scholarly journals Automated vehicles and the morality of post-collision behavior

2021 ◽  
Author(s):  
Sebastian Krügel ◽  
Matthias Uhl ◽  
Bryn Balcombe
Keyword(s):  
European Commission ◽  
Research Program ◽  
Collision Detection ◽  
Expert Group ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Data Provision

AbstractWe address the considerations of the European Commission Expert Group on the ethics of connected and automated vehicles regarding data provision in the event of collisions. While human drivers’ appropriate post-collision behavior is clearly defined, regulations for automated driving do not provide for collision detection. We agree it is important to systematically incorporate citizens’ intuitions into the discourse on the ethics of automated vehicles. Therefore, we investigate whether people expect automated vehicles to behave like humans after an accident, even if this behavior does not directly affect the consequences of the accident. We find that appropriate post-collision behavior substantially influences people’s evaluation of the underlying crash scenario. Moreover, people clearly think that automated vehicles can and should record the accident, stop at the site, and call the police. They are even willing to pay for technological features that enable post-collision behavior. Our study might begin a research program on post-collision behavior, enriching the empirically informed study of automated driving ethics that so far exclusively focuses on pre-collision behavior.

Ethics of Artificial Intelligence in Transport

2020 ◽  
pp. 667-683
Author(s):  
Bryant Walker Smith
Keyword(s):  
Artificial Intelligence ◽  
Ethical Issues ◽  
Ethical Question ◽  
Power Dynamics ◽  
Automated Vehicles ◽  
Automated Driving ◽  
The U.S ◽  
Policy Solutions

This chapter highlights key ethical issues in the use of artificial intelligence in transport by using automated driving as an example. These issues include the tension between technological solutions and policy solutions; the consequences of safety expectations; the complex choice between human authority and computer authority; and power dynamics among individuals, governments, and companies. In 2017 and 2018, the U.S. Congress considered automated driving legislation that was generally supported by many of the larger automated-driving developers. However, this automated-driving legislation failed to pass because of a lack of trust in technologies and institutions. Trustworthiness is much more of an ethical question. Automated vehicles will not be driven by individuals or even by computers; they will be driven by companies acting through their human and machine agents. An essential issue for this field—and for artificial intelligence generally—is how the companies that develop and deploy these technologies should earn people’s trust.

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 The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1737
Author(s):  
Wooseop Lee ◽  
Min-Hee Kang ◽  
Jaein Song ◽  
Keeyeon Hwang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Processing Speed ◽  
Model Comparison ◽  
Distance Estimation ◽  
Visual Object ◽  
Suitable Model ◽  
Automated Vehicles ◽  
Automated Driving

As automated vehicles have been considered one of the important trends in intelligent transportation systems, various research is being conducted to enhance their safety. In particular, the importance of technologies for the design of preventive automated driving systems, such as detection of surrounding objects and estimation of distance between vehicles. Object detection is mainly performed through cameras and LiDAR, but due to the cost and limits of LiDAR’s recognition distance, the need to improve Camera recognition technique, which is relatively convenient for commercialization, is increasing. This study learned convolutional neural network (CNN)-based faster regions with CNN (Faster R-CNN) and You Only Look Once (YOLO) V2 to improve the recognition techniques of vehicle-mounted monocular cameras for the design of preventive automated driving systems, recognizing surrounding vehicles in black box highway driving videos and estimating distances from surrounding vehicles through more suitable models for automated driving systems. Moreover, we learned the PASCAL visual object classes (VOC) dataset for model comparison. Faster R-CNN showed similar accuracy, with a mean average precision (mAP) of 76.4 to YOLO with a mAP of 78.6, but with a Frame Per Second (FPS) of 5, showing slower processing speed than YOLO V2 with an FPS of 40, and a Faster R-CNN, which we had difficulty detecting. As a result, YOLO V2, which shows better performance in accuracy and processing speed, was determined to be a more suitable model for automated driving systems, further progressing in estimating the distance between vehicles. For distance estimation, we conducted coordinate value conversion through camera calibration and perspective transform, set the threshold to 0.7, and performed object detection and distance estimation, showing more than 80% accuracy for near-distance vehicles. Through this study, it is believed that it will be able to help prevent accidents in automated vehicles, and it is expected that additional research will provide various accident prevention alternatives such as calculating and securing appropriate safety distances, depending on the vehicle types.

