Analysis of visual risk perception model for braking control behaviour of human drivers: A literature review
Analysis of visual risk perception model for braking control behaviour of human drivers: A literature review
复制标题
DOI：
10.1049/itr2.12170
复制
发表时间：
2022-01
影响因子：
2.7
通讯作者：
Chao Liu;Zheng Wang;Edric John Cruz Nacpil;W. Hou;R. Zheng
中科院分区：
文献类型：
--
作者：
Chao Liu;Zheng Wang;Edric John Cruz Nacpil;W. Hou;R. Zheng
为了驾驶安全，了解驾驶员风险评估对于开发以人为本的自动驾驶系统至关重要。视觉感知在观察、分析和预测驾驶碰撞风险方面发挥着核心作用。此外，在风险感知指标的开发中，视觉感知也取得了全面进展。然而，了解依赖于视觉感知的驾驶员控制行为仍然很有趣。因此，本文献综述的目的是评估风险感知和制动控制行为的剩余时间线索耦合的潜力。首先，传统的风险感知指标根据轨迹、接触和状态原则以及从传统风险感知指标衍生的新分析指标进行分类。然后，根据视觉感知信息讨论分析指标。接下来，根据环境、驾驶员和物体特征总结驾驶员风险评估。此外，还比较了制动行为模型与视觉感知变量、动作可供性和行为动力学的关系。当前的评论进一步讨论了将驾驶员行为建模应用于自动驾驶车辆的感知、导航和空间意识的可能性。这种以人为本的方法有可能改善驾驶员和自动化之间的互动。
In the interest of driving safety, it is essential to understand driver risk assessment to develop human‐centred automated driving systems. Visual perception plays a core role in observing, analysing, and predicting driving crash risks. Furthermore, comprehensive progress of visual perception has been achieved in the development of risk perception metrics. However, it is still of interest to understand driver control behaviours, which depend on visual perception. Therefore, the objective of this literature review is to assess the potential of coupling time‐remaining cues for risk perception and braking control behaviour. First, conventional risk perception metrics are classified based on trajectory, contact, and state principles, along with new analysis metrics that have been derived from conventional ones. Then, the analysis metrics are discussed based on visual perception information. Next, driver risk assessment is summarised according to the environment, driver, and object characteristics. Moreover, braking behaviour models are compared in relation to visual perception variables, action affordances, and behaviour dynamics. The current review further discusses the possibility of applying driver behaviour modelling to perception, navigation, and spatial awareness in autonomous vehicles. This human‐centred approach has the potential to improve interaction between drivers and automation.