Subassembly to Full Assembly: Effective Assembly Sequence Planning through Graph-based Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914953848422400 |
|---|---|
| author | Shu, Chang Kim, Anton Park, Shinkyu |
| author_facet | Shu, Chang Kim, Anton Park, Shinkyu |
| contents | This paper proposes an assembly sequence planning framework, named Subassembly to Assembly (S2A). The framework is designed to enable a robotic manipulator to assemble multiple parts in a prespecified structure by leveraging object manipulation actions. The primary technical challenge lies in the exponentially increasing complexity of identifying a feasible assembly sequence as the number of parts grows. To address this, we introduce a graph-based reinforcement learning approach, where a graph attention network is trained using a delayed reward assignment strategy. In this strategy, rewards are assigned only when an assembly action contributes to the successful completion of the assembly task. We validate the framework's performance through physics-based simulations, comparing it against various baselines to emphasize the significance of the proposed reward assignment approach. Additionally, we demonstrate the feasibility of deploying our framework in a real-world robotic assembly scenario. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13620 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Subassembly to Full Assembly: Effective Assembly Sequence Planning through Graph-based Reinforcement Learning Shu, Chang Kim, Anton Park, Shinkyu Robotics This paper proposes an assembly sequence planning framework, named Subassembly to Assembly (S2A). The framework is designed to enable a robotic manipulator to assemble multiple parts in a prespecified structure by leveraging object manipulation actions. The primary technical challenge lies in the exponentially increasing complexity of identifying a feasible assembly sequence as the number of parts grows. To address this, we introduce a graph-based reinforcement learning approach, where a graph attention network is trained using a delayed reward assignment strategy. In this strategy, rewards are assigned only when an assembly action contributes to the successful completion of the assembly task. We validate the framework's performance through physics-based simulations, comparing it against various baselines to emphasize the significance of the proposed reward assignment approach. Additionally, we demonstrate the feasibility of deploying our framework in a real-world robotic assembly scenario. |
| title | Subassembly to Full Assembly: Effective Assembly Sequence Planning through Graph-based Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2409.13620 |