Development and Evaluation of Cooperative Intersection Management Algorithm under Connected and Automated Vehicles Environment

2021 ◽  
pp. 036119812199458
Author(s):  
Slobodan Gutesa ◽  
Joyoung Lee ◽  
Dejan Besenski
Keyword(s):  
Travel Time ◽  
Information Exchange ◽  
Fixed Time ◽  
Optimization Method ◽  
Time Signal ◽  
Market Penetration ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Concept Evaluation ◽  
Intersection Management

Recent technological advancements in the automotive and transportation industry established a firm foundation for development and implementation of various connected and automated vehicle solutions around the globe. Wireless communication technologies such as the dedicated short-range communication protocol are enabling information exchange between vehicles and infrastructure. This research paper introduces an intersection management strategy for a corridor with automated vehicles utilizing vehicular trajectory-driven optimization method. Trajectory-Driven Optimization for Automated Driving provides an optimal trajectory for automated vehicles based on current vehicle position, prevailing traffic, and signal status on the corridor. All inputs are used by the control algorithm to provide optimal trajectories for automated vehicles, resulting in the reduction of vehicle delay along the signalized corridor with fixed-time signal control. The concept evaluation through microsimulation reveals that, even with low market penetration (i.e., less than 10%), the technology reduces overall travel time of the corridor by 2%. Further increase in market penetration produces travel time and fuel consumption reductions of up to 19.5% and 22.5%, respectively.

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.

When the automated driving system fails: Dynamics of public responses to automated vehicles

2021 ◽  
Vol 129 ◽  
pp. 103271
Author(s):  
Zhigang Xu ◽  
Zijun Jiang ◽  
Guanqun Wang ◽  
Runmin Wang ◽  
Tingting Li ◽  
...  
Keyword(s):  
Automated Vehicles ◽  
Automated Driving ◽  
Driving System

Use Cases for Assessing, Testing, and Validating the Human Machine Interface of Automated Driving Systems

2018 ◽  
Vol 62 (1) ◽  
pp. 1873-1877 ◽  
Author(s):  
Frederik Naujoks ◽  
Sebastian Hergeth ◽  
Katharina Wiedemann ◽  
Nadja Schömig ◽  
Andreas Keinath
Keyword(s):  
Traffic Safety ◽  
Test Methods ◽  
Use Cases ◽  
Highway Traffic ◽  
Automated Vehicles ◽  
Automated Driving ◽  
National Highway Traffic Safety ◽  
Minimum Requirements ◽  
Machine Interface ◽  
Increasing Demand

Reflecting the increasing demand for harmonization of human machine interfaces (HMI) of automated vehicles, different taxonomies of use cases for investigating automated driving systems (ADS) have been proposed. Existing taxonomies tend to serve specific purposes such as categorizing transitions between automation modes; however, they cannot be generalized to different systems or combinations of systems. In particular, there is no exhaustive set of use cases that allows entities to assess and validate the HMI of a given ADS that takes into account all possible system modes and transitions. The present paper describes a newly developed framework based on combinatorics of SAE (Society of Automotive Engineers) automation levels that incorporates a comprehensive taxonomy of use cases required for the assessment and validation of ADS HMIs. This forms a much-needed basis for test methods required to verify whether an HMI meets minimum requirements such as those outlined in the National Highway Traffic Safety Administration’s Federal Automated Vehicles policy.

scholarly journals A Division Method of Determining the Early-Warning Zone on an Expressway for Automated Vehicles

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Jiawen Wang ◽  
Shaobo Li ◽  
Yining Lu ◽  
Lubang Wang
Keyword(s):  
Cellular Automaton ◽  
Early Warning ◽  
Cellular Automaton Model ◽  
Mixed Traffic ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Traffic Incidents ◽  
Lane Changing ◽  
Automatic Driving ◽  
Urban Expressway

Using a cellular automaton model, this paper studied the evolution mechanism of traffic incidents affecting the capacity of urban expressway under the mixed traffic environment of manual driving and automatic driving. It showed that the length of the automated-driving early-warning zone could affect the capacity of expressway. Specifically, the early-warning zone is divided into an accelerate lane-changing area, a decelerate lane-changing area, and a forced lane-changing area. The areas vary according to the distance between the vehicle and the location of incident. Based on the study, this paper establishes a codirectional two-lane cellular automaton model. The analysis showed that the capacity of the urban expressway varies under different combinations of early-warning area length and division ratio of early-warning zone. In the case of two-lane reduction caused by traffic incidents, the capacity of the expressway is optimized when the length of early-warning zone is between 450 and 600 m, and the ratio of accelerate zone, decelerate zone, and forced zone to the length of early-warning zone is, respectively, 75%, 10%, and 15%. In addition, this study showed that the capacity will rise with the increase in automated vehicles.

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.

Sign in / Sign up

Export Citation Format

Share Document