Abstract: A method for tracking progression of a construction site at different points in time relative to an expected progression of the construction site as represented by a computer model. The method includes generating an image of the construction site by scanning the construction site with an imaging device and detecting a fiducial marker appearing in the image at a location on the construction site. The fiducial marker is unique among fiducial markers positioned on the construction site. The method further includes identifying the detected fiducial marker in association with a unique identifier among the fiducial markers and aligning a coordinate system of the identified fiducial marker with a coordinate system of the computer model, which represents the construction site at points in time.

Abstract: Methods, apparatuses, and embodiments related to a technique for monitoring construction of a structure. In an example, a robot with a sensor, such as a LIDAR device, enters a building and obtains sensor readings of the building. The sensor data is analyzed and components related to the building are identified. The components are mapped to corresponding components of an architect's three dimensional design of the building, and the installation of the components is checked for accuracy. When a discrepancy above a certain threshold is detected, an error is flagged and project managers are notified. Construction progress updates do not give credit for completed construction that includes an error, resulting in improved accuracy progress updates and corresponding improved accuracy for project schedule and cost estimates.

Abstract: The disclosed embodiments include a method for automating alignment of image data captured of a three-dimensional (3D) physical structure with a computer model of the 3D physical structure. The method can include obtaining two-dimensional (2D) images of the 3D physical structure undergoing construction, detecting fiducial markers corresponding to control points in the 2D images, and determining a transformation function based on the control points. The method can further include obtaining more 2D images, detecting other fiducial markers, and aligning image data to a computer model by utilizing the transformation function. The method can further include refining an alignment by utilizing a refinement transformation based on 3D physical elements of the 3D physical structure.