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

2026-02-02

AI Summary

This work addresses the challenges of outlier interference and inadequate uncertainty modeling in AI-driven six-degree-of-freedom relative pose estimation for multiple objects. To this end, the authors propose a decoupled measurement model that separates position and orientation, enabling selective outlier rejection within an extended Kalman filter (EKF) framework. Instead of relying on fixed observation covariance assumptions, the method dynamically constructs the observation covariance using aleatoric uncertainty predicted by a deep neural network. This approach significantly improves the accuracy and consistency of state estimation, effectively mitigates the adverse impact of erroneous rotation estimates on the overall pose, and enhances system robustness under partial observation failures.

Technology Category

• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

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.

Problem

• multi-object relative state estimation
• aleatoric uncertainty
• outlier rejection
• 6-DoF pose
• AI-based measurement

Innovation

• aleatoric uncertainty
• outlier rejection
• relative pose estimation
• Extended Kalman Filter
• deep neural networks