scholarly journals Using an Integrated Cognitive Architecture to Model the Effect of Environmental Complexity on Drivers’ Situation Awareness

2019 ◽  
Vol 63 (1) ◽  
pp. 812-816
Author(s):  
Umair Rehman ◽  
Shi Cao ◽  
Carolyn MacGregor
Keyword(s):  
Situation Awareness ◽  
Driving Simulator ◽  
Cognitive Architecture ◽  
Cognitive Model ◽  
Queueing Network ◽  
Driver Model ◽  
Human Cognition ◽  
Environmental Complexity ◽  
Preliminary Validation ◽  
Human Participants

The goal of this research is to computationally model and simulate drivers’ situation awareness (SA). In order to achieve this, we have developed a computational cognitive model in a cognitive architecture that can be connected to interact with a driving simulator, as means to infer quantitative predictions of drivers’ SA. We demonstrate the theory of modelling and predicting SA through the lens of human cognition utilizing the QN-ACTR (Queueing Network-Adaptive Control of Thought-Rational) framework as a foundation. We integrate a dynamic visual sampling model (SEEV) to create QN-ACTR-SA in order to allow the model to simulate realistic attention allocation patterns of human drivers. A driver model is also incorporated within QN-ACTR-SA architecture that can simulate human driving behavior by interacting with a driving simulator with the help of virtual modalities such as motor, visual and memory functions. A preliminary validation study is conducted to determine whether SA results of the model correspond to empirical data. The model is probed with SA queries similar to how a Situation Awareness Global Assessment Technique (SAGAT) is conducted on human participants. A comparative assessment demonstrates the model’s ability to simulate drivers’ SA in both easy (with fewer traffic vehicles and signboards) and complex (with more traffic vehicles and signboards) driving conditions.

Toward an Integrated Model of Driver Behavior in Cognitive Architecture

2001 ◽  
Vol 1779 (1) ◽  
pp. 9-16 ◽  
Author(s):  
Dario D. Salvucci ◽  
Erwin R. Boer ◽  
Andrew Liu
Keyword(s):  
Driving Simulator ◽  
Driver Behavior ◽  
Cognitive Architecture ◽  
Driver Model ◽  
Behavioral Variability ◽  
Level Control ◽  
Cognitive Architectures ◽  
Computational Framework ◽  
Lane Changes ◽  
Motor Processes

Driving is a multitasking activity that requires drivers to manage their attention among various driving- and non-driving-related tasks. When one models drivers as continuous controllers, the discrete nature of drivers’ control actions is lost and with it an important component for characterizing behavioral variability. A proposal is made for the use of cognitive architectures for developing models of driver behavior that integrate cognitive and perceptual-motor processes in a serial model of task and attention management. A cognitive architecture is a computational framework that incorporates built-in, well-tested parameters and constraints on cognitive and perceptual-motor processes. All driver models implemented in a cognitive architecture necessarily inherit these parameters and constraints, resulting in more predictive and psychologically plausible models than those that do not characterize driving as a multitasking activity. These benefits are demonstrated with a driver model developed in the ACT-R cognitive architecture. The model is validated by comparing its behavior to that of human drivers navigating a four-lane highway with traffic in a fixed-based driving simulator. Results show that the model successfully predicts aspects of both lower-level control, such as steering and eye movements during lane changes, and higher-level cognitive tasks, such as task management and decision making. Many of these predictions are not explicitly built into the model but come from the cognitive architecture as a result of the model’s implementation in the ACT-R architecture.

Modeling Interruption and Resumption in a Smartphone Task: An ACT-R Approach

i-com ◽  
2015 ◽  
Vol 14 (2) ◽  
Author(s):  
Maria Wirzberger ◽  
Nele Russwinkel
Keyword(s):  
Cognitive Processing ◽  
Cognitive Modeling ◽  
Cognitive Architecture ◽  
Human Cognition ◽  
Mental Demand ◽  
Model Predictions ◽  
Mental Demands ◽  
Human Participants ◽  
Shed Light ◽  
Respective Number

AbstractThis research aims to inspect human cognition when being interrupted while performing a smartphone task with varying levels of mental demand. Due to its benefits especially in the early stages of interface development, a cognitive modeling approach is used. It applies the cognitive architecture ACT-R to shed light on task-related cognitive processing. The inspected task setting involves a shopping scenario, manipulating interruption via product advertisements and mental demands by the respective number of people shopping is done for. Model predictions are validated through a corresponding experimental setting with 62 human participants. Comparing model and human data in a defined set of performance-related parameters displays mixed results that indicate an acceptable fit – at least in some cases. Potential explanations for the observed differences are discussed at the end.

