Authors:
Matthias Graichen
1
and
Lisa Graichen
2
Affiliations:
1
Independet Researcher, Munich, Germany
;
2
Institute of Psychology and Ergonomics, Human Machine Systems, Technical University Berlin, Berlin, Germany
Keyword(s):
Driving Behavior, Driving Data, Map Data, GPS Data, Driving Maneuvers, Data Analysis, Data Processing, Prediction Algorithms.
Abstract:
Analyzing and modeling behavioral data from driving studies can be challenging and often entails numerous steps of data handling, preparation, and aggregation before the final data modeling and extraction of results can be performed. In research papers, these steps are often described only briefly due to the natural limitation of words and intended focus on the related research questions. However, for smaller research groups or individual researchers without IT experts, the engineering of appropriate data processing pipelines for this type of research can be challenging. To address this issue, this work presents a step-by-step guide on how we tackled one of these challenges in our recent research activities. Our work focused on the implementation of a published algorithm for the prediction of turning maneuvers at intersections, which partly relies on map data for computing path curvature. We describe how we used freely available technologies and which steps were applied for building
a data processing pipeline to enrich the recorded driving data with map data obtained via the OpenStreetMap platform and API.
(More)