Driving Simulator System to Evaluate Driver’s Workload Using ADAS in Different Driving Contexts

Giandomenico Caruso, Daniele Ruscio*, Dedy Ariansyah, Monica Bordegoni

*Corresponding author

Research output: Contribution to journalConference article


The advancement of in-vehicle technology for driving safety has considerably improved. Current Advanced Driver-Assistance Systems (ADAS) make road safer by alerting the driver, through visual, auditory, and haptic signals about dangerous driving situations, and consequently, preventing possible collisions. However, in some circumstances the driver can fail to properly respond to the alert since human cognition systems can be influenced by the driving context. Driving simulation can help evaluating this aspect since it is possible to reproduce different ADAS in safe driving conditions. However, driving simulation alone does not provide information about how the change in driver’s workload affects the interaction of the driver with ADAS. This paper presents a driving simulator system integrating physiological sensors that acquire heart’s activity, blood volume pulse, respiration rate, and skin conductance parameters. Through a specific processing of these measurements, it is possible to measure different cognitive processes that contribute to the change of driver’s workload while using ADAS, in different driving contexts. The preliminary studies conducted in this research show the effectiveness of this system and provide guidelines for the future acquisition and the treatment of the physiological data to assess ADAS workload.
Original languageEnglish
Pages (from-to)V001T02A066-V001T02A066
Journal37th Computers and Information in Engineering Conference
Publication statusPublished - 2017
Externally publishedYes
EventInternational Design Engineering Technical Conferences and Computers and Information in Engineering Conference - Cleveland, Ohio, USA
Duration: 6 Aug 20179 Aug 2017


  • Automation
  • Human Factors


Dive into the research topics of 'Driving Simulator System to Evaluate Driver’s Workload Using ADAS in Different Driving Contexts'. Together they form a unique fingerprint.

Cite this