Trajectory-Based Clustering of Real-World Urban Driving Sequences with Multiple Traffic Objects

Ries, Lennart; Rigoll, Philipp; Braun, Thilo; Schulik, Thomas; Daube, Johannes; Sax, Eric

doi:10.1109/itsc48978.2021.9564636

Cited by 10 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In literature, three different testing criteria categories, namely external, internal and relative indices, are defined to be able to estimate the quality of clustering results [20]. In accordance with present work in the field of unsupervised scenario extraction (e.g., [33], [34], and [38]), one branch of our evaluation approach can be assigned to the external indices category, where external information is used as standard to validate the clustering results. For this purpose, we use the map information available within the datasets in the form of images of the corresponding traffic spaces.…”

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. The proposed method is the only one we are aware of that leverages clustering to extract urban traffic scenarios with different road user types and numbers including potentially differing sequence lengths.…”

Section: Data-driven Scenario Extractionmentioning

confidence: 99%

See 1 more Smart Citation

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%

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

show abstract

“…Analyzing traffic scenarios from the ego information and other objects is realized in [12]. A procedure based on DTW and manual thresholds determines if a scenario is known.…”

Section: Related Workmentioning

confidence: 99%

Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios

Wurst

Balasubramanian

Botsch

et al. 2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Clustering traffic scenarios and detecting novel scenario types are required for scenario-based testing of autonomous vehicles. These tasks benefit from either good similarity measures or good representations for the traffic scenarios. In this work, an expert-knowledge aided representation learning for traffic scenarios is presented. The latent space so formed is used for successful clustering and novel scenario type detection. Expert-knowledge is used to define objectives that the latent representations of traffic scenarios shall fulfill. It is presented, how the network architecture and loss is designed from these objectives, thereby incorporating expert-knowledge. An automatic mining strategy for traffic scenarios is presented, such that no manual labeling is required. Results show the performance advantage compared to baseline methods. Additionally, extensive analysis of the latent space is performed.

show abstract

“…The affinity of the scenarios are described by the similarity of the corresponding histograms. Another approach by Ries et al [8] uses DTW to compare trajectories of traffic participant. Scenarios are similar and can be clustered once two scenarios exist with the same traffic participant types and similar trajectories.…”

Section: A Clustering Of Traffic Scenes and Scenariosmentioning

confidence: 99%

Towards Traffic Scene Description: The Semantic Scene Graph

Zipfl

Zöllner

2022

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

Autonomous vehicles hold great promise in improving the future of transportation. The driving models used in these vehicles are based on neural networks, which can be difficult to validate. However, ensuring the safety of these models is crucial. Traditional field tests can be costly, time-consuming, and dangerous. To address these issues, scenario-based closed-loop simulations can simulate many hours of vehicle operation in a shorter amount of time and allow for specific investigation of important situations. Nonetheless, the detection of relevant traffic scenarios that also offer substantial testing benefits remains a significant challenge. To address this need, in this paper we build an imitation learning based trajectory prediction for traffic participants. We combine an image-based (CNN) approach to represent spatial environmental factors and a graph-based (GNN) approach to specifically represent relations between traffic participants. In our understanding, traffic scenes that are highly interactive due to the network's significant utilization of the social component are more pertinent for a validation process. Therefore, we propose to use the activity of such sub networks as a measure of interactivity of a traffic scene. We evaluate our model using a motion dataset and discuss the value of the relationship information with respect to different traffic situations.

show abstract

Trajectory-Based Clustering of Real-World Urban Driving Sequences with Multiple Traffic Objects

Cited by 10 publications

References 17 publications

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

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

Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios

Towards Traffic Scene Description: The Semantic Scene Graph

Contact Info

Product

Resources

About