Reproduce “A Coordinated Dual-Arm Framework for Delicate Snap-Fit Assemblies” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Shreyas Kumar, Barat S, Debojit Das, Yug Desai, Siddhi Jain, Rajesh Kumar, Harish J. Palanthandalam-Madapusi
Researchers from IITGN Robotics Laboratory and Addverb Technologies developed a unified dual-arm robotic framework for delicate snap-fit assemblies. It achieves a 100% success rate on challenging tasks and reduces peak contact forces by approximately 30% by integrating proprioceptive snap detection (SnapNet), dynamical-systems-based bimanual coordination, and event-triggered variable impedance control, without external sensors.
Key insights
- Reliable snap-fit engagement detection can be achieved using only readily available proprioceptive joint-velocity signals, obviating the need for external sensing.
- A holistic approach that integrates detection, coordination, and compliant control within a unified framework is critical for robustly automating complex bimanual assembly tasks.
- Dynamical systems with phase-gated coupling provide a flexible and stable method for bimanual coordination, allowing for task-dependent synchronization and decoupling of robotic arms.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.