Modeling Pilot Flight Performance in a Cognitive Architecture: Model Demonstration

2021 ◽  
Vol 65 (1) ◽  
pp. 1254-1258
Author(s):  
Rongbing Xu ◽  
Shi Cao
Keyword(s):  
Situation Awareness ◽  
Human Performance ◽  
Mental Workload ◽  
Cognitive Architecture ◽  
Queueing Network ◽  
Architecture Model ◽  
Human In The Loop ◽  
Pilot Model ◽  
Competency Based ◽  
Machine Systems

Cognitive architecture models can support the simulation and prediction of human performance in complex human-machine systems. In the current work, we demonstrate a pilot model that can perform and simulate taxiing and takeoff tasks. The model was built in Queueing Network-Adaptive Control of Thought Rational (QN-ACTR) cognitive architecture and can be connected to flight simulators such as X-Plane to generate various data, including performance, mental workload, and situation awareness. The model results are determined in combination by the declarative knowledge chunks, production rules, and a set of parameters. Currently, the model can generate flight operation behavior similar to human pilots. We will collect human pilot data to examine further and validate model assumptions and parameter values. Once validated, such models can support interface evaluation and competency-based pilot training, providing a theory-based predictive approach complementary to human-in-the-loop experiments for aviation research and development.

Précis ofUnified theories of cognition

1992 ◽  
Vol 15 (3) ◽  
pp. 425-437 ◽  
Author(s):  
Allen Newell
Keyword(s):  
Cognitive Science ◽  
Full Range ◽  
Cognitive Architecture ◽  
Convincing Evidence ◽  
Syllogistic Reasoning ◽  
Human Cognition ◽  
Unified Theory ◽  
Theoretical Concepts ◽  
Wide Range ◽  
Unified Theories

AbstractThe book presents the case that cognitive science should turn its attention to developing theories of human cognition that cover the full range of human perceptual, cognitive, and action phenomena. Cognitive science has now produced a massive number of high-quality regularities with many microtheories that reveal important mechanisms. The need for integration is pressing and will continue to increase. Equally important, cognitive science now has the theoretical concepts and tools to support serious attempts at unified theories. The argument is made entirely by presenting an exemplar unified theory of cognition both to show what a real unified theory would be like and to provide convincing evidence that such theories are feasible. The exemplar is SOAR, a cognitive architecture, which is realized as a software system. After a detailed discussion of the architecture and its properties, with its relation to the constraints on cognition in the real world and to existing ideas in cognitive science, SOAR is used as theory for a wide range of cognitive phenomena: immediate responses (stimulus-response compatibility and the Sternberg phenomena); discrete motor skills (transcription typing); memory and learning (episodic memory and the acquisition of skill through practice); problem solving (cryptarithmetic puzzles and syllogistic reasoning); language (sentence verification and taking instructions); and development (transitions in the balance beam task). The treatments vary in depth and adequacy, but they clearly reveal a single, highly specific, operational theory that works over the entire range of human cognition, SOAR is presented as an exemplar unified theory, not as the sole candidate. Cognitive science is not ready yet for a single theory – there must be multiple attempts. But cognitive science must begin to work toward such unified theories.

Driver Support Functions Under Resource-Limited Situations

2007 ◽  
Vol 51 (4) ◽  
pp. 176-180 ◽  
Author(s):  
T. Inagaki ◽  
M. Itoh ◽  
Y. Nagai
Keyword(s):  
Situation Awareness ◽  
Driving Simulator ◽  
Reasoning Under Uncertainty ◽  
Support Functions ◽  
Traffic Condition ◽  
Monitoring Method ◽  
Safety Control ◽  
Resource Limited ◽  
Action Type ◽  
Driver Support

What type of support should be given to an automobile driver when it is determined, via some monitoring method, that the driver's situation awareness may not be appropriate to a given traffic condition? With a driving simulator, the following three conditions were compared: (a) Warning type support in which an auditory warning is given to the driver to enhance situation awareness, (b) action type support in which an autonomous safety control action is executed to avoid an accident, and (c) the no-aid baseline condition. Although the both types of driver support are effective, the warning type support sometimes fail to assure safety, which suggests a limitation of the human locus of control assumption. Efficacy of the action type support can also be degraded due to a characteristic of human reasoning under uncertainty. This paper discusses viewpoints needed in the design of systems for supporting drivers in resource-limited situations.

