ABSTRACT

This article reports a systematic investigation carried out to model the lateral movement decisions of Powered-Two-Wheelers (PTWs) in disordered heterogeneous traffic conditions. The lateral maneuvering decisions of PTWs were framed as a typical multiclass classification problem, and significant factors governing such decisions were identified. Four machine learning models, along with the statistical model, were built to achieve this objective. The comparative analysis regarding the predictive performance of these models shown that the random forest model outperforms the rest of the considered models in terms of its classification power. To this end, the results from this investigation revealed that the lateral movement pattern of PTWs could be predicted using speed and spatial information of its surrounding vehicles. Interestingly, this information can be seamlessly collected with some sensors presently deployed in the advanced vehicles. Thus, the developed models would help in the design of active safety and driving assistance systems for such vehicles.

摘要

本文报告了一项系统调查，以模拟无序异构交通条件下动力双轮车 (PTW) 的横向运动决策。PTW 的横向机动决策被视为典型的多类分类问题，并确定了控制此类决策的重要因素。为了实现这一目标，建立了四个机器学习模型以及统计模型。关于这些模型的预测性能的比较分析表明，随机森林模型在分类能力方面优于其他所考虑的模型。为此，本次调查的结果表明，可以使用周围车辆的速度和空间信息来预测 PTW 的横向运动模式。有趣的是，这些信息可以通过目前部署在先进车辆中的一些传感器无缝收集。因此，开发的模型将有助于为此类车辆设计主动安全和驾驶辅助系统。