Deep Visual Odometry Methods for Mobile Robots

Abstract

Technology has made navigation in 3D real time possible and this has made possible what seemed impossible. This paper explores the aspect of deep visual odometry methods for mobile robots. Visual odometry has been instrumental in making this navigation successful. Noticeable challenges in mobile robots including the inability to attain Simultaneous Localization and Mapping have been solved by visual odometry through its cameras which are suitable for human environments. More intuitive, precise and accurate detection have been made possible by visual odometry in mobile robots. Another challenge in the mobile robot world is the 3D map reconstruction for exploration. A dense map in mobile robots can facilitate for localization and more accurate findings.

References in corpus (8)

• DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
• Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots
• DeepVO: A Deep Learning approach for Monocular Visual Odometry
• Sparse-then-Dense Alignment based 3D Map Reconstruction Method for Endoscopic Capsule Robots
• A Deep Learning Based 6 Degree-of-Freedom Localization Method for Endoscopic Capsule Robots
• A fully dense and globally consistent 3D map reconstruction approach for GI tract to enhance therapeutic relevance of the endoscopic capsule robot
• Endo-VMFuseNet: Deep Visual-Magnetic Sensor Fusion Approach for Uncalibrated, Unsynchronized and Asymmetric Endoscopic Capsule Robot Localization Data
• Direct Monocular Odometry Using Points and Lines