scholarly journals Investigating drivers’ trust in autonomous vehicles’ decisions of lane changing events

2020 ◽  
Vol 64 (1) ◽  
pp. 1274-1278
Author(s):  
Jackie Ayoub ◽  
Feng Zhou
Keyword(s):  
Autonomous Vehicles ◽  
Visual Display ◽  
Survey Study ◽  
Decision Making Process ◽  
Lane Changing ◽  
Information Display ◽  
Mental Demand ◽  
Subject Design ◽  
Machine Learning Model ◽  
Better Than

It is potential to improve the interaction between autonomous vehicles (AVs) and drivers by calibrating drivers’ trust in AVs. In this study, we investigated drivers’ trust in AVs’ decisions of changing lanes on a six-lane highway. We derived the AV lane changing scenarios using a machine learning model. The scenarios were rated by 250 participants recruited from Amazon Mechanical Turks (AMTs) in a survey study. The study was designed as a mixed-subject design where the between-subject variable was the amount of information presented (i.e., 3, 4, 5, 6, 7 pieces of information) and the within-subject variable was the information display format (i.e., tabular or visual forms). The results showed that 1) mental demand was always lower in the visual display compared to the tabular one, 2) trust and risk seemed to be inversely proportional across conditions, and 3) 4, 5, or 6 pieces of information tended to be preferred better than others. These results provide design implications on calibrating trust in AV systems by involving the driver in the decision-making process.

scholarly journals A Game Theory-Based Approach for Modeling Autonomous Vehicle Behavior in Congested, Urban Lane-Changing Scenarios

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1523
Author(s):  
Nikita Smirnov ◽  
Yuzhou Liu ◽  
Aso Validi ◽  
Walter Morales-Alvarez ◽  
Cristina Olaverri-Monreal
Keyword(s):  
Game Theory ◽  
Decision Making ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Urban Traffic ◽  
Road User ◽  
Lane Change ◽  
Traffic Light ◽  
User Interactions ◽  
Lane Changing

Autonomous vehicles are expected to display human-like behavior, at least to the extent that their decisions can be intuitively understood by other road users. If this is not the case, the coexistence of manual and autonomous vehicles in a mixed environment might affect road user interactions negatively and might jeopardize road safety. To this end, it is highly important to design algorithms that are capable of analyzing human decision-making processes and of reproducing them. In this context, lane-change maneuvers have been studied extensively. However, not all potential scenarios have been considered, since most works have focused on highway rather than urban scenarios. We contribute to the field of research by investigating a particular urban traffic scenario in which an autonomous vehicle needs to determine the level of cooperation of the vehicles in the adjacent lane in order to proceed with a lane change. To this end, we present a game theory-based decision-making model for lane changing in congested urban intersections. The model takes as input driving-related parameters related to vehicles in the intersection before they come to a complete stop. We validated the model by relying on the Co-AutoSim simulator. We compared the prediction model outcomes with actual participant decisions, i.e., whether they allowed the autonomous vehicle to drive in front of them. The results are promising, with the prediction accuracy being 100% in all of the cases in which the participants allowed the lane change and 83.3% in the other cases. The false predictions were due to delays in resuming driving after the traffic light turned green.

scholarly journals Decentralized Cooperative Lane-Changing Decision-Making for Connected Autonomous Vehicles*

IEEE Access ◽  
2016 ◽  
Vol 4 ◽  
pp. 9413-9420 ◽  
Author(s):  
Jianqiang Nie ◽  
Jian Zhang ◽  
Wanting Ding ◽  
Xia Wan ◽  
Xiaoxuan Chen ◽  
...  
Keyword(s):  
Decision Making ◽  
Autonomous Vehicles ◽  
Lane Changing

Enhancing the Performance of a Model to Predict Driving Distraction with the Random Forest Classifier

2021 ◽  
pp. 036119812110186
Author(s):  
Samira Ahangari ◽  
Mansoureh Jeihani ◽  
Anam Ardeshiri ◽  
Md Mahmudur Rahman ◽  
Abdollah Dehzangi
Keyword(s):  
Random Forest ◽  
Driving Simulator ◽  
Situational Awareness ◽  
True Positive Rate ◽  
The United States ◽  
Driving Performance ◽  
Lane Changing ◽  
Wide Range ◽  
Positive Rate ◽  
Better Than

Distracted driving is known to be one of the main causes of crashes in the United States, accounting for about 40% of all crashes. Drivers’ situational awareness, decision-making, and driving performance are impaired as a result of temporarily diverting their attention from the primary task of driving to other unrelated tasks. Detecting driver distraction would help in adapting the most effective countermeasures. To tackle this problem, we employed a random forest (RF) classifier, one of the best classifiers that has attained promising results for a wide range of problems. Here, we trained RF using the data collected from a driving simulator, in which 92 participants drove under six different distraction scenarios of handheld calling, hands-free calling, texting, voice command, clothing, and eating/drinking on four different road classes (rural collector, freeway, urban arterial, and local road in a school zone). Various driving performance measures such as speed, acceleration, throttle, lane changing, brake, collision, and offset from the lane center were investigated. Using the RF method, we achieved 76.5% prediction accuracy on the independent test set, which is over 8.2% better than results reported in previous studies. We also obtained a 76.6% true positive rate, which is 14% better than those reported in previous studies. Such results demonstrate the preference of RF over other machine learning methods to identify driving distractions.

