3141/2602-04

23.

Gershon

Shinar

Oron-Gilad

Parmet

Ronen

(2011). Usage and perceived effectiveness of fatigue countermeasures for professional and nonprofessional drivers. Accident Analysis & Prevention, 43(3), 797–803. https://doi.org/10.1016/j.aap.2010.10.027

24.

Hayashi

Kamezaki

Sugano

(2021). Toward health–related accident prevention: Symptom detection and intervention based on driver monitoring and verbal interaction. IEEE Open Journal of Intelligent Transportation Systems, 2, 240–253. https://doi.org/10.1109/OJITS.2021.3102125

25.

Wang

Khalil

E. B.

Donmez

Qiao

Kumar

(2022). Classification of driver cognitive load: Exploring the benefits of fusing eye-tracking and physiological measures. Transportation Research Record: Journal of the Transportation Research Board, 2676(10), 670–681. https://doi.org/10.1177/03611981221090937

26.

Heitmann

Guttkuhn

Aguirre

Trutschel

Moore-Ede

(2001). Technologies for the monitoring and prevention of driver fatigue. In Driving Assessment Conference (Vol.1 No. 2001). University of Iowa. https://doi.org/10.17077/drivingassessment.1013

27.

Hilditch

C. J.,

McHill

A. W.

(2019). Sleep inertia: Current insights. Nature and Science of Sleep, 11, 155–165. https://doi.org/10.2147/NSS.S188911

28.

Horberry

Mulvihill

Fitzharris

Lawrence

Lenné

Kuo

Wood

(2022). Human-centered design for an in-vehicle truck driver fatigue and distraction warning system. IEEE Transactions on Intelligent Transportation Systems, 23(6), 5350–5359. https://doi.org/10.1109/TITS.2021.3053096

29.

Jang

Kim

Cho

(2017). Stretchertainment: Inducing passive stretching with HUD infotainment in automotive. In Proceedings of the 9th International Conference on Automotive User Interfaces and Interactive Vehicular Applications Adjunct. (pp. 173–177). https://doi.org/10.1145/3131726.3131739

30.

Kircher

Claezon

(2009). Distraction and drowsiness - a field study: Technical report (638A). Statens väg- och transportforskningsinstitut. http://urn.kb.se/resolve?urn=urn:nbn:se:vti:diva-6494

31.

Koo

Kim

Han

(2015). A method for driving control authority transition for cooperative autonomous vehicle. In 2015 IEEE Intelligent Vehicles Symposium (IV) (pp. 394–399). https://doi.org/10.1109/IVS.2015.7225717

32.

Körber

Cingel

Zimmermann

Bengler

(2015). Vigilance decrement and passive fatigue caused by monotony in automated Driving. Procedia Manufacturing, 3, 2403–2409. https://doi.org/10.1016/j.promfg.2015.07.499

33.

Kozak

Pohl

Birk

Greenberg

Artz

Blommer

Cathey

Curry

(2006). Evaluation of lane departure warnings for drowsy drivers. Proceedings of the Human Factors and Ergonomics Society - Annual Meeting, 50(22), 2400–2404. https://doi.org/10.1177/154193120605002211

34.

Kundinger

Mayr

Riener

(2020). Towards a reliable ground truth for drowsiness: A complexity analysis on the example of driver fatigue. Proceedings of the ACM on Human-Computer Interaction, 4(EICS), 1–18. https://doi.org/10.1145/3394980

35.

Kundinger

Riener

Bhat

(2021). Performance and acceptance evaluation of a driver drowsiness detection system based on smart wearables. In 13th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (pp. 49–58). https://doi.org/10.1145/3409118.3475141

36.

Little

S.,

Armstrong

(2021, October 15). Video shows Tesla driver who appears asleep at the wheel on B.C. bridge at rush hour. Global News. https://globalnews.ca/

37.

