Benrabah Mohamed, Orou Mousse Charifou, Randriamiarintsoa Elie, Chapuis Roland, Aufrère Romuald
Clermont Auvergne INP, CNRS, Institut Pascal, Université Clermont Auvergne, F-63000 Clermont-Ferrand, France.
Sensors (Basel). 2024 Mar 16;24(6):1909. doi: 10.3390/s24061909.
Evaluating the risk associated with operations is an essential element of safe planning and an essential prerequisite in mobile robotics. This issue is very broad, with numerous definitions emerging in the recent literature adapting different application scenarios and leading to different algorithmic approaches. In this review, we will investigate how the state-of-the-art approaches define the traversability risk, particularly for mobile robots, whereby we classify existing risk-aware navigation algorithms according to their characterization of risk. Subsequently, we will overview the formulations of risk assessment along a path using traversability grid maps since it is essential for a mobile robot to evaluate its path to predict potential hazards. Finally, we will discuss the consistency of commonly used risk metrics in robotics. The aim of the review is to offer a comprehensive overview to newcomers in the field, to provide a structured reference for practitioners, and to also inspire future developments.
评估与操作相关的风险是安全规划的重要组成部分，也是移动机器人领域的基本前提。这个问题非常广泛，最近的文献中出现了许多定义，适用于不同的应用场景，并导致不同的算法方法。在本综述中，我们将研究当前的先进方法如何定义可通行性风险，特别是对于移动机器人而言，我们将根据现有风险感知导航算法对风险的特征描述对其进行分类。随后，我们将概述使用可通行性网格地图沿路径进行风险评估的公式，因为对于移动机器人来说，评估其路径以预测潜在危险至关重要。最后，我们将讨论机器人技术中常用风险度量的一致性。本综述的目的是为该领域的新手提供全面的概述，为从业者提供结构化的参考，并激发未来的发展。
