VLBiMan: 视觉-语言锚定的一次示例演示使通用化双臂机器人操作成为可能
VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation
AI总结：
VLBiMan通过任务感知分解从单个示例中提取可重用技能，实现双臂机器人操作的通用化，减少演示需求并增强跨平台适应性。
摘要：
实现通用化双臂操作需要能从最少人类输入中高效学习并适应现实世界不确定性和多样化机体的系统。现有方法面临两难：模仿策略学习需要大量演示覆盖任务变化，而模块化方法在动态场景中缺乏灵活性。我们引入VLBiMan框架，通过任务感知分解从单个示例中提取可重用技能，保留不变原语作为锚点，同时通过视觉-语言锚定动态调整可调组件。该适应机制在不重新训练策略的情况下解决背景变化、物体重新定位或视觉杂乱导致的场景歧义，利用语义解析和几何可行性约束。此外，系统继承了类人混合控制能力，实现双臂同步和异步混合使用。大量实验验证了VLBiMan在工具使用和多物体任务中的表现：(1) 相比模仿基线大幅减少演示需求；(2) 通过原子技能拼接实现长周期任务的组合泛化；(3) 对新但语义相似的对象和外部干扰具有鲁棒性；(4) 跨机体迁移能力强，证明从人类演示中学习的技能可在不同机器人平台上无需重新训练即可实例化。通过将人类先验与视觉-语言锚定适应相结合，我们的工作迈出了在无结构环境中实现实用且多功能双臂操作的一步。
英文摘要：
Achieving generalizable bimanual manipulation requires systems that can learn efficiently from minimal human input while adapting to real-world uncertainties and diverse embodiments. Existing approaches face a dilemma: imitation policy learning demands extensive demonstrations to cover task variations, while modular methods often lack flexibility in dynamic scenes. We introduce VLBiMan, a framework that derives reusable skills from a single human example through task-aware decomposition, preserving invariant primitives as anchors while dynamically adapting adjustable components via vision-language grounding. This adaptation mechanism resolves scene ambiguities caused by background changes, object repositioning, or visual clutter without policy retraining, leveraging semantic parsing and geometric feasibility constraints. Moreover, the system inherits human-like hybrid control capabilities, enabling mixed synchronous and asynchronous use of both arms. Extensive experiments validate VLBiMan across tool-use and multi-object tasks, demonstrating: (1) a drastic reduction in demonstration requirements compared to imitation baselines, (2) compositional generalization through atomic skill splicing for long-horizon tasks, (3) robustness to novel but semantically similar objects and external disturbances, and (4) strong cross-embodiment transfer, showing that skills learned from human demonstrations can be instantiated on different robotic platforms without retraining. By bridging human priors with vision-language anchored adaptation, our work takes a step toward practical and versatile dual-arm manipulation in unstructured settings.
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。
