Prof. Benjamin LECOUTEUX,
benjamin.lecouteux@univ-grenoble-alpes.fr
Prof. Philippe MARIN,
philippe.marin@grenoble.archi.fr
The construction and architectural sectors are struggling to embrace digital transformation, and regulatory bodies have identified the need to support the sector’s transformation by fostering the development of new knowledge and technical skills. The sector accounts for 30% of Europe’s environmental footprint, making it one of the main contributors. It is essential to give greater consideration to environmental issues right from the initial design phases.
AI plays a key role in these issues. In this context, the project has two objectives:
To contribute to the “capabilities” of designers and address the training challenges facing architecture schools and professionals;
To contribute to the design of a more environmentally friendly built environment by leveraging the qualities of AI systems.
Three main scientific challenges have been identified:
In terms of architectural sciences: Reframing computational co-creativity, considering the effects and role of language in the design process, and integrating environmental performance from the very beginning of the design phases.
In terms of computer sciences: Adapting language models (LLMs) to architecture-specific tasks by combining them with domain-specific data and appropriately evaluating their performance and ethical implications.
In terms of engineering sciences: Optimizing solar production and solar system designs is a complex task involving a multi-criteria optimization problem that considers heterogeneous parameters such as PV production, usage, structure, comfort, energy, solar potential, and local climate. AI facilitates these activities and speeds up simulation processes.
The chair is organized around three packs:
The research pack is structured around two axes:
Computational Co-Creativity (CCC): AI and creativity: How LLMs can support humans in design (impacts and modalities of language interactions for representation production).
Data-Driven Design (DDD): AI simulation and optimization: How to predict shape based on performance requirements and integrate environmental parameters into generative design processes.
The training pack has three components:
The innovation pack covers four main activities:
License:
