用深度学习从稀疏点推断空间约束机构参数与运动轨迹
O-ConNet: Geometry-Aware End-to-End Inference of Over-Constrained Spatial Mechanisms
- 端到端神经网络直接从三个稀疏点预测机构参数和完整运动路径
- 在42,860个样本上参数误差0.276±0.077，轨迹误差0.145±0.018
- 无需求解约束方程，适合稀疏观测下的空间机构逆向设计
深度学习在科学发现中展现出巨大潜力，但其对宏观刚体运动约束的建模仍不充分。本文针对空间过约束机构，提出O-ConNet端到端框架，仅需三个稀疏可达点即可推断机构结构参数并重建完整运动轨迹，推理过程无需显式求解约束方程。在自构建的Bennett 4R数据集（42,860个有效样本）上，O-ConNet实现参数平均绝对误差（Param-MAE）0.276±0.077、轨迹平均绝对误差（Traj-MAE）0.145±0.018（10次运行均值±标准差），分别优于最强序列基线（LSTM-Seq2Seq）65.1%和88.2%。结果表明，端到端学习可捕捉闭合环几何结构，为极端稀疏观测下空间过约束机构的逆向设计提供可行路径。
原文摘要 · Abstract (English)
Deep learning has shown strong potential for scientific discovery, but its ability to model macroscopic rigid-body kinematic constraints remains underexplored. We study this problem on spatial over-constrained mechanisms and propose O-ConNet, an end-to-end framework that infers mechanism structural parameters from only three sparse reachable points while reconstructing the full motion trajectory, without explicitly solving constraint equations during inference. On a self-constructed Bennett 4R dataset of 42,860 valid samples, O-ConNet achieves Param-MAE 0.276 +/- 0.077 and Traj-MAE 0.145 +/- 0.018 (mean +/- std over 10 runs), outperforming the strongest sequence baseline (LSTM-Seq2Seq) by 65.1 percent and 88.2 percent, respectively. These results suggest that end-to-end learning can capture closed-loop geometric structure and provide a practical route for inverse design of spatial over-constrained mechanisms under extremely sparse observations.
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。