Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.17774 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908977174937600 |
|---|---|
| author | Mozaffari, Salma Ruan, Daniel Bogert, William van den Fazeli, Nima Adriaenssens, Sigrid Adel, Arash |
| author_facet | Mozaffari, Salma Ruan, Daniel Bogert, William van den Fazeli, Nima Adriaenssens, Sigrid Adel, Arash |
| contents | Fabrication uncertainty arising from tolerance accumulation, material imperfection, and positioning errors remains a critical barrier to automated robotic assembly in construction, particularly for contact-rich manipulation tasks governed by friction and geometric constraints. This paper investigates the deployment of diffusion policy learning on construction-scale industrial robots to enable robust, high-precision assembly under such uncertainty, using tight-fitting mortise and tenon timber joinery as a representative case study. Sensory-motor diffusion policies are trained using teleoperated demonstrations collected from an industrial robotic workcell equipped with force/torque sensing. A two-phase experimental study evaluates baseline performance and robustness under randomized positional perturbations up to 10 mm, far exceeding the sub-millimeter joint clearance. The best-performing policy achieved 100% success under nominal conditions and 75% average success under uncertainty. These results provide initial evidence that diffusion policies compensate for misalignments through contact-aware control, representing a step toward robust robotic assembly in construction under tight tolerances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17774 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contact-Rich Robotic Assembly in Construction via Diffusion Policy Learning Mozaffari, Salma Ruan, Daniel Bogert, William van den Fazeli, Nima Adriaenssens, Sigrid Adel, Arash Robotics Fabrication uncertainty arising from tolerance accumulation, material imperfection, and positioning errors remains a critical barrier to automated robotic assembly in construction, particularly for contact-rich manipulation tasks governed by friction and geometric constraints. This paper investigates the deployment of diffusion policy learning on construction-scale industrial robots to enable robust, high-precision assembly under such uncertainty, using tight-fitting mortise and tenon timber joinery as a representative case study. Sensory-motor diffusion policies are trained using teleoperated demonstrations collected from an industrial robotic workcell equipped with force/torque sensing. A two-phase experimental study evaluates baseline performance and robustness under randomized positional perturbations up to 10 mm, far exceeding the sub-millimeter joint clearance. The best-performing policy achieved 100% success under nominal conditions and 75% average success under uncertainty. These results provide initial evidence that diffusion policies compensate for misalignments through contact-aware control, representing a step toward robust robotic assembly in construction under tight tolerances. |
| title | Contact-Rich Robotic Assembly in Construction via Diffusion Policy Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.17774 |