Ensuring safety and performance requirements of automated driving systems is a major challenge for the automotive industry. One way to tackle this challenge is a simulationbased approach. However, to rely on results generated by using this approach, the simulation needs to fulfill certain quality criteria depending on the intended usage. Hence, quality must be measured and determined at many different levels and areas of the testing and developing landscape, providing information with varying abstraction degrees. Additionally, quality not only has to be assessed for the automated driving system but also for the simulation models that simulate the vehicles components. Only if the simulation models have a certain quality level can they be used for the simulation. The taxonomy presented in this paper provides a better understanding of the concept of quality during the development and test process. It introduces the possibility to systematically evaluate whether development steps in this process need to be repeated or further assessed.

A taxonomy for quality in simulation-based development and testing of automated driving systems.

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. 

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

Ensuring the quality of automated driving systems is a major challenge the automotive industry is facing. In this context, quality defines the degree to which an object meets expectations and requirements. Especially, automated vehicles at SAE level 4 and 5 will be expected to operate safely in various contexts and complex situations without misconduct. Thus, a systematic approach is needed to show their safe operation. A way to address this challenge is simulation-based testing as pure physical testing is not feasible. During simulation-based testing, the data used to evaluate the actual quality of an automated driving system are generated using a simulation. However, to rely on these simulation data, the overall simulation, which also includes its simulation models, must provide a certain quality level. This quality level depends on the intended purpose for which the generated simulation data should be used. Therefore, three categories of quality can be considered: quality of the automated driving system and simulation quality, consisting of simulation model quality and scenario quality. Hence, quality must be determined and evaluated in various process steps in developing and testing automated driving systems, the overall simulation, and the simulation models used for the simulation. In this paper, we propose a taxonomy to serve a better understanding of the concept of quality in the development and testing process to have a clear separation and insight where further testing is needed -- both in terms of automated driving systems and simulation, including their simulation models and scenarios used for testing. 

A Taxonomy for Quality in Simulation-Based Development and Testing of Automated Driving Systems

Handling large amounts of data has become a key for developing automated driving systems. Especially for developing highly automated driving functions, working with images has become increasingly challenging due to the sheer size of the required data. Such data has to satisfy different requirements to be usable in machine learning-based approaches. Thus, engineers need to fully understand their large image data sets for the development and test of machine learning algorithms. However, current approaches lack automatability, are not generic and are limited in their expressiveness. Hence, this paper aims to analyze a state-of-the-art text and image embedding neural network and guides through the application in the automotive domain. This approach enables the search for similar images and the search based on a human understandable text-based description. Our experiments show the automatability and generalizability of our proposed method for handling large data sets in the automotive domain.

Focus on the Challenges: Analysis of a User-friendly Data Search Approach with CLIP in the Automotive Domain

The high-resolution high-accuracy time-series trajectory data preserves rich motion status and characteristic information of vehicles in a microscopic manner. In order to analyze novel driving events or broadcast potentially hazardous situations to nearby road users, the initial step is how to identify them. Traditional approaches of manually checking trajectory datasets are extremely time-consuming and error-prone. Therefore, how to identify very few anomalous or atypical vehicle trajectories efficiently and effectively from a huge number of regular or typical trajectories is a problem that needs to be solved. This paper introduces an algorithm to automatically identify anomalous trajectories from recorded trajectory datasets in the order of trajectory clustering, template trajectory extraction, trajectory similarity comparison, and anomaly detection. A Dynamic Time Warping (DTW)-based hierarchical clustering model is leveraged to extract critical template trajectories from historical trajectories. By comparing the distance similarity with the templates, trajectories can be assigned a normal or anomalous label. A case study using a public vehicle trajectory dataset (inD dataset) demonstrates the effectiveness of the proposed method in anomaly detection at four urban intersections. 

Automatic Identification of Anomalous Driving Events from Trajectory Data

Highly Automated Driving (HAD) has become one of the leading trends in the automotive industry. Mandatory tasks like environment perception and scene understanding challenge existing rule-based methods. Thus, data-driven technologies and Artificial Intelligence (AI) have been introduced to automotive software development. Utilizing data in the development process has become essential as these systems are no longer developed with classical systems engineering methods, but rather by deriving requirements from and training the algorithms with recorded real-world data. This entails the introduction of data-driven workflows and data-management as new aspects of Automotive Systems Engineering (ASE). Tasks related to the development of Artificial Intelligence (AI) software differ from their classical engineering and programming counterparts. Thus, engineers require new tools and methods for developing safe and accurate AI-based software and handling data efficiently during ASE. Another important aspect of data-driven development is ensuring data quality throughout the systems engineering process. Hence, this paper aims to take a step towards the introduction of a data engineering process in data-driven automotive systems engineering. Putting a spotlight on developing well-designed data sets as the central element for training and validating AI-based software. Besides determining the quality of data sets, we present steps towards improving data and data set quality.

Towards a Data Engineering Process in Data-Driven Systems Engineering

The validation of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) is a major challenge for the automotive industry. Scenario based testing is a promising validation approach, but relies on a scenario database with a high coverage of possible scenarios. Especially in urban areas, the presence of different traffic objects and vulnerable road users (VRU) in combination with semi-structured environments leads to a huge number of possible scenarios. In this paper, a clustering method for grouping real-world driving sequences into semantically similar sequences is introduced. The method allows to deal with the complexity due to the varying number of traffic objects and different sequence lengths and can provide insights over realworld probabilities of driving scenarios. For comparison of different driving sequences, dynamic time warping (DTW) is leveraged. The method is applied to the vehicle trajectories of four urban intersections from the inD dataset and tested with different evaluations. Results show, that an analysis of raw trajectories provides useful insights and is an important component on the path towards a sufficient scenario database.

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

Since highly automated driving functions are obligated to work safely without human interference, careful and comprehensive testing is mandatory. Due to the open world context, automated driving functions must be able to cope with a huge variety of driving situations. To achieve this goal, huge data sets are being recorded. These data sets are used in the development and in open loop tests where the data is replayed to examine driving functions under diverse conditions. The driving functions design is based on machine learning to cope with the variant environment. For the generation of meaningful testing evidences, well-tailored data sets are necessary. To avoid costly processing of voluminous sensor data, the focus lies on a method based on metadata. Therefore, we present a methodology based only on the position and temporal information for the distillation of automotive data sets. The method is intended to support the driving function experts and can be easily parameterized by them according to their requirements. This enables broad scalability and allows to efficiently find specific and potentially challenging situations. The process is presented exemplarily for sun positions and geographical data.

Scalable Data Set Distillation for the Development of Automated Driving Functions

Huge image data sets are the fundament for the development of the perception of automated driving systems. A large number of images is necessary to train robust neural networks that can cope with diverse situations. A sufficiently large data set contains challenging situations and objects. For testing the resulting functions, it is necessary that these situations and objects can be found and extracted from the data set. While it is relatively easy to record a large amount of unlabeled data, it is far more difficult to find demanding situations and objects. However, during the development of perception systems, it must be possible to access challenging data without having to perform lengthy and time-consuming annotations. A developer must therefore be able to search dynamically for specific situations and objects in a data set. Thus, we designed a method which is based on state-of-the-art neural networks to search for objects with certain properties within an image. For the ease of use, the query of this search is described using natural language. To determine the time savings and performance gains, we evaluated our method qualitatively and quantitatively on automotive data sets.

Unveiling Objects with SOLA: An Annotation-Free Image Search on the Object Level for Automotive Data Sets

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Philipp Rigoll

Author Tools

Chat about Author