Architectural intelligence最新文献

Architected porosity in masonry structures can be created by transforming stock materials into a lattice of interlocking units through an automated batch process. Porous masonry forms numerous enclosed cavities for thermal performance and reduces material usage while maintaining structural integrity. This work investigates the potential and limits of digital tectonics of porous masonry through a complete process of design, manufacturing, and construction. The confluence of digital fabrication with tectonic exploration opens new dimensions unattainable by traditional stereotomy. Interlocking materials inspired by Abeille vault and digital stereotomy have made rapid progress. Following the theory of poetic construction, this work proposes that masonry construction should evoke visual or haptic enhancement through the fulfillment of pragmatic functions. We formulated a design challenge for a confined dry masonry wall for the envelope of the 2226 building. It assumes batch-cutting bespoke units out of large blocks of high-strength foam. Through a process of cutting and reassembling, the stock material is topologically expanded into a porous structure. A series of prototypes were developed to explore novel articulation, structural and thermal performance, and economical manufacturing. One can perceive the logic of porous construction through visual and haptic empathy. The materialization process interacts with the design masonry units and the interlocking mechanism. For future practice in masonry, the porosity should be planned at multiple scales (molecular scale, aggerate scale, construction scale) across the life cycle of the material.

Chain mail structures, known for flexibility and adaptability, hold increasing promise for architectural applications, including transportable and reconfigurable systems. However, there is a dearth of knowledge on both systematic methods to design them, and complex behaviours of interlocking modules that comprise the structure. Preliminary studies, in response to this research gap, demonstrate the chain mail’s structural potential as programmable architecture. Nevertheless, to validate our models, we must move from the small scale to recognisably viable structures at an architectural scale.

Acknowledging the multiscale prototype’s significance for developing new architectural systems, this study scales up chain mail structures from a small 1:10 scale to larger 1:2 and 1:1 scales. Employing a Research-Through-Design approach, we systematically addressed the challenges, focusing on module fabrication and prototype construction through analogue computation. Fabrication adjustments involve changing materials and modifying designs to suit manufacturing techniques. Additional design elements and process steps are needed to facilitate programming the larger scale structures due to the increased weight during construction. The research culminated in a full-scale saddle-like structure, illustrating the feasibility of direct scaling from smaller to larger scales and the expansive architectural potential of chain mail structures.

In conclusion, the study successfully identified and responded to specific challenges related to the fabrication and construction of upscaled chain mail prototypes, aligning solutions with practical contexts. In doing so, this research contributes a set of considerations to enable more systematic design approaches for chain mail structural systems in architecture. At the same time, scaling up uncovers the inherent intelligence of these structures, providing a foundation for both empirical testing through analogue experimentation, and developing a predictive framework for their development and application in the field.

Self-shaping systems offer a promising approach for making complex 3D geometries from the material-driven transformation of 2D sheets. However, current research development of such systems is focused on small-scale applications. This study proposes a self-shaping composite for generation of larger-scale curved surfaces suitable for spatial structures. The composite arises from the novel combination of a perforated plate passive layer and a heat-shrinkable active layer. Experimental investigations are undertaken to assess the influence of perforation parameters of the passive layer over the degree of curvature generated in the self-shaping composite system. A 3D scanner and parametric curvature evaluation tool were used to extract and analyse the fabricated surface curvatures. Three key deformation characteristics were identified: the generated surface is cylindrical with dominant curvature in the x-direction; curvature is approximately uniform across the surface width and length; and curvature is strongly influenced by perforation bridge and strap length parameters. Results of this study support the application of self-shaping curved surfaces for customizable discrete structure parts.

When a robot is printing a sequence of non-horizontal goal poses, its joint values often undergo significant variations, resulting in challenges such as singularities or exceeding joint limits. This paper proposes two new methods aimed at optimizing goal poses to solve the problem. The first method, employing an analytical approach, modifies the goal poses to maintain the 4th joint value of a 6-axis industrial robot at zero. This adjustment effectively reduces the motion range of the 5th and 6th axes. The second method utilizes numerical optimization to adjust the goal poses, aiming to minimize the motion range of all joints. Leveraging the analytical method to obtain one good initial value, numerical optimization is subsequently applied to complete the entire path optimization, creating an optimization workflow. It is also possible to use only analytical methods for computational efficiency. The feasibility and effectiveness of these two methods are validated through simulation and real project case.

