仅用接触信息实现复杂零件插入的高精度位姿估计。
Learning the Contact Manifold for Accurate Pose Estimation During Peg-in-Hole Insertion of Complex Geometries
- 通过探测构建局部接触流形，与离线预计算流形对齐求解位姿。
- 10秒内完成估计，误差小于1毫米和1度，成功率93.3%。
- 轻量网络替代耗时搜索，速度提升95倍且更准，适合工业装配场景。
具有紧密公差的复杂非凸零件的高接触率装配仍是重大挑战。纯模型方法难以处理接触动力学的不连续性，而模型无关方法需大量数据且精度不足。本文提出一种混合框架，仅利用复杂插销与其配合孔之间的接触状态信息，即可在装配过程中恢复完整的SE(3)位姿。在线执行不超过10秒，通过一系列基础探测动作构建局部接触子流形，并与离线预计算的接触流形对齐，实现亚毫米级和亚度级的位姿估计。为避免昂贵的k-NN搜索，我们训练了一个轻量网络，将稀疏接触观测投影到接触流形上，速度提升95倍，准确率提高18%。该方法在三种工业相关几何结构上评估，公差范围为0.1–1.0 mm，成功率达93.3%，较无状态估计的原始策略提升4.1倍。
原文摘要 · Abstract (English)
Contact-rich assembly of complex, non-convex parts with tight tolerances remains a formidable challenge. Purely model-based methods struggle with discontinuous contact dynamics, while model-free methods require vast data and often lack precision. In this work, we introduce a hybrid framework that uses only contact-state information between a complex peg and its mating hole to recover the full SE(3) pose during assembly. In under 10 seconds of online execution, a sequence of primitive probing motions constructs a local contact submanifold, which is then aligned to a precomputed offline contact manifold to yield sub-mm and sub-degree pose estimates. To eliminate costly k-NN searches, we train a lightweight network that projects sparse contact observations onto the contact manifold and is 95x faster and 18% more accurate. Our method, evaluated on three industrially relevant geometries with clearances of 0.1-1.0 mm, achieves a success rate of 93.3%, a 4.1x improvement compared to primitive-only strategies without state estimation.
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。