Next Article in Journal
Performance Improvement of Thermoelectric Air Cooler System by Using Variable-Pulse Current for Building Applications
Next Article in Special Issue
Monitor Activity for the Implementation of a Pavement—Management System at Cagliari Airport
Previous Article in Journal
Beer Industry in the Czech Republic: Reasons for Founding a Craft Brewery
Previous Article in Special Issue
Proposal and Implementation of a Heliport Pavement Management System: Technical and Economic Comparison of Maintenance Strategies
Article

Surrogate Safety Measures Prediction at Multiple Timescales in V2P Conflicts Based on Gated Recurrent Unit

1
Polytechnic Department of Engineering and Architecture (DPIA), University of Udine, Via del Cotonificio 114, 33100 Udine, Italy
2
Department of Mathematics, Computer Science and Physics (DMIF), University of Udine, Via delle Scienze 206, 33100 Udine, Italy
3
Department of Languages, Literatures, Communication, Education and Society (DILL), University of Udine, Via Margreth 3, 33100 Udine, Italy
4
Claudiana—Landesfachhochschule für Gesundheitsberufe, I-39100 Bolzano, Italy
*
Author to whom correspondence should be addressed.
Academic Editors: Maria Rosaria De Blasiis, Chiara Ferrante, Valerio Veraldi and Marco Guerrieri
Sustainability 2021, 13(17), 9681; https://doi.org/10.3390/su13179681
Received: 30 July 2021 / Revised: 23 August 2021 / Accepted: 26 August 2021 / Published: 28 August 2021
(This article belongs to the Special Issue Transportation Safety and Pavement Management)
Improving pedestrian safety at urban intersections requires intelligent systems that should not only understand the actual vehicle–pedestrian (V2P) interaction state but also proactively anticipate the event’s future severity pattern. This paper presents a Gated Recurrent Unit-based system that aims to predict, up to 3 s ahead in time, the severity level of V2P encounters, depending on the current scene representation drawn from on-board radars’ data. A car-driving simulator experiment has been designed to collect sequential mobility features on a cohort of 65 licensed university students who faced different V2P conflicts on a planned urban route. To accurately describe the pedestrian safety condition during the encounter process, a combination of surrogate safety indicators, namely TAdv (Time Advantage) and T2 (Nearness of the Encroachment), are considered for modeling. Due to the nature of these indicators, multiple recurrent neural networks are trained to separately predict T2 continuous values and TAdv categories. Afterwards, their predictions are exploited to label serious conflict interactions. As a comparison, an additional Gated Recurrent Unit (GRU) neural network is developed to directly predict the severity level of inner-city encounters. The latter neural model reaches the best performance on the test set, scoring a recall value of 0.899. Based on selected threshold values, the presented models can be used to label pedestrians near accident events and to enhance existing intelligent driving systems. View Full-Text
Keywords: ADAS; traffic safety; surrogate safety measures; driver behavior; Gated Recurrent Units; driving simulator ADAS; traffic safety; surrogate safety measures; driver behavior; Gated Recurrent Units; driving simulator
Show Figures

Figure 1

MDPI and ACS Style

Miani, M.; Dunnhofer, M.; Micheloni, C.; Marini, A.; Baldo, N. Surrogate Safety Measures Prediction at Multiple Timescales in V2P Conflicts Based on Gated Recurrent Unit. Sustainability 2021, 13, 9681. https://doi.org/10.3390/su13179681

AMA Style

Miani M, Dunnhofer M, Micheloni C, Marini A, Baldo N. Surrogate Safety Measures Prediction at Multiple Timescales in V2P Conflicts Based on Gated Recurrent Unit. Sustainability. 2021; 13(17):9681. https://doi.org/10.3390/su13179681

Chicago/Turabian Style

Miani, Matteo, Matteo Dunnhofer, Christian Micheloni, Andrea Marini, and Nicola Baldo. 2021. "Surrogate Safety Measures Prediction at Multiple Timescales in V2P Conflicts Based on Gated Recurrent Unit" Sustainability 13, no. 17: 9681. https://doi.org/10.3390/su13179681

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop