Capturing the Variety of Urban Logical Scenarios from Bird-view Trajectories

King, Christian; Braun, Thilo; Braess, Constantin; Langner, Jacob; Sax, Eric

doi:10.5220/0010441204710480

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering is a subjective process in nature due to the absence of a ground truth [20], [37], since the main goal of the clustering and the subsequent result interpretation itself is to find these before unknown labels as good as possible within the given data. Clustering results heavily depend on the choice of the clustering approach, and even for the same algorithm, the selection of related parameters [20].…”

Section: E Cluster Validation and Results Interpretationmentioning

confidence: 99%

“…Regarding valuable work in terms of scenario extraction based on naturalistic road traffic data, King et al [37] propose an approach for deriving logical vehicle-to-vehicle interaction scenarios for an unsignalized intersection. Finally, Ries et al [38] introduce a raw-data based clustering method for grouping real driving sequences into semantically similar sequences.…”

Section: Data-driven Scenario Extractionmentioning

confidence: 99%

“…Req. M5) [37]. Furthermore, instead of a sequential and pairwise similarity estimation between trajectories belonging to a concrete scenario, we want to compare the dynamics of multiple road users simultaneously (cf.…”

Section: Data-driven Scenario Extractionmentioning

confidence: 99%

See 2 more Smart Citations

UnScenE: Toward Unsupervised Scenario Extraction for Automated Driving Systems from Urban Naturalistic Road Traffic Data

Weber¹,

Thiem²,

Konigorski³

2022

Preprint

View full text Add to dashboard Cite

Scenario-based testing is a promising approach to solve the challenge of proving the safe behavior of vehicles equipped with automated driving systems (ADS). Since an infinite number of concrete scenarios can theoretically occur in real-world road traffic, the extraction of relevant scenarios that are sensitive regarding the safety-related behavior of ADSequipped vehicles is a key aspect for the successful verification and validation of these systems. Therefore, this paper provides a method for extracting multimodal urban traffic scenarios from naturalistic road traffic data in an unsupervised manner for minimizing the amount of (potentially biased) prior expert knowledge needed. Rather than an (expensive) rule-based assignment by extracting concrete scenarios into predefined functional scenarios, the presented method deploys an unsupervised machine learning pipeline. It includes principal feature analysis, feature extraction with so-called scenario grids, dimensionality reduction by principal component analysis, scenario clustering as well as cluster validation. The approach allows exploring the unknown natures of the data and interpreting them as scenarios that experts could not have anticipated. The method is demonstrated and evaluated for naturalistic road traffic data at urban intersections from the inD and the Silicon Valley dataset. The findings encourage the use of this type of data as well as unsupervised machine learning approaches as important pillar for a systematic construction of a relevant scenario database with sufficient coverage for testing ADS.

show abstract

Section: E Cluster Validation and Results Interpretationmentioning

confidence: 99%

Section: Data-driven Scenario Extractionmentioning

confidence: 99%