Tactile-Sensitive NewtonianVAE for High-Accuracy Industrial Connector Insertion

TL;DR

This paper introduces a tactile-sensitive NewtonianVAE that enables high-precision industrial connector insertion by accurately estimating pose with grasp pose compensation, achieving 0.3 mm accuracy and outperforming state-of-the-art methods.

Contribution

The work extends NewtonianVAE with tactile sensing and grasp pose compensation, enabling precise pose estimation for industrial tasks without extra annotation or engineering.

Findings

Achieved 100% success rate in USB connector insertion

Demonstrated 0.3 mm positioning accuracy

Outperformed CNN-based goal pose regression methods

Abstract

An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug. Thus, highly accurate estimation of the relative pose between a plug and socket is fundamental for achieving the task. World models are promising technologies for visuomotor control because they obtain appropriate state representation to jointly optimize feature extraction and latent dynamics model. Recent studies show that the NewtonianVAE, a type of the world model, acquires latent space equivalent to mapping from images to physical coordinates. Proportional control can be achieved in the latent space of NewtonianVAE. However, applying NewtonianVAE to high-accuracy industrial tasks in physical environments is an open problem. Moreover, the existing framework does not consider the grasp pose compensation in the obtained latent space. In this work, we proposed tactile-sensitive NewtonianVAE and applied it to a USB connector insertion with grasp pose variation in the physical environments. We adopted a GelSight-type tactile sensor and estimated the insertion position compensated by the grasp pose of the plug. Our method trains the latent space in an end-to-end manner, and no additional engineering and annotation are required. Simple proportional control is available in the obtained latent space. Moreover, we showed that the original NewtonianVAE fails in some situations, and demonstrated that domain knowledge induction improves model accuracy. This domain knowledge can be easily obtained using robot specification and grasp pose error measurement. We demonstrated that our proposed method achieved a 100\% success rate and 0.3 mm positioning accuracy in the USB connector insertion task in the physical environment. It outperformed SOTA CNN-based two-stage goal pose regression with grasp pose compensation using coordinate transformation.