Infrastructure-based pedestrian risk tagging methodology to support AV risk assessment

Chia, W. M. D., Keoh, S. L. , Michala, A. L. and Goh, C. (2022) Infrastructure-based pedestrian risk tagging methodology to support AV risk assessment. IEEE Access, 10, pp. 71462-71480. (doi: 10.1109/ACCESS.2022.3188306)

Abstract

Safety is paramount in AV deployment. Traditionally, AV safety is incorporated during development by identifying the failure of vehicular components using risk and scenarios-based validation approaches with risk indicators. The main challenge of having a comprehensive risk assessment for AV safety is to include all potential complex environments that could occur in real-time, which is more critical for higher AV automation levels. Real-world real-time risk assessment research addresses this shortcoming by providing an advanced warning to the AV during deployment either at the vehicle level or at the infrastructure level. This paper proposes a risk tagging methodology to quantitatively risk tag the severity rating of the real-world environment for real-time risk assessment of AV using the existing roadside infrastructure. The proposed methodology - Spatial-Temporal Risk Estimation Ensemble Technique (STREET), provides advanced risk indicators in the form of pedestrian risk tag figure and time to collision value to the AV. This paper includes the evaluation of STREET, tested on four events over a pre-defined uncontrolled traffic scene from the infrastructure and validated using ground truth and heatmap of pedestrian occurrence. This methodology includes three different algorithms developed to emphasize different events depending on the AV risk and safety management strategy. The STREET reduces the bandwidth needed compared to traditional approaches of streaming video images for lightweight integration of AV risk assessment. The outcome of the pedestrian risk tag from STREET can be used as a severity rating for the existing real-time risk assessment of AV via cooperative mode.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Goh, Dr Cindy Sf and Keoh, Dr Sye Loong and Michala, Dr Lito
• Authors: Chia, W. M. D., Keoh, S. L., Michala, A. L., and Goh, C.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: IEEE Access
• Publisher: IEEE
• ISSN: 2169-3536
• ISSN (Online): 2169-3536
• Published Online: 04 July 2022
• Copyright Holders: Copyright © 2022 The Authors
• First Published: First published in IEEE Access 10: 71462-71480
• Publisher Policy: Reproduced under a Creative Commons licence