Logical Scenario Derivation by Clustering Dynamic-Length-Segments Extracted from Real-World-Driving-Data

For the development of Advanced Driver Assistant Systems (ADAS) and Automated Driving Systems (ADS) a change from test case-based testing towards scenario-based testing can be observed. Based on current approaches to define scenarios and their inherent problems, we identify the need to extract scenarios including the static environment from recorded real-world-driving-data. We present an approach, that solves the problem to extract dynamic-length-segments containing a single scenario. These segments are enriched with a feature vector with information relevant for the feature under test. By clustering these scenarios a logical scenario catalog is created, containing all scenarios within the test data. Corner cases are represented as well as common scenarios. An accumulated total length can be calculated for each logical scenario, giving a brief understanding about existing test coverage of the scenario.

[1]  Jacob Langner,et al.  Framework for using real driving data in automotive feature development and validation , 2017 .

[2]  Wenshuo Wang,et al.  Clustering of Driving Scenarios Using Connected Vehicle Datasets , 2018, ArXiv.

[3]  Alois Knoll,et al.  Collecting Simulation Scenarios by Analyzing Physical Test Drives , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[4]  Erwin de Gelder,et al.  Assessment of Automated Driving Systems using real-life scenarios , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[5]  Falko Saust,et al.  Effiziente systematische Testgenerierung für Fahrerassistenzsysteme in virtuellen Umgebungen , 2013 .

[6]  David J. Ketchen,et al.  THE APPLICATION OF CLUSTER ANALYSIS IN STRATEGIC MANAGEMENT RESEARCH: AN ANALYSIS AND CRITIQUE , 1996 .

[7]  Marc Albrecht,et al.  Vorausschauend effizient fahren mit dem elektronischen Co-Piloten , 2018, ATZextra.

[8]  Hermann Winner,et al.  Metrik zur Bewertung der Kritikalität von Verkehrssituationen und -szenarien , 2017 .

[9]  Thao Dang,et al.  Maneuver recognition using probabilistic finite-state machines and fuzzy logic , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[10]  Olaf Op den Camp,et al.  Scenario Identification for Validation of Automated Driving Functions , 2016 .

[11]  Hermann Winner,et al.  Functional Decomposition: An Approach to Reduce the Approval Effort for Highly Automated Driving , 2017 .

[12]  Arati Gerdes.  Automatic Maneuver Recognition in the Automobile: the Fusion of Uncertain Sensor Values using Bayesian Models , 2006 .

[13]  Hermann Winner,et al.  Herausforderungen in der Absicherung von Fahrerassistenzsystemen bei der Benutzung maschinell gelernter und lernender Algorithmen , 2017 .

[14]  Eric Sax,et al.  Estimating the Uniqueness of Test Scenarios derived from Recorded Real-World-Driving-Data using Autoencoders , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[15]  Eric Sax,et al.  Reactive-Replay Approach for Verification and Validation of Closed-Loop Control Systems in Early Development , 2017 .

[16]  Andreas Pütz,et al.  Absicherung hochautomatisierter Fahrfunktionen mithilfe einer Datenbank relevanter Szenarien , 2017 .

[17]  Hermann Winner,et al.  The Release of Autonomous Vehicles , 2016 .

[18]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[19]  Ralf Kohlhaas,et al.  Data-driven simulation and parametrization of traffic scenarios for the development of advanced driver assistance systems , 2015, 2015 18th International Conference on Information Fusion (Fusion).