Active learning of driving scenario trajectories. (August 2022)

• Record Type: Journal Article
• Authors: Jarl, Sanna; Aronsson, Linus; Rahrovani, Sadegh; Chehreghani, Morteza Haghir
• Is Part Of: Engineering applications of artificial intelligence. Volume 113(2022)
• Publication Date: 2022-08
• Subjects: Active learning -- Time series analysis -- Latent space representation -- Autonomous drive verification -- Active safety; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.104972
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: 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 labeling 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.