Liu

C. C.

Hosking

S. G.

Lenné

M. G.

(2009). Predicting driver drowsiness using vehicle measures: Recent insights and future challenges. Journal of Safety Research, 40(4), 239–245. https://doi.org/10.1016/j.jsr.2009.04.005

38.

Liu

C.-L.,

Uang

S.-T.

(2010). A neuro-fuzzy control alarm on momentum of driving behavior for detecting and combating driver fatigue. Journal of the Chinese Institute of Industrial Engineers, 27(5), 379–393. https://doi.org/10.1080/10170669.2010.504059

39.

Lohani

Payne

B. R.

Strayer

D. L.

(2019). A review of psychophysiological measures to assess cognitive states in real-world driving. Frontiers in Human Neuroscience, 13, 57. https://doi.org/10.3389/fnhum.2019.00057

40.

Sjörs Dahlman

Karlsson

Candefjord

(2022). Detecting driver fatigue using heart rate variability: A systematic review. Accident Analysis & Prevention, 178, 106830. https://doi.org/10.1016/j.aap.2022.106830

41.

Marshall

D. C.

Lee

J. D.

Austria

R. A.

(2007). Alerts for in-vehicle information systems: Annoyance, urgency, and appropriateness. Human Factors, 49(1), 145–157. https://doi.org/10.1518/001872007779598145

42.

May

J. F.,

Baldwin

C. L.

(2009). Driver fatigue: The importance of identifying causal factors of fatigue when considering detection and countermeasure technologies. Transportation Research Part F: Traffic Psychology and Behaviour, 12(3), 218–224. https://doi.org/10.1016/j.trf.2008.11.005

43.

Ngxande

Tapamo

J. R.

Burke

(2017). Driver drowsiness detection using behavioral measures and machine learning techniques: A review of state-of-art techniques. In 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech), 156–161. https://doi.org/10.1109/RoboMech.2017.8261140

44.

Nishigaki

Shirakata

(2019). Driver attention level estimation using driver model identification. In 2019 IEEE Intelligent Transportation Systems Conference (ITSC) (pp. 3520–3525). IEEE. https://doi.org/10.1109/ITSC.2019.8917380

45.

Niu

J.,

(2022). Is it good or bad to provide driver fatigue warning during take-over in highly automated driving? Transportation Research Record: Journal of the Transportation Research Board, 2676(2), 762–774. https://doi.org/10.1177/03611981211046920

46.

Owens

J. M.

Dingus

T. A.

Guo

Fang

Perez

McClafferty

Tefft

(2018). Prevalence of drowsy driving crashes: Estimates from a large-scale naturalistic driving study [Research Brief]. AAA Foundation for Traffic Safety.

47.

Parasuraman

Riley

(1997). Humans and automation: Use, misuse, disuse, abuse. Human Factors: The Journal of the Human Factors and Ergonomics Society, 39(2), 230–253. https://doi.org/10.1518/001872097778543886

48.

Sahayadhas

Sundaraj

Murugappan

(2012). Detecting driver drowsiness based on sensors: A review. Sensors, 12(12), 16937–16953. https://doi.org/10.3390/s121216937

49.

Saito

Itoh

Inagaki

(2016). Driver assistance system with a dual control scheme: Effectiveness of identifying driver drowsiness and preventing lane departure accidents. IEEE Transactions on Human-Machine Systems, 46(5), 660–671. https://doi.org/10.1109/THMS.2016.2549032

50.

Saito

Itoh

Inagaki

(2020). Effects of driver drowsiness on driving performance in the context of partial driving automation requiring hands-on-wheel. In 2020 IEEE International Conference on Human-Machine Systems (ICHMS) (pp. 1–4). IEEE. https://doi.org/10.1109/ICHMS49158.2020.9209459

51.

Schömig

Hargutt

Neukum

Petermann-Stock

Othersen

(2015). The interaction between highly automated driving and the development of drowsiness. Procedia Manufacturing, 3, 6652–6659. https://doi.org/10.1016/j.promfg.2015.11.005

52.

