Open Access
Peer-Reviewed
Original Research
Adapting to Complexity: Learning Effects on Pedestrian Perceived Safety and Understanding of Intentions During Interactions with Driverless Vehicles
Abstract
The deployment of driverless vehicles in urban environments raises concerns about pedestrian safety due to the loss of traditional driver communication cues. This study investigated the subjective crossing experience of young and older adult pedestrians facing two different driverless vehicles in a shared space. In a virtual reality setting, 44 participants (24 young adults and 20 older adults) were asked to cross while a driverless car and a driverless shuttle approached. The complexity of the crossing was manipulated so that the two driverless vehicles either had the same behavior (i.e., both yielding or both passing) or different behaviors (i.e., one yielding, the other passing). Additionally, the two vehicles could both be equipped with an external Human-Machine Interface (eHMI) indicating their respective intention (i.e., to yield or to pass) using visual and sound signals, or had none. After each crossing, the participants rated their perceived safety and understanding of the vehicles’ intentions using questionnaires. Semi-structured interviews were conducted post-experiment to gather qualitative feedback on the participants’ crossings and the bimodal eHMI. Firstly, our results indicated that the older adults reported better understanding of both the cars and shuttle’s intentions than the young adults, likely due to their broader integration of environmental cues. Moreover, a learning effect among the older adults was found, indicating improved understanding of the car’s intentions over time when the two vehicles exhibited different behaviors, reflecting preserved learning abilities in normal ageing that support adaptation to complex traffic scenarios. Furthermore, both age groups report ed an initial loss of perceived safety when the two vehicles behave differently, which diminished with repeated exposure, suggesting an adaptive learning process in complex traffic scenarios. Finally, t he presence of the bimodal eHMI on driverless v ehicles demonstrated a positive impact at different levels of the pedestrian crossing experience. These findings are further discussed.
Keywords
Computer Science
Information Systems
Software Engineering
Artificial Intelligence
IADIS
Data Analytics
Declarations & Ethics
Funding:
This research received academic dissemination support through ESCAP / JournalsHub publishing programs.
Conflicts of Interest:
The authors declare no competing financial or institutional interests.
Peer Review:
Double-blind peer reviewed by international subject specialists.
License:
Creative Commons Attribution 4.0 International (CC BY 4.0).
How to Cite This Article
APA / MLA / BibTeX
SahaĂŻ, et al. (2025). Adapting to Complexity: Learning Effects on Pedestrian Perceived Safety and Understanding of Intentions During Interactions with Driverless Vehicles. IADIS International Journal on Computer Science and Information Systems, 20(2). https://doi.org/10.33965/ijcsis_2025_v20i2_02
SahaĂŻ, et al. "Adapting to Complexity: Learning Effects on Pedestrian Perceived Safety and Understanding of Intentions During Interactions with Driverless Vehicles." IADIS International Journal on Computer Science and Information Systems, vol. 20, no. 2, 2025. https://doi.org/10.33965/ijcsis_2025_v20i2_02
SahaĂŻ, et al. "Adapting to Complexity: Learning Effects on Pedestrian Perceived Safety and Understanding of Intentions During Interactions with Driverless Vehicles." IADIS International Journal on Computer Science and Information Systems 20, no. 2 (2025). https://doi.org/10.33965/ijcsis_2025_v20i2_02