arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2407.07320cs.LGcs.RO
收藏

流向罕见事件:归一化流在自动驾驶汽车验证的时序重要性采样中的应用

Flow to Rare Events: An Application of Normalizing Flow in Temporal Importance Sampling for Automated Vehicle Validation

KTH Royal Institute of Technology(KTH皇家理工学院)

Yichun Ye, He Zhang, Ye Tian, Jian Sun, Karl Meinke

AI总结:

针对自动驾驶验证中风险罕见事件分布难以刻画的问题,提出基于归一化流的时序重要性采样方法TrimFlow,通过分解时序变量并引入风险指示函数生成罕见事件分布,在估计跟车碰撞率时减少了86.1%的测试。

摘要:

基于模拟测试的自动驾驶汽车(AV)验证需要无偏评估和高效性。一种有效的解决方案是在对概率测度进行重新加权的同时,增加对风险罕见事件的暴露度。然而,由于样本匮乏和连续场景变量的时序性,刻画风险事件的分布尤为具有挑战性。为了解决这一问题,我们设计了一种方法来表示、生成和重新加权风险罕见事件的分布。基于条件概率,我们将连续变量的时间演化分解为多个分布分量。通过引入风险指示函数,风险罕见事件的分布在理论上从自然驾驶分布中析出。该目标分布通过归一化流(Normalizing Flow)实际生成,从而实现了对复杂分布的精确且可计算的概率评估。随后,该罕见事件分布被证明是具有优势的重要性采样分布。我们还推进了时序重要性采样技术。我们将这种组合方法命名为TrimFlow,并作为初步实践执行于估计跟车场景的碰撞率。结果表明,从罕见事件分布中采样背景车辆的操作可以将测试场景演变为危险状态。与根据测试场景在自然驾驶环境中的暴露度生成场景相比,TrimFlow减少了86.1%的测试。此外,TrimFlow方法并不局限于单一特定类型的功能场景。

英文摘要:

Automated Vehicle (AV) validation based on simulated testing requires unbiased evaluation and high efficiency. One effective solution is to increase the exposure to risky rare events while reweighting the probability measure. However, characterizing the distribution of risky events is particularly challenging due to the paucity of samples and the temporality of continuous scenario variables. To solve it, we devise a method to represent, generate, and reweight the distribution of risky rare events. We decompose the temporal evolution of continuous variables into distribution components based on conditional probability. By introducing the Risk Indicator Function, the distribution of risky rare events is theoretically precipitated out of naturalistic driving distribution. This targeted distribution is practically generated via Normalizing Flow, which achieves exact and tractable probability evaluation of intricate distribution. The rare event distribution is then demonstrated as the advantageous Importance Sampling distribution. We also promote the technique of temporal Importance Sampling. The combined method, named as TrimFlow, is executed to estimate the collision rate of Car-following scenarios as a tentative practice. The results showed that sampling background vehicle maneuvers from rare event distribution could evolve testing scenarios to hazardous states. TrimFlow reduced 86.1% of tests compared to generating testing scenarios according to their exposure in the naturalistic driving environment. In addition, the TrimFlow method is not limited to one specific type of functional scenario.

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。

↑