Robotic system achieves human-level success in unscrewing tasks
DAWN: Diffusion-based Alignment and unfastening Workflow Network
Robotics
Summary
Removing screws with robots is hard because it needs careful alignment and the right amount of force. The authors designed a robot system called DAWN that splits the task into two parts: first, lining up the screwdriver correctly, and second, turning the screw out carefully. DAWN uses different types of sensors and smart programs to know when each step is done. Tests showed it can do these tasks almost as well as trained humans and works well in new situations.
What this means in practice
- •For recycling facility operators: Automate the removal of screws from electronic waste to speed up recycling and reduce manual labor.
- •For industrial safety teams: Deploy robots to unfasten components in hazardous environments, reducing risk to human workers.
Authors
Hemant Kumar, Piyush Goenka, Nikhil Chopra
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.