Computational-rabi’s driver training model for prime decision-making in driving

• Main Authors: Mustapha, Rabi, Yusof, Yuhanis, Ab. Aziz, Azizi
• Format: Article
• Language: English
• Published: JATIT 2019
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://repo.uum.edu.my/27045/1/JATIT%2097%2013%202019%203540%203558.pdf; http://repo.uum.edu.my/27045/; http://www.jatit.org/volumes/ninetyseven13.php

Recent development of technology has led to the invention of driver assistance systems that support driving and help to prevent accidents. These systems employ Recognition-Primed Decision (RPD) model that explains how human make decisions based on prior experience. However, the RPD model does not include necessary training factors in making prime decision. Although, there exist an integrated RPD-SA model known as Integrated Decision-making Model (IDM) that includes training factors from Situation Awareness (SA) model, the training factors were not detailed. Hence, the model could not provide reasoning capability. Therefore, this study enhanced the IDM by proposing Computational-Rabi’s Driver Training (C-RDT) model that includes improvement on RPD component of the IDM. The C-RDT includes 18 additional training factors obtained from cognitive theories that make a total of 24 training factors that facilitate driver’s prime decision-making during emergencies. The designed model is realized by identifying factors for prime decision-making in driving domain, designing the conceptual model of the RDT model and formalizing it using differential equation. To demonstrate the designed model, simulation scenarios based on driver’s training and awareness has been implemented. The simulation results are found to support related concepts found in literature. The results also provide insight into the robustness nature of the model. The computational model realized in this study practically can serve as a guideline for software developers on the development of driving assistance systems for prime decision-making process. Also, the computational model when combined with support components can serve as an intelligent artefact for driver’s assistance system. Moreover, the C-RDT model offers reasoning ability that allows backtracking on why certain prime-decision has been made.