A quantitative approach to behavioural analysis of drivers in highways using particle filtering

Mamouei, M.H., Kaparias, I. and Halikias, G. (2015) A quantitative approach to behavioural analysis of drivers in highways using particle filtering. 47th Annual Conference of the Universities’ Transport Study Group, London, United Kingdom. 05 - 07 Jan 2015. 12 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

The analysis of the driving behaviour is a challenging area in transport that has applications in numerous fields ranging from highway design to micro-simulation and development of advanced driver assistance systems (ADAS). There has been evidence suggesting changes in the driving behaviour in response to changes in traffic conditions, and this is known as adaptive driving behaviour. Identifying these changes, the conditions under which they happen, and describing them in a systematic way would contribute greatly to the accuracy of micro-simulation and more importantly to the understanding of the traffic flow, and will therefore pave the way for introducing further improvements in the efficiency of the transport network. In this paper adaptive driving behaviour is linked to changes in the model parameters for a given car-following model. These changes are tracked using a dynamic system identification method, namely unscented particle filtering.

Text

4-35.pdf - Accepted Manuscript

Available under License University of Southampton Accepted Manuscript Licence.

Download (793kB)