Our researchers
Research_
Trust and Safety in Autonomous Mobility Systems
Enabling the safe adoption of driverless cars in urban spaces
This project aims to develop new interfaces for autonomous vehicles to communicate with the people around them, and how this is linked to perceived trust and safety.
Australia is seen as a leader in the development and adoption of driverless cars. Australia’s Smart Cities Plan highlights that their transformational impact will “fundamentally change how we live and work”. Driverless cars and other autonomous vehicles have the potential to contribute to the strategic goals of Australian cities, addressing sustainability and liveability through shared ownership models and reduced congestion.
Recently completed, this project explored questions of how to make autonomous vehicles sympathetic to the social life of the urban spaces they inhabit, a factor often overlooked in much of the research on autonomous vehicles. It tackled this challenge by developing new understandings about how autonomous vehicles interact with people around them, and how this is linked to perceived trust and safety.The project developed interfaces for communicating the state and intent of autonomous vehicles to pedestrians and validated the use of virtual reality simulators to test how people interact with vehicles.
Project findings provide evidence for autonomous vehicle trials and guidance on when to use hyperreal prototypes and when to use computer-generated environments when testing the impact of autonomous vehicles on other road users. This knowledge has the potential to reduce the risk of accidents from pedestrians misinterpreting the intention of the vehicle and to improve public perceptions.
Project objectives
The project had three overarching aims:
- To develop means for allowing pedestrian participants to interact with AVs in a VR environment using devices (e.g. a smartphone) and gestures (e.g. hand waving), thus extending the one-way communication in previous VR simulations of AVs to allow for a bi-directional communication between pedestrians and AVs.
- To compare the effectiveness of a 3D modelled AV and environment with 360-degree video recordings from the physical AV and environment for evaluating perceived trust and safety.
- To validate the efficacy of hyperreal prototypes by comparing how participants respond to VR representations of AVs and their AV-pedestrian interfaces with how participants respond to the same AV-pedestrian interfaces implemented on our existing physical AV experienced in a real urban environment.
Publications
Jones, R., Sadowski, J., Dowling, R., Worrall, S., Tomitsch, M., & Nebot, E. (2023). Beyond the driverless car: A typology of forms and functions for autonomous mobility. Applied Mobilities, 8(1), 26-46.
Tran, T. T. M., Parker, C., Wang, Y., & Tomitsch, M. (2022). Designing wearable augmented reality concepts to support scalability in autonomous vehicle-pedestrian interaction. Frontiers in Computer Science, 4, 866516.
Hoggenmueller, M., Tomitsch, M., & Worrall, S. (2022). Designing interactions with shared AVs in complex urban mobility scenarios. Frontiers in Computer Science, 4, 866258.
Project team
- Luke Hespanhol - Lecturer in Design and Computation
- Stewart Worrall - Research Fellow, Australian Centre for Field Robotics
- Eduardo Nebot - Emeritus Professor, Patrick Chair in Automation and Logistics, Australian Centre for Field Robotics
- Jennifer Kent - Senior Research Fellow in Urbanism, DECRA and Robinson Fellow
- Martin Tomitsch - Professor, Head of Transdisciplinary School, UTS
- Alexander Wiethoff - Senior Lecturer, LMU Munich
- Adrian Ellison - Associate Director (Data Science Consulting), DSpark PTY LTD
The project was funded through the Australian Research Council (ARC) Discovery Project (DP) scheme under the number DP200102604.