Driver Readiness Research Articles

Using driver monitoring to estimate readiness in automation: a conceptual model based on simulator experimental data

AbstractThis paper provides a theoretical overview of how the concept of driver readiness can be objectively measured, using controlled experimental data. First, a literature review regarding the concept of driver readiness is provided. Then, it highlights challenges for a standardized readiness estimation model. A conceptual readiness estimation model is presented, and a methodology is proposed for defining readiness thresholds for use by Driver State Monitoring (DSM) systems. The paper then explores how this model can be used to estimate readiness thresholds. A proof of concept for the model application is presented, using previously collected experimental involving SAE Level 2 automation. This paper contributes to the state of the art in DSM-development, by providing a methodology for estimating driver readiness, while considering variabilities across individual drivers. The model also allows readiness thresholds to be defined with data from driving simulator experiments, without relying on subjective assessment of readiness as its ground truth.

Implementing the OT-FIRST Method & Clinical Observations Measure With Young Novice Drivers: A Feasibility Study

Abstract Date Presented 04/22/2023 This study assessed the feasibility of using clinical observations of driver readiness with young novice students using modified aspects of the OT-FIRST method. The study provides scientific evidence supporting the implementation of this young driver readiness assessment process and approach by OT practitioners. This innovative tool and approach supports a necessary step in addressing service and safety gaps identified in OT practice for teens and young adults. Primary Author and Speaker: Missy Bell

Development of Logistics Driver Tenko System (ORIENT) Application Using Scrum Framework

Occupational safety and health hold significant importance for both agencies and individuals alike. A crucial aspect of assessing driver readiness involves examining their physical well-being. Truck drivers who possess unhealthy physical conditions face a four-fold higher risk of work accidents compared to those with sound physical health. PT. Toyota Motor Manufacturing Indonesia (TMMIN), being a manufacturing company, must prioritize occupational safety and health, particularly within the logistics domain. Presently, some logistics partners collaborating with TMMIN adhere to their own standards when conducting checks, relying on paper records for documenting the results. Unfortunately, this approach hinders proper archiving of inspection records and fails to establish a direct link with logistics partner customers in cases involving drivers with health issues. Hence, PT. Toyota Motor Manufacturing Indonesia is dedicated to enhancing the quality of driver health checks through logistics partners by implementing an integrated recording system called the Logistics Driver Tenko System Application (ORIENT). The development of ORIENT is based on the Scrum framework. This research aims to offer insights into the direct implementation of the Scrum method in project development.

DIPNet: Driver intention prediction for a safe takeover transition in autonomous vehicles

AbstractFollowing the successful development of advanced driver assistance systems (ADAS), the current research directions focus on highely automated vehicles aiming at reducing human driving tasks, and extending the operational design domain, while maintaining a higher level of safety. Currently, there are high research demands in academia and industry to predict driver intention and understating driver readiness, e.g. in response to a “take‐over request” when a transition from automated driving mode to human mode is needed. A driver intention prediction system can assess the driver's readiness for a safe takeover transition. In this study, a novel deep neural network framework is developed by adopting and adapting the DenseNet, long short‐term memory, attention, FlowNet2, and RAFT models to anticipate the diver maneuver intention. Using the public “Brain4Cars” dataset, the driver maneuver intention will be predicted up to 4 s in advance, before the commencement of the driver's action. The driver intention prediction is assessed based on 1) in‐cabin 2) out‐cabin (road) and 3) both in‐out cabin video data. Utilizing K‐fold cross‐validation, the performance of the model is evaluated using accuracy, precision, recall, and F1‐score metrics. The experiments show the proposed DIPNet model outperforms the state‐of‐the‐art in the majority of the driving scenarios.

Physiological Measures of Risk Perception in Highly Automated Driving

Highly automated driving will likely result in drivers being out-of-the-loop during specific scenarios and engaging in a wide range of non-driving related tasks. Manifesting in lower levels of risk perception to emerging events, and thus affect drivers’ availability to take-over manual control in safety-critical scenarios. In this empirical research, we measured drivers’ (N = 20) risk perception with cardiac and skin conductance indicators through a series of high-fidelity, simulated highly automated driving scenarios. By manipulating the presence of surrounding traffic and changing driving conditions as long-term risk modulators, and including a driving hazard event as a short-term risk modulator, we hypothesised that an increase in risk perception would induce greater physiological arousal. Our results demonstrate that heart rate variability features are superior at capturing arousal variations from these long-term, low to moderate risk scenarios. In contrast, skin conductance responses are more sensitive to rapidly evolving situations associated with moderate to high risk. Based on this research, future driver state monitoring systems should adopt multiple physiological measures to capture changes in the long and short term, modulation of risk perception. This will enable enhanced perception of driver readiness and improved availability to safely deal with take-over events when requested by an automated vehicle.

