Analysis and comparison of similarity measures for validation of generative algorithms in the context of probability density functions
Seiten
- Keine Verlagsinformationen verfügbar
- Artikel merken
About 3700 people die in traffic accidents every day. Human error is the number one causeof accidents. Autonomous driving can greatly reduce the occurrence of traffic accidents. Torelease self-driving cars for road traffic, the system including software must be validated and testedefficiently. However, due to their criticality, the amount of data corresponding to safety-criticaldriving scenarios are limited. These driving scenes can be expressed as a time series. They representthe corresponding movement of the vehicle, including time vector, position coordinates, speed andacceleration. Such data can be provided on different ways. For example, in the form of a kinematic model. Alternatively, artificial intelligence or machine learning methods can be used. They havebeen widely used in the development of autonomous vehicles. For example, generative algorithmscan be used to generate such safety-critical driving data. However, the validation of generativealgorithms is a challenge in general. In most cases, their quality is assessed by means of expertknowledge (qualitative). In order to achieve a higher degree of automation, a quantitative validationapproach is necessary. Generative algorithms are based on probability distributions or probabilitydensity functions. Accordingly, similarity measures can be used to evaluate generative algorithms. In this publication, such similarity measures are described and compared on the basis of definedevaluation criteria. With respect to the use case mentioned, a recommended similarity measure isimplemented and validated for an example of a typical safety-critical driving scenario.
| Erscheinungsdatum | 30.06.2021 |
|---|---|
| Verlagsort | Göttingen |
| Sprache | englisch |
| Maße | 148 x 210 mm |
| Themenwelt | Mathematik / Informatik ► Informatik ► Theorie / Studium |
| Schlagworte | acceleration • Ähnlichkeit • Ähnlichkeitsmaß • Artificial Intelligence • Autonomes Fahren • Autonomous Driving • Beschleunigung • Bregman-Divergences • causes of accidents • Cramér Distance • criticality • Dissimilarität • dissimilarity • divergences • Fahrzeugdaten • Fahrzeugsbewegung • f-Divergences • generative algorithm • generativer Algorithmus • Geschwindigkeit • Hellinger distance • histogram-spline approximation • Histogram-Spline-Approximation • Information Theoretic Measures • Integral Probability Metrics • Itakura-Saito Distance • Jensen-Shannon Divergence • Kernel density estimators • Kernel-Dichte-Schätzer • Kolmogorov-Smirnov Distance • Kritikalität • Kullback-Leibler Divergence • Künstliche Intelligenz • machine learning • Mahalanobis Distance • Maschinelles Lernen • Maximum Mean Discrepancy • Minkowski Metric • Mobilität • Mobility • Nicht-Negativität • non-negativity • Probability density function • quantitativ • Quantitative • Reflexivität • reflexivity • Road Safety • Safety-Critical • safety-critical driving • safety-critical driving scenario • SICHERHEITSKRITISCH • sicherheitskritisches Fahren • sicherheitskritisches Fahrszenario • Similarity • similarity measure • Similiarity Coefficients • Speed • Symmetrie • symmetry • Taxonomie • Taxonomy • Total Variation Metric • Traffic Accidents • Unfallursachen • Validation • Validierung • vehicle data • vehicle movement • Verkehrssicherheit • Verkehrsunfälle • Wahrscheinlichkeitsdichtefunktion • Wasserstein distance • χ²-Distance |
| ISBN-10 | 3-7369-7454-X / 373697454X |
| ISBN-13 | 978-3-7369-7454-8 / 9783736974548 |
| Zustand | Neuware |
| Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
Grundlagen – Anwendungen – Perspektiven
Buch | Softcover (2022)
Springer Vieweg (Verlag)
CHF 48,95
Eine Einführung in die Systemtheorie
Buch | Softcover (2022)
UTB (Verlag)
CHF 34,95
