SLAM Backends with Objects in Motion: A Unifying Framework and Tutorial

TL;DR

This paper introduces a unifying optimization framework for dynamic SLAM environments, presents a new filtering-based dynamic SLAM algorithm, and demonstrates its high accuracy and efficiency through simulated experiments.

Contribution

It extends a recent SLAM backend framework to dynamic scenes and introduces dynamic EKF SLAM, a novel filtering-based algorithm mathematically equivalent to classical EKF SLAM in dynamic settings.

Findings

Dynamic EKF SLAM achieves high localization accuracy.

The algorithm provides precise mobile object pose estimation.

It operates efficiently in simulated environments.

Abstract

Simultaneous Localization and Mapping (SLAM) algorithms are frequently deployed to support a wide range of robotics applications, such as autonomous navigation in unknown environments, and scene mapping in virtual reality. Many of these applications require autonomous agents to perform SLAM in highly dynamic scenes. To this end, this tutorial extends a recently introduced, unifying optimization-based SLAM backend framework to environments with moving objects and features. Using this framework, we consider a rapprochement of recent advances in dynamic SLAM. Moreover, we present dynamic EKF SLAM: a novel, filtering-based dynamic SLAM algorithm generated from our framework, and prove that it is mathematically equivalent to a direct extension of the classical EKF SLAM algorithm to the dynamic environment setting. Empirical results with simulated data indicate that dynamic EKF SLAM can achieve high localization and mobile object pose estimation accuracy, as well as high map precision, with high efficiency.