Analysis of suitable generative algorithms for the generation of safety-critical driving data in the field of autonomous driving

Nico Schick (Autor)

Buch

30 Seiten

2021
Cuvillier Verlag
978-3-7369-7453-1 (ISBN)

Infos

Approximately 3700 people die in traffic accidents each day. The mostfrequent cause of accidents is human error. Autonomous driving can significantly reduce thenumber of traffic accidents. To prepare autonomous vehicles for road traffic, the software andsystem components must be thoroughly validated and tested. However, due to their criticality, thereis only a limited amount of data for safety-critical driving scenarios. Such driving scenarios canbe represented in the form of time series. These represent the corresponding kinematic vehiclemovements by including vectors of time, position coordinates, velocities, and accelerations. Thereare several ways to provide such data. For example, this can be done in the form of a kinematicmodel. Alternatively, methods of artificial intelligence or machine learning can be used. These arealready being widely used in the development of autonomous vehicles. For example, generativealgorithms can be used to generate safety-critical driving data. A novel taxonomy for the generationof time series and suitable generative algorithms will be described in this paper. In addition, agenerative algorithm will be recommended and used to demonstrate the generation of time seriesassociated with a typical example of a driving-critical scenario.

Produkt-Details

• Erscheinungsdatum: 30.06.2021
• Verlagsort: Göttingen
• Sprache: englisch
• Maße: 148 x 210 mm
• Themenwelt: Mathematik / Informatik ► Informatik ► Theorie / Studium
• Schlagworte: acceleration • Artificial Intelligence • autonomes Auto • Autonomes Fahren • Autonomous Car • Autonomous Driving • Beschleunigung • cause of accident • Conditional Restricted Boltzmann Machine • CRBM • criticality • emergency braking scenario • Factored Conditional Restricted Boltzmann Machine • Fahrzeugdaten • FCRBM • GaN • Generative Adversarial Network • generative algorithm • generativer Algorithmus • Geschwindigkeit • kinematic • kinematic model • Kinematik • kinematisches Modell • Kritikalität • Künstliche Intelligenz • machine learning • Maschinelles Lernen • Mobilität • Mobility • Netzwerk • Notbremsszenario • Notbremsung • position coordinates • Positionskoordinaten • Probability Distribution • RBM • RCGAN • Recurrent-Conditional Generative Adversarial Network • Recurrent Neural Network • Recurrent Temporal Restricted Boltzmann Machine • Restricted Boltzmann Machine • RNN • Road Traffic • RTRBM • Safety-Critical • safety-critical driving • safety-critical driving maneuver • safety-critical driving scenario • safety-critical driving scene • Sicherheit • sicherheitskritische Fahrszene • sicherheitskritisches Fahren • sicherheitskritisches Fahrmanöver • sicherheitskritisches Fahrszenario • Straßenverkehr • supervised learning • Taxonomie • Taxonomy • TimeGAN • Time Series • time series data • Time-Series Generative Adversarial Network • traffic accident • überwachtes Lernen • Unfallursache • Unsupervised Learning • unüberwachtes Lernen • VAE-GAN • Variational-Autoencoder Generative Adversarial Network • vehicle data • velocitie • Verkehrsunfall • Wahrscheinlichkeitsverteilung • Zeitreihe • Zeitreihendaten
• ISBN-10: 3-7369-7453-1 / 3736974531
• ISBN-13: 978-3-7369-7453-1 / 9783736974531
• Zustand: Neuware