Sikander

Anwar

(2019). Driver fatigue detection systems: A review. IEEE Transactions on Intelligent Transportation Systems, 20(6), 2339–2352. https://doi.org/10.1109/TITS.2018.2868499

53.

Smith

S. S.

Horswill

M. S.

Chambers

Wetton

(2009). Hazard perception in novice and experienced drivers: The effects of sleepiness. Accident Analysis & Prevention, 41(4), 729–733. https://doi.org/10.1016/j.aap.2009.03.016

54.

Takahashi

Takaishi

Yokoyama

(2014). Overcoming drowsiness by inducing cardiorespiratory phase synchronization. IEEE Transactions on Intelligent Transportation Systems, 15(3), 982–991. https://doi.org/10.1109/TITS.2013.2292115

55.

Tefft

B. C.

(2012). Prevalence of motor vehicle crashes involving drowsy drivers, United States, 1999–2008. Accident Analysis & Prevention, 45, 180–186. https://doi.org/10.1016/j.aap.2011.05.028

56.

Tricco

A. C.

Lillie

Zarin

O’Brien

K. K.

Colquhoun

Levac

Moher

Peters

M. D. J.

Horsley

Weeks

Hempel

Akl

E. A.

Chang

McGowan

Stewart

Hartling

Aldcroft

Wilson

M. G.

Garritty

Straus

S. E.

(2018). PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and explanation. Annals of Internal Medicine, 169(7), 467–473. https://doi.org/10.7326/M18-0850

57.

Valdez

(2019). Circadian rhythms in attention. Yale Journal of Biology & Medicine, 92(1), 81–92.

58.

Vincent

Noy

Laing

(1998). Behavioural adaptation to fatigue warning systems. In Proceedings of the 16th International Technical Conference on the Enhanced Safety of Vehicles., Ontario–Canada, DOTHS808759, Available at: http://www-nrd.nhtsa.dot.gov/pdf/nrd-01/Esv/Esv16/98S2P21.pdf

59.

Watling

C. N.

Hasan

Md Mahmudul

Larue

G. S.

(2021). Sensitivity and specificity of the driver sleepiness detection methods using physiological signals: A systematic review. Accident Analysis & Prevention, 150. https://doi.org/10.1016/j.aap.2020.105900

60.

Wierwille

W. W.,

Ellsworth

L. A.

(1994). Evaluation of driver drowsiness by trained raters. Accident Analysis & Prevention, 26(5), 571–581. https://doi.org/10.1016/0001-4575(94)90019-1

61.

Wilken

Hüske-Kraus

Klausen

Koch

Schlauch

Röhrig

(2017). Alarm fatigue: Causes and effects. Studies in Health Technology and Informatics, 243, 107–111.

62.

Wolkow

A. P.

Rajaratnam

S. M. W.

Wilkinson

Shee

Baker

Lillington

Roest

Marx

Chew

Tucker

Haque

Schaefer

Howard

M. E.

(2020). The impact of heart rate-based drowsiness monitoring on adverse driving events in heavy vehicle drivers under naturalistic conditions. Sleep Health, 6(3), 366–373. https://doi.org/10.1016/j.sleh.2020.03.005

63.

Wörle

Kenntner-Mabiala

Metz

Fritzsch

Purucker

Befelein

Prill

(2020). Sleep inertia countermeasures in automated driving: A concept of cognitive stimulation. Information, 11(7), 342. https://doi.org/10.3390/info11070342

64.

Yusoff

N. M.

Ahmad

R. F.

Guillet

Malik

A. S.

Saad

N. M.

Merienne

(2017). Selection of measurement method for detection of driver visual cognitive distraction: A review. IEEE Access, 5, 22844–22854. https://doi.org/10.1109/ACCESS.2017.2750743

65.

Zhao

Fang

Rong

Liu

(2012). Sound as a countermeasure against driving fatigue based on ECG (pp. 401–413). https://doi.org/10.1061/41127(382)44

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.25 MB

0.13 MB

0.16 MB

0.44 MB