The Effect of Partial Automation on Driver Attention: A Naturalistic Driving Study

2019 ◽  
Vol 61 (8) ◽  
pp. 1261-1276 ◽  
Author(s):  
John Gaspar ◽  
Cher Carney
Keyword(s):  
Visual Attention ◽  
New Technology ◽  
Video Data ◽  
Instrument Panel ◽  
Negative Consequences ◽  
Automated Vehicle ◽  
Naturalistic Driving Study ◽  
Naturalistic Driving ◽  
Vehicle Automation ◽  
Partial Automation

Objective: This naturalistic driving study investigated how drivers deploy visual attention in a partially automated vehicle. Background: Vehicle automation is rapidly increasing across vehicle fleets. This increase in automation will likely have both positive and negative consequences as drivers learn to use the new technology. Research is needed to understand how drivers interact with partially automated vehicle systems and what impact new technology has on driver attention. Method: Ten participants drove a Tesla Model S for 1 week during their daily commute on a stretch of busy interstate. Drivers were instructed to use Autopilot, a system that provides both lateral and longitudinal control, as much as they felt comfortable while driving on the interstate. Driver-facing video data were recorded and manually reduced to examine glance behavior. Results: Drivers primarily allocated their visual attention between the forward roadway (74% of glance time) and the instrument panel (13%). With partial automation engaged, drivers made longer single glances and had longer maximum total-eyes-off-road time (TEORT) associated with a glance cluster. Conclusion: These results provide a window into the nature of visual attention while driving with partial vehicle automation. The results suggest that drivers may be more willing to execute long, “outlier” glances and clusters of glances to off-road locations with partial automation. The findings highlight several important human factors considerations for partially automated vehicles.

Effects and Risks of Distance Learning in Higher Education

2020 ◽  
pp. 61-73
Author(s):  
Yu. M. Tsygalov
Keyword(s):  
Higher Education ◽  
Distance Learning ◽  
Online Education ◽  
New Technology ◽  
Negative Consequences ◽  
Higher Education System ◽  
First Results ◽  
Spread Of Infection ◽  
The Cost

The forced work of Russian universities remotely in the context of the pandemic (COVID-19) has generated a lot of discussion about the benefits of the new form of education. The first results were summed up and reports were presented, the materials of which showed that the main goal of online education — the prevention of the spread of infection, - has been achieved. Against this background, proposals and publications have appeared substantiating the effectiveness of the massive introduction of distance learning in Russia, including in higher education. However, the assessment of such training by the population and students in publications and in social networks was predominantly negative and showed that the number of emerging problems exceeds the possible benefits of the new educational technology. Based on the analysis of the materials of publications and personal experience of teaching online, the potential benefits and problems of distance learning in higher education in Russia are considered. It is proposed to consider the effects separately for the suppliers of new technology (government, universities) and consumers (students, teachers, society). It is substantiated that the massive introduction of online education allows not only to reduce the negative consequences of epidemics, but also to reduce budgetary funding for universities, optimize the age composition of teachers, and reduce the cost of maintaining educational buildings. However, there will be a leveling / averaging of the quality of education, and responsibility for the quality of training will shift from the state/universities to students. The critical shortcomings of online education are the low degree of readiness of the digital infrastructure, the lack of a mechanism for identifying and monitoring the work of students, information security problems, and the lack of trust in such training of the population. The massive use of online education creates a number of risks for the country, the most critical of which is the destruction of the higher education system and a drop in the effectiveness of personnel training. The consequences of this risk realization are not compensated by any possible budget savings.

Machine Learning Approach for Predicting Lane-Change Maneuvers using the SHRP2 Naturalistic Driving Study Data

2021 ◽  
pp. 036119812110035
Author(s):  
Anik Das ◽  
Mohamed M. Ahmed
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Lane Change ◽  
Adaptive Boosting ◽  
Extreme Gradient Boosting ◽  
Naturalistic Driving Study ◽  
Naturalistic Driving ◽  
Change Prediction

