Visual-Inertial SLAM

SLAM: Simultaneous Localization and Mapping

Overview

Visual-inertial SLAM uses camera images and inertial measurements to track a robot’s motion while building a map, helping it navigate when GPS is unavailable. Systems commonly combine feature tracking or learned visual front ends with filtering or sliding-window optimization, bundle adjustment, and loop closure; newer approaches also use event cameras, multiple cameras, and learned depth or scene representations. Benchmarks such as EuRoC and TUM-VI test trajectory accuracy, while real-world settings including UAV flights, construction sites, forests, and underwater environments expose different sensing challenges. A central tension is balancing accuracy and robustness to motion, poor lighting, textureless or dynamic scenes, and sensor failures against limited onboard computation and power.

Latest papers

31 papers2 papers in the last four weeks, down 78% on the four weeks before. 0.0% of all new papers.

Sep 13, 2025

FastTrack: GPU-Accelerated Tracking for Visual SLAM

The tracking module of a visual-inertial SLAM system processes incoming image frames and IMU data to estimate the position of the frame in relation to the map. It is important for the tracking to complete in a timely manner for each frame to avoid poor localization or tracking loss. We therefore present a new approach which leverages GPU computing power to accelerate time-consuming components of tracking in order to improve its performance. These components include stereo feature matching and local map tracking. We implement our design inside the ORB-SLAM3 tracking process using CUDA. Our evaluation demonstrates an overall improvement in tracking performance of up to 2.8x on a desktop and Jetson Xavier NX board in stereo-inertial mode, using the well-known SLAM datasets EuRoC and TUM-VI.