Uncertainty Quantification for Visual Object Pose Estimation

TL;DR

This paper introduces SLUE, a distribution-free method for quantifying uncertainty in monocular object pose estimation, providing high-probability bounds without strict distributional assumptions, and demonstrates its effectiveness on datasets and real-world scenarios.

Contribution

We develop SLUE, a convex program that computes high-confidence, distribution-free pose uncertainty bounds, extending to a hierarchy for tighter bounds, with practical evaluation on datasets and drone tracking.

Findings

SLUE produces smaller translation bounds than prior methods.

SLUE provides competitive orientation bounds.

The hierarchy converges to the minimum volume ellipsoid.

Abstract

Quantifying the uncertainty of an object's pose estimate is essential for robust control and planning. Although pose estimation is a well-studied robotics problem, attaching statistically rigorous uncertainty is not well understood without strict distributional assumptions. We develop distribution-free pose uncertainty bounds about a given pose estimate in the monocular setting. Our pose uncertainty only requires high probability noise bounds on pixel detections of 2D semantic keypoints on a known object. This noise model induces an implicit, non-convex set of pose uncertainty constraints. Our key contribution is SLUE (S-Lemma Uncertainty Estimation), a convex program to reduce this set to a single ellipsoidal uncertainty bound that is guaranteed to contain the true object pose with high probability. SLUE solves a relaxation of the minimum volume bounding ellipsoid problem inspired by the celebrated S-lemma. It requires no initial guess of the bound's shape or size and is guaranteed to contain the true object pose with high probability. For tighter uncertainty bounds at the same confidence, we extend SLUE to a sum-of-squares relaxation hierarchy which is guaranteed to converge to the minimum volume ellipsoidal uncertainty bound for a given set of keypoint constraints. We show this pose uncertainty bound can easily be projected to independent translation and axis-angle orientation bounds. We evaluate SLUE on two pose estimation datasets and a real-world drone tracking scenario. Compared to prior work, SLUE generates substantially smaller translation bounds and competitive orientation bounds. We release code at https://github.com/MIT-SPARK/PoseUncertaintySets.