Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning

TL;DR

This paper introduces a novel sim-to-real transfer learning framework for precise, model-free robotic grasping that leverages a large-scale dataset and data augmentation to improve success rates on novel objects.

Contribution

The study presents a new data generation and transfer learning approach that significantly reduces the sim-to-real gap in robotic grasping tasks.

Findings

Achieved over 90% success rate on single objects

Reached 85.71% success in multi-object scenarios

Outperformed existing state-of-the-art methods

Abstract

Precise robotic grasping of several novel objects is a huge challenge in manufacturing, automation, and logistics. Most of the current methods for model-free grasping are disadvantaged by the sparse data in grasping datasets and by errors in sensor data and contact models. This study combines data generation and sim-to-real transfer learning in a grasping framework that reduces the sim-to-real gap and enables precise and reliable model-free grasping. A large-scale robotic grasping dataset with dense grasp labels is generated using domain randomization methods and a novel data augmentation method for deep learning-based robotic grasping to solve data sparse problem. We present an end-to-end robotic grasping network with a grasp optimizer. The grasp policies are trained with sim-to-real transfer learning. The presented results suggest that our grasping framework reduces the uncertainties in grasping datasets, sensor data, and contact models. In physical robotic experiments, our grasping framework grasped single known objects and novel complex-shaped household objects with a success rate of 90.91%. In a complex scenario with multi-objects robotic grasping, the success rate was 85.71%. The proposed grasping framework outperformed two state-of-the-art methods in both known and unknown object robotic grasping.