Andrea Settimi

Ordinary electric woodworking tools are integrated into a multiple-object-aware augmented framework to assist operators in fabrication tasks. This study presents an advanced evaluation of the developed open-source fabrication software Augmented Carpentry (AC), focusing on the technical challenges, potential bottlenecks, and precision of the proposed system, which is designed to recognize both objects and tools. In the workflow, computer vision tools and sensors implement inside-out tracking techniques for the retrofitting tools. This method enables operators to perform precise saw-cutting and drilling tasks using computer-generated feedback. In the design and manufacturing process pipeline, manual fabrication tasks are performed directly from the computer-aided design environment, as computer numerical control machines are widely used in the timber construction industry. Traditional non-digital methods employing execution drawings, markings, and jigs can now be replaced, and manual labor can be directly integrated into the digital value chain. First, this paper introduces the developed methodology and explains its devices and functional phases in detail. Second, the fabrication methodology is evaluated by experimentally scanning the produced one-to-one scale mock-up elements and comparing the discrepancies with their respective three-dimensional execution models. Finally, improvements and limitations in the tool-aware fabrication process, as well as the potential impact of AC in the digital timber fabrication landscape, are discussed.

TimberSLAM (TSLAM) is an object-centered, tag-based visual self-localization and mapping (SLAM) system for monocular RGB cameras. It was specifically developed to support a robust and augmented reality pipeline for close-range, noisy, and cluttered fabrication sequences that involve woodworking operations, such as cutting, drilling, sawing, and screwing with multiple tools and end-effectors. By leveraging and combining multiple open-source projects, we obtain a functional pipeline that can map, three-dimensionally reconstruct, and finally provide a robust camera pose stream during fabrication time to overlay an execution model with its digital-twin model, even under close-range views, dynamic environments, and heavy scene obstructions. To benchmark the proposed navigation system under real fabrication scenarios, we produce a data set of 1344 closeups of different woodworking operations with multiple tools, tool heads, and varying parameters (e.g., tag layout and density). The evaluation campaign indicates that TSLAM is satisfyingly capable of detecting the camera’s millimeter position and subangular rotation during the majority of fabrication sequences. The reconstruction algorithm’s accuracy is also gauged and yields results that demonstrate its capacity to acquire shapes of timber beams with up to two preexisting joints. We have made the entire source code, evaluation pipeline, and data set open to the public for reproducibility and the benefit of the community. Graphic

We present TimberTool (TTool v2.1.1), a software designed for woodworking tasks assisted by augmented reality (AR), emphasizing its essential function of the real-time localization of a tool head’s poses within camera frames. The localization process, a fundamental aspect of AR-assisted tool operations, enables informed integration with contextual tracking, facilitating the computation of meaningful feedback for guiding users during tasks on the target object. In the context of timber construction, where object pose tracking has been predominantly explored in additive processes, TTool addresses a noticeable gap by focusing on subtractive tasks with manual tools. The proposed methodology utilizes a machine learning (ML) classifier to detect tool heads, offering users the capability to input a global pose and utilizing an automatic pose refiner for final pose detection and model alignment. Notably, TTool boasts adaptability through a customizable platform tailored to specific tool sets, and its open accessibility encourages widespread utilization. To assess the effectiveness of TTool in AR-assisted woodworking, we conducted a preliminary experimental campaign using a set of tools commonly employed in timber carpentry. The findings suggest that TTool can effectively contribute to AR-assisted woodworking tasks by detecting the six-degrees-of-freedom (6DoF) pose of tool heads to a satisfactory level, with a millimetric positional error of 3.9 ± 1 mm with possible large room for improvement and 1.19 ± 0.6° for what concerns the angular accuracy.

Augmented reality in additive fabrication is predominantly applied to the manufacturing of structures from regularly shaped materials. Our work however embraces natural heterogeneity, by focusing on the assembly of irregularly shaped elements such as mineral scraps. We introduce a computer-aided framework with a 3D stacking engine and an augmented reality interface capable of guiding users through the balanced positioning of discrete and highly nonuniform objects according to an on-the-fly computed model and without prior trimming of the building unit. The pipeline is tested by the construction of two dry-stone structures (i.e., lacking any adhesives), and its accuracy is validated with a comparative study between the point cloud of the as-built digitized artifacts and the generated execution model, which shows an average 2.9 ± 1.8 cm error between the stones of the two models. We finally show how the proposed framework could be improved both in terms of software and hardware. In the interests of reproducibility, all the methods are shared as open source with the community. Graphical