用接触类比实现一次学习，快速适配新物体的抓取策略
One-Shot Manipulation Strategy Learning by Making Contact Analogies
- 基于参考动作轨迹，通过全局形状与局部曲率匹配找相似接触点
- 在舀取、悬挂、钩取任务中，速度与泛化能力显著优于现有方法
- 适合需要快速适应新物体的机器人操作场景
我们提出一种新方法MAGIC（可泛化的智能接触类比），实现对抓取策略的一次学习，并快速广泛地推广到新物体。通过利用参考动作轨迹，MAGIC能有效识别新物体上与示范动作相似的接触点和动作序列，例如使用不同钩子抓取不同形状大小的远距离物体。该方法采用两阶段接触点匹配：先用预训练神经特征进行全局形状匹配，再结合局部曲率分析确保接触点精确且物理合理。我们在舀取、悬挂、钩取三个任务上进行实验，结果表明MAGIC在运行速度和对不同物体类别的泛化能力上均显著优于现有方法。
原文摘要 · Abstract (English)
We present a novel approach, MAGIC (manipulation analogies for generalizable intelligent contacts), for one-shot learning of manipulation strategies with fast and extensive generalization to novel objects. By leveraging a reference action trajectory, MAGIC effectively identifies similar contact points and sequences of actions on novel objects to replicate a demonstrated strategy, such as using different hooks to retrieve distant objects of different shapes and sizes. Our method is based on a two-stage contact-point matching process that combines global shape matching using pretrained neural features with local curvature analysis to ensure precise and physically plausible contact points. We experiment with three tasks including scooping, hanging, and hooking objects. MAGIC demonstrates superior performance over existing methods, achieving significant improvements in runtime speed and generalization to different object categories. Website: https://magic-2024.github.io/ .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。