scholarly journals A temporal analysis of safety drivers taking back control in public roadway automated driving trials

2019 ◽  
Vol 63 (1) ◽  
pp. 1532-1536
Author(s):  
Nicole M. Corcoran ◽  
Daniel V. McGehee ◽  
T. Zachary Noonan
Keyword(s):  
Autonomous Vehicle ◽  
Temporal Analysis ◽  
Automated Vehicles ◽  
Automated Driving ◽  
The Public ◽  
Environment Research ◽  
Operational Design ◽  
Take Back ◽  
Driving Task ◽  
Over Time

In 2019, industry is in the testing stages of level 4 SAE/NHTSA automated vehicles. While in testing, L4 vehicles require a safety driver to monitor the driving task at all times. These specially trained drivers must take back control if the vehicle doesn’t seem to be responding correctly to the ever-changing roadway and environment. Research suggests that monitoring the driving task can lead to a decrease in vigilance over time. Recently, Waymo publicly released takeover request and mileage data on its 2018 L4 autonomous vehicle takeover requests. From this data, which was represented in mileage, we created temporal metric which showed that there were typically 150-250 hours without a takeover request. From this we suggest that there may be a decrement in vigilance for Waymo safety drivers. While there are still many unknowns, we suggest Waymo release takeover requests in terms of time rather than mileage and provide more information on the operational design domains of these vehicles. Expanding the content of this publicly-released data could then give researchers and the public more understanding of the conditions under which safety drivers are functioning.

scholarly journals Potential Crash Rate Benchmarks for Automated Vehicles

2021 ◽  
pp. 036119812110098
Author(s):  
Noah J. Goodall
Keyword(s):  
Stated Preference ◽  
Average Rate ◽  
Crash Risk ◽  
Automated Vehicles ◽  
Automated Driving ◽  
The Public ◽  
Crash Rates ◽  
Potential Safety ◽  
Transportation Modes ◽  
Driving Task

Most automobile manufacturers and several technology companies are testing automated vehicles (AVs) on public roads. While automation of the driving task is expected to reduce crashes, there is no consensus as to how safe an AV must be before it can be deployed. An AV should be at least as safe as the average driver, but national crash rates include drunk and distracted driving, meaning that an AV that crashes at the average rate is somewhere between drunk and sober. In this paper, safety benchmarks for AVs are explored from three perspectives. First, crash rates from naturalistic driving studies are used to determine the crash risk of the model (i.e., sober, rested, attentive, cautious) driver. Second, stated preference surveys in the literature are reviewed to estimate the AV risk acceptable to the public. Third, crash, injury, and fatality rates from other transportation modes are compared as baseline safety levels. A range of potential safety targets is presented as a guide for policymakers, regulators, and AV developers to assist in evaluating the safety of automated driving technologies for public use.

First encounter effects in testing of highly automated vehicles during two experimental occasions – The need for recurrent testing

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Jonas Andersson ◽  
Azra Habibovic ◽  
Daban Rizgary
Keyword(s):  
Driver Behavior ◽  
Added Value ◽  
Future Research ◽  
Gaze Behavior ◽  
Repeated Testing ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Perceived Safety ◽  
Repeated Interaction ◽  
Over Time

Abstract To explore driver behavior in highly automated vehicles (HAVs), independent researchers are mainly conducting short experiments. This limits the ability to explore drivers’ behavioral changes over time, which is crucial when research has the intention to reveal human behavior beyond the first-time use. The current paper shows the methodological importance of repeated testing in experience and behavior related studies of HAVs. The study combined quantitative and qualitative data to capture effects of repeated interaction between drivers and HAVs. Each driver ( n = 8 n=8 ) participated in the experiment on two different occasions (∼90 minutes) with one-week interval. On both occasions, the drivers traveled approximately 40 km on a rural road at AstaZero proving grounds in Sweden and encountered various traffic situations. The participants could use automated driving (SAE level 4) or choose to drive manually. Examples of data collected include gaze behavior, perceived safety, as well as interviews and questionnaires capturing general impressions, trust and acceptance. The analysis shows that habituation effects were attenuated over time. The drivers went from being exhilarated on the first occasion, to a more neutral behavior on the second occasion. Furthermore, there were smaller variations in drivers’ self-assessed perceived safety on the second occasion, and drivers were faster to engage in non-driving related activities and become relaxed (e. g., they spent more time glancing off road and could focus more on non-driving related activities such as reading). These findings suggest that exposing drivers to HAVs on two (or more) successive occasions may provide more informative and realistic insights into driver behavior and experience as compared to only one occasion. Repeating an experiment on several occasions is of course a balance between the cost and added value, and future research should investigate in more detail which studies need to be repeated on several occasions and to what extent.

