Using ontologies for dataset engineering in automotive AI applications

Herrmann, Martin; Witt, Christian; Lake, Laureen; Guneshka, Stefani; Heinzemann, Christian; Bonarens, Frank; Feifel, Patrick; Funke, Simon W.

doi:10.23919/date54114.2022.9774675

Cited by 15 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this is a challenging field itself. Based on the generated scenarios, which were created by human Scenario Designers, automated variations can be introduced to drastically increase the number of available scenarios, as shown by [29,23,30]. This way, a powerful combination of knowledge-and data-driven scenario generation can be achieved for the long tail of rare corner cases.…”

Section: Discussionmentioning

confidence: 99%

“…While there exist many ways of describing scenarios [6], ontologies are the most powerful way of doing so, as these are not only human-and machine-readable, but also extremely scalable for the generation of scenarios, when used in the right fashion [23]. Ontologies are being widely used for the description of scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…While they claim to have developed an ontology, the released code [46] only contains scripted scenarios, which might be derived from an ontology structurally. Hermann et al [23] propose an ontology for dataset creation, with a demonstrated focus on pedestrian detection, including pedestrian occlusions. Their ontology is structurally inspired by the Pegasus model [38] and consists of 22 sub-ontologies.…”

Section: Related Workmentioning

confidence: 99%

“…Ontology available Fuchs et al [16] 2008 --✓ ---Hummel [25] 2010 -✓ ----Hülsen et al [26] 2011 ✓ ✓ ----Armand et al [1] 2014 ------Zhao et al [47] 2017 -✓ ---✓ Bagschik et al [5] 2018 ✓ -----Chen and Kloul [13] 2018 ✓ -----Huang et al [24] 2019 ✓ -----Menzel et al [30] 2019 ✓ ✓ -✓ --Li et al [29] 2020 ✓ ✓ -✓ --Tahir and Alexander [39] 2022 ✓ --✓ --Hermann et al [23] 2022…”

Section: Corner Case Categorizationmentioning

confidence: 99%

See 3 more Smart Citations

One Ontology to Rule Them All: Corner Case Scenarios for Autonomous Driving

Bogdoll¹,

Guneshka²,

Zöllner³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The core obstacle towards a large-scale deployment of autonomous vehicles currently lies in the long tail of rare events. These are extremely challenging since they do not occur often in the utilized training data for deep neural networks. To tackle this problem, we propose the generation of additional synthetic training data, covering a wide variety of corner case scenarios. As ontologies can represent human expert knowledge while enabling computational processing, we use them to describe scenarios. Our proposed master ontology is capable to model scenarios from all common corner case categories found in the literature. From this one master ontology, arbitrary scenario-describing ontologies can be derived. In an automated fashion, these can be converted into the OpenSCENARIO format and subsequently executed in simulation. This way, also challenging test and evaluation scenarios can be generated.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Corner Case Categorizationmentioning

confidence: 99%

See 2 more Smart Citations

One Ontology to Rule Them All: Corner Case Scenarios for Autonomous Driving

Bogdoll¹,

Guneshka²,

Zöllner³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning (DL) [44,92,29] has made remarkable breakthroughs with significant impact on the performance of AD systems. However, DL methods do not provide information to adequately understand what the network has learned and thus are hard to interpret and validate [12,42]. In safety-critical applications, this is a major drawback.…”

Section: Introductionmentioning

confidence: 99%

A Survey on Knowledge Graph-based Methods for Automated Driving

Luettin¹,

Monka²,

Henson³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated driving is one of the most active research areas in computer science. Deep learning methods have made remarkable breakthroughs in machine learning in general and in automated driving (AD) in particular. However, there are still unsolved problems to guarantee reliability and safety of automated systems, especially to effectively incorporate all available information and knowledge in the driving task. Knowledge graphs (KG) have recently gained significant attention from both industry and academia for applications that benefit by exploiting structured, dynamic, and relational data. The complexity of graph-structured data with complex relationships and inter-dependencies between objects has posed significant challenges to existing machine learning algorithms. However, recent progress in knowledge graph embeddings and graph neural networks allows to applying machine learning to graph-structured data. Therefore, we motivate and discuss the potential benefit of KGs applied to the main tasks of AD including 1) ontologies 2) perception, 3) scene understanding, 4) motion planning, and 5) validation. Then, we survey, analyze and categorize ontologies and KG-based approaches for AD. We discuss current research challenges and propose promising future research directions for KG-based solutions for AD.

show abstract