Title: Detection of steering events using hidden Markov models with multivariate observations

Authors: Roza Maghsood; Pär Johannesson; Jonas Wallin

Addresses: Chalmers University of Technology, Göteborg, Sweden ' SP Technical Research Institute of Sweden, Borås, Sweden ' Lund University, Lund, Sweden

Abstract: In this article we propose a method to identify steering events, such as curves and manoeuvres for vehicles. We use a hidden Markov model with multidimensional observations, to estimate the number of events. Three signals, lateral acceleration, steering angle speed and vehicle speed, are used as observations. We demonstrate that hidden Markov models with a combination of continuous and discrete distributions for observations can be used to detect steering events. Further, the expected number of events is estimated using the transition matrix of hidden states. The results from both measured and simulated data show that the method works well and accurately estimates the number of steering events.

Keywords: hidden Markov models; HMMs; Laplace distribution; discrete distribution; EM algorithm; steering events.

DOI: 10.1504/IJVSMT.2016.083752

International Journal of Vehicle Systems Modelling and Testing, 2016 Vol.11 No.4, pp.313 - 329

Received: 26 May 2016
Accepted: 24 Sep 2016

Published online: 12 Apr 2017 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article