@misc{14042,
  abstract     = {{This paper investigates co-creativity in architectural robotics through
a design-research experiment that repositions the robot from a fabrication tool
to an active collaborator in spatial exploration. A turn-based assembly process
enables a human designer and a robotic arm to alternately place modular bricks
within a shared three-dimensional environment. Each move is evaluated through
computational rules—support, stability, and collision—and interpreted in real
time via an AI image-to-image diffusion model. This sequential exchange
establishes a reciprocal design dialogue: the human reads the robot’s action as
a spatial proposition, while the robot responds to the evolving structure.
Creative agency becomes distributed across human and machine, encouraging
reflection on intent and positioning robotic intelligence as a source of suggestion
rather than execution. By prioritizing responsiveness and interpretation over
efficiency, the research challenges conventional file-to-factory paradigms and
frames robotics as an active participant in design thinking. It contributes to
discussions on human–machine collaboration by proposing co-creative robotics
as a framework for rethinking authorship in architecture.
Keywords. Human–robot Collaboration, Co-Creation, Computational
Creativity, Robotic Fabrication, Artificial Intelligence, Digital Fabrication,
Generative Models, Discrete Assembly, Human–Machine Interaction.}},
  author       = {{Sardenberg, Victor and Aykin, Yusuf and Sachs, Hans and Schneider, Bo}},
  booktitle    = {{eCAADe 2026 - Informed creativity in architecture and engineering }},
  editor       = {{eCAADe, eCaade}},
  isbn         = {{9789491207426}},
  issn         = {{2684-1843}},
  keywords     = {{Co Creative Robots, Collaborative Robots, Design, Architecture}},
  location     = {{Lübeck}},
  pages        = {{357--366}},
  publisher    = {{CumInCAD}},
  title        = {{{Co-Creative Robotics : Turn-Based Human–Robot Assembly for Architectural Design Exploration}}},
  doi          = {{https://doi.org/10.52842/conf.ecaade.2026.2.357}},
  volume       = {{44}},
  year         = {{2026}},
}

@misc{14070,
  abstract     = {{Deploying digital twins across the broader building stock is constrained by a key bottleneck: high-quality 3D content from LiDAR or photogrammetry remains labor-intensive and difficult to scale. We introduce Generative Twins (GT), a workflow that shifts digital twin creation from explicit geometric reconstruction toward probabilistic 3D synthesis. The pipeline takes a
single street-level façade photograph, corrects perspective distortion and removes occlusions, uses an instruction-conditioned multimodal image model to synthesise an isometric view of the building, and passes that view to an image-to-3D reconstruction model that leverages learned shape priors to produce a textured mesh without manual modelling. Three image to-3D platforms (Hitem3D, Hyper3D and Hunyuan3D 3.1) are compared on identical isometric inputs and assessed on architectural boundary clarity. We demonstrate GT through two applied cases: (i) reconstruction of ordinary residential streets in Detmold as stimuli for a virtual-reality study of multi sensory urban perception, and (ii) Green Editor, a design-exploration tool in which façade greenery is added or removed at the image layer before mesh generation.
Together these cases position Generative Twins as a scalable pathway for the digitization of ordinary building stock, with emphasis on controllability, editability, and iterative design workflows.}},
  author       = {{Ashmawy, Mohamed Khaled and Akay, Buse and Balderrama, Alvaro}},
  booktitle    = {{eCAADe proceedings}},
  issn         = {{2684-1843}},
  keywords     = {{Digital Twins, Virtual Reality (VR, Artificial Intelligence (AI), Image-to-3D, Generative Design.}},
  location     = {{Lübeck}},
  publisher    = {{eCAADe}},
  title        = {{{Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis}}},
  doi          = {{10.52842/conf.ecaade.2026.1.619}},
  volume       = {{1}},
  year         = {{2026}},
}