arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07740cs.LGstat.ML
收藏

流量场景的深度表示学习和聚类

Deep Representation Learning and Clustering of Traffic Scenarios

BMW Group(宝马集团);Technical University of Munich(慕尼黑工业大学)

Nick Harmening, Marin Biloš, Stephan Günnemann

摘要:

确定交通场景空间是自动驾驶功能认证和覆盖评估的主要挑战。在目前的方法,主要是基于网络和依赖于专家知识,我们介绍了两个数据驱动的自动编码模型,学习交通场景的潜在表示。首先是基于CNN的时空模型,其自动编码交通参与者的位置的网格。其次,我们开发了一个基于纯时间RNN的模型,它可以自动编码一系列集合。为了处理无序集合数据,我们必须结合置换不变性。最后,我们展示了如何潜在的场景嵌入可用于聚类交通场景和相似性检索。

英文摘要:

Determining the traffic scenario space is a major challenge for the homologation and coverage assessment of automated driving functions. In contrast to current approaches that are mainly scenario-based and rely on expert knowledge, we introduce two data driven autoencoding models that learn a latent representation of traffic scenes. First is a CNN based spatio-temporal model that autoencodes a grid of traffic participants' positions. Secondly, we develop a pure temporal RNN based model that auto-encodes a sequence of sets. To handle the unordered set data, we had to incorporate the permutation invariance property. Finally, we show how the latent scenario embeddings can be used for clustering traffic scenarios and similarity retrieval.

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。

↑