Accurate lane-change prediction information in real time is essential to safely operate Autonomous Vehicles (AVs) on the roadways, especially at the early stage of AVs deployment, where there will be an interaction between AVs and human-driven vehicles. This study proposed reliable lane-change prediction models considering features from vehicle kinematics, machine vision, driver, and roadway geometric characteristics using the trajectory-level SHRP2 Naturalistic Driving Study and Roadway Information Database. Several machine learning algorithms were trained, validated, tested, and comparatively analyzed including, Classification And Regression Trees (CART), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Naïve Bayes (NB) based on six different sets of features. In each feature set, relevant features were extracted through a wrapper-based algorithm named Boruta. The results showed that the XGBoost model outperformed all other models in relation to its highest overall prediction accuracy (97%) and F1-score (95.5%) considering all features. However, the highest overall prediction accuracy of 97.3% and F1-score of 95.9% were observed in the XGBoost model based on vehicle kinematics features. Moreover, it was found that XGBoost was the only model that achieved a reliable and balanced prediction performance across all six feature sets. Furthermore, a simplified XGBoost model was developed for each feature set considering the practical implementation of the model. The proposed prediction model could help in trajectory planning for AVs and could be used to develop more reliable advanced driver assistance systems (ADAS) in a cooperative connected and automated vehicle environment.

Understanding Gap Acceptance Behavior at Unsignalized Intersections using Naturalistic Driving Study Data

2021 ◽  
pp. 036119812110071
Author(s):  
Yingfeng (Eric) Li ◽  
Haiyan Hao ◽  
Ronald B. Gibbons ◽  
Alejandra Medina
Keyword(s):  
Road Traffic ◽  
Wait Time ◽  
Study Data ◽  
Gap Acceptance ◽  
Factors Affecting ◽  
Unsignalized Intersections ◽  
Research Activities ◽  
Stop Sign ◽  
Naturalistic Driving Study ◽  
Naturalistic Driving

Even though drivers disregarding a stop sign is widely considered a major contributing factor for crashes at unsignalized intersections, an equally important problem that leads to severe crashes at such locations is misjudgment of gaps. This paper presents the results of an effort to fully understand gap acceptance behavior at unsignalized intersections using SHPR2 Naturalistic Driving Study data. The paper focuses on the findings of two research activities: the identification of critical gaps for common traffic/roadway scenarios at unsignalized intersections, and the investigation of significant factors affecting driver gap acceptance behaviors at such intersections. The study used multiple statistical and machine learning methods, allowing a comprehensive understanding of gap acceptance behavior while demonstrating the advantages of each method. Overall, the study showed an average critical gap of 5.25 s for right-turn and 6.19 s for left-turn movements. Although a variety of factors affected gap acceptance behaviors, gap size, wait time, major-road traffic volume, and how frequently the driver drives annually were examples of the most significant.

scholarly journals Impact of External Human–Machine Interface Communication Strategies of Automated Vehicles on Pedestrians’ Crossing Decisions and Behaviors in an Urban Environment

2021 ◽  
Vol 13 (15) ◽  
pp. 8396
Author(s):  
Marc Wilbrink ◽  
Merle Lau ◽  
Johannes Illgner ◽  
Anna Schieben ◽  
Michael Oehl
Keyword(s):  
Urban Traffic ◽  
Automated Vehicles ◽  
Negative Effects ◽  
Communication Tools ◽  
Automated Vehicle ◽  
Additional Information ◽  
Road Users ◽  
Vulnerable Road Users ◽  
And Behaviors ◽  
Vehicle Automation

The development of automated vehicles (AVs) and their integration into traffic are seen by many vehicle manufacturers and stakeholders such as cities or transportation companies as a revolution in mobility. In future urban traffic, it is more likely that AVs will operate not in separated traffic spaces but in so-called mixed traffic environments where different types of traffic participants interact. Therefore, AVs must be able to communicate with other traffic participants, e.g., pedestrians as vulnerable road users (VRUs), to solve ambiguous traffic situations. To achieve well-working communication and thereby safe interaction between AVs and other traffic participants, the latest research discusses external human–machine interfaces (eHMIs) as promising communication tools. Therefore, this study examines the potential positive and negative effects of AVs equipped with static (only displaying the current vehicle automation status (VAS)) and dynamic (communicating an AV’s perception and intention) eHMIs on the interaction with pedestrians by taking subjective and objective measurements into account. In a Virtual Reality (VR) simulator study, 62 participants were instructed to cross a street while interacting with non-automated (without eHMI) and automated vehicles (equipped with static eHMI or dynamic eHMI). The results reveal that a static eHMI had no effect on pedestrians’ crossing decisions and behaviors compared to a non-automated vehicle without any eHMI. However, participants benefit from the additional information of a dynamic eHMI by making earlier decisions to cross the street and higher certainties regarding their decisions when interacting with an AV with a dynamic eHMI compared to an AV with a static eHMI or a non-automated vehicle. Implications for a holistic evaluation of eHMIs as AV communication tools and their safe introduction into traffic are discussed based on the results.

