Agent based Parametric Semiology

Architecture and urbanism order social processes via their semantic associations as much as via physical separation and connection. The built environment functions through its visual appearance, via its legibility and its related capacity to frame and prime communication. The built environment is not just channelling bodies. It is orienting sentient, socialized beings who must actively comprehend and navigate ever more complex urban scenes. As a communicative frame, a designed space is itself a communication as premise for all communications that take place within its territory. In a conventional design process, every designer adapts to and intervenes intuitively within the spontaneous and historically evolving semiological system of the built environment. The aim of agent based parametric semiology is it to move from an intuitive participation within an evolving semiosis to an explicit design agenda that understands the design of a large scale architectural complex as an opportunity to design a new, coherent system of signification, a new artificial architectural language, without relying on the familiar codes found in the existing built environments. To operationalize the semantic layer of the designed environment within the design process the research proposes to develop agent based life process simulations. The semiological code is defined in terms of the agents behavioural rules or scripts being triggered by designed environmental features. This is the most original innovation within the proposed research project. The aim of the research project is to develop new computational simulation capacities and thus a new approach to architectural design that better engages with the opportunities and challenges of today`s networked society and which might lead to a new compelling type of architectural service that can meet the aspirations of contemporary clients. Collaborating with leading experts in the field of crowd simulation, as well as in structural and environmental optimization, the research involves the development of a new approach, setting a new task, developing new tools. The research culminates in exemplary creative design works that demonstrate the capacity and potential impact of the new approach on contemporary architectural and urban design. This research project is thus at the same time an artistic project, a form of research by design. The research project will be headed by Patrik Schumacher, a leading figure in the fields of parametric design and architectural design research. Schumacher will be leading a team of distinguished researchers, who each can look back on a proven track record of academic research and experimental digital design practice, focusing on advanced scripting techniques, digital formal experimentation and the understanding of our built environment as an interface for interaction with its users.

Agent-based Parametric Semiology aims to analyse, simulate, and predict contemporary spatial occupation patterns in social spaces to understand and develop the performance criteria that interactively link these spaces and interiors with their users. The research ambition is to develop a cross-disciplinary method of architectural design that generates spatial environments with high social performativity by developing novel computational simulations to link human behaviour to a specific semiological context, exemplified in the context of contemporary working environments. To operationalize this semantic layer within the design process, the research proposes to develop agent-based life process simulations, borrowing from agent-based modelling, crowd simulations and spatial statistics. The semiological code is defined in terms of the agents' behavioural rules being triggered by designed environmental features. The complex problem of simulating human behaviour was solved by developing a novel behaviour model which reduces the complexity of social interaction mechanics to two context specific parameters. The ability to draw observations of the implication spatial features and organisations and emergent group behaviour have on each other is a key benefit of the systematic development of the algorithm. The algorithm allows - through generation of interaction patterns, occupancy heat maps, path tracing and influence maps - to measure different performance criteria of occupancy and group interaction for a variety of spatial layouts. When systematically running our algorithms on various office scenarios, results clearly indicated that different object formations within one and the same space do indeed influence the number of social interactions, and - as a consequence - render a space more or less performative. The results also indicated that the simulation tools we developed were able to pick up these differences in social performance and were useful as analytical tools. Shifting from the empirical approach of data analysis to the predictive approach of data analysis prediction models have been developed. Here, information from similar simulation scenarios can be used to train a statistics-based prediction algorithm to forecast the spatial occupation pattern for novel scenario. This results in a shift from an observing/describing point of view to a qualitative and predictive one, ultimately improving the understanding of how space influences behaviour and how behaviour can influence space. Using these results, it is possible to draw new insights for architectural and interior design that showed significant differences in overall informal communication potential. The results also imply further research potential. At this point, the overall realism of these simulations is hard to assess. However, the simulation's comparative finding that a specific layout shows relative advantages in performance, is telling even if absolute performance values might be inexact. The purpose of the simulations is to use facilitate the selection of the best option, ceteris paribus, not the prediction of performance values.