A Method for Crash Prediction and Avoidance Using Hidden Markov Models

TL;DR

This paper introduces a novel crash prediction method for highways using Hidden Markov Models to analyze traffic patterns and vehicle behaviors, aiming to enhance active safety systems and reduce accidents.

Contribution

The paper develops a new approach employing Hidden Markov Models for predicting highway crashes and implementing preventive safety measures.

Findings

HMM-based models effectively predict crash probabilities.

Simulation results demonstrate improved safety predictions.

The method shows potential for real-time crash prevention.

Abstract

In recent years, automotive technology has made a steady progress. In particular, Advanced Driver Assistance System (ADAS) has enabled many safety features in commercial vehicles, for instance, pedestrian detection, lane keeping assist, emergency automatic braking, etc. Although these features provide drivers with a safer operational environment, crashes still happen occasionally due to the complex road conditions and the unpredictable movement of road users including vehicles, pedestrians, bicyclists, and non-motorized vehicles. In this paper, we aim at predicting the possibilities of crashes between vehicles on highway and implementing an appropriate active safety system to prevent the same. In particular, hidden Markov models are developed for the traffic lanes and speed change of vehicles on highway. Algorithms are developed for the prediction of crash probabilities. Simulation experiments are conducted using Matlab, the results illustrate the effectiveness of the proposed research.