CoJACK: A high-level cognitive architecture with demonstrations of moderators, variability, and implications for situation awareness

2012 ◽  
Vol 1 ◽  
pp. 2-13 ◽  
Author(s):  
Frank E. Ritter ◽  
Jennifer L. Bittner ◽  
Sue E. Kase ◽  
Rick Evertsz ◽  
Matteo Pedrotti ◽  
...  
Keyword(s):  
Situation Awareness ◽  
Cognitive Architecture ◽  
High Level

Level of Automation Forms a Key Aspect of Autonomy Design

2017 ◽  
Vol 12 (1) ◽  
pp. 29-34 ◽  
Author(s):  
Mica R. Endsley
Keyword(s):  
Situation Awareness ◽  
Interface Design ◽  
Human Performance ◽  
Human Cognition ◽  
Level Of Automation ◽  
Out Of The Loop ◽  
Wide Range ◽  
Levels Of Automation ◽  
And Performance ◽  
The Impact

The concept of different levels of automation (LOAs) has been pervasive in the automation literature since its introduction by Sheridan and Verplanck. LOA taxonomies have been very useful in guiding understanding of how automation affects human cognition and performance, with several practical and theoretical benefits. Over the past several decades a wide body of research has been conducted on the impact of various LOAs on human performance, workload, and situation awareness (SA). LOA has a significant effect on operator SA and level of engagement that helps to ameliorate out-of-the-loop performance problems. Together with other aspects of system design, including adaptive automation, granularity of control, and automation interface design, LOA is a fundamental design characteristic that determines the ability of operators to provide effective oversight and interaction with system autonomy. LOA research provides a solid foundation for guiding the creation of effective human–automation interaction, which is critical for the wide range of autonomous and semiautonomous systems currently being developed across many industries.

Identification of a Driver Steering Model, and Model Uncertainty, From Driving Simulator Data

2001 ◽  
Author(s):  
Liang-Kuang Chen ◽  
A. Galip Ulsoy
Keyword(s):  
Model Uncertainty ◽  
Driving Simulator ◽  
Driver Model ◽  
Active Safety ◽  
Control Loop ◽  
Structured Uncertainty ◽  
Active Safety Systems ◽  
Safety Systems ◽  
Uncertainty Models ◽  
Adaptation Scheme

Abstract Driver steering models have been extensively studied. However, driver model uncertainty has received relatively little attention. For active safety systems that function while the driver is still in the control loop, such uncertainty can affect overall system performance significantly. In this paper, an approach to obtain both the driver model and its uncertainty from driving simulator data is presented. The structured uncertainty is used to represent the driver’s time-varying behavior, and the unstructured uncertainty is used to account for unmodeled dynamics. The uncertainty models can be used to represent both the uncertainty within one driver and the uncertainty across multiple drivers. The results show that the unstructured uncertainty is significant, probably due to randomness in driver behavior. The structured uncertainty suggests that an estimation and adaptation scheme might be applicable for the design of controllers for active safety systems.

Driving Home the Message

2014 ◽  
Vol 6 (1) ◽  
pp. 50-63 ◽  
Author(s):  
Edward Downs
Keyword(s):  
Video Game ◽  
Driving Simulator ◽  
Cognitive Architecture ◽  
Distracted Driving ◽  
Driving Safety ◽  
Control Group ◽  
Comparison Results ◽  
Post Test ◽  
Game Console ◽  
Original Procedure

A pre-test, post-test experiment was conducted to determine if using a popular racing game on a PlayStation® 3 video game console could change a player's intent to drive distracted. Results indicated that those who were driving distracted (texting or talking) in a video game driving simulator had significantly more crashes, speed violations, and fog-line crossings than those in a non-distracted driving control group. These findings are consistent with predictions from the ACT-R cognitive architecture and threaded cognition theory. A follow-up study manipulated the original protocol by establishing a non-distracted baseline for participants' driving abilities as a comparison. Results demonstrated that this manipulation resulted in a significantly stronger change in attitude against driving distracted than in the original procedure. The implications help to inform driving safety programs on proper protocol for the use of game consoles to change attitudes toward distracted driving.

A motivational driver model for the design of a rear-end crash avoidance system

2019 ◽  
Vol 234 (1) ◽  
pp. 10-26
Author(s):  
Hamed Mozaffari ◽  
Ali Nahvi
Keyword(s):  
Driving Simulator ◽  
Human Subjects ◽  
Autonomous Driving ◽  
Driver Model ◽  
Driver Assistance Systems ◽  
Optimal Point ◽  
Time To Collision ◽  
Human Aspects ◽  
Crash Avoidance ◽  
Assistance Systems

A motivational driver model is developed to design a rear-end crash avoidance system. Current driver assistance systems use engineering methods without considering psychological human aspects, which leads to false activation of assistance systems and complicated control algorithms. The presented driver model estimates driver’s psychological motivations using the combined longitudinal and lateral time to collision, the vehicle kinematics, and the vehicle dynamics. These motivations simplify both autonomous driving algorithms and human-machine interactions. The optimal point of a motivational multi-objective cost function defines the decision for the autonomous driving. Moreover, the motivations are used as risk assessment factors for driver–machine interaction in dangerous situations. The system is evaluated on 10 human subjects in a driving simulator. The assistance system had no false activation during the tests. It avoided collisions in all the rear-end crash avoidance scenarios, while 90% of human subjects did not.

Sign in / Sign up

Export Citation Format

Share Document