Abstract: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.
From: Arash Adel [view email]
[v1]
Fri, 21 Nov 2025 20:43:46 UTC (49,022 KB)
[v2]
Tue, 17 Feb 2026 21:12:51 UTC (48,943 KB)
[v3]
Sun, 19 Apr 2026 16:43:04 UTC (49,079 KB)
[v4]
Sat, 22 Aug 2026 21:54:13 UTC (17,366 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。