The ability of deep learning has been tested to learn graphical features for building-plan generation. However, whether the deeper space allocation strategies can be obtained and thus reduce energy consumption has still not been investigated. In the present study, we aimed to train a neural network by employing a characterized sample set to generate a residential building floor plan (RBFP) for achieving energy reduction effects. The network is based on Pix2Pix, including two sub-models: functional segmentation layout (FSL) generation and building floor plan (BFP) generation. To better characterize the energy efficiency, 98 screened floor plans of Solar Decathlon (SD) entries were labeled as the sample set. The data augmentation method was adopted to improve the performance of the FSL sub-model after the preliminary testing. Three existing residential buildings were used as cases to observe whether the network-generated RBFP gained the effect of decreasing energy consumption with decent space allocation. The results showed that, under the same simulation settings and building exterior profile (BEP) conditions, the function arrangement of the generated scheme was more reasonable compared to the original scheme in each case. The annual total energy consumption was reduced by 13.38%, 12.74%, and 7.47%, respectively. In conclusion, trained by the sample set that characterizes energy efficiency, the RBFP generation network has a positive effect in both optimizing the space allocation and reducing energy consumption. The implemented data augmentation method can significantly improve the network’s training results with a small sample size.

Robotic tectonics have been integrated into the architectural profession through automated construction for more than a decade, advancing sustainability initiatives in the industry and increasing the quality of building construction. Over the years, avant-garde architects have explored the feasibility of this new design paradigm through the integration of newly-developed digital design software into automated construction. This robotic digital workflow continues to push designers to re-think the complete architecture process (from design conception to physical construction) and guides the building industry towards more precise, efficient, and sustainable development. However, in the current environment of architectural education, professional courses can be fragmented, thematic, and overly academic. Such content is not inherently compatible with the latest technological developments. The lack of understanding and application of digital technological can subsequently lead to the lack of sustainable development in architectural education. In this paper, we aim to introduce a new didactic pedagogical approach that is reliant on the principles of robotic tectonics and is defined through linear development in four distinct, developmental stages (based on information gleaned from four “Robotic Tectonics” workshops and various other rich teaching practices). This pedagogical framework provides interdisciplinary knowledge to architecture students and enables them to use advanced digital tools such as robots for automated construction, laying the groundwork for the discovery of new and complex building processes that will redefine architecture in the near future.