Scenario Parameter Generation Method and Scenario Representativeness Metric for Scenario-Based Assessment of Automated Vehicles
TNO(荷兰应用科学研究组织);Radboud University Medical Center(拉德堡德大学医学中心);Radboud University(拉德堡德大学);Eindhoven University of Technology(埃因霍温理工大学);Delft University of Technology(代尔夫特理工大学)
Erwin de Gelder, Jasper Hof, Eric Cator, Jan-Pieter Paardekooper, Olaf Op den Camp, Jeroen Ploeg, Bart De Schutter
备注:
14 pages, 11 figures, 4 tables, accepted for publication in IEEE Transactions on Intelligent Transportation Systems
由于自动驾驶汽车(AVs)运行域的复杂性,开发自动驾驶汽车性能的评估方法对于推动自动驾驶技术的部署至关重要。一种候选方案是基于场景的评估,其中测试用例来源于从驾驶数据中提取的真实道路交通场景。由于可能场景的多样性极高,仅使用观测到的场景进行评估是不够的。因此,需要生成额外场景的方法。\n我们的贡献有两方面。首先,我们提出了一种方法,用于在充分程度上确定描述场景的参数,而不依赖于对表征场景参数的强假设。通过估计这些参数的概率密度函数(pdf),可以生成真实的参数值。其次,我们提出了基于 Wasserstein 距离的场景代表性(SR)度量,用于量化使用生成参数值的场景在多大程度上能代表真实世界场景,同时覆盖真实世界场景中存在的实际多样性。\n将我们提出的方法与依赖场景参数化和 pdf 估计假设的方法进行比较,结果表明,所提方法能够自动确定最优的场景参数化和 pdf 估计。此外,我们证明了 SR 度量可用于选择最能描述场景的参数(及其数量)。所提方法前景广阔,因为参数化和 pdf 估计可直接应用于现有的重要性采样策略,以加速 AVs 的评估。
英文摘要:
The development of assessment methods for the performance of Automated Vehicles (AVs) is essential to enable the deployment of automated driving technologies, due to the complex operational domain of AVs. One candidate is scenario-based assessment, in which test cases are derived from real-world road traffic scenarios obtained from driving data. Because of the high variety of the possible scenarios, using only observed scenarios for the assessment is not sufficient. Therefore, methods for generating additional scenarios are necessary.
Our contribution is twofold. First, we propose a method to determine the parameters that describe the scenarios to a sufficient degree without relying on strong assumptions on the parameters that characterize the scenarios. By estimating the probability density function (pdf) of these parameters, realistic parameter values can be generated. Second, we present the Scenario Representativeness (SR) metric based on the Wasserstein distance, which quantifies to what extent the scenarios with the generated parameter values are representative of real-world scenarios while covering the actual variety found in the real-world scenarios.
A comparison of our proposed method with methods relying on assumptions of the scenario parametrization and pdf estimation shows that the proposed method can automatically determine the optimal scenario parametrization and pdf estimation. Furthermore, we demonstrate that our SR metric can be used to choose the (number of) parameters that best describe a scenario. The presented method is promising, because the parameterization and pdf estimation can directly be applied to already available importance sampling strategies for accelerating the evaluation of AVs.
Behavioral Safety Assessment towards Large-scale Deployment of Autonomous Vehicles, Part II: Assessment Results
University of Michigan Transportation Research Institute(密歇根大学交通研究所);University of Michigan(密歇根大学);The University of Hong Kong(香港大学);Laplace Intelligence(拉普拉斯智能公司);Tsinghua University(清华大学)
Behavioral Safety Assessment towards Large-scale Deployment of Autonomous Vehicles, Part I: Methodology
University of Michigan Transportation Research Institute(密歇根大学交通研究所);University of Michigan(密歇根大学);The University of Hong Kong(香港大学);Laplace Intelligence(拉普拉斯智能);Tsinghua University(清华大学)
The Application of Driver Models in the Safety Assessment of Autonomous Vehicles: A Survey
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Vehicle Safety Institute, Graz University of Technology(格拉茨技术大学车辆安全研究所);State Key Laboratory of Automotive Simulation and Control, Jilin University(吉林大学汽车仿真与控制国家重点实验室)
Dynamic Risk Assessment for Autonomous Vehicles from Spatio-Temporal Probabilistic Occupancy Heatmaps
Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA(加州大学伯克利分校土木与环境工程系);D3 Analytics Innovation, Allstate Insurance Company, Northbrook, IL, USA(Allstate保险公司D3 Analytics创新部门);Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA(加州大学伯克利分校电气工程与计算机科学系)
Qualitative and Quantitative Risk Analysis and Safety Assessment of Unmanned Aerial Vehicles Missions over the Internet
Jinan University(暨南大学);University of Tunis El Manar(突尼斯马纳尔大学);National Institute of Applied Sciences and Technology, University of Carthage(迦太基大学应用科学与技术国家研究所);Prince Sultan University(苏丹王子大学);CISTER/INESC TEC;ISEP-IPP(波尔图理工学院工程学院);National School of Electronics and Telecommunication(国立电子与电信学院)
Courteous MPC for Autonomous Driving with CBF-inspired Risk Assessment
Department of Computer Science, University of North Carolina at Charlotte(计算机科学系,北卡罗来纳大学夏洛特分校);Department of Electrical and Computer Engineering, Carnegie Mellon University(电气与计算机工程系,卡内基梅隆大学);Walker Department of Mechanical Engineering, University of Texas at Austin(沃克机械工程系,德克萨斯大学奥斯汀分校)
FLUID: A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories
School of Intelligent Systems Engineering, Sun Yat-sen University(智能系统工程学院,中山大学);Guangdong Provincial Key Laboratory of Intelligent Transportation Systems(广东省智能交通系统重点实验室);Pengcheng Laboratory(鹏城实验室)
Scenario-based Evaluation of Prediction Models for Automated Vehicles
Eindhoven University of Technology(埃因霍温理工大学);TomTom(TomTom公司);TNO(荷兰应用科学研究组织)
为了安全运行,自动驾驶汽车(AV)必须预测周围环境的变化。为此,重要的是要知道哪些预测模型最适合每种情况。目前,预测模型的评估通常是在一组轨迹上执行的,而不区分它们捕获的运动类型,导致无法确定每个模型对不同情况的适用性。在这项工作中,我们说明了标准化的评估方法如何导致错误的结论模型的预测能力,防止明确的评估预测模型,并可能导致危险的道路情况。我们认为,以下的评价实践中的安全评估AV,评估的预测模型,应在一个基于神经网络的方式进行。为了鼓励对预测模型进行基于统计的评估,并说明评估不当的危险,我们根据它们捕获的运动类型对Waymo Open Motion数据集的轨迹进行了分类。接下来,针对不同的轨迹类型和预测范围,对三种不同的模型进行了全面评估。结果表明,共同的评价方法是不够的,评估应根据应用程序中的模型将操作。
Looking and Listening Inside and Outside: Multimodal Artificial Intelligence Systems for Driver Safety Assessment and Intelligent Vehicle Decision-Making
Machine Intelligence, Interaction, and Imagination (Mi3) Laboratory(机器智能、交互与想象实验室);Laboratory for Intelligent and Safe Automobiles (LISA)(智能与安全汽车实验室);Johns Hopkins University(约翰霍普金斯大学);Center for Medicinal Cannabis Research (CMCR)(医药大麻研究中心)