scholarly journals Driver intervention performance assessment as a key aspect of L3–L4 automated vehicles deployment

2021 ◽  
Vol 11 (1) ◽  
pp. 845-852
Author(s):  
Aleksandra Rodak ◽  
Paweł Budziszewski ◽  
Małgorzata Pędzierska ◽  
Mikołaj Kruszewski
Keyword(s):  
Performance Assessment ◽  
Minimal Risk ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Driving System ◽  
Driving Task ◽  
Driving Conditions

Abstract In L3–L4 vehicles, driving task is performed primarily by automated driving system (ADS). Automation mode permits to engage in non-driving-related tasks; however, it necessitates continuous vigilance and attention. Although the driver may be distracted, a request to intervene may suddenly occur, requiring immediate and appropriate response to driving conditions. To increase safety, automated vehicles should be equipped with a Driver Intervention Performance Assessment module (DIPA), ensuring that the driver is able to take the control of the vehicle and maintain it safely. Otherwise, ADS should regain control from the driver and perform a minimal risk manoeuvre. The paper explains the essence of DIPA, indicates possible measures, and describes a concept of DIPA framework being developed in the project.

scholarly journals Leveraging Transfer Learning to Analyze Opinions, Attitudes, and Behavioral Intentions Toward COVID-19 Vaccines: Social Media Content and Temporal Analysis (Preprint)

2021 ◽  
Author(s):  
Siru Liu ◽  
Jili Li ◽  
Jialin Liu
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Transfer Learning ◽  
Behavioral Intentions ◽  
Temporal Analysis ◽  
Public Understanding ◽  
Support Vector ◽  
Learning Models ◽  
The Public ◽  
Over Time

BACKGROUND The COVID-19 vaccine is considered to be the most promising approach to alleviate the pandemic. However, in recent surveys, acceptance of the COVID-19 vaccine has been low. To design more effective outreach interventions, there is an urgent need to understand public perceptions of COVID-19 vaccines. OBJECTIVE Our objective was to analyze the potential of leveraging transfer learning to detect tweets containing opinions, attitudes, and behavioral intentions toward COVID-19 vaccines, and to explore temporal trends as well as automatically extract topics across a large number of tweets. METHODS We developed machine learning and transfer learning models to classify tweets, followed by temporal analysis and topic modeling on a dataset of COVID-19 vaccine–related tweets posted from November 1, 2020 to January 31, 2021. We used the F1 values as the primary outcome to compare the performance of machine learning and transfer learning models. The statistical values and <i>P</i> values from the Augmented Dickey-Fuller test were used to assess whether users’ perceptions changed over time. The main topics in tweets were extracted by latent Dirichlet allocation analysis. RESULTS We collected 2,678,372 tweets related to COVID-19 vaccines from 841,978 unique users and annotated 5000 tweets. The F1 values of transfer learning models were 0.792 (95% CI 0.789-0.795), 0.578 (95% CI 0.572-0.584), and 0.614 (95% CI 0.606-0.622) for these three tasks, which significantly outperformed the machine learning models (logistic regression, random forest, and support vector machine). The prevalence of tweets containing attitudes and behavioral intentions varied significantly over time. Specifically, tweets containing positive behavioral intentions increased significantly in December 2020. In addition, we selected tweets in the following categories: positive attitudes, negative attitudes, positive behavioral intentions, and negative behavioral intentions. We then identified 10 main topics and relevant terms for each category. CONCLUSIONS Overall, we provided a method to automatically analyze the public understanding of COVID-19 vaccines from real-time data in social media, which can be used to tailor educational programs and other interventions to effectively promote the public acceptance of COVID-19 vaccines.

scholarly journals Influence of Adaptive Human–Machine Interface on Electric-Vehicle Range-Anxiety Mitigation

