Related Experiment Video
Updated: Oct 27, 2025
11:53
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
Published on: October 14, 2017
11.9K
Self-Localization of Mobile Robots Using a Single Catadioptric Camera with Line Feature Extraction
Huei-Yung Lin1, Yuan-Chi Chung2, Ming-Liang Wang2
1Department of Electrical Engineering, Advanced Institute of Manufacturing with High-Tech Innovation, National Chung Cheng University, Chia-Yi 621, Taiwan.
Sensors (Basel, Switzerland)
|July 24, 2021
Summary
This study introduces a new self-localization method for mobile robots using a central catadioptric camera. The technique accurately computes 3D robot positions and trajectories from consecutive images for enhanced navigation.
Area of Science:
- Robotics
- Computer Vision
- Navigation Systems
Background:
- Mobile robot localization is crucial for autonomous navigation.
- Existing stereo vision techniques have limitations in depth computation.
- Catadioptric cameras offer a wide field of view for robot perception.
Purpose of the Study:
- To develop a novel self-localization technique for mobile robots.
- To leverage a central catadioptric camera for accurate 3D pose estimation.
- To enable robust robot navigation in unknown environments.
Main Methods:
- Calibrated a central catadioptric camera using a unified sphere model.
- Utilized geometric properties to project vertical lines onto the ground plane.
- Computed depth and 3D coordinates using plane equations and consecutive image frames.
- Developed a feature matching algorithm based on 3D structural invariance.
Main Results:
- Successfully derived 3D coordinates of base points on the ground plane.
- Calculated robot motion trajectories by computing rotation and translation between positions.
- Experimental results validated the feasibility of the proposed self-localization method.
Conclusions:
- The proposed self-localization technique is effective for mobile robots.
- The method provides accurate 3D pose estimation and trajectory derivation.
- This approach enhances mobile robot navigation capabilities.
