DynoSAM: Open-Source Smoothing and Mapping Framework for Dynamic SLAM

TL;DR

DynoSAM is an open-source framework that advances dynamic SLAM by integrating static and dynamic measurements, enabling accurate motion estimation and improved scene understanding in complex environments.

Contribution

We developed DynoSAM, a flexible, open-source framework for dynamic SLAM that unifies static and dynamic data in a factor graph for enhanced motion estimation.

Findings

Achieved state-of-the-art motion estimation accuracy in diverse environments

Demonstrated improved 3D reconstruction of dynamic scenes

Validated effectiveness in real-world and simulated datasets

Abstract

Traditional Visual Simultaneous Localization and Mapping (vSLAM) systems focus solely on static scene structures, overlooking dynamic elements in the environment. Although effective for accurate visual odometry in complex scenarios, these methods discard crucial information about moving objects. By incorporating this information into a Dynamic SLAM framework, the motion of dynamic entities can be estimated, enhancing navigation whilst ensuring accurate localization. However, the fundamental formulation of Dynamic SLAM remains an open challenge, with no consensus on the optimal approach for accurate motion estimation within a SLAM pipeline. Therefore, we developed DynoSAM, an open-source framework for Dynamic SLAM that enables the efficient implementation, testing, and comparison of various Dynamic SLAM optimization formulations. DynoSAM integrates static and dynamic measurements into a unified optimization problem solved using factor graphs, simultaneously estimating camera poses, static scene, object motion or poses, and object structures. We evaluate DynoSAM across diverse simulated and real-world datasets, achieving state-of-the-art motion estimation in indoor and outdoor environments, with substantial improvements over existing systems. Additionally, we demonstrate DynoSAM utility in downstream applications, including 3D reconstruction of dynamic scenes and trajectory prediction, thereby showcasing potential for advancing dynamic object-aware SLAM systems. DynoSAM is open-sourced at https://github.com/ACFR-RPG/DynOSAM.