Grasp Learning: Models, Methods, and Performance

TL;DR

This paper reviews the rapid advancements in robotic grasp learning, highlighting the evolution from challenging research problems to industrial applications, and discusses current methods, models, and the state of the art.

Contribution

It provides a comprehensive overview of current grasp learning techniques, models, and performance, summarizing recent progress and methodological approaches in the field.

Findings

Robotic grasp learning has transitioned from research challenge to industrial use.

Various machine learning models are employed in grasp learning.

Current state-of-the-art methods enable grasping of novel objects in cluttered environments.

Abstract

Grasp learning has become an exciting and important topic in robotics. Just a few years ago, the problem of grasping novel objects from unstructured piles of clutter was considered a serious research challenge. Now, it is a capability that is quickly becoming incorporated into industrial supply chain automation. How did that happen? What is the current state of the art in robotic grasp learning, what are the different methodological approaches, and what machine learning models are used? This review attempts to give an overview of the current state of the art of grasp learning research.