DAWN：基于扩散的对齐与旋松工作流网络
DAWN: Diffusion-based Alignment and unfastening Workflow Network
Hemant Kumar · Piyush Goenka · Nikhil Chopra
中文摘要
DAWN（Diffusion-based Alignment and unfastening Workflow Network）是一个分层机器人框架，通过多模态（multimodal）感知融合完成真实环境中的旋松任务。自主旋松对提升回收流程、增强安全性、降低运营成本至关重要，但因螺丝刀与紧固件的精确啮合、精细力控执行以及对环境变化的鲁棒性等固有挑战，目前仍以人工为主。为应对长时程、接触密集操作任务的学习复杂性，将旋松流程划分为两个连续阶段：(1) 对齐与插入，(2) 旋松。DAWN 包含三个关键组件：AlignNet，基于扩散的策略，确保螺丝刀尖端精确啮合；LatchNet，多模态分类器，可靠检测阶段转换是否成功；UnfastNet，实现稳定、力控的螺丝移除。在 Franka Emika 机器人上的实验验证表明，DAWN 的对齐与插入成功率与训练有素的人类操作员相当，阶段间转换鲁棒，并在多种未见场景中取得令人印象深刻的旋松成功率。消融研究进一步阐明关键输入模态与有效训练策略，凸显 DAWN 的可扩展性、鲁棒性与数据效率。
关键要点
- 01旋松任务因精确啮合、力控执行与环境变化而多依赖人工，自动化存在明显空白
- 02将长时程任务拆为对齐插入与旋松两阶段，并用扩散策略 AlignNet 保证啮合精度
- 03LatchNet 多模态分类器检测阶段转换，UnfastNet 实现稳定力控螺丝移除
- 04在 Franka Emika 上对齐插入成功率与人类操作员相当，未见场景旋松成功率较高
- 05消融实验揭示关键输入模态与训练策略，体现可扩展性、鲁棒性与数据效率
解读
尚无解读。
原始英文摘要
arXiv:2610.40537v1 Announce Type: new Abstract: We present DAWN (Diffusion-based Alignment and unfastening Workflow Network), a hierarchical robotic framework designed to perform real-world, unfastening tasks through multi-modal sensory integration. Autonomous robotic unfastening is crucial for improving recycling processes, enhancing safety, and reducing operational costs; yet, it remains predominantly manual due to inherent challenges in precise screwdriver engagement with fasteners, detailed force execution, and robustness to environmental variability. To address the complexity of learning long-horizon, contact-rich manipulation tasks, we subdivide the unfastening task procedure into two sequential stages: (1) alignment & insertion, and (2) unfastening. DAWN consists of three key components: AlignNet, a diffusion-based policy ensuring precise screwdriver tip engagement; LatchNet, a multi-modal classifier reliably detecting successful stage transitions; and UnfastNet, which achieves stable, force-controlled screw removal. Experimental validation on a Franka Emika robot demonstrates that DAWN achieves alignment & insertion success rates comparable to trained human operators, robustly transitions between stages, and attains an impressive success rate in unfastening across various unseen scenarios. Ablation studies further elucidate critical input modalities and effective training strategies, highlighting DAWN's scalability, robustness, and data efficiency.