A Coordinated Dual-Arm Framework for Delicate Snap-Fit Assemblies

TL;DR

This paper presents a real-time neural network and a dual-arm control framework for delicate snap-fit assembly tasks, improving detection accuracy and reducing impact forces during assembly.

Contribution

It introduces SnapNet, a neural network for engagement detection using proprioceptive signals, and a dual-arm coordination framework for precise, compliant assembly.

Findings

Over 96% detection recall with SnapNet

Up to 30% reduction in peak impact forces

Effective across diverse geometries

Abstract

Delicate snap-fit assemblies, such as inserting a lens into an eye-wear frame or during electronics assembly, demand timely engagement detection and rapid force attenuation to prevent overshoot-induced component damage or assembly failure. We address these challenges with two key contributions. First, we introduce SnapNet, a lightweight neural network that detects snap-fit engagement from joint-velocity transients in real-time, showing that reliable detection can be achieved using proprioceptive signals without external sensors. Second, we present a dynamical-systems-based dual-arm coordination framework that integrates SnapNet driven detection with an event-triggered impedance modulation, enabling accurate alignment and compliant insertion during delicate snap-fit assemblies. Experiments across diverse geometries on a heterogeneous bimanual platform demonstrate high detection accuracy (over 96% recall) and up to a 30% reduction in peak impact forces compared to standard impedance control.