利用基础模型推理与部件定位实现即时自适应铰接物体操作
Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding
AI总结：
本文提出 AdaRPG 框架，利用基础模型进行部件提取、可供性推理与机制推理，结合部件级数据集和原语技能控制，实现机器人对未见类别铰接物体的自适应操作泛化。
摘要：
铰接物体给机器人带来了多样化的操作挑战。由于其内部结构无法直接观察，机器人必须自适应地探索并细化动作，以生成成功的操作轨迹。尽管现有工作已尝试在自适应铰接物体操作中实现跨类别泛化，但仍存在两大挑战：（1）真实世界铰接物体的几何多样性使视觉感知与理解变得复杂；（2）物体功能和机制的差异阻碍了统一自适应操作策略的开发。为应对这些挑战，我们提出了 AdaRPG，这是一种利用基础模型提取物体部件的新颖框架；相比完整物体，这些部件表现出更强的局部几何相似性，从而增强了功能原语技能的视觉可供性泛化。为支持这一点，我们构建了一个部件级可供性标注数据集来训练可供性模型。此外，AdaRPG 利用基础模型中嵌入的常识来推理复杂机制，并生成高层控制代码，根据部件可供性推断调用原语技能函数。仿真和真实世界实验证明了 AdaRPG 在新颖铰接物体类别上的强大泛化能力。
英文摘要：
Articulated objects pose diverse manipulation challenges for robots. Since their internal structures are not directly observable, robots must adaptively explore and refine actions to generate successful manipulation trajectories. While existing works have attempted cross-category generalization in adaptive articulated object manipulation, two major challenges persist: (1) the geometric diversity of real-world articulated objects complicates visual perception and understanding, and (2) variations in object functions and mechanisms hinder the development of a unified adaptive manipulation strategy. To address these challenges, we propose AdaRPG, a novel framework that leverages foundation models to extract object parts, which exhibit greater local geometric similarity than entire objects, thereby enhancing visual affordance generalization for functional primitive skills. To support this, we construct a part-level affordance annotation dataset to train the affordance model. Additionally, AdaRPG utilizes the common knowledge embedded in foundation models to reason about complex mechanisms and generate high-level control codes that invoke primitive skill functions based on part affordance inference. Simulation and real-world experiments demonstrate AdaRPG's strong generalization ability across novel articulated object categories.
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。
