Autonomous Driving Scenario Generation in Overtake Manoeuvres Through Data Fusion

Abstract

For an effective study of specific driving scenarios, in particular related to overtaking manoeuvres, developing well-thought-out manoeuvre databases from the acquired data will greatly improve the analysis process. The key point being that identifying clearly the studied scenario and clustering the manoeuvres based on specific sub-cases of this will bring an extra dimension of information that allows to visualise existing correlations between a given set of conditions and the manoeuvres performed under them. This paper expands on how to obtain these databases starting from only from overtaken manoeuvres extracted from experimental data. Consisting in two main procedures, the manoeuvre classification itself, in which a hybrid-classifier that combines both supervised and unsupervised algorithms generates the scenario sub-cases, and the database compilation stage, in where it displays the different types of databases that can be created, based on the aim of the study.

Categorizing Data-Driven Methods for Test Scenario Generation to Assess Automated Driving Systems

“…Examples of supervised prediction tasks used include modified Random Forests [17], Logistic Regressions [28], and Recurrent Neural Networks (RNNs) [40]. Furthermore, combinations of several approaches exist, such as the combination of supervised and unsupervised learning, to identify scenarios [18], [21], [60].…”

“…To choose the ideal approach, one should consider the demands of the generation approach, which is facilitated by the overview and categorization presented in Tables A1 and A2, respectively. The corresponding methods [17], [21], [45], [51], [74] are worth considering for ADS designed for highways. If only drone data are accessible for scenario generation, the appropriate methods can also be filtered from Table A2.…”

PerfECT Design Tool: Electric Vehicle Modelling and Experimental Validation

“…J. 2023, 14, x. https://doi.org/10.3390/xxxxx www.mdpi.com/jo of active control systems [54][55][56][57][58], ADAS and autonomous driving [59,60] solu EVs. The novelty of the solution is its multi-step nature, modularity, and flexibili plementation which, in comparison with commercial tools, can offer a more tai perience to professionals working on different phases of the design process.…”

“…The main contribution of the article is the logic and method proposed for the streamlined design process of new electric vehicles, specifically regarding the first phases of the product development process, always keeping in mind that for each component or subsystem there are dedicated tools and methods that run in parallel. Apart from this, other uses are also envisioned; for example, the method can be used as a platform for the design of active control systems [54][55][56][57][58], ADAS and autonomous driving [59,60] solutions for EVs. The novelty of the solution is its multi-step nature, modularity, and flexibility of implementation which, in comparison with commercial tools, can offer a more tailored experience to professionals working on different phases of the design process.…”