Enrichment of OpenStreetMap Data Completeness with Sidewalk Geometries for Wheelchair Routing

Tailored routing and navigation services utilized by wheelchair users (such as provided by OpenRouteService.org ) require certain information about sidewalk geometries and their attributes to execute efficiently. Except some minor regions/cities, such detailed information is often not sufficiently present in current versions of crowdsourced mapping databases including OpenStreetMap. In a recent study (1) we aim to use (and enrich) OpenStreetMap for making it fit to the purpose of wheelchair routing. In this respect, this study presents a modified methodology based on data mining techniques for constructing sidewalk geometries using multiple GPS traces collected by wheelchair users during an urban travel experiment. The algorithm is composed of four main steps (followed by an enrichment step): pre-processing and cleaning; data clustering and significant point filtering; map matching and candidate point selection; and sidewalk network construction. The derived sidewalk geometries can be used to enrich OpenStreetMap to support wheelchair routing. The proposed method was applied to a case study in Heidelberg, Germany. The constructed sidewalk geometries were compared to an official reference dataset (“ground truth dataset”). The case study shows that the constructed sidewalk network overlays with 96% of the official reference dataset. Furthermore, in terms of positional accuracy, a low Root Mean Square Error (RMSE) value (0.93 m) is achieved. The article presents our discussion on the results as well as the conclusion and future research directions. Note that the length of the path is only one important factor for efficient wheelchair navigation. Further considerations are: (1) presence of a curb cut (roadway access point); (2) presence or enrichment of crosswalks; (3) the running slope and (more critically) the cross slope of the walkway; and (4) walkway surface materials. Hence, future research study needs to be done for developing methods to collect and enrich attributes of sidewalks such as sidewalk width, incline, surface texture, etc. Moreover, the assumption that GPS traces represent the sidewalk travelled is not always true. Also deviations from a sidewalk are very common in an urban setting, and are caused by wheelchair users needing to travel in the roadway around obstacles. These deviations (and their causes) are important to explore in future work.

Reference / further reading:

Mobasheri A., Huang H., Degrossi L.C. and A. Zipf (2018): Enrichment of OpenStreetMap Data Completeness with Sidewalk Geometries Using Data Mining Techniques. Sensors 2018, 18(2), 509; doi:10.3390/s18020509

Selected earlier work