2020 ◽  
Vol 4 (1) ◽  
pp. 4
Author(s):  
Antonyo Musabini ◽  
Kevin Nguyen ◽  
Romain Rouyer ◽  
Yannis Lilis
Keyword(s):  
Electric Vehicle ◽  
Autonomous Vehicle ◽  
Human Machine Interface ◽  
Traffic Light ◽  
Automated Driving ◽  
Range Anxiety ◽  
Driving Task ◽  
Machine Interface ◽  
Emergency Stop ◽  
Save Energy

The electrification of vehicles is without a doubt one of the milestones of today’s automotive technology. Even though industry actors perceive it as a future standard, acceptance, and adoption of this kind of vehicles by the end user remain a huge challenge. One of the main issues is the range anxiety related to the electric vehicle’s remaining battery level. In the scope of the H2020 ADAS&ME project, we designed and developed an intelligent Human Machine Interface (HMI) to ease acceptance of Electric Vehicle (EV) technology. This HMI is mounted on a fake autonomous vehicle piloted by a hidden joystick (called Wizard of Oz (WoZ) driving). We examined 22 inexperienced EV drivers during a one-hour driving task tailored to generate range anxiety. According to our protocol, once the remaining battery level started to become critical after manual driving, the HMI proposed accurate coping techniques to inform the drivers how to reduce the power consumption of the vehicle. In the following steps of the protocol, the vehicle was totally out of battery, and the drivers had to experience an emergency stop. The first result of this paper was that an intelligent HMI could reduce the range anxiety of the driver by proposing adapted coping strategies (i.e., transmitting how to save energy when the vehicle approaches a traffic light). The second result was that such an HMI and automated driving to a safe spot could reduce the stress of the driver when an emergency stop is necessary.

scholarly journals A Taxonomy of Strategies For Supporting Time-Sharing With Non-Driving Tasks in Automated Driving

2019 ◽  
Vol 63 (1) ◽  
pp. 2088-2092
Author(s):  
Dengbo He ◽  
Dina Kanaan ◽  
Birsen Donmez
Keyword(s):  
Driver Distraction ◽  
Mitigation Strategies ◽  
Future Research ◽  
Time Sharing ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Negative Effects ◽  
Spare Capacity ◽  
Control Automation ◽  
Driving Task

Driver distraction is one of the leading causes of vehicle crashes. The introduction of higher levels of vehicle control automation is expected to alleviate the negative effects of distraction by delegating the driving task to automation, thus enabling drivers to engage in non-driving-related tasks more safely. However, before fully automated vehicles are realized, drivers are still expected to play a supervisory role and intervene with the driving task if necessary while potentially having more spare capacity for engaging in non-driving-related tasks. Traditional distraction mitigation perspectives need to be shifted for automated vehicles from mainly preventing the occurrence of non-driving-related tasks to dynamically coordinating time-sharing between driving and non-driving-related tasks. In this paper, we provide a revised and expanded taxonomy of driver distraction mitigation strategies, discuss how the different strategies can be used in an automated driving context, and propose directions for future research in supporting time-sharing in automated vehicles.

Peripheral Monitoring of Traffic in Conditionally Automated Driving

2018 ◽  
Vol 62 (1) ◽  
pp. 1828-1832 ◽  
Author(s):  
Jonas Radlmayr ◽  
Karin Brüch ◽  
Kathrin Schmidt ◽  
Christine Solbeck ◽  
Tristan Wehner
Keyword(s):  
Situation Awareness ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Active System ◽  
Subject Design ◽  
Level 3 ◽  
Driving Task

Conditionally automated vehicles (level 3) allow drivers to engage in visual, non-driving related tasks (NDRTs) while the automation is active. System limits require drivers to reengage in the dynamic driving task in take-over situations. If the NDRT is visually engaging, situation awareness (SA) necessary for a successful take-over can decrease. This study analyzed, if the SA of drivers increases while monitoring the surrounding traffic peripherally. A semi-transparent balloon game in the head-up display operationalized the engagement into a visual NDRT with the possibility of peripheral monitoring. In addition, participants without the possibility of monitoring due to simulated heavy fog (second group) were tested along with a third group that could monitor surroundings self-determined without a NDRT. The between-subject design included 57 participants. Results showed that self-determined monitoring leads to higher situation awareness compared to peripheral monitoring and no monitoring. This did not result in better take-over performances.

scholarly journals Transitions Between Highly Automated and Longitudinally Assisted Driving: The Role of the Initiator in the Fight for Authority

