학술논문

Multi robot SLAM for features based environment modelling
Document Type
Conference
Source
2014 IEEE International Conference on Mechatronics and Automation Mechatronics and Automation (ICMA), 2014 IEEE International Conference on. :711-716 Aug, 2014
Subject
Bioengineering
Components, Circuits, Devices and Systems
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Simultaneous localization and mapping
Cameras
Robot vision systems
Lasers
Feature extraction
EKF SLAM
MonoSLAM
features extraction
RBPF SLAM
Language
ISSN
2152-7431
2152-744X
Abstract
This paper is presenting a multi robot simultaneous localization and mapping (