Does Shared Mode Improve Steering and Vehicle Motions During Control Transition From Automated to Manual Driving in Real Passenger Car?

Drivers occasionally need to resume vehicle control when an automated driving system (ADS) cannot handle a situation. However, a lack of driver readiness can prevent a smooth transition. For example, in an obstacle avoidance situation, a method to transfer the vehicle control based on the driver’s input of the steering angle can be adopted where rapid steering operation by the driver is required immediately after resuming control. It was observed from the previous studies based on fixed-based driving simulator that the discontinuity in control due to a sudden disengagement of the control torque of the ADS resulted in steering instability. In addition, the previous studies had proposed a shared mode, in which haptic shared control (HSC) was placed between the automated and manual driving. It was demonstrated that steering stability could be improved through the shared mode. However, in the previous studies, the observation of steering instability and verification of HSC effectiveness of the shared mode were limited to fixed-based driving simulator experiments, in which there was no vehicle motion. In addition, for practical applications, a method using a torque sensor in the previous method is expected to be replaced by a more robust method, because it may introduce noise and the use of a lowpass filter leads to some time lag. Therefore, in this study, we developed a new control transition method that uses only the steering angle. We conducted experiments using a real car, in which the participants were instructed to resume steering control from the automated driving mode. The results demonstrate that the discontinuity in control during the control transition deteriorates the steering stability and vehicle motion, and the shared mode can improve them.

A novel study on subjective driver readiness in terms of non-driving related tasks and take-over performance

This study investigates the influence of Non-Driving Related Tasks (NDRTs) on subjective driver readiness and take-over performance in level 3 automated driving system, and the effect of the readiness on driver’s take-over performance. A driving simulator was used to measure driver readiness and take-over performance in the system-initiated transition situation while the driver performed different NDRTs. The results on driver readiness demonstrate that NDRT has a significant effect and the readiness influences take-over performance; driver readiness has a negative correlation with take-over time, on the contrary, a positive correlation with vehicle control quality. NDRT influenced subjective driver readiness resulting in the participants’ take-over performance. We proposed a model for driver readiness and explained subjective driver readiness change at each transition phase using the analyzed data from the simulation study.

An approach to organizing the transition of vehicle control from an automated driving system to a person

The analysis of trends in the development of the automotive industry and well-known methods of automating vehicle control served the basis for us to propose an approach to organizing the transfer of vehicle control from an automated driving system to a person. The approach involves monitoring the vehicle performance and the systems that provide automated driving, the state of the environment and the driver's psychophysiological state, as well as road conditions on the upcoming path, predicting the place and time of transition of control to the driver, determining and regulating his/her readiness to take control if necessary. This approach is peculiar for in time of automated driving, the minimum level of the driver's readiness to operate the vehicle is constantly maintained, which is brought to optimal within a certain time before the scheduled transition to manual control. This two-level monitoring of the condition of drivers of highly automated vehicles will improve road safety both in cases of predicted and unexpected need for an emergency transition from automated to manual driving. The aim of the work is to develop a methodology for improving road safety with highly automated vehicles involved.

Chronic Care for Attention-Deficit/Hyperactivity Disorder: Clinical Management from Childhood Through Adolescence.

Impairments generally persist when children diagnosed with attention-deficit/hyperactivity disorder (ADHD) mature into adolescence. To examine changes in ADHD care during the transition from childhood to adolescence, we conducted a retrospective, longitudinal cohort study of patients diagnosed with ADHD before the age of 10 years to assess changes from preadolescence through adolescence in (1) frequency by which primary care providers offer ADHD care to patients, (2) range of concerns assessed during patient encounters, and (3) treatments implemented or recommended. We identified patients from 3 practices included in a large primary care network who (1) were born between 1996 and 1997, (2) were diagnosed with ADHD before the age of 10 years, and (3) received primary care continuously from age 9 through late adolescence. Clinical care was compared among patients in preadolescence (age 9-11), early adolescence (age 12-14), and late adolescence (age 15-18). Children diagnosed with ADHD before the age of 10 years were less likely to have a documented visit for ADHD during late adolescence (41% of patients) compared with preadolescence (63%, p < 0.001). Evidence of monitoring for depression, suicide, and substance abuse increased from preadolescence to adolescence (p < 0.001) and occurred in about 90% of adolescent patients. However, monitoring for risky sexual activity occurred in only about 50% of adolescents. Discussions of medication diversion and driver readiness were essentially not documented. The findings raise concerns about how primary care providers manage adolescents with a history of ADHD. Improving monitoring of risky sexual behavior and driver readiness and providing patient education about medication diversion are needed.

