Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/24158

Title: A new methodology for collision risk assessment of autonomous vehicles
Authors: Katrakazas, Christos
Quddus, Mohammed A.
Chen, Wen-Hua
Keywords: Autonomous vehicles
Traffic safety
Real-time risk assessment
Dynamic bayesian network
Random forest
Issue Date: 2017
Publisher: © the Authors
Citation: KATRAKAZAS, C., QUDDUS, M.A. and CHEN, W-H., 2017. A new methodology for collision risk assessment of autonomous vehicles. Presented at the Transportation Research Board 96th Annual Meeting, January 8–12, 2017, Washington D.C., USA.
Series/Report no.: TRB 96th Annual Meeting Compendium of Papers; 17-03229
Abstract: Risk assessment methods of autonomous vehicles (AVs) have recently begun to treat the motion of the vehicles as dependent on the context of the traffic scene that the vehicle resides in. In most of the cases, Dynamic Bayesian Network (DBN) models are employed for interaction aware motion models (i.e. models that take inter-vehicle dependencies into account). However, communications between vehicles are assumed and the developed models require a lot of parameters to be tuned. Even with these requirements, current approaches cannot cope with traffic scenarios of high complexity. To overcome these limitations, the current study proposes a new methodology that integrates real-time collision prediction as studied by traffic engineers with an interaction-aware motion model for autonomous vehicles real-time risk assessment. Results from a random forest classifier for real-time collision prediction are used as an example for the estimation of probabilities required for the DBN model. It is shown that a well-calibrated collision prediction classifier can provide a supplementary hint to already developed interaction-aware motion models and enhance real-time risk assessment for autonomous vehicles.
Description: Closed access. This paper was peer-reviewed by TRB and presented at the TRB 96th Annual Meeting, Washington, D.C., January 2017.
Sponsor: This research was funded by a grant from the UK Engineering and Physical Sciences Research Council (EPSRC) (Grant reference: EP/J011525/1).
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/24158
Publisher Link: http://pubsindex.trb.org/view/2017/C/1438290
Appears in Collections:Closed Access (Architecture, Building and Civil Engineering)

Files associated with this item:

File Description SizeFormat
Katrakazas_2017_TRB_NetworkLevel3_corrected_clean.pdfAccepted version283.54 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.