Road graph generator: Mapping roads at construction sites from GPS data

We propose a new method for inferring roads from GPS trajectories to map construction sites. This task presents a unique challenge due to the erratic and non-standard movement patterns of construction machinery, which significantly diverge from typical vehicular traffic on established roads. Our proposed method first identifies intersections in the road network that serve as critical decision points, and then connects them with edges to produce a graph, which can subsequently be used for planning and task allocation. The method includes several physically meaningful parameters that can be tuned to adapt it to different scenarios. We demonstrate the approach by mapping roads at a real-life construction site in Norway. The method is validated on four increasingly complex segments of the map. In our tests, the method achieved perfect precision and recall in detecting intersections and inferring roads in data with no or low noise, while its performance was reduced in areas with significant noise and consistently missing GPS updates. • Novel road inference method: Introduces a new approach to extracting roads and intersections from GPS data, specifically designed to handle the erratic movement of construction machinery. • Graph-based representation: Constructs a road network graph, where nodes represent intersections and critical decision points, and edges define the connecting roads. • Adaptive and tunable: Incorporates physically meaningful parameters, enabling customization for different scenarios and improving adaptability across various environments. • Real-world validation: The method is evaluated on data from a real construction site, demonstrating its effectiveness across diverse terrains.