FusedNet: End-to-End Mobile Robot Relocalization in Dynamic Large-Scale Scene
- 4 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4099-4105
Abstract
To improve robot relocalization accuracy in both static and dynamic environments, we introduce a novel network, FusedNet, which incorporates a cross-attention to fuse global and local image features for end-to-end relocalization. This approach relies solely on a monocular camera sensor that is fixed on the mobile robot, and directly predicts the absolute pose from the input RGB image. Additionally, we have collected a mobile robot relocalization dataset, termed moBotReloc, consisting of dynamic large-scale scenes, using the Unity 3D simulation platform and a real mobile robot. Through extensive experiments on 7Scenes and moBotReloc, we demonstrate that FusedNet achieves significant accuracy in 6-DoF camera relocalization in static scenes, and exhibits superior relocalization performance in dynamic large-scale scenes for mobile robot applications, outperforming existing end-to-end methods that rely solely on a single global or local feature.Keywords
Funding Information
- Guangdong Natural Science Fund-General Programme (2022A1515011234)
- University Key Projects Stablely
- Shenzhen Science and Technology Innovation Commission (WDZC20200821140447001)
- Tsinghua-Pudu Joint Research Center of Intelligent Service Robots
This publication has 27 references indexed in Scilit:
- FeatLoc: Absolute pose regressor for indoor 2D sparse features with simplistic view synthesizingISPRS Journal of Photogrammetry and Remote Sensing, 2022
- RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets2018
- InLoc: Indoor Visual Localization with Dense Matching and View Synthesis2018
- Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions2018
- Geometry-Aware Learning of Maps for Camera Localization2018
- Geometric Loss Functions for Camera Pose Regression with Deep Learning2017
- Learning to Navigate the Energy Landscape2016
- Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images2013
- Visual Place Recognition with Repetitive Structures2013
- All About VLAD2013