An Intelligent Predictive Algorithm for the Anti-Rollover Prevention of Heavy Vehicles for Off-Road Applications

Abstract

Rollover detection and prevention are among the most critical aspects affecting the stability and safety assessment of heavy vehicles, especially for off-road driving applications. This topic has been studied in the past and analyzed in depth in terms of vehicle modelling and control algorithms design able to prevent the rollover risk. However, it still represents a serious problem for automotive carmakers due to the huge counts among the main causes for traffic accidents. The risk also becomes more challenging to predict for off-road heavy vehicles, for which the incipient rollover might be triggered by external factors, i.e., road irregularities, bank angles as well as by aggressive input from the driver. The recent advances in road profile measurement and estimation systems make road-preview-based algorithms a viable solution for the rollover detection. This paper describes a model-based formulation to analytically evaluate the load transfer dynamics and its variation due to the presence of road perturbations, i.e., road bank angle and irregularities. An algorithm to detect and predict the rollover risk for heavy vehicles is also presented, even in presence of irregular road profiles, with the calculation of the ISO-LTR Predictive Time through the Phase-Plane analysis. Furthermore, the artificial intelligence techniques, based on the recurrent neural network approach, is also presented as a preliminary solution for a realistic implementation of the methodology. The paper finally assess the efficacy of the proposed rollover predictive algorithm by providing numerical results from the simulation of the most severe maneuvers in realistic off-road driving scenarios, also demonstrating its promising predictive capabilities.

Development of a Fuzzy Algorithm With Multiple Inputs for the Active Stabilizer Bar to Improve Vehicle Stability When Steering

“…The membership function of the fuzzy controller is shown in Figure 4, Figure 5, and Figure 6. These functions are briefly described in the formula (14). ( )…”

“…According to the article's content [11], these graphs described the dependence between maximum roll angle, the distance from the CG to the RA (roll axis), velocity, and minimum vertical force. The idea of using a limited roll angle to evaluate the rollover phenomenon was also mentioned in [12] by Nguyen et al There were many methods used to estimate and predict the vehicle roll angle, such as neural estimation in the MPC (model predictive control) system [13], an intelligent algorithm [14], a neural network [15], etc. In addition, several indicators that have been used to warn of lateral instability are also used, such as LTR (load transfer ratio) [16,17] or RI (rollover index) [18].…”

An IoT-Based Automatic Vehicle Accident Detection and Visual Situation Reporting System

“…According to the World Health Organization (WHO) report, nearly 1.3 million people die and 50 million people get injured in road trafc accidents each year [6][7][8]. Several eforts have been made to prevent accidents by analyzing road conditions [9], black ice on the road [10], vehicles and obstacles [11], prediction of threats to drivers for safe driving [12,13], and evaluating them based on driving behavior [14]. Despite eforts, road trafc accidents are ranked as the eighth leading cause of death around the world and it may jump to the ffth rank in coming years.…”

Anti-Rollover Control and HIL Verification for an Independently Driven Heavy Vehicle Based on Improved LTR

“…Zhang et al (2022) [9] established a 14-DOF space vehicle model and proposed a cooperative control method for space stability, including four-wheel differential drive and front-wheel active steering to improve vehicle space stability. At the same time, considering the characteristics of heaviness and a high center of mass possessed by heavy vehicles, some scholars established a rollover model for heavy vehicles [10][11][12][13][14][15][16][17][18][19][20]. Therefore, scholars can establish corresponding rollover models according to the focuses of their research.…”