arXiv 2605.307402026-05-29cs.ROcs.AI

GSAM: 一种通用且安全的铰接物体操作机器人框架

GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation

College of Computer Science, Chongqing University, Chongqing, China（重庆大学计算机学院）；Lumos Robotics, China（Lumos机器人中国）；Xi'an Jiaotong-Liverpool University, China（西安交通大学利物浦大学）；Fudan University, China（复旦大学）；Department of Information Engineering and Computer Science, University of Trento, Trento, Italy（特伦托大学信息工程与计算机科学系）

Beichen Shao, Mengying Xie, Heng Su, Wanyi Zhang, Mingyan Li, Yan Ding, Fausto Giunchiglia, Chao Chen

备注：: Accepted by the 19th International Conference on Parallel Problem Solving from Nature (PPSN 2026)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出GSAM框架，通过视觉感知器生成运动学参数、基于VLM的细调器进行常识推理修正、交互约束函数生成器集成障碍物避免知识，并由运动学感知规划器验证轨迹可达性，在50个铰链任务上相比最佳基线将标准差降低3.1%、操作成功率提升36.0%。

摘要：

铰接物体操作对服务机器人是一个独特的挑战。现有方法采用端到端策略学习、视觉运动规划以及大语言/视觉语言模型（LLM/VLM），但往往忽视了铰接物体的多样性和末端执行器与手柄之间交互的复杂性，导致泛化能力有限和破坏性碰撞。为了解决这一问题，我们提出了GSAM，一个通用且安全的铰接物体操作机器人框架。具体来说，一个基于视觉的感知器生成运动学参数。考虑到感知器中预训练标记产生的原始估计可能偏离常识，我们提出了一个基于VLM的细调器，利用链式思维（COT）常识推理来细化感知。为了防止破坏性碰撞，我们设计了一个交互约束函数生成器，将铰接物体、交互姿态和障碍物避免知识集成到一个基中。然后LLM将这些约束函数化，并将其应用于轨迹和姿态规划。一个运动学感知的操作规划器验证轨迹和姿态的可达性。在5个物体类别的50个铰链任务和50个随机初始化的末端执行器-手柄配置上的实验表明，与最佳基线相比，GSAM将标准差降低了3.1%，操作成功率提高了36.0%，分别展示了GSAM在实际场景中优越的物体泛化能力和交互安全性。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。