The objective of autonomous robotic additive manufacturing for construction in the architectural scale is currently being investigated in parts both within the research communities of computational design and robotic fabrication (CDRF) and deep reinforcement learning (DRL) in robotics. The presented study summarizes the relevant state of the art in both research areas and lays out how their respective accomplishments can be combined to achieve higher degrees of autonomy in robotic construction within the Architecture, Engineering and Construction (AEC) industry. A distributed control and communication infrastructure for agent training and task execution is presented, that leverages the potentials of combining tools, standards and algorithms of both fields. It is geared towards industrial CDRF applications. Using this framework, a robotic agent is trained to autonomously plan and build structures using two model-free DRL algorithms (TD3, SAC) in two case studies: robotic block stacking and sensor-adaptive 3D printing. The first case study serves to demonstrate the general applicability of computational design environments for DRL training and the comparative learning success of the utilized algorithms. Case study two highlights the benefit of our setup in terms of tool path planning, geometric state reconstruction, the incorporation of fabrication constraints and action evaluation as part of the training and execution process through parametric modeling routines. The study benefits from highly efficient geometry compression based on convolutional autoencoders (CAE) and signed distance fields (SDF), real-time physics simulation in CAD, industry-grade hardware control and distinct action complementation through geometric scripting. Most of the developed code is provided open source.

State-of-the-art rapid additive manufacturing (RAM)-specifically fused filament fabrication (FFF)-has gained popularity among architects, engineers and designers for the quick prototyping of technical devices, the rapid production of small series and even the construction scale fabrication of architectural elements. The spectrum of producible shapes and the resolution of detail, however, are determined and constrained by the layer-based nature of the fabrication process. These aspects significantly limit FFF-based approaches for the prefabrication and in situ fabrication of free-form shells at the architectural scale. Snails exhibit a shell building process that suggests ways to overcome these limits. They produce a soft, pliable proteinaceous film-the periostracum-which later hardens and serves, among other functions, as a form-giving surface for an inner calcium carbonate layer. Snail shell formation behavior is interpreted from a technical point of view to extract potentially useful aspects for a biomimetic transfer. A RAM concept for the continuous extrusion of thin free-form composite shells inspired by the snail shell formation is presented.

No abstract

No abstract