GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation
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_ | 1866916064117391360 |
|---|---|
| author | Shao, Beichen Xie, Mengying Su, Heng Zhang, Wanyi Li, Mingyan Ding, Yan Giunchiglia, Fausto Chen, Chao |
| author_facet | Shao, Beichen Xie, Mengying Su, Heng Zhang, Wanyi Li, Mingyan Ding, Yan Giunchiglia, Fausto Chen, Chao |
| contents | Articulated object manipulation is a unique challenge for service robots. Existing methods employ end-to-end policy learning, visionmotion planning, and large-language/visual-language model (LLM/VLM), but often overlook the diversity of articulated objects and the complexity of interactions between end-effector and handle, leading to limited generalization and destructive collisions. To address this, we propose GSAM, a generalizable and safe robotic framework for articulated object manipulation. Specifically, a vision-based perceiver generates the kinematic parameters. Considering that pre-trained markers in perceiver yield raw estimations that may deviate from commonsense, we present a f ine-tuned VLM-based refiner, using chain-of-thought (COT) commonsense reasoning to refine perception. To prevent destructive collisions, we design an interaction constraint function generator, integrating articulated object, interaction pose, and obstacle avoidance knowledge into a base. LLM then functionalize these constraints and apply them to trajectory and posture planning. A kinematic-aware manipulation planner verifies reachability for trajectory and posture. Experiments on 50 hinge tasks across 5 object categories and 50 randomly initialized end-effectorhandle configurations show that GSAM reduces standard deviation by 3.1% and improves manipulation success rate by 36.0% compared to the best baseline, respectively demonstrating the superior object generalization and interaction safety of GSAM in practical scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30740 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation Shao, Beichen Xie, Mengying Su, Heng Zhang, Wanyi Li, Mingyan Ding, Yan Giunchiglia, Fausto Chen, Chao Robotics Artificial Intelligence Articulated object manipulation is a unique challenge for service robots. Existing methods employ end-to-end policy learning, visionmotion planning, and large-language/visual-language model (LLM/VLM), but often overlook the diversity of articulated objects and the complexity of interactions between end-effector and handle, leading to limited generalization and destructive collisions. To address this, we propose GSAM, a generalizable and safe robotic framework for articulated object manipulation. Specifically, a vision-based perceiver generates the kinematic parameters. Considering that pre-trained markers in perceiver yield raw estimations that may deviate from commonsense, we present a f ine-tuned VLM-based refiner, using chain-of-thought (COT) commonsense reasoning to refine perception. To prevent destructive collisions, we design an interaction constraint function generator, integrating articulated object, interaction pose, and obstacle avoidance knowledge into a base. LLM then functionalize these constraints and apply them to trajectory and posture planning. A kinematic-aware manipulation planner verifies reachability for trajectory and posture. Experiments on 50 hinge tasks across 5 object categories and 50 randomly initialized end-effectorhandle configurations show that GSAM reduces standard deviation by 3.1% and improves manipulation success rate by 36.0% compared to the best baseline, respectively demonstrating the superior object generalization and interaction safety of GSAM in practical scenarios. |
| title | GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.30740 |