arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.03217cs.LGcs.AI
收藏

驾驶场景轨迹的主动学习

Active Learning of Driving Scenario Trajectories

Chalmers University of Technology(查尔姆斯理工大学);Volvo Cars Corporation(沃尔沃汽车公司)

Sanna Jarl, Linus Aronsson, Sadegh Rahrovani, Morteza Haghir Chehreghani

摘要:

注释的驾驶场景轨迹对于自动驾驶车辆的验证和确认至关重要。然而,仅基于显式规则(即,基于知识的方法)对这样的轨迹的注释可能容易出现错误,诸如对位于两个场景类的边界上的场景的假阳性/阴性分类、遗漏未知场景类、或者甚至未能检测到异常。另一方面,由注释者对标签进行验证并不具有成本效益。为此目的,主动学习(AL)可以通过以有效的方式包括注释者/专家来潜在地改进注释过程。在这项研究中,我们开发了一个通用的主动学习框架来注释驾驶轨迹时间序列数据。我们首先计算嵌入的轨迹到一个潜在的空间,以提取数据的时间性质。给定这样的嵌入,该框架变得与任务无关,因为主动学习可以使用任何分类方法和任何查询策略来执行,而不管原始时间序列数据的结构如何。此外,我们利用我们的主动学习框架来发现未知的驾驶场景轨迹。这将确保先前未知的轨迹类型可以被有效地检测并包括在标记的数据集中。我们评估我们提出的框架,在不同的设置在新的现实世界的数据集组成的驾驶轨迹沃尔沃汽车公司收集。我们观察到,主动学习构成了一个有效的工具,标签驾驶轨迹,以及检测未知类。预期的是,嵌入的质量在所提出的框架的成功中起着重要作用。

英文摘要:

Annotated driving scenario trajectories are crucial for verification and validation of autonomous vehicles. However, annotation of such trajectories based only on explicit rules (i.e. knowledge-based methods) may be prone to errors, such as false positive/negative classification of scenarios that lie on the border of two scenario classes, missing unknown scenario classes, or even failing to detect anomalies. On the other hand, verification of labels by annotators is not cost-efficient. For this purpose, active learning (AL) could potentially improve the annotation procedure by including an annotator/expert in an efficient way. In this study, we develop a generic active learning framework to annotate driving trajectory time series data. We first compute an embedding of the trajectories into a latent space in order to extract the temporal nature of the data. Given such an embedding, the framework becomes task agnostic since active learning can be performed using any classification method and any query strategy, regardless of the structure of the original time series data. Furthermore, we utilize our active learning framework to discover unknown driving scenario trajectories. This will ensure that previously unknown trajectory types can be effectively detected and included in the labeled dataset. We evaluate our proposed framework in different settings on novel real-world datasets consisting of driving trajectories collected by Volvo Cars Corporation. We observe that active learning constitutes an effective tool for labelling driving trajectories as well as for detecting unknown classes. Expectedly, the quality of the embedding plays an important role in the success of the proposed framework.

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。

↑