Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception
This addresses the issue of task failure in robotic grasping due to uncertainty in pose estimation, though it is incremental as it builds on existing pose estimation and uncertainty quantification research.
The paper tackles the problem of overconfident deep object pose estimators in robotic grasping by proposing a method to predict grasp success before execution, using training data from real images and simulated grasping.
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.