A Self-supervised Contrastive Learning Method for Grasp Outcomes Prediction

TL;DR

This paper explores the use of contrastive learning, specifically a dynamic-dictionary-based method, for predicting grasp outcomes in robotics, achieving high accuracy with minimal tactile sensor data.

Contribution

It introduces a novel contrastive learning approach with momentum updating for grasp outcome prediction, outperforming existing unsupervised methods.

Findings

Achieved 81.83% accuracy with a single tactile sensor.

Demonstrated the effectiveness of contrastive learning in grasp outcome prediction.

Highlighted the potential of unsupervised methods for stable robotic grasping.

Abstract

In this paper, we investigate the effectiveness of contrastive learning methods for predicting grasp outcomes in an unsupervised manner. By utilizing a publicly available dataset, we demonstrate that contrastive learning methods perform well on the task of grasp outcomes prediction. Specifically, the dynamic-dictionary-based method with the momentum updating technique achieves a satisfactory accuracy of 81.83% using data from one single tactile sensor, outperforming other unsupervised methods. Our results reveal the potential of contrastive learning methods for applications in the field of robot grasping and highlight the importance of accurate grasp prediction for achieving stable grasps.