The advent of artificial intelligence in the era of ubiquitous computation also influences the disciplines of architecture, engineering, construction, and operation (AECO) as a part of revolutionizing Industry 4.0. The newly developed intelligent methods of assembly, robotic production, and advanced digital fabrication techniques require serious attention from designers, even in the early design stages. The digital production process affects the product's design itself. However, strictly digital processes sometimes neglect human creative skills, craft abilities, authorship, and creativity. Therefore, “Co-intelligent Assemblies” investigates how we can employ human designers’ creativity, intelligence, and skills in design and production processes with the support of design computation and artificial intelligence into one coherent design workflow. By incorporating the Design for Manufacture and Assembly method, genetic algorithms, and rules-driven combinatorial spatial aggregation strategies in one digital workflow, designers can extend design space exploration with unforeseen outcomes based on unconventional design approaches. Combining bottom-up generative techniques provided by a machine with intuitive top-down design intents explored by a human designer yields a robust foundation upon which the architectural space can be created.
Can architectural space be defined, produced, and delivered through a kit-of-parts system? If the modular kit-of-part is a product, is architectural space utilizing modular parts a product, too? How do parts fit together, and how can they make a solid assembly, creating a spatial quality?

This project aspires to augment the standard numerical control (NC) production technology with additional co-creative human and machine intelligence in cooperation and interaction. It will explore how to engage the human agent with robots where the human can act as an expert and demonstrator to teach the robot a construction/building task to be executed and, consequently, how a robot can make production decisions independently.

The human and machine agents will encompass human-driven toolpath generation through intuitive gestures and demonstrations, while human logic, preferences, memory, cognition, and creative acts will be investigated and captured. These aspects will be tested to be transferable to a machine in a continuous training and learning process driven by a human agent (expert).

Consequently, the machine will constantly improve its capability based on human agents' inputs and become more autonomous in the decision-making and generation of design and production space. The project will develop a series of digital experiments utilizing computational frameworks and employing the digital twin of the collaborative robotic arm, a cable-driven robot for an assembly system, and a plug-and-play method of construction equipped with a set of sensors in a multisensorial setup. The assembly process will be tested in a 1:1 scenario.