The rounD Dataset: A Drone Dataset of Road User Trajectories at Roundabouts in Germany

Krajewski, Robert; Moers, Tobias; Bock, Julian; Vater, Lennart; Eckstein, Lutz

doi:10.1109/itsc45102.2020.9294728

Cited by 130 publications

(61 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Als Datensatz wurde dazu der im Jahr 2018 mit der Drohnenmess methodik erstellte Datensatz von deut schen Autobahnen (highD, highway drone dataset) [6] Zur Förderung der Forschung wird der uniDDatensatz für nichtkommer zielle öffentliche Forschungszwecke wieder kostenfrei zur Verfügung gestellt. In den vergangenen Jahren erfolgte eine solche Forschungsunterstützung durch levelXdata bereits für den highDDaten satz [6], den Kreuzungsdatensatz inD (intersection drone dataset) [8] und den Kreisverkehrdatensatz rounD (round about drone dataset) [9]. Eine Lizenz zur Nutzung dieser Datensätze kann online über www.dronedataset.com beantragt werden.…”

Section: Trajektorien-und Szenariendaten Für Die Entwicklungunclassified

Hochgenaue Szenarien- und Referenzdaten für das automatisierte Fahren

Bock

Vater

Krajewski

et al. 2021

ATZ Automobiltech Z

Self Cite

View full text Add to dashboard Cite

Hochgenaue Daten sind entscheidend für die Entwicklung und Absicherung des automatisierten Fahrens. Das umfasst beispielsweise im Realverkehr gemessene Szenarien oder Referenzmessungen für die Umfeld erfassung eines Prototyps. Die fka hat einen Ansatz entwickelt, bei dem mithilfe unbemannter Luftfahrzeuge hochgenaue Messdaten generiert werden. Mit diesen Informationen ist es möglich, Szenarien zu erzeugen und eine fahrzeugunabhängige Referenzmessung für Umfeldsensoren bereitzustellen. g Die Entwicklung und Absiche rung hochautomatisierter Fahrfunktio nen basiert immer stärker auf daten getriebenen Methoden. Große Daten sätze in Form von Trajektorien der im Realverkehr gemessenen Bewegungs muster von Verkehrsteilnehmern sind für verschiedene Einsatzbereiche im Entwicklungsprozess des automatisier BILD 1 Anwendungen der Drohnendaten für das automatisierte Fahren, basierend auf dem A-Modell [2] (© fka) www.springerprofessional.de/automobiltechnik 5 0 ENT WICKLUNG AUtoMAtISIERtES FAHREn ATZ 0506|2021 123. Jahrgang 55 READ THE ENGLISH E-MAGAZINE test now for 30 days free of charge: www.atzworldwide.com AIP designs and manufactures individual test systems for development and manufacturing centers, most vehicle OEM's and their tier suppliers as well as testing institutions, locally and globally.

show abstract

Section: Trajektorien-und Szenariendaten Für Die Entwicklungunclassified

Hochgenaue Szenarien- und Referenzdaten für das automatisierte Fahren

Bock

Vater

Krajewski

et al. 2021

ATZ Automobiltech Z

Self Cite

View full text Add to dashboard Cite

show abstract

“…For each participant they include their pose, velocity, acceleration, size, and also the frames where it appears. Within the considered public available datasets (INTERACTION [4], rounD [5], and openDD [6]), 9 different roundabouts were identified, from which the situation with a higher interactivity, was selected.…”

Section: A Dataset Processingmentioning

confidence: 99%

“…In this paper, a method to classify the intentions of the surrounding vehicles at unsignalized roundabouts is proposed. The framework here presented is evaluated in 9 roundabouts with data from the datasets INTERACTION [4], rounD [5], and openDD [6]. The main contributions of this article are:…”

Section: Introductionmentioning

confidence: 99%

Interaction-Aware Intention Estimation at Roundabouts

Trentin¹,

Artuñedo

Godoy

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Roundabouts have many benefits when compared with traditional signal-controlled intersections: improve safety, reduce delay, improve traffic flow, are less expensive and occupy less area. The behavior of traffic participants is full of uncertainties in the real world. An automated system that relies only on its perception is unable to safely enter the roundabout until a large gap occurs or the vehicle approaching has actually left the roundabout or passed the conflict area. In order to improve the driving quality, autonomous vehicles should be able to infer the correct intention at roundabout as early as possible. In this work, a method to classify the intentions of the surrounding vehicles at unsignalized roundabouts is proposed. For each vehicle at the scene, a Dynamic Bayesian Network is instantiated and the intentions are inferred using a particle filter.

show abstract

“…Action-to-action prediction requires acceleration and steering angle values in tracked data, otherwise they can be inferred from states via inverse models such as (5). Examples of datasets where accelerations are provided are [6], [36].…”

Section: B Learned Mappingsmentioning

confidence: 99%

Self-Supervised Action-Space Prediction for Automated Driving

Janjoš¹,

Dolgov²,

Zöllner³

2021

Preprint

View full text Add to dashboard Cite

Making informed driving decisions requires reliable prediction of other vehicles' trajectories. In this paper, we present a novel learned multi-modal trajectory prediction architecture for automated driving. It achieves kinematically feasible predictions by casting the learning problem into the space of accelerations and steering angles -by performing action-space prediction, we can leverage valuable model knowledge. Additionally, the dimensionality of the action manifold is lower than that of the state manifold, whose intrinsically correlated states are more difficult to capture in a learned manner. For the purpose of action-space prediction, we present the simple Feed-Forward Action-Space Prediction (FFW-ASP) architecture. Then, we build on this notion and introduce the novel Self-Supervised Action-Space Prediction (SSP-ASP) architecture that outputs future environment context features in addition to trajectories. A key element in the self-supervised architecture is that, based on an observed action history and past context features, future context features are predicted prior to future trajectories. The proposed methods are evaluated on real-world datasets containing urban intersections and roundabouts, and show accurate predictions, outperforming state-of-the-art for kinematically feasible predictions in several prediction metrics.

show abstract

The rounD Dataset: A Drone Dataset of Road User Trajectories at Roundabouts in Germany

Cited by 130 publications

References 12 publications

Hochgenaue Szenarien- und Referenzdaten für das automatisierte Fahren

Hochgenaue Szenarien- und Referenzdaten für das automatisierte Fahren

Interaction-Aware Intention Estimation at Roundabouts

Self-Supervised Action-Space Prediction for Automated Driving

Contact Info

Product

Resources

About