Learning to Build: Autonomous Robotic Assembly of Stable Structures Without Predefined Plans
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911473741070336 |
|---|---|
| author | Wang, Jingwen Kirschner, Johannes Rolland, Paul Salamanca, Luis Parascho, Stefana |
| author_facet | Wang, Jingwen Kirschner, Johannes Rolland, Paul Salamanca, Luis Parascho, Stefana |
| contents | This paper presents a novel autonomous robotic assembly framework for constructing stable structures without relying on predefined architectural blueprints. Instead of following fixed plans, construction tasks are defined through targets and obstacles, allowing the system to adapt more flexibly to environmental uncertainty and variations during the building process. A reinforcement learning (RL) policy, trained using deep Q-learning with successor features, serves as the decision-making component. As a proof of concept, we evaluate the approach on a benchmark of 15 2D robotic assembly tasks of discrete block construction. Experiments using a real-world closed-loop robotic setup demonstrate the feasibility of the method and its ability to handle construction noise. The results suggest that our framework offers a promising direction for more adaptable and robust robotic construction in real-world environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23934 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Build: Autonomous Robotic Assembly of Stable Structures Without Predefined Plans Wang, Jingwen Kirschner, Johannes Rolland, Paul Salamanca, Luis Parascho, Stefana Robotics Machine Learning This paper presents a novel autonomous robotic assembly framework for constructing stable structures without relying on predefined architectural blueprints. Instead of following fixed plans, construction tasks are defined through targets and obstacles, allowing the system to adapt more flexibly to environmental uncertainty and variations during the building process. A reinforcement learning (RL) policy, trained using deep Q-learning with successor features, serves as the decision-making component. As a proof of concept, we evaluate the approach on a benchmark of 15 2D robotic assembly tasks of discrete block construction. Experiments using a real-world closed-loop robotic setup demonstrate the feasibility of the method and its ability to handle construction noise. The results suggest that our framework offers a promising direction for more adaptable and robust robotic construction in real-world environments. |
| title | Learning to Build: Autonomous Robotic Assembly of Stable Structures Without Predefined Plans |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2602.23934 |