Research on identification method of heavy vehicle rollover based on hidden Markov model

Abstract

Aiming at the problem of early warning credibility degradation as the heavy vehicle load and its center of gravity change greatly; the heavy vehicle rollover state identi cation method based on the Hidden Markov Model (HMM, is introduced to identify heavy vehicle lateral conditions dynamically in this paper. In this method, the lateral acceleration and roll angle are taken as the observation values of the model base. The Viterbi algorithm is used to predict the state sequence with the highest probability in the observed sequence, and the Markov prediction algorithm is adopted to calculate the state transition law and to predict the state of the vehicle in a certain period of time in the future. According to combination conditions of Double lane change and steering , applying Trucksim and Matlab trained hidden Markov model, the model is applied to the online identi cation of heavy vehicle rollover states. The identi cation results show that the model can accurately and e ciently identify the vehicle rollover state, and has good applicability. This study provides a novel method and a general strategy for active safety early warning and control of vehicles, which has reference signi cance for the application of the Hidden Markov theory in collision, rear-end and lane departure warning system.

Assessing the dependence of vehicle rollover on many factors based on new 4D graphs

“…However, the tripped condition occurs more rarely than others. According to Zhao et al, vehicle size and load parameters can also affect rollover [ 3 ]. If the vehicle’s height is too high or the track width is quite small, the car may more easily roll over.…”

A Deep Learning Method for Lane Changing Situation Assessment and Decision Making

“…Meanwhile, many existing LC warning systems utilize machine learning algorithms (including support vector machine [8], hidden Markov model [10], Bayes classifier [11], [12], random forest, AdaBoost [5] and artificial neural network [13], [14]) to construct a situation assessment model. The information obtained by these models includes driver behavior observation (e.g., eye-tracking), sensor information about the environment (e.g., lidar, camera sensors and GPS) and vehicle parameters (e.g., vehicle speed and acceleration) [14]- [17].…”