Testing Advanced Driver Assistance Systems with a serious-game-based human factors analysis suite

Abstract

The development of Advanced Driver Assistance Systems (ADAS) is rapidly growing. However, most of the ADAS require field test, which is expensive, unpredictable and time consuming. In this paper we propose a multiagent-based driving simulator which integrates a human factor analysis suite and enables rapid and low-cost experimentation of mobile-device ADAS. Our architecture uses a microscopic simulator and a serious-game-based driving simulator. The latter allows the user to control a vehicle and change the correspondent simulation state in the microscopic simulator. The driving simulator also connects to an Android device and sends several kinds of data, such as current GPS coordinates or transportation network data. One important feature of this architecture is its suitability to serve as an appropriate means to conduct behaviour elicitation through peer-designed agents, so as to improve modelling of various driving styles accounting for different aspects of preferences and perception abilities, as well as other performance measures related to drivers' interaction with ADAS solutions. The potentials of our approach to aid experiments in human factor analysis are still to be tested, but are undoubtedly huge and encouraging.

Serious games as research instruments – Do’s and don’ts from a cross-case-analysis in transportation

“…As transportation is a complex system and a serious game represents a simplified model of such system, one might ask if games are an appropriate tool to analyse and design such systems. Many studies (e.g., Antle et al, 2014;Ariffin et al, 2010;Ebnali et al, 2019;Gonçalves et al, 2014;Rosetti et al, 2013;Van den Hoogen et al, 2012) have already discussed this topic and came to the conclusion that especially games are a suitable tool to analyse human behaviour in a safe environment. This is one of the advantages games have in comparison with other methods.…”

“…Due to the named benefits of games, the transportation domain already makes use of games as a tool for informing citizens about transport systems (Brannolte et al, 2004), initiating discussions among stakeholders (Guimarães et al, 2014;Rosetti et al, 2013), specifying user requirements (Gabrielli et al, 2013), and for policy exercises (Schiefelbusch, 2005). Adding on this, the potential of serious games for studying user perception, choice and behaviour is exploited in behavioural modelling tools in different transportation subfields, like road safety (Ariffin et al, 2010), driverassistance systems and autonomous driving (Ebnali et al, 2019;Gonçalves et al, 2014), and microscopic traffic modelling (Biurrun-Quel et al, 2017;Rosetti et al, 2013).…”

ECMS 2021 Proceedings edited by Khalid Al-Begain, Mauro Iacono, Lelio Campanile, Andrzej Bargiela

“…The earliest publication found mentioning a connection between SUMO and Unity3D dates back to 2014, to create a platform for faster, safer and cheaper testing of ADAS (Advanced Driving Assistance Systems) using simulated environments (J. S. V. Gonçalves et al 2014). This implementation used SUMO as a central server that provides information to remaining modules, including the IC-DEEP simulator (J.…”

Cooperative driver assistance system for the lane change

“…However, despite of this disadvantage, automotive industry (AEBERHARD et al, 2015;ZEEB, 2010;CHALLEN, 2008) Source: Smith, Witt and Bakowski (2008). GIETELINK et al, 2006;GONCALVES et al, 2014;MAAG et al, 2012;BIFULCO et al, 2012;NOTH;EDELBRUNNER;IOSSIFIDIS, 2012;YOSHIMOTO;SUETOMI, 2008) have a driving simulator available to facilitate the design, development, and test of their proposals.…”