Model-free Grasping with Multi-Suction Cup Grippers for Robotic Bin Picking

TL;DR

This paper introduces a model-free, neural network-based method for predicting grasp poses for multi-suction cup robotic grippers, enabling effective bin picking without gripper-specific training data.

Contribution

It presents a gripper-agnostic, two-step approach combining grasp quality prediction and optimization, along with an automated labeling method for training.

Findings

Effective grasp prediction in real-world bin picking scenarios

Gripper-agnostic approach adaptable to various designs

Automated labeling improves training efficiency

Abstract

This paper presents a novel method for model-free prediction of grasp poses for suction grippers with multiple suction cups. Our approach is agnostic to the design of the gripper and does not require gripper-specific training data. In particular, we propose a two-step approach, where first, a neural network predicts pixel-wise grasp quality for an input image to indicate areas that are generally graspable. Second, an optimization step determines the optimal gripper selection and corresponding grasp poses based on configured gripper layouts and activation schemes. In addition, we introduce a method for automated labeling for supervised training of the grasp quality network. Experimental evaluations on a real-world industrial application with bin picking scenes of varying difficulty demonstrate the effectiveness of our method.