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

CardsList

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

  1. FastTrack: GPU-Accelerated Tracking for Visual SLAM

    Sep 13, 2025Kimia Khabiri, Parsa Hosseininejad, Shishir Gopinath +2GPU AccelerationVisual SLAM