“Driver Take Over”: A Preliminary Exploration of Driver Trust and Performance in Autonomous Vehicles

2017 ◽  
Vol 61 (1) ◽  
pp. 1969-1973 ◽  
Author(s):  
Michelle Hester ◽  
Kevin Lee ◽  
Brian P. Dyre
Keyword(s):  
Situation Awareness ◽  
Autonomous Vehicles ◽  
Autonomous Systems ◽  
Automated Vehicles ◽  
Automated Vehicle ◽  
Preliminary Study ◽  
And Performance ◽  
Task Irrelevant ◽  
Statistical Results ◽  
And Task

Automated vehicles are becoming more prominent in research and development. These automated vehicles introduce issues that have been seen in other autonomous systems such as decreases in situation awareness, complacency, and trust. Previous literature has looked at the effects of alerts and voice agents on driving performance. This preliminary study compares different in-car alerts (no alert, sound alert, task irrelevant voice alert, and task relevant voice alert) on trust and the driver’s ability to get back in-the-loop when the automation has failed. Participants were asked to monitor a simulated automated vehicle as it drove down a straight two-lane road. The main statistical results of our study show no difference in trust between the four different conditions; however, more participants avoided collision with a leading car in the task relevant voice condition in comparison to the three other conditions. These preliminary findings have important implications for the design of automated vehicles.

Driver Vigilance in Automated Vehicles: Hazard Detection Failures Are a Matter of Time

2018 ◽  
Vol 60 (4) ◽  
pp. 465-476 ◽  
Author(s):  
Eric T. Greenlee ◽  
Patricia R. DeLucia ◽  
David C. Newton
Keyword(s):  
Safety Concern ◽  
Reaction Times ◽  
Vigilance Task ◽  
Time On Task ◽  
Vigilance Decrement ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Automated Vehicle ◽  
Hazard Detection ◽  
And Performance

Objective: The primary aim of the current study was to determine whether monitoring the roadway for hazards during automated driving results in a vigilance decrement. Background: Although automated vehicles are relatively novel, the nature of human-automation interaction within them has the classic hallmarks of a vigilance task. Drivers must maintain attention for prolonged periods of time to detect and respond to rare and unpredictable events, for example, roadway hazards that automation may be ill equipped to detect. Given the similarity with traditional vigilance tasks, we predicted that drivers of a simulated automated vehicle would demonstrate a vigilance decrement in hazard detection performance. Method: Participants “drove” a simulated automated vehicle for 40 minutes. During that time, their task was to monitor the roadway for roadway hazards. Results: As predicted, hazard detection rate declined precipitously, and reaction times slowed as the drive progressed. Further, subjective ratings of workload and task-related stress indicated that sustained monitoring is demanding and distressing and it is a challenge to maintain task engagement. Conclusion: Monitoring the roadway for potential hazards during automated driving results in workload, stress, and performance decrements similar to those observed in traditional vigilance tasks. Application: To the degree that vigilance is required of automated vehicle drivers, performance errors and associated safety risks are likely to occur as a function of time on task. Vigilance should be a focal safety concern in the development of vehicle automation.

Autonomous Driving Systems: A Preliminary Naturalistic Study of the Tesla Model S

2017 ◽  
Vol 11 (3) ◽  
pp. 225-238 ◽  
Author(s):  
Mica R. Endsley
Keyword(s):  
Situation Awareness ◽  
Autonomous Vehicles ◽  
Autonomous Systems ◽  
Model Development ◽  
Autonomous Driving ◽  
Discrete Control ◽  
Driving Safety ◽  
Future Research ◽  
Continuous Control ◽  
Development Mode

Autonomous and semiautonomous vehicles are currently being developed by over14 companies. These vehicles may improve driving safety and convenience, or they may create new challenges for drivers, particularly with regard to situation awareness (SA) and autonomy interaction. I conducted a naturalistic driving study on the autonomy features in the Tesla Model S, recording my experiences over a 6-month period, including assessments of SA and problems with the autonomy. This preliminary analysis provides insights into the challenges that drivers may face in dealing with new autonomous automobiles in realistic driving conditions, and it extends previous research on human-autonomy interaction to the driving domain. Issues were found with driver training, mental model development, mode confusion, unexpected mode interactions, SA, and susceptibility to distraction. New insights into challenges with semiautonomous driving systems include increased variability in SA, the replacement of continuous control with serial discrete control, and the need for more complex decisions. Issues that deserve consideration in future research and a set of guidelines for driver interfaces of autonomous systems are presented and used to create recommendations for improving driver SA when interacting with autonomous vehicles.

