Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
Working with irregular, reclaimed, and non-standard materials is essential to reducing the environmental impact of construction. Yet most robotic design-to-fabrication workflows rely on uniform components and predefined plans. This disconnect reflects a missed opportunity: material uncertainty, rather than being treated as a constraint, can become a catalyst for creativity when made actionable through well-designed human–robot interfaces. Building on the Truss from Trash framework, this paper presents an extended human–robot system for the adaptive assembly of timber trusses from offcuts. A projection-based interface embeds interaction within the fabrication environment, allowing users to select materials and adjust the design using tangible tokens, while real-time overlays provide member assignment guidance and cut previews. An on-demand form-finding component supports decision-making by validating equilibrium for user edits and proposing feasible design adaptations based on available stock. Validated changes propagate to the robot, which executes pick-cut-place cycles to incrementally assemble the structure. Through fabrication experiments, we show how our system enables users to reconcile material availability, design intent, and structural feasibility alongside fabrication.