用扩散模型让机器人在木材拼接中抗误差，提高施工自动化精度
Learning Diffusion Policies for Robotic Manipulation of Timber Joinery under Fabrication Uncertainty
- 通过力觉反馈的遥控示范训练扩散策略，学习复杂拼接动作
- 在10毫米位置偏差下仍达75%平均成功率，优于传统方法
- 适合需要高精度、抗制造误差的建筑机器人场景
由公差累积、材料缺陷和定位误差引起的制造不确定性，仍是建筑领域自动化机器人装配的关键障碍，尤其在几何间隙极小的接触密集型操作中。本文研究在工业级机器人上部署扩散策略学习，以应对此类不确定性，采用紧配合榫卯结构作为典型任务案例。利用配备力/力矩传感器的工业机器人工作台采集遥控操作示范数据，训练感官-运动扩散策略。通过两阶段实验评估基准性能与随机位置扰动（最大达10 mm）下的鲁棒性，远超关节间隙。表现最佳的策略在理想条件下实现100%成功率，在不确定性下平均成功率达75%。结果表明，扩散策略可显著提升对制造引发错位的鲁棒性，是实现严苛公差下建筑机器人可靠装配的重要一步。
原文摘要 · Abstract (English)
Fabrication uncertainty arising from tolerance accumulation, material imperfection, and positioning errors remains a critical barrier to automated robotic assembly in construction, particularly for contact-rich manipulation tasks under minimal geometric clearance. This paper investigates the deployment of diffusion policy learning on construction-scale industrial robots to enable robust, high-precision assembly under such uncertainty, using tight-clearance mortise and tenon timber joinery as a representative case study. Sensory-motor diffusion policies are trained using teleoperated demonstrations collected from an industrial robotic workcell equipped with force/torque sensing. A two-phase experimental study evaluates baseline performance and robustness under randomized positional perturbations up to 10 mm, far exceeding the joint clearance. The best-performing policy achieved 100% success under nominal conditions and 75% average success under uncertainty. These results suggest that diffusion policies can improve robustness to fabrication-induced misalignment, representing a step toward reliable robotic assembly in construction under tight tolerances.
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。