Crew Structure, Automation and Communication: Interaction of Social and Technological Factors on Complex Systems Performance

1989 ◽  
Vol 33 (13) ◽  
pp. 783-787 ◽  
Author(s):  
Susan G. Straus ◽  
Russell S. Cooper
Keyword(s):  
Group Communication ◽  
Group Structure ◽  
Automated Control ◽  
Flight Experiment ◽  
Technological Factors ◽  
Flight Experience ◽  
Communication Interaction ◽  
And Performance ◽  
Task Irrelevant ◽  
And Task

The effects of automation and task group social structure on group communication and performance are investigated in a simulated flight experiment. Fifty, two-person crews flew a ninety minute mission in a fully instrumented, GAT-II simulator. Crews were composed to be either homogeneous or heterogeneous with respect to crew members' flight experience and age. Approximately half of the crews flew with the aid of automated control; the other half flew manually. All cockpit communications were recorded and subjected to content analysis. Based on the analysis of twenty-four transcripts, there was no overall difference in communication patterns as a function of crew composition. However, the results indicated that heterogeneous crews tended to exchange a higher ratio of task relevant to task irrelevant statements compared to homogeneous crews, but this tendency was moderated by automation level. This interaction corresponds to performance data that show enhanced performance for heterogeneous crews in the automated condition. Additional evidence and discussion suggest that group structure and interaction may contribute to the observed performance differences.

Do We Need a Change in Road Winter Maintenance to Accommodate for Automated Vehicles? A State-of-the-Art Literature Review Considering Automated Vehicle Technology’s Usage of Road Infrastructure During Winter

2021 ◽  
pp. 036119812110124
Author(s):  
Ingvild Ødegård ◽  
Alex Klein-Paste
Keyword(s):  
Literature Review ◽  
Autonomous Vehicles ◽  
Satellite System ◽  
Level Of Service ◽  
Automated Vehicles ◽  
Time Data ◽  
Road Infrastructure ◽  
Winter Maintenance ◽  
Automated Vehicle ◽  
Adverse Weather

For automated vehicles to be allowed to join the modern car fleet, and, in the future, replace human drivers, they must be able to handle adverse weather, including snowy conditions. This literature review focuses on how automated vehicles utilize the road and how this use is suitable for winter maintenance strategies. Where global navigation satellite system (GNSS) service is unavailable, automated vehicles need bare roads to perform relative navigation based on real-time data about lane markings, obstacles, and road infrastructure. Snow-covered tracks hinder vehicle navigation and lane marking detection, which might generate wheel slippage that in turn causes emergency stop and challenging friction estimates. Although the entry of automated vehicles into the car fleet does not demand change in the strategies of winter maintenance, it does demand higher level of service than today. Maintaining an entire road network on which autonomous vehicles always can operate is tremendously expensive and likely not feasible. One solution could be to add another maintenance class in a bare road strategy, that is, an automated vehicle maintenance class with a high level of service and a set of operational criteria allowing automated vehicles to operate. The maintenance class should be used for certain main routes where there is a high frequency of automated vehicles. A model that recommends preferable routes to the destination based on current road conditions within the operational envelope should be provided to the automated vehicle system.

scholarly journals Autonomous and Automated Vehicles in Germany and Hungary, with Special Attention to the Question of Civil Liability

2021 ◽  
Vol 10 (1) ◽  
pp. 55-64
Author(s):  
Béla Csitei
Keyword(s):  
Autonomous Vehicles ◽  
Road Traffic ◽  
Autonomous Vehicle ◽  
Civil Liability ◽  
Automated Vehicles ◽  
Automated Vehicle ◽  
Legal Literature ◽  
The World ◽  
History Of ◽  
Definition Of

The most frequent questions associated with autonomous vehicles both in the world press and in legal literature are those that look for the answer as to who is responsible for the accidents caused by these machines. However, only a few such questions deal with the issue that all factums apply different definitions, and the terminology is the basis of applying the particular factum. So, among others, answering the question is inevitable as to whether the autonomous or automated vehicle can be considered a ‘vehicle’, or the human sitting in the car can be considered the ‘driver’. If we decide not to consider the autonomous vehicle to be a vehicle, and – ad absurdum – we create an independent, sui generis category of vehicles, then the legal factums regarding the definition of the vehicle will not be applicable to the factum concerning the history of autonomous vehicles; however, their applicability will surely be questioned. With regard to this, I focus in my study on how the German Road Traffic Act (Straßenverkehrsgesetz) accommodates more advanced automated vehicles, and after this I compare the Hungarian and German rules that are relevant in terms of civil liability if we study the vehicles in question.

scholarly journals Context-Based Visual Aids to Support the Situation Awareness of Field Engineers Conducting Windstorm Risk Surveys