2020 ◽  
pp. 001872082094618 ◽  
Author(s):  
Davide Maggi ◽  
Richard Romano ◽  
Oliver Carsten
Keyword(s):  
Road Safety ◽  
Driving Simulator ◽  
Cruise Control ◽  
Automated Driving ◽  
Safety Issues ◽  
The Road ◽  
Operational Design ◽  
Level 3 ◽  
Driving Task

Objective A driving simulator study explored how drivers behaved depending on their initial role during transitions between highly automated driving (HAD) and longitudinally assisted driving (via adaptive cruise control). Background During HAD, drivers might issue a take-over request (TOR), initiating a transition of control that was not planned. Understanding how drivers behave in this situation and, ultimately, the implications on road safety is of paramount importance. Method Sixteen participants were recruited for this study and performed transitions of control between HAD and longitudinally assisted driving in a driving simulator. While comparing how drivers behaved depending on whether or not they were the initiators, different handover strategies were presented to analyze how drivers adapted to variations in the authority level they were granted at various stages of the transitions. Results Whenever they initiated the transition, drivers were more engaged with the driving task and less prone to follow the guidance of the proposed strategies. Moreover, initiating a transition and having the highest authority share during the handover made the drivers more engaged with the driving task and attentive toward the road. Conclusion Handover strategies that retained a larger authority share were more effective whenever the automation initiated the transition. Under driver-initiated transitions, reducing drivers’ authority was detrimental for both performance and comfort. Application As the operational design domain of automated vehicles (Society of Automotive Engineers [SAE] Level 3/4) expands, the drivers might very well fight boredom by taking over spontaneously, introducing safety issues so far not considered but nevertheless very important.

scholarly journals Potential Crash Rate Benchmarks for Automated Vehicles

2021 ◽  
Author(s):  
Noah J. Goodall
Keyword(s):  
Stated Preference ◽  
Average Rate ◽  
Crash Risk ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Automated Vehicle ◽  
Crash Rates ◽  
Potential Safety ◽  
Transportation Modes ◽  
Driving Task

Most automobile manufacturers and several technology companies are testing automated vehicles on public roads. While automation of the driving task is expected to reduce crashes, there is no consensus regarding how safe an automated vehicle must be before it can be deployed. An automated vehicle should be at least as safe as the average driver, but national crash rates include drunk and distracted driving, meaning that an automated vehicle that crashes at the average rate is somewhere between drunk and sober. In this paper, automated vehicle safety benchmarks are explored from three perspectives. First, crash rates from naturalistic driving studies are used to determine the crash risk of the model (i.e., sober, rested, attentive, cautious) driver. Second, stated preference surveys in the literature are reviewed to estimate the public’s acceptable automated vehicle risk. Third, crash, injury, and fatality rates from other transportation modes are compared as baseline safety levels. A range of potential safety targets is presented as a guide for policymakers, regulators, and automated vehicle developers to assist in evaluating the safety of automated driving technologies for public use.

scholarly journals Augmented Reality Windshield Displays and Their Potential to Enhance User Experience in Automated Driving

i-com ◽  
2019 ◽  
Vol 18 (2) ◽  
pp. 127-149 ◽  
Author(s):  
Andreas Riegler ◽  
Philipp Wintersberger ◽  
Andreas Riener ◽  
Clemens Holzmann
Keyword(s):  
User Experience ◽  
User Study ◽  
User Preferences ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Level Of Automation ◽  
Levels Of Automation ◽  
Driving Task ◽  
Vehicle Automation ◽  
Fully Automated Driving

Abstract Increasing vehicle automation presents challenges as drivers of highly automated vehicles become more disengaged from the primary driving task. However, even with fully automated driving, there will still be activities that require interfaces for vehicle-passenger interactions. Windshield displays are a technology with a promising potential for automated driving, as they are able to provide large content areas supporting drivers in non-driving related activities. However, it is still unknown how potential drivers or passengers would use these displays. This work addresses user preferences for windshield displays in automated driving. Participants of a user study (N=63) were presented two levels of automation (conditional and full), and could freely choose preferred positions, content types, as well as size, transparency levels and importance levels of content windows using a simulated “ideal” windshield display. We visualized the results in form of heatmap data which show that user preferences differ with respect to the level of automation, age, gender, or environment aspects. These insights can help designers of interiors and in-vehicle applications to provide a rich user experience in highly automated vehicles.

Sign in / Sign up

Export Citation Format

Share Document