Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Clouds

TL;DR

This paper introduces a neural network approach for estimating object pose uncertainty from 3D point clouds without color information, addressing visual ambiguity in industrial robotic perception.

Contribution

It is the first deep learning method to estimate pose distributions using only 3D data, enhancing reliability in industrial applications with ambiguous visual cues.

Findings

Successfully estimates pose uncertainty in real-world bin picking.

Handles symmetries related to reflection and revolution.

Framework is extendable to full SE(3) pose distribution estimation.

Abstract

Object pose estimation is crucial to robotic perception and typically provides a single-pose estimate. However, a single estimate cannot capture pose uncertainty deriving from visual ambiguity, which can lead to unreliable behavior. Existing pose distribution methods rely heavily on color information, often unavailable in industrial settings. We propose a novel neural network-based method for estimating object pose uncertainty using only 3D colorless data. To the best of our knowledge, this is the first approach that leverages deep learning for pose distribution estimation without relying on RGB input. We validate our method in a real-world bin picking scenario with objects of varying geometric ambiguity. Our current implementation focuses on symmetries in reflection and revolution, but the framework is extendable to full SE(3) pose distribution estimation. Source code available at opde3d.github.io