Grasp success prediction with quality metrics

TL;DR

This paper develops a machine learning-based model that combines various quality metrics to predict the success of robotic grasps, validated across different robots and objects with a 76% success rate.

Contribution

It introduces a novel approach that integrates multiple metrics and machine learning to improve grasp success prediction in robotic manipulation.

Findings

Achieved a 76% success rate in predicting grasp outcomes.

Validated the model on different robots and objects in simulation and real-world.

Categorized grasp outcomes into robust, fragile, and futile.

Abstract

Current robotic manipulation requires reliable methods to predict whether a certain grasp on an object will be successful or not prior to its execution. Different methods and metrics have been developed for this purpose but there is still work to do to provide a robust solution. In this article we combine different metrics to evaluate real grasp executions. We use different machine learning algorithms to train a classifier able to predict the success of candidate grasps. Our experiments are performed with two different robotic grippers and different objects. Grasp candidates are evaluated in both simulation and real world. We consider 3 different categories to label grasp executions: robust, fragile and futile. Our results shows the proposed prediction model has success rate of 76\%.