Experimental Comparison of Visual-Aided Odometry Methods for Rail Vehicles

Abstract

Today, rail vehicle localization is based on infrastructure-side Balises (beacons) together with on-board odometry to determine whether a rail segment is occupied. Such a coarse locking leads to a sub-optimal usage of the rail networks. New railway standards propose the use of moving blocks centered around the rail vehicles to increase the capacity of the network. However, this approach requires accurate and robust position and velocity estimation of all vehicles. In this work, we investigate the applicability, challenges and limitations of current visual and visual-inertial motion estimation frameworks for rail applications. An evaluation against RTK-GPS ground truth is performed on multiple datasets recorded in industrial, sub-urban, and forest environments. Our results show that stereo visual-inertial odometry has a great potential to provide a precise motion estimation because of its complementing sensor modalities and shows superior performance in challenging situations compared to other frameworks.

References in corpus (9)

• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
• Visual-Inertial Monocular SLAM with Map Reuse
• maplab: An Open Framework for Research in Visual-inertial Mapping and Localization
• Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization
• Visual-inertial self-calibration on informative motion segments
• Robust Odometry using Sensor Consensus Analysis
• Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments

Cited by in corpus (9)

• IDOL: A Framework for IMU-DVS Odometry using Lines
• VersaVIS: An Open Versatile Multi-Camera Visual-Inertial Sensor Suite
• Hough2Map -- Iterative Event-based Hough Transform for High-Speed Railway Mapping
• The Autonomous Siemens Tram
• Four years of multi-modal odometry and mapping on the rail vehicles
• Superquadric Object Representation for Optimization-based Semantic SLAM
• RailLoMer: Rail Vehicle Localization and Mapping with LiDAR-IMU-Odometer-GNSS Data Fusion
• Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning
• Optical Navigation in Unstructured Dynamic Railroad Environments