POV-SLAM: Probabilistic Object-Aware Variational SLAM in Semi-Static Environments

TL;DR

POV-SLAM introduces a probabilistic, object-aware SLAM framework capable of tracking and reconstructing semi-static scene changes over long periods, enhancing robustness in dynamic environments.

Contribution

It presents a novel variational EM approach with a Gaussian-Uniform bimodal likelihood for semi-static object change detection in SLAM.

Findings

Improves localization robustness in semi-static environments.

Effective in long-term real-world warehouse scenarios.

Outperforms existing SLAM methods in dynamic scene handling.

Abstract

Simultaneous localization and mapping (SLAM) in slowly varying scenes is important for long-term robot task completion. Failing to detect scene changes may lead to inaccurate maps and, ultimately, lost robots. Classical SLAM algorithms assume static scenes, and recent works take dynamics into account, but require scene changes to be observed in consecutive frames. Semi-static scenes, wherein objects appear, disappear, or move slowly over time, are often overlooked, yet are critical for long-term operation. We propose an object-aware, factor-graph SLAM framework that tracks and reconstructs semi-static object-level changes. Our novel variational expectation-maximization strategy is used to optimize factor graphs involving a Gaussian-Uniform bimodal measurement likelihood for potentially-changing objects. We evaluate our approach alongside the state-of-the-art SLAM solutions in simulation and on our novel real-world SLAM dataset captured in a warehouse over four months. Our method improves the robustness of localization in the presence of semi-static changes, providing object-level reasoning about the scene.