Statistical Outlier Identification in Multi-robot Visual SLAM using Expectation Maximization

TL;DR

This paper presents a distributed probabilistic method using Expectation-Maximization for detecting outliers in multi-robot SLAM, improving robustness without requiring good initialization and handling multiple maps.

Contribution

It introduces a novel EM-based approach for outlier detection in multi-robot SLAM that does not depend on initial conditions and manages multiple maps simultaneously.

Findings

Superior outlier detection performance demonstrated in simulations and real-world data.

The new inference procedure outperforms belief propagation with convergence guarantees.

Effective detection of incorrect orientation measurements improves SLAM accuracy.

Abstract

This paper introduces a novel and distributed method for detecting inter-map loop closure outliers in simultaneous localization and mapping (SLAM). The proposed algorithm does not rely on a good initialization and can handle more than two maps at a time. In multi-robot SLAM applications, maps made by different agents have nonidentical spatial frames of reference which makes initialization very difficult in the presence of outliers. This paper presents a probabilistic approach for detecting incorrect orientation measurements prior to pose graph optimization by checking the geometric consistency of rotation measurements. Expectation-Maximization is used to fine-tune the model parameters. As ancillary contributions, a new approximate discrete inference procedure is presented which uses evidence on loops in a graph and is based on optimization (Alternate Direction Method of Multipliers). This method yields superior results compared to Belief Propagation and has convergence guarantees. Simulation and experimental results are presented that evaluate the performance of the outlier detection method and the inference algorithm on synthetic and real-world data.