A systematic review on sensor-based driver behaviour studies: coherent taxonomy, motivations, challenges, recommendations, substantial analysis and future directions

Abstract

In the plan and development of Intelligent Transportation Systems (ITS), understanding drivers behaviour is considered highly valuable. Reckless driving, incompetent preventive measures, and the reliance on slow and incompetent assistance systems are attributed to the increasing rates of traffic accidents. This survey aims to review and scrutinize the literature related to sensor-based driver behaviour domain and to answer questions that are not covered so far by existing reviews. It covers the factors that are required in improving the understanding of various appropriate characteristics of this domain and outlines the common incentives, open confrontations, and imminent commendations from former researchers. Systematic scanning of the literature, from January 2014 to December 2020, mainly from four main databases, namely, IEEEXplore, ScienceDirect, Scopus and Web of Science to locate highly credible peer-reviewed articles. Amongst the 5,962 articles found, a total of 83 articles are selected based on the author’s predefined inclusion and exclusion criteria. Then, a taxonomy of existing literature is presented to recognize the various aspects of this relevant research area. Common issues, motivations, and recommendations of previous studies are identified and discussed. Moreover, substantial analysis is performed to identify gaps and weaknesses in current literature and guide future researchers into planning their experiments appropriately. Finally, future directions are provided for researchers interested in driver profiling and recognition. This survey is expected to aid in emphasizing existing research prospects and create further research directions in the near future.

Investigating the Effect of Social and Cultural Factors on Drivers in Malaysia: A Naturalistic Driving Study

“…Furthermore, researchers in [46] advocated for the development of a reliable, costefficient DAS. As a result, the proposed DAS had a total cost of only 406 dollars (excluding the laptop and the smartphone).…”

Driver Behavior Profiling and Recognition Using Deep-Learning Methods: In Accordance with Traffic Regulations and Experts Guidelines

“…According to the literature, there are numerous methods for collecting driving data. Since survey and questionnaire results are dependent on self-reported values, they are not appropriate for profiling [2][3][4][5][6][7][8][9][10]. The answers given by drivers are largely subjective, as drivers tend to overestimate their own performance [6].…”

“…The answers given by drivers are largely subjective, as drivers tend to overestimate their own performance [6]. Throughout the literature, the usage of simulators has been cited as a drawback [10,[14][15][16][17]. Simulation flaws include providing a safe environment for drivers, which causes them to become aggressive [5].…”

“…Data collection methods include surveys, questionnaires, simulations, roadside camera observations, and naturalistic experiments. Surveys and questionnaires may not be ideal because they rely on self-reported values [2][3][4][5][6][7][8][9][10], and the questions asked are often 2 of 23 subjective [4][5][6][7][8][10][11][12]. A driving simulator provides a safe driving environment for participants.…”

“…In addition, data from cameras is imprecise, therefore, reducing the reliability of observational studies [5,8]. As a result, naturalistic experiments have become an important and reliable source of data [10,13].…”