Detection and defense of cyberattacks on the machine learning control of robotic systems

2021 ◽  
pp. 154851292110438
Author(s):  
George W Clark ◽  
Todd R Andel ◽  
J Todd McDonald ◽  
Tom Johnsten ◽  
Tom Thomas
Keyword(s):  
Machine Learning ◽  
Autonomous Vehicles ◽  
Defense Mechanisms ◽  
Autonomous Vehicle ◽  
Learning Algorithms ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Robotic Systems ◽  
Machine Learning Model ◽  
Attack Surface

Robotic systems are no longer simply built and designed to perform sequential repetitive tasks primarily in a static manufacturing environment. Systems such as autonomous vehicles make use of intricate machine learning algorithms to adapt their behavior to dynamic conditions in their operating environment. These machine learning algorithms provide an additional attack surface for an adversary to exploit in order to perform a cyberattack. Since an attack on robotic systems such as autonomous vehicles have the potential to cause great damage and harm to humans, it is essential that detection and defenses of these attacks be explored. This paper discusses the plausibility of direct and indirect cyberattacks on a machine learning model through the use of a virtual autonomous vehicle operating in a simulation environment using a machine learning model for control. Using this vehicle, this paper proposes various methods of detection of cyberattacks on its machine learning model and discusses possible defense mechanisms to prevent such attacks.

scholarly journals Users’ Acceptance of Connected and Automated Shuttles for Tourism Purposes: A Survey Study

2020 ◽  
Vol 12 (23) ◽  
pp. 10188
Author(s):  
Roberto Battistini ◽  
Luca Mantecchini ◽  
Maria Nadia Postorino
Keyword(s):  
Willingness To Pay ◽  
Autonomous Vehicles ◽  
Social Inclusion ◽  
Physical Disabilities ◽  
Survey Study ◽  
High Confidence ◽  
Collective Transport ◽  
Transport Services ◽  
Potential Benefits ◽  
People With Physical Disabilities

In recent years, autonomous vehicles have received increasing attention and many studies in the literature have discussed the potentialities and the opportunities they could offer. Despite the potential benefits, mainly related to the expected reduction in accidents and congestion phenomena as well as the potentially improved social inclusion of people with driving difficulties (e.g., people with physical disabilities or elderly people), many aspects remain to be addressed, mainly for understanding users’ acceptance in the case of collective transport vehicles. This study proposes an analysis based on a survey aimed at exploring user’s preferences with respect to the use of autonomous shuttles (ASs) for tourism purposes. The main correlations between the variables considered and the preferences of potential users have been discussed. Interviewees expressed high confidence in AS technology, although the analyses performed about willingness to pay show that users give more relevance to the provided transport services than the AS technology.

Simulated Navigation Performance with Marine Electronic Chart and Information Display Systems (ECDIS)

2004 ◽  
Vol 57 (2) ◽  
pp. 189-202 ◽  
Author(s):  
Don C. Donderi ◽  
Robert Mercer ◽  
M. Blair Hong ◽  
Douglas Skinner
Keyword(s):  
Nova Scotia ◽  
Information Display ◽  
Paper Chart ◽  
Low Visibility ◽  
Electronic Chart ◽  
Display Systems ◽  
Better Than

Licensed mariners carried out two simulated navigation studies testing electronic chart and information display systems (ECDIS) against paper chart navigation. In the first study, six mariners each completed approaches to Halifax, Nova Scotia, harbour with good and bad visibility and a range of wind and currents. Conditions included chart with radar, ECDIS with radar overlay and ECDIS with separate radar. ECDIS produced better performance and a smaller workload than paper charts and the radar overlay was slightly better than the separate radar display. In the second study, six new mariners completed exercises with low visibility and heavy or light radar traffic using ECDIS with radar overlay, ECDIS without overlay and ECDIS with optional overlay. Mariners preferred the optional overlay but all three conditions produced about equal performance. Based on mariners' performance and expressed preference, we recommend that ECDIS systems provide optional radar overlays.

Transfer of Landing Skill after Training with Supplementary Visual Cues

1979 ◽  
Vol 23 (1) ◽  
pp. 301-304 ◽  
Author(s):  
Gavan Lintern
Keyword(s):  
Transfer Of Training ◽  
Visual Cues ◽  
Closed Loop ◽  
Transfer Task ◽  
Visual Display ◽  
Training Condition ◽  
Training Design ◽  
Augmented Feedback ◽  
Trained Subjects ◽  
Better Than

An aircraft simulator with a closed-loop computer-generated visual display, was used to teach flight-naive subjects to land. A control training condition in which subjects learned to land with reference to a skeletal airport scene consisting of a horizon, runway, centerline, and aiming bar, was tested against training with constantly augmented feedback, adaptively augmented feedback, and a flightpath tracking display. A simulator-to-simulator transfer-of-training design showed that adaptively trained subjects performed best in a transfer task that was identical to the control group's training condition. Several subjects attempted six landings in a light airplane after they had completed their experimental work in the simulator. They performed better than another group of subjects that had not had any landing practice in the simulator.

Sign in / Sign up

Export Citation Format

Share Document