Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception

TL;DR

This paper introduces a method for training lightweight deep networks to predict grasp success probabilities based on RGB images and pose uncertainty, enhancing robotic grasping reliability.

Contribution

It presents a novel approach to estimate grasp success likelihood using RGB perception and pose uncertainty, trained on real and simulated data, applicable across diverse objects.

Findings

Networks trained on all objects jointly perform better.

Pose uncertainty prediction improves grasp success estimation.

Training on diverse objects enhances generalization.

Abstract

Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high uncertainty. Even though object pose estimation improves and uncertainty quantification research continues to make strides, few studies have connected them to the downstream task of robotic grasping. We propose a method for training lightweight, deep networks to predict whether a grasp guided by an image-based pose estimate will succeed before that grasp is attempted. We generate training data for our networks via object pose estimation on real images and simulated grasping. We also find that, despite high object variability in grasping trials, networks benefit from training on all objects jointly, suggesting that a diverse variety of objects can nevertheless contribute to the same goal.