arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.04896eess.SYcs.SY
收藏

面向自动驾驶车辆的加速测试方法:背景交通由联合分布描述

An Accelerated Testing Approach for Automated Vehicles with Background Traffic Described by Joint Distributions

University of Michigan(密歇根大学);Columbia University(哥伦比亚大学)

Zhiyuan Huang, Henry Lam, Ding Zhao

AI总结:

本文提出基于联合统计模型的新框架,用于评估自动驾驶车辆在自然驾驶环境中的风险。通过扩展多变量模型到联合统计,引入重要性采样技术构建高斯混合模型,并利用单调性避免联合分布的维度灾难,验证了方法的有效性及降低测试成本的潜力。

摘要:

本文提出了一种基于联合统计模型的新框架,用于评估自动驾驶车辆在自然驾驶环境中的风险。先前关于自动驾驶车辆加速评估的研究从多变量模型扩展到联合统计。所提出的工具包包括对罕见事件(如碰撞)集的探索以及利用重要性采样技术构建高斯混合模型的加速分布。此外,利用单调性以避免联合分布引入的维度灾难。仿真结果表明,该过程有效且有潜力降低自动驾驶车辆的测试成本。

英文摘要:

This paper proposes a new framework based on joint statistical models for evaluating risks of automated vehicles in a naturalistic driving environment. The previous studies on the Accelerated Evaluation for automated vehicles are extended from multi-independent-variate models to joint statistics. The proposed toolkit includes exploration of the rare event (e.g. crash) sets and construction of accelerated distributions for Gaussian Mixture models using Importance Sampling techniques. Furthermore, the monotonic property is used to avoid the curse of dimensionality introduced by the joint distributions. Simulation results show that the procedure is effective and has a great potential to reduce the test cost for automated vehicles.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