ObVi-SLAM: Long-Term Object-Visual SLAM

TL;DR

ObVi-SLAM combines low-level visual features and object detection to achieve robust, scalable long-term SLAM capable of maintaining accurate localization despite environmental changes over multiple deployments.

Contribution

It introduces a novel SLAM system that integrates visual odometry with an uncertainty-aware persistent object map for long-term consistency.

Findings

Achieves accurate long-term localization across diverse environmental conditions.

Maintains a compact map size suitable for long-term deployments.

Demonstrates robustness over 16 deployment sessions with varying weather and lighting.

Abstract

Robots responsible for tasks over long time scales must be able to localize consistently and scalably amid geometric, viewpoint, and appearance changes. Existing visual SLAM approaches rely on low-level feature descriptors that are not robust to such environmental changes and result in large map sizes that scale poorly over long-term deployments. In contrast, object detections are robust to environmental variations and lead to more compact representations, but most object-based SLAM systems target short-term indoor deployments with close objects. In this paper, we introduce ObVi-SLAM to overcome these challenges by leveraging the best of both approaches. ObVi-SLAM uses low-level visual features for high-quality short-term visual odometry; and to ensure global, long-term consistency, ObVi-SLAM builds an uncertainty-aware long-term map of persistent objects and updates it after every deployment. By evaluating ObVi-SLAM on data from 16 deployment sessions spanning different weather and lighting conditions, we empirically show that ObVi-SLAM generates accurate localization estimates consistent over long-time scales in spite of varying appearance conditions.