title: Assistive tactical decisions for safe and fast trajectories
creator: Gruber, Thierry
creator: Larue, Gregoire S.
creator: Rakotonirainy, Andry
creator: Poulsen, Niels K.
subject: 010299 Applied Mathematics not elsewhere classified
subject: 091500 INTERDISCIPLINARY ENGINEERING
subject: 111799 Public Health and Health Services not elsewhere classified
subject: Road safety
subject: optimal trajectories
subject: Artificial Intelligence
description: It is the dawn of an area where Advanced Driving Assistance Systems (ADAS) are gradually enhanced to provide fully automated systems, ADAS have huge potential for improving road safety and travel times. However their take-up in the market is very slow. Assistive systems should take into account driver’s preferences in terms of driving style in order to increase adoption rates. The aim of this paper is to compute online optimal trajectories given a traffic condition on a highway while considering the motorist’s driving style. Travel duration and safety are the main parameters used to find the optimal trajectory. A simulation framework to determine the optimal trajectory was developed in which the ego car travels in a highway environment scenario. An agent-oriented algorithm - using time and safety as optimality criteria – was defined for real-time feedback. The performance of the algorithm was compared against optimal trajectories computed offline with the hybrid A* algorithm. The new framework provides trajectories close to the optimal trajectory and is computationally achievable. The agents were shown to follow safe and fast trajectories in three tests scenarios: emergency braking, overtaking, and a complex situation with multiple vehicles around the ego vehicle.
date: 2016-10-14
type: Conference Paper
format: application/pdf
relation: https://eprints.qut.edu.au/101641/1/ITS16_paper_revised.pdf
relation:    Gruber, Thierry, Larue, Gregoire S., Rakotonirainy, Andry,  & Poulsen, Niels K.   (2016)   Assistive tactical decisions for safe and fast trajectories. In  23rd World Congress on Intelligent Transport Systems, 10–14 October 2016, Melbourne, VIC.   
identifier: https://eprints.qut.edu.au/101641/
rights: Copyright 2016 [please consult the author]
source: Centre for Accident Research & Road Safety - Qld (CARRS-Q); Faculty of Health; Institute of Health and Biomedical Innovation; School of Psychology & Counselling