弥合形态差距：通过意图条件微调使VLA模型适应灵巧操作
InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation
AI总结：
提出InDex框架，通过将预训练的1-DoF平行抓取输出重用作宏观虚拟抓取意图代理，结合两阶段解耦学习架构，实现VLA模型从低自由度夹爪到高自由度灵巧手的适应，有效缓解灾难性遗忘和动作流形坍缩。
摘要：
视觉-语言-动作（VLA）模型在机器人操作中展现了显著的零样本泛化能力，然而绝大多数预训练流程严格局限于低自由度平行夹爪。将这些丰富的语义先验适应到高自由度灵巧手引入了严重的形态差距，直接的端到端联合微调会由于数据稀缺而导致空间推理的灾难性遗忘和急性动作流形坍缩。在本文中，我们提出了InDex，一种新颖的、数据高效的适应框架，其根植于跨形态语义继承。我们不丢弃预训练的1-DoF平行抓取输出，而是将其重新用作连续的、宏观的虚拟抓取意图代理，以顺序化控制拓扑。我们实现了一个两阶段解耦学习架构：第一阶段参数高效地将VLA主干对齐以预测连续的臂轨迹和标量抓取意图；第二阶段冻结该空间主干，并利用一个意图条件去噪扩散头来解码多指末端执行器的细粒度关节运动。跨一系列多阶段、高接触灵巧操作任务的广泛模拟基准测试表明，InDex能够以最少的演示数据有效掌握复杂技能，显著优于整体基线，同时保留了原始VLA先验的鲁棒空间泛化能力。
英文摘要：
Pre-trained Vision-Language-Action (VLA) models provide useful semantic and spatial priors, yet their parallel-gripper action interfaces do not specify how those priors should be realized by a dexterous hand. Directly appending finger joints conflates two decisions with different structure: when contact should be established and how a morphology-specific hand trajectory should establish it. We introduce InDex, an intent-conditioned adaptation framework that separates these decisions without discarding full hand supervision. InDex derives a normalized grasp intent from retargeted demonstrations. A first stage predicts synchronized end-effector--intent chunks; conditioned on these predictions, VLA context, and proprioception, a diffusion decoder generates multi-joint hand actions. The scalar intent is therefore a temporal coordination interface rather than a compressed hand pose. Across four simulated tasks, three VLA backbones, and a physical arm--hand platform, InDex preserves the VLA's reaching competence while markedly improving conversion from approach to stable grasp and task completion. Ablations isolate complementary roles: intent aligns the contact transition, whereas diffusion represents the multiple hand trajectories compatible with the same task-space plan. These results identify post-reach arm--hand coordination, rather than object localization alone, as the principal bottleneck in adapting parallel-gripper VLAs to dexterous manipulation.
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。