This paper presents a case study on the use of 3D concrete printing (3DCP) to qualify rocky pontoons with spaces for recreational use—namely sitting areas, circulation trails and fishing spots—and biodiversity protection—providing habitat and refuge for native marine species—with a focus on the challenges and opportunities associated with 3DCP prefabrication for such a complex topographical context. We first discuss the benefits and disadvantages of 3DCP over traditional methods for retrofitting strategies with the support of state-of-the-art literature review. We then present a methodology and an experimental case study, organized in three stages: (1) a photogrammetric survey and digital reconstruction of the site´s rocky landscape, (2) the creation of a tool to generate and optimize custom-fit slabs based on their location on site, intended use and role in the protection of the natural ecosystem, and (3) the robotic fabrication of these slabs through 3DCP. Finally, we present our key findings, revealing that 3DCP offers a viable and more efficient alternative for appropriating and revitalizing sites with a disorderly and highly complex topography.

The Vibrant Fields project endeavors to construct novel representational tectonics of urbanization, aiming to comprehend the materiality of forms and the genesis of multispectral relations within complex information systems governing the interplay of atmospheric and embodied energy cycles in the biosphere. This project asserts that any perceivable condition of nature arises from dynamic processes that transcend human sensory perception.

Inspired by theoretical biology, the project models the urban environment as a systemic entity characterized by modularity, representing the biosphere's dynamic interplay of chemical and physical elements engaged in information exchange within ecological systems, influenced by technology, geography, and atmospheric conditions.

Vibrant Fields utilizes layers of observation systems to translate the complex biosphere into dimensionally reduced data streams. It introduces complementary devices, bridging the gap between global and local data to better understand microclimatic phenomena.

The project observes the simultaneous realities and temporalities of urban field information within its ecological context. It investigates the architecture, technology, flora, and fauna of cities in relation to their geographic, geological, and ecological conditions, analyzing multiple temporal historical and geological scales.

The recent advancements in digital technologies and artificial intelligence in the architecture, engineering, construction, and operation sector (AECO) have induced high demands on the digital skills of human experts, builders, and workers. At the same time, to satisfy the standards of the production-efficient AECO sector by reducing costs, energy, health risk, material resources, and labor demand through efficient production and construction methods such as design for manufacture and assembly (DfMA), it is necessary to resolve efficiency-related problems in mutual human‒machine collaborations. In this article, a method utilizing artificial intelligence (AI), namely, generative adversarial imitation learning (GAIL), is presented then evaluated in two independent experiments related to the processes of DfMA as an efficient human‒machine collaboration. These experiments include a) training the digital twin of a robot to execute a robotic toolpath according to human gestures and b) the generation of a spatial configuration driven by a human's design intent provided in a demonstration. The framework encompasses human intelligence and creativity, which the AI agent in the learning process observes, understands, learns, and imitates. For both experimental cases, the human demonstration, the agent's training, the toolpath execution, and the assembly configuration process are conducted digitally. Following the scenario generated by an AI agent in a digital space, physical assembly is undertaken by human builders as the next step. The implemented workflow successfully delivers the learned toolpath and scalable spatial assemblies, articulating human intelligence, intuition, and creativity in the cocreative design.

This research presents an innovative approach that integrated gesture recognition into a Mixed Reality (MR) interface for human–machine collaboration in the quality control, fabrication, and assembly of the Unlog Tower. MR platforms enable users to interact with three-dimensional holographic instructions during the assembly and fabrication of highly custom and parametric architectural constructions without the necessity of two-dimensional drawings. Previous MR fabrication projects have primarily relied on digital menus and custom buttons within the interface for user interaction between virtual and physical environments. Despite this approach being widely adopted, it is limited in its ability to allow for direct human interaction with physical objects to modify fabrication instructions within the virtual environment. The research integrates user interactions with physical objects through real-time gesture recognition as input to modify, update, or generate new digital information. This integration facilitates reciprocal stimuli between the physical and virtual environments, wherein the digital environment is generative of the user’s tactile interaction with physical objects. Thereby providing user with direct, seamless feedback during the fabrication process. Through this method, the research has developed and presents three distinct Gesture-Based Mixed Reality (GBMR) workflows: object localization, object identification, and object calibration. These workflows utilize gesture recognition to enhance the interaction between virtual and physical environments, allowing for precise localization of objects, intuitive identification processes, and accurate calibrations. The results of these methods are demonstrated through a comprehensive case study: the construction of the Unlog Tower, a 36’ tall robotically fabricated timber structure.