arXiv 2604.084102026-04-14cs.CVcs.RO

BLaDA: 在3DGS场域中实现语言到功能灵巧动作的桥梁

BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields

School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（机器人视觉感知与控制技术国家工程研究中心，湖南大学）；Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University（教育部贵州大学先进制造技术重点实验室）

Fan Yang, Wenrui Chen, Guorun Yan, Ruize Liao, Wanjun Jia, Dongsheng Luo, Jiacheng Lin, Kailun Yang, Zhiyong Li, Yaonan Wang

备注：: Code will be publicly available at https://github.com/PopeyePxx/BLaDA

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

BLaDA提出一个可解释的零样本框架，通过解析自然语言为结构化的六元组操作约束，结合三角功能点定位模块和3D关键点抓取矩阵转换执行模块，实现功能灵巧操作的高精度和高成功率。

摘要：

在无结构环境中，功能灵巧抓取需要紧密整合语义理解、精确3D功能定位和物理可解释的执行。模块化层次方法比端到端VLA方法更可控和可解释，但现有方法仍依赖预定义的用途标签且缺乏必要的语义-姿态耦合。为此，我们提出BLaDA（在3DGS场域中实现语言到灵巧动作的桥梁），一个可解释的零样本框架，将开放词汇指令作为感知和控制约束用于功能灵巧操作。BLaDA通过首先解析自然语言为结构化的六元组操作约束，利用知识引导语言解析（KLP）模块建立可解释的推理链。为了实现姿态一致的空间推理，我们引入三角功能点定位（TriLocation）模块，该模块利用3D高斯点划法作为连续场景表示，并在三角几何约束下识别功能区域。最后，3D关键点抓取矩阵转换执行（KGT3D+）模块将这些语义-几何约束解码为物理上合理的手腕姿态和手指级指令。在复杂基准测试中，BLaDA在功能操作的精度和成功率方面显著优于现有方法，代码将在https://github.com/PopeyePxx/BLaDA上公开。

英文摘要：

In unstructured environments, functional dexterous grasping calls for the tight integration of semantic understanding, precise 3D functional localization, and physically interpretable execution. Modular hierarchical methods are more controllable and interpretable than end-to-end VLA approaches, but existing ones still rely on predefined affordance labels and lack the tight semantic--pose coupling needed for functional dexterous manipulation. To address this, we propose BLaDA (Bridging Language to Dexterous Actions in 3DGS fields), an interpretable zero-shot framework that grounds open-vocabulary instructions as perceptual and control constraints for functional dexterous manipulation. BLaDA establishes an interpretable reasoning chain by first parsing natural language into a structured sextuple of manipulation constraints via a Knowledge-guided Language Parsing (KLP) module. To achieve pose-consistent spatial reasoning, we introduce the Triangular Functional Point Localization (TriLocation) module, which utilizes 3D Gaussian Splatting as a continuous scene representation and identifies functional regions under triangular geometric constraints. Finally, the 3D Keypoint Grasp Matrix Transformation Execution (KGT3D+) module decodes these semantic-geometric constraints into physically plausible wrist poses and finger-level commands. Extensive experiments on complex benchmarks demonstrate that BLaDA significantly outperforms existing methods in both affordance grounding precision and the success rate of functional manipulation across diverse categories and tasks. Code will be publicly available at https://github.com/PopeyePxx/BLaDA.

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。