Deriving Fabrication Information from BIM for Automated Robotic Task Planning

Construction robotics enables the integration of multiple technologies (e.g., Building Information Modelling, Artificial Intelligence and Additive Manufacturing), thus presenting an opportunity for further productivity gains for the construction industry. However, a key obstacle lies in generating fine-grained information required for robots to plan autonomous tasks. To achieve reliable robot-based construction automation, information about the product design to be built and the status of construction progress must be available to the robot systems in real time. Building Information Modeling (BIM) holds promise in converting high-level building information into the requisite level of detail for robotic operations. One approach is to enrich the data from Industry Foundation Classes (IFC) models with construction data and convert it into a robotic format for robot task planning. We propose leveraging and extending the data extracted from BIM models to integrate with Robotic Operating Systems (ROS), a prevalent framework for robot control. The framework is evaluated through robotised bricklaying realised by MoveIt, and visualised using Rviz.