Validation of Perception and Decision-Making Systems for Autonomous Driving via Statistical Model Checking
Validation of Perception and Decision-Making Systems for Autonomous Driving via Statistical Model Checking
复制标题
通过统计模型检查验证自动驾驶感知和决策系统
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Olivier Simonin
中科院分区：
文献类型：
--
作者：
M. Barbier;A. Renzaglia;J. Quilbeuf;Lukas Rummelhard;Anshul K. Paigwar;C. Laugier;Axel Legay;J. Guzman;Olivier Simonin
汽车系统必须在释放商用车之前严格进行验证过程。随着自主系统中概率方法的使用越来越多，标准验证方法不适用于此目的。此外，现实生活中的验证，即使有可能，就意味着可能是阻碍的成本。因此，需要进行验证和测试的新方法。在本文中，我们提出了一种通用方法，以评估用于自动驾驶的复杂概率框架。该方法基于统计模型检查（SM C），使用特定定义的关键性能指标（KPI）作为时间属性，具体取决于一组确定的指标。通过通过我们的统计模型检查器研究这些指标的行为，我们最终评估了系统满足KPI的概率。我们展示了该方法如何应用于自动驾驶汽车的两个不同子系统：感知系统和决策方法。给出了这两个系统的概述，以了解相关的验证挑战。然后为决策案例提供广泛的验证结果。
Automotive systems must undergo a strict process of validation before their release on commercial vehicles. With the increased use of probabilistic approaches in autonomous systems, standard validation methods are not applicable to this end. Furthermore, real life validation, when even possible, implies costs which can be obstructive. New methods for validation and testing are thus necessary. In this paper, we propose a generic method to evaluate complex probabilistic frameworks for autonomous driving. The method is based on Statistical Model Checking (SM C), using specifically defined Key Performance Indicators (KPIs), as temporal properties depending on a set of identified metrics. By studying the behavior of these metrics during a large number of simulations via our statistical model checker, we finally evaluate the probability for the system to meet the KPIs. We show how this method can be applied to two different subsystems of an autonomous vehicle: a perception system and a decision-making approach. An overview of these two systems is given to understand related validation challenges. Extensive validation results are then provided for the decision-making case.