Teaching Autistic Adolescents and Young Adults to Drive: Perspectives of Specialized Driving Instructors.

Why was this study done? Becoming licensed to drive increases the independence and mobility of adolescents, potentially improving access to educational, occupational training, social, and community engagement opportunities. Driving instructors are a critical resource for families, particularly for autistic adolescents who may receive training from specialized instructors, such as occupational therapists (OTs). However, little is known about the process and experience of teaching autistic adolescents to drive, which limits the ability to provide adolescents and families with guidance to prepare for and support the learning-to-drive process. What was the purpose of this study? The goal of this study was to examine the experiences and perspectives of driving instructors who provide behind-the-wheel training for autistic adolescents and young adults. What did the researchers do? We conducted semistructured interviews with specialized driving instructors who had experience working with autistic youth. Team members transcribed the interviews, coded them, and summarized common themes. What were the results of the study? We interviewed 17 driving instructors who primarily identified as OTs. Key themes included the importance of parents as partners, the need to encourage independence in daily living skills before driving, and the individualized approach used when working with autistic adolescents. Instructors provided suggestions for enhancing the learning-to-drive process and supporting nonspecialized instructors who also provide training to adolescents. Suggestions included enhancing the use of state-level Vocational Rehabilitation Services to provide financial support for instruction, use of a life skills checklist to identify and promote prerequisite driving skills, parent-supervised practice driving (including commentary driving where adolescents narrate driving instructions to a driver), and individualization of instruction tailored to adolescents' particular needs. What do these findings add to what was already known? These results inform efforts to prepare parents, nonspecialized instructors, and autistic adolescents themselves for undertaking on-road instruction and licensure. Instructors recommended that parents help adolescents develop independence, including skills to use alternative forms of transportation and practice predriving skills, such as navigation. Furthermore, these results highlight the need to establish best practices for instruction and refinement of tools and strategies used by both specialized and general driving instructors. What are potential weaknesses in the study? Our recruitment approach may have led instructors with similar training or opinions to participate, so important aspects of teaching autistic drivers may have not been elicited. We did not interview general driving instructors who may have different perspectives and needs that were not discussed. We were unable to determine how characteristics such as work location, race/ethnicity, or years in practice may have influenced participants' responses. How will these findings help autistic adults now or in the future? Results from this study identify tools, such as a life skills checklist, and practice activities, such as commentary driving, that can be used by families to support autistic adolescents who are learning to drive. This study highlights the need to examine experiences with the learning-to-drive process from autistic adolescents and parents themselves to understand their needs and recommendations for enhancing the process of safely learning to drive.

Transitions to manual control from highly automated driving in non-critical truck platooning scenarios

Automated truck platooning is getting an increasing interest for its potentially beneficial effects on fuel consumption, driver workload, traffic flow efficiency, and safety. Nevertheless, one major challenge lies in the safe and comfortable transitions of control from the automated system back to the human drivers, especially when they have been inattentive during highly automated driving. In this study, we investigated truck drivers’ take-over response times after a system initiated request to take back control in non-critical truck platooning scenarios. 22 professional truck drivers participated in the truck driving simulator experiment and everyone was instructed to drive under three task conditions during highly automated driving: Driver monitoring condition (drivers were instructed to monitor the surroundings), Driver not-monitoring condition (drivers were provided with a hand-held tablet and were asked to use this), and Eyes-closed condition (drivers were not allowed to open their eyes). The total take-over response time was divided into the perception response time and the movement response time by manual video annotation. Results showed significantly longer total take-over times with high variability in both Driver not-monitoring and Eyes-closed conditions compared to the Driver monitoring condition. Hand movement response time was found to be the dominant component of the total take-over time, being influenced by the motoric manoeuvres to resume physical readiness before taking over control (e.g., putting away the hand-held tablet, or adjusting seating position). These results suggest the importance of a personalized driver readiness predictor as an input parameter for a safe and comfortable transition of control.

Brake Response Time Recovery After Achilles Tendon Repair.

