Reformulating AI-based Multi-Object Relative State Estimation for Aleatoric Uncertainty-based Outlier Rejection of Partial Measurements

TL;DR

This paper enhances multi-object localization for robots by reformulating the measurement model in AI-based state estimation, utilizing aleatoric uncertainty for outlier rejection and improving estimator robustness and accuracy.

Contribution

It introduces a reformulated EKF that decouples position and rotation measurements and incorporates aleatoric uncertainty for better outlier rejection in partial measurements.

Findings

Decoupling position and rotation improves robustness.

Using aleatoric uncertainty enhances outlier rejection.

Performance and consistency of the estimator are improved.

Abstract

Precise localization with respect to a set of objects of interest enables mobile robots to perform various tasks. With the rise of edge devices capable of deploying deep neural networks (DNNs) for real-time inference, it stands to reason to use artificial intelligence (AI) for the extraction of object-specific, semantic information from raw image data, such as the object class and the relative six degrees of freedom (6-DoF) pose. However, fusing such AI-based measurements in an Extended Kalman Filter (EKF) requires quantifying the DNNs' uncertainty and outlier rejection capabilities. This paper presents the benefits of reformulating the measurement equation in AI-based, object-relative state estimation. By deriving an EKF using the direct object-relative pose measurement, we can decouple the position and rotation measurements, thus limiting the influence of erroneous rotation measurements and allowing partial measurement rejection. Furthermore, we investigate the performance and consistency improvements for state estimators provided by replacing the fixed measurement covariance matrix of the 6-DoF object-relative pose measurements with the predicted aleatoric uncertainty of the DNN.