外观
论文arXiv 2407.098992024-07-13
DexGrasp-Diffusion：统一多灵巧手功能抓取生成框架
本文由 AI 根据公开内容整理，可能有误，请以原文为准：DexGrasp-Diffusion: Diffusion-based Unified Functional Grasp Synthesis Method for Multi-Dexterous Robotic Hands（arXiv 2407.09899）
核心内容
针对多灵巧手功能抓取合成难题，论文提出DexGrasp-Diffusion端到端模块化方法。该框架旨在解决不同构型灵巧手在遵循物体Affordance指令时的泛化问题，通过统一数据驱动模型与物理/功能双重过滤机制，实现了从感知到功能抓取的闭环生成。实验基于MultiDex数据集进行量化评估，证实该方法在抓取成功率、姿态多样性及碰撞深度控制等核心指标上均显著超越现有基线模型。
技术架构包含两大核心组件：MultiHandDiffuser作为统一扩散模型负责多手型抓取估计；DexDiscriminator则结合Physics Discriminator与开放词汇Functional Discriminator，依据物体Affordance筛选物理可行且符合语义的功能抓取。系统支持根据自然语言指令生成特定家庭物品的操作姿态，验证了其在复杂语义约束下对异构灵巧手的适配能力，为具身操作提供了通用的抓取合成范式。
关键看点
- 统一扩散模型：MultiHandDiffuser实现单一模型适配多种灵巧手构型，解决异构手部抓取生成泛化难题
- 双重判别机制：集成物理与开放词汇功能判别器，确保生成姿态同时满足力学稳定性与语义Affordance约束
- 性能量化验证：在MultiDex数据集上测试，抓取成功率、多样性及碰撞深度指标均优于基线模型
- 语义指令驱动：支持根据自然语言Affordance指令生成特定功能抓取，验证了家庭场景下的任务对齐能力
工程与产业观察
该工作通过统一扩散模型与双重判别器解耦了灵巧手构型差异与功能语义约束，为具身智能提供了跨本体抓取生成的通用算法底座。其开放词汇功能判别机制解决了传统方法难以泛化到新物体/新指令的痛点，对降低多机器人平台数据采集成本、提升Sim-to-Real迁移效率具有直接工程参考价值。
英文摘要 (Abstract)
The versatility and adaptability of human grasping catalyze advancing dexterous robotic manipulation. While significant strides have been made in dexterous grasp generation, current research endeavors pivot towards optimizing object manipulation while ensuring functional integrity, emphasizing the synthesis of functional grasps following desired affordance instructions. This paper addresses the challenge of synthesizing functional grasps tailored to diverse dexterous robotic hands by proposing DexGrasp-Diffusion, an end-to-end modularized diffusion-based method. DexGrasp-Diffusion integrates MultiHandDiffuser, a novel unified data-driven diffusion model for multi-dexterous hands grasp estimation, with DexDiscriminator, which employs a Physics Discriminator and a Functional Discriminator with open-vocabulary setting to filter physically plausible functional grasps based on object affordances. The experimental evaluation conducted on the MultiDex dataset provides substantiating evidence supporting the superior performance of MultiHandDiffuser over the baseline model in terms of success rate, grasp diversity, and collision depth. Moreover, we demonstrate the capacity of DexGrasp-Diffusion to reliably generate functional grasps for household objects aligned with specific affordance instructions.
作者：Zhengshen Zhang, Lei Zhou, Chenchen Liu, Zhiyang Liu, Chengran Yuan, Sheng Guo, Ruiteng Zhao, Marcelo H. Ang, Francis EH Tay
来源
本页事实对应的公开页面，以原文为准。