Background. This study evaluated when patients' brake response time (BRT) recovers after right Achilles repair. Methods. Institutional review board-approved prospective study of 60 patients. Assessments included visual analogue scale pain (VAS) score, Achilles Tendon Total Rupture Score (ATRS), and a driver readiness survey. Emergent brake pedal operation was simulated at 6 weeks postoperatively and repeated until patients achieved a passing BRT. Results. Fifty-seven patients completed the study. At 6 weeks, 54 of 59 (91.5%) patients had a passing BRT with a mean of 0.60 seconds (SD 0.08 seconds). Five (8.5%) patients had a failing BRT with a significantly higher mean of 0.95 seconds (SD 0.13 seconds, P = .01). At first testing, all patients were ambulating in a walking boot with removable heel wedges. Those who passed were using significantly fewer wedges (mean 1.9 vs 2.6 wedges, P = .04). Mean VAS pain scores (Passed: 1.1, SD 1.57, vs Failed: 2.8, SD 3.35, P = .32) were not significantly different. The mean ATRS was significantly lower among those who passed (63.7, SD 16.7, vs 85.4, SD 11.1, P = .01. Three patients repeated testing at a mean 7.3 weeks (range 6.7-8). All achieved passing times (mean 0.68 seconds, range 0.55 to 0.77 seconds). The driving readiness survey was 100% sensitive but 31.3% specific for passing BRT. Its positive predictive value was 80%, and its negative predictive value was 100%. Conclusion. BRT normalizes around 6 to 7 weeks after open right Achilles tendon repair. The ATRS and driver readiness questionnaire corresponded to achieving a passing BRT. Levels of Evidence: Prognostic Level II: Prospective Cohort Study.

Driving After Total Ankle Arthroplasty

Category: Ankle Introduction/Purpose: With the increase in number of total ankle arthroplasty surgery, physician guidelines on when to begin to consider patients’ return to driving is valuable. The ability to accurately and efficiently determine when a patient can return to driving is important both from a patient safety and a medicolegal perspective. The purpose of the study was to determine when patients’ brake reaction time (BRT) returns to a safe value after right total ankle arthroplasty. We also aimed to identify predictive factors that may identify those patients who may not be safe to drive. Methods: After institutional review board approval, fifty-five patients undergoing right total ankle arthroplasty were recruited prospectively. Patient demographics include an age range of 43 to 83 years (median 63 years), of which 31 were male (56%) and 24 were female (44%). BRT was tested at six weeks and repeated weekly until patients achieved a passing BRT. A control group of twenty healthy patients was used to establish a passing BRT of 0.850 seconds. Patients were given a validated, novel driver readiness survey to complete of which a 10/15 point or higher score was considered passing. Results: At 6 weeks, 50 patients (91%) achieved a passing BRT and were considered safe to drive, and the passing group average BRT was 0.662 seconds. At 9 weeks, 52 patients (100%) of those who completed the study achieved a passing BRT. Patients that failed at 6 weeks had statistically greater visual analog scale (VAS) for pain (p=0.037) and significantly diminished ankle plantarflexion (p=0.029). There is a significant (p&lt;0.001) and large (r=-0.455) correlation between BRT and the validated driver readiness survey scores. 5/5 (100%) patients that failed the BRT also failed the driver readiness survey (p=0.049). Interestingly, males were more likely to think they were ready to drive based on their driver readiness survey but were no more likely to pass the BRT than females (p=0.002). Conclusion: Over 90% of patients may be eligible to return to driving as early as 6 weeks post-operatively. Indications that a patient is not safe to return to driving at 6 weeks are higher VAS, limited plantarflexion, and a failed driver readiness survey. Although many factors determine whether a patient may safely return to driving, patients may be informed that BRT normalizes 9 weeks after right total ankle arthroplasty.

Driving After Hallux Valgus Surgery.

The purpose of the study was to determine when patients can safely return to driving after first metatarsal osteotomy for hallux valgus correction. After institutional review board approval, 60 patients undergoing right first metatarsal osteotomy for hallux valgus correction surgery were recruited prospectively. Patients' brake reaction time (BRT) was tested at 6 weeks and repeated until patients achieved a passing BRT. A control group of twenty healthy patients was used to establish as passing BRT. Patients were given a novel driver readiness survey to complete. At 6 weeks, 51 of the 60 patients (85%) had BRT less than 0.85 seconds and were considered safe to drive. At 6 weeks, the passing group average was 0.64 seconds. At the 8 weeks, 59 patients (100%) of those who completed the study achieved a passing BRT. Patients that failed at 6 weeks had statistically greater visual analog scale (VAS) pain score and diminished first metatarsophalangeal (MTP) range of motion (ROM). On the novel driver readiness survey, 8 of the 9 patients (89%) who did not pass disagreed or strongly disagreed with the statement, "Based on what I think my braking reaction time is, I think that I am ready to drive." Most patients may be informed that they can safely return to driving 8 weeks after right metatarsal osteotomy for hallux valgus correction. Some patients may be eligible to return to driving sooner depending on their VAS, first MTP ROM, and driver readiness survey results. Level II, comparative study.