Probabilistic Uncertainty-Aware Risk Spot Detector for Naturalistic Driving

Risk assessment is a central element for the development and validation of autonomous vehicles. It comprises a combination of occurrence probability and severity of future critical events. Time headway (TH) as well as time-to-contact (TTC) are commonly used risk metrics and have qualitative relation...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent vehicles 2019-09, Vol.4 (3), p.406-415
Main Authors: Puphal, Tim, Probst, Malte, Eggert, Julian
Format: Article
Language:English
Subjects:
Automobiles
Autonomous vehicles
collision probability
Computational modeling
criticality maps
Deceleration
Driving
Gaussian method
Hidden Markov models
Intersections
Predictive models
Reliability
Risk assessment
Roads
Statistical analysis
Survival analysis
time headway
time-to-collision
uncertainties in normal driving
Uncertainty
Validation of automated driving
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Risk assessment is a central element for the development and validation of autonomous vehicles. It comprises a combination of occurrence probability and severity of future critical events. Time headway (TH) as well as time-to-contact (TTC) are commonly used risk metrics and have qualitative relations to occurrence probability. However, they lack theoretical derivations and additionally they are designed to only cover special types of traffic scenarios (e.g., longitudinal following between single car pairs). In this paper, we present a probabilistic situation risk model based on survival analysis considerations and extend it to naturally incorporate sensory, temporal, and behavioral uncertainties as they arise in real-world scenarios. The resulting risk spot detector (RSD) is applied and tested on naturalistic driving data of a multilane boulevard with several intersections, enabling the visualization of road criticality maps. Compared to TH and TTC, our approach is more selective and specific in predicting risk. RSD concentrates on driving sections of high vehicle density where large accelerations and decelerations or approaches with high velocity occur.
ISSN:2379-8858
2379-8904
DOI:10.1109/TIV.2019.2919465