ECNNs: Ensemble Learning Methods for Improving Planar Grasp Quality Estimation

TL;DR

This paper introduces ECNNs, an ensemble learning approach that combines multiple robotic grasp algorithms using a Mixture of Experts model, significantly improving grasp success rates with minimal computational overhead.

Contribution

The paper proposes a novel ensemble learning framework for robotic grasping that integrates existing algorithms via a Mixture of Experts neural network, enhancing success rates.

Findings

Achieved a 6% increase in grasp success on the Cornell Dataset.

Demonstrated real-world applicability with a Franka Emika Panda robot.

Introduced a computationally efficient ensemble method.

Abstract

We present an ensemble learning methodology that combines multiple existing robotic grasp synthesis algorithms and obtain a success rate that is significantly better than the individual algorithms. The methodology treats the grasping algorithms as "experts" providing grasp "opinions". An Ensemble Convolutional Neural Network (ECNN) is trained using a Mixture of Experts (MOE) model that integrates these opinions and determines the final grasping decision. The ECNN introduces minimal computational cost overhead, and the network can virtually run as fast as the slowest expert. We test this architecture using open-source algorithms in the literature by adopting GQCNN 4.0, GGCNN and a custom variation of GGCNN as experts and obtained a 6% increase in the grasp success on the Cornell Dataset compared to the best-performing individual algorithm. The performance of the method is also demonstrated using a Franka Emika Panda arm.