BIM-based Localization and Mapping for Mobile Robots in Construction

Abstract

Building information modeling (BIM) has been increasingly adopted by construction project managers, as it covers the entire building life cycle and allows better coordination among different specialities. Mobile robots, on the other hand, are becoming the next frontier on automation of construction processes, and can largely exploit the geometric and semantic information provided by BIM models for many of their tasks. This work, in the context of the COBOLLEAGUE European project, presents a BIM-based interface that processes 3D building information, appending structural data to the pose-graph of a simultaneous localization and mapping (SLAM) system used by a mobile robot. This enables the robot to access a 3D map of the reference model and to determine its own pose in the construction environment, saving time and being able to perform autonomous navigation without previously exploring the map. Also, the methodology presented enables tracking the construction state and flagging updates to the reference model as well, a relevant feature for the construction industry. Results from simulations with publicly available models and real tests at an industrial site indicate a coherent mapping and consistent robot localization over time.