2019 ◽  
Vol 63 (1) ◽  
pp. 1898-1902
Author(s):  
Sruthy Agnisarman ◽  
Kapil Chalil Madathil ◽  
Jeffery Bertrand
Keyword(s):  
Experimental Design ◽  
Situation Awareness ◽  
Decision Aids ◽  
Weather Condition ◽  
Extreme Weather ◽  
Visual Aids ◽  
Loss Prevention ◽  
Predictive Display ◽  
Independent Variable ◽  
And Performance

Insurance loss prevention survey, specifically windstorm risk inspection survey is the process of investigating potential damages associated with a building or structure in the event of an extreme weather condition such as a hurricane or tornado. This process is performed by a trained windstorm risk engineer who physically goes to a facility to assess the wind vulnerabilities associated with it. This process is highly subjective, and the accuracy of findings depends on the experience and skillsets of the engineer. Although using sensors and automation enabled systems help engineers gather data, their ability to make sense of this information is vital. Further, their Situation Awareness (SA) can be affected by the use of such systems. Using a between-subjects experimental design, this study explored the use of various context-based visualization strategies to support the SA requirements and performance of windstorm risk engineers. The independent variable included in this study is the type of context-based visualizations used (with 3 levels: no visual aids, checklist based and predictive display based visual aids). We measured SA using SAGAT and performance using a questionnaire. SA and performance were found to be higher for the predictive display and checklist based conditions. The findings from this study will inform the design of context-based decision aids to support the SA of risk engineers.

scholarly journals Road Characteristics Detection Based on Joint Convolutional Neural Networks with Adaptive Squares

2021 ◽  
Vol 10 (6) ◽  
pp. 377
Author(s):  
Chiao-Ling Kuo ◽  
Ming-Hua Tsai
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Autonomous Vehicles ◽  
Detection Accuracy ◽  
Geospatial Information ◽  
Combination Rules ◽  
And Performance ◽  
Road Characteristics ◽  
Machine Readable ◽  
Background Image

The importance of road characteristics has been highlighted, as road characteristics are fundamental structures established to support many transportation-relevant services. However, there is still huge room for improvement in terms of types and performance of road characteristics detection. With the advantage of geographically tiled maps with high update rates, remarkable accessibility, and increasing availability, this paper proposes a novel simple deep-learning-based approach, namely joint convolutional neural networks (CNNs) adopting adaptive squares with combination rules to detect road characteristics from roadmap tiles. The proposed joint CNNs are responsible for the foreground and background image classification and various types of road characteristics classification from previous foreground images, raising detection accuracy. The adaptive squares with combination rules help efficiently focus road characteristics, augmenting the ability to detect them and provide optimal detection results. Five types of road characteristics—crossroads, T-junctions, Y-junctions, corners, and curves—are exploited, and experimental results demonstrate successful outcomes with outstanding performance in reality. The information of exploited road characteristics with location and type is, thus, converted from human-readable to machine-readable, the results will benefit many applications like feature point reminders, road condition reports, or alert detection for users, drivers, and even autonomous vehicles. We believe this approach will also enable a new path for object detection and geospatial information extraction from valuable map tiles.

scholarly journals Characterizing Bilingual Effects on Cognition: The Search for Meaningful Individual Differences

2021 ◽  
Vol 11 (1) ◽  
pp. 81
Author(s):  
Kristina C. Backer ◽  
Heather Bortfeld
Keyword(s):  
Individual Differences ◽  
Cognitive Processes ◽  
Language Background ◽  
Bilingual Advantage ◽  
The Past ◽  
General Movement ◽  
And Performance ◽  
Task Irrelevant ◽  
Analytical Approaches ◽  
The Relationship

A debate over the past decade has focused on the so-called bilingual advantage—the idea that bilingual and multilingual individuals have enhanced domain-general executive functions, relative to monolinguals, due to competition-induced monitoring of both processing and representation from the task-irrelevant language(s). In this commentary, we consider a recent study by Pot, Keijzer, and de Bot (2018), which focused on the relationship between individual differences in language usage and performance on an executive function task among multilingual older adults. We discuss their approach and findings in light of a more general movement towards embracing complexity in this domain of research, including individuals’ sociocultural context and position in the lifespan. The field increasingly considers interactions between bilingualism/multilingualism and cognition, employing measures of language use well beyond the early dichotomous perspectives on language background. Moreover, new measures of bilingualism and analytical approaches are helping researchers interrogate the complexities of specific processing issues. Indeed, our review of the bilingualism/multilingualism literature confirms the increased appreciation researchers have for the range of factors—beyond whether someone speaks one, two, or more languages—that impact specific cognitive processes. Here, we highlight some of the most salient of these, and incorporate suggestions for a way forward that likewise encompasses neural perspectives on the topic.

Sign in / Sign up

Export Citation Format

Share Document