scholarly journals Drivers’ Perceptions of Functionality Implied by Terms Used to Describe Automation in Vehicles

2018 ◽  
Vol 62 (1) ◽  
pp. 1893-1897 ◽  
Author(s):  
Michael A. Nees
Keyword(s):  
Future Research ◽  
Automated Vehicle ◽  
Human Driver ◽  
Trust In Automation ◽  
Vehicle Automation ◽  
First Time

The expectations induced by the labels used to describe vehicle automation are important to understand, because research has shown that expectations can affect trust in automation even before a person uses the system for the first time. An online sample of drivers rated the perceived division of driving responsibilities implied by common terms used to describe automation. Ratings of 13 terms were made on a scale from 1 (“human driver is entirely responsible”) to 7 (“vehicle is entirely responsible”) for three driving tasks (steering, accelerating/braking, and monitoring). In several instances, the functionality implied by automation terms did not match the technical definitions of the terms and/or the actual capabilities of the automated vehicle functions currently described by the terms. These exploratory findings may spur and guide future research on this under-examined topic.

scholarly journals Usability Flaws in Medication Alerting Systems: Impact on Usage and Work System

2015 ◽  
Vol 24 (01) ◽  
pp. 55-67 ◽  
Author(s):  
E. Ammenwerth ◽  
E. Roehrer ◽  
S. Pelayo ◽  
F. Vasseur ◽  
M.-C. Beuscart-Zéphir ◽  
...  
Keyword(s):  
Patient Safety ◽  
New Technology ◽  
Medication Management ◽  
Secondary Analysis ◽  
Previous Attempt ◽  
Negative Consequences ◽  
Negative Outcomes ◽  
Work Systems ◽  
Work System ◽  
Alerting Systems

Summary Objectives: Previous research has shown that medication alerting systems face usability issues. There has been no previous attempt to systematically explore the consequences of usability flaws in such systems on users (i.e. usage problems) and work systems (i.e. negative outcomes). This paper aims at exploring and synthesizing the consequences of usability flaws in terms of usage problems and negative outcomes on the work system. Methods: A secondary analysis of 26 papers included in a prior systematic review of the usability flaws in medication alerting was performed. Usage problems and negative outcomes were extracted and sorted. Links between usability flaws, usage problems, and negative outcomes were also analyzed. Results: Poor usability generates a large variety of consequences. It impacts the user from a cognitive, behavioral, emotional, and attitudinal perspective. Ultimately, usability flaws have negative consequences on the workflow, the effectiveness of the technology, the medication management process, and, more importantly, patient safety. Only few complete pathways leading from usability flaws to negative outcomes were identified.Conclusion: Usability flaws in medication alerting systems impede users, and ultimately their work system, and negatively impact patient safety. Therefore, the usability dimension may act as a hidden explanatory variable that could explain, at least partly, the (absence of) intended outcomes of new technology.

Studying Driving Behavior on Horizontal Curves using Naturalistic Driving Study Data

2018 ◽  
Vol 2672 (17) ◽  
pp. 83-95 ◽  
Author(s):  
Bashar Dhahir ◽  
Yasser Hassan
Keyword(s):  
Data Collection ◽  
Weather Conditions ◽  
Driving Behavior ◽  
Study Data ◽  
Output Analysis ◽  
Horizontal Curves ◽  
Naturalistic Driving Study ◽  
Naturalistic Driving ◽  
Design Consistency ◽  
Favorable Weather

Many studies have been conducted to develop models to predict speed and driver comfort thresholds on horizontal curves, and to evaluate design consistency. The approaches used to develop these models differ from one another in data collection, data processing, assumptions, and analysis. However, some issues might be associated with the data collection that can affect the reliability of collected data and developed models. In addition, analysis of speed behavior on the assumption that vehicles traverse horizontal curves at a constant speed is far from actual driving behavior. Using the Naturalistic Driving Study (NDS) database can help overcome problems associated with data collection. This paper aimed at using NDS data to investigate driving behavior on horizontal curves in terms of speed, longitudinal acceleration, and comfort threshold. The NDS data were valuable in providing clear insight on drivers’ behavior during daytime and favorable weather conditions. A methodology was developed to evaluate driver behavior and was coded in Matlab. Sensitivity analysis was performed to recommend values for the parameters that can affect the output. Analysis of the drivers’ speed behavior and comfort threshold highlighted several issues that describe how drivers traverse horizontal curves that need to be considered in horizontal curve design and consistency evaluation.

Sign in / Sign up

Export Citation Format

Share Document