Abstract
Transitioning from a digital design to a robotic assembly process currently requires months of expert manual tuning to reconcile part geometries with robotic constraints. This paper presents an end-to-end, autonomous pipeline for the design and physical construction of bespoke wooden assemblies. A generative AI agent translates user prompts into initial 3D geometries, balancing the visual fidelity of the design with select physical constraints. The assemblability of the design is further improved by a gradient-based repair stage that backpropagates through a graph attention network surrogate to adjust component geometries. In addition to correcting for disjointed and overlapping components, we demonstrate hardware-specific corrections, differentiably optimizing the geometry of components to enable robot screwdriving for 86.7% of 60 novel natural language inputs, significantly outperforming prior work by a factor of ten. For ten of the structures, we physically demonstrate assemblability with two UR5e robots. This work marks a meaningful step toward on-demand robotic manufacturing, enabling the rapid production of customized, low-volume goods.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Schlafly, M., Schaub, F., Pais, D. C., Lelli, L., Dvorak, J., Colmont, C., Marti, S., & Fuge, M. D. (2026). On-Demand Robotic Assembly via Differentiable Geometric Part Repair. https://omanscience.com/en/articles/on-demand-robotic-assembly-via-differentiable-geometric-part-repair
MLA 9
Schlafly, Millicent, et al. "On-Demand Robotic Assembly via Differentiable Geometric Part Repair." https://omanscience.com/en/articles/on-demand-robotic-assembly-via-differentiable-geometric-part-repair.
Chicago (author–date)
Schlafly, Millicent, Fabio Schaub, Diogo Costa Pais, Luca Lelli, Janne Dvorak, Claire Colmont, Sven Marti, and Mark D. Fuge. 2026. "On-Demand Robotic Assembly via Differentiable Geometric Part Repair." https://omanscience.com/en/articles/on-demand-robotic-assembly-via-differentiable-geometric-part-repair.
Harvard
Schlafly, M., Schaub, F., Pais, D. C., Lelli, L., Dvorak, J., Colmont, C., Marti, S. and Fuge, M. D. (2026) 'On-Demand Robotic Assembly via Differentiable Geometric Part Repair', Available at: https://omanscience.com/en/articles/on-demand-robotic-assembly-via-differentiable-geometric-part-repair.
Vancouver
Schlafly M, Schaub F, Pais DC, Lelli L, Dvorak J, Colmont C, et al. On-Demand Robotic Assembly via Differentiable Geometric Part Repair. https://omanscience.com/en/articles/on-demand-robotic-assembly-via-differentiable-geometric-part-repair
IEEE
M. Schlafly, F. Schaub, D. C. Pais, L. Lelli, J. Dvorak, C. Colmont, S. Marti, and M. D. Fuge, "On-Demand Robotic Assembly via Differentiable Geometric Part Repair," https://omanscience.com/en/articles/on-demand-robotic-assembly-via-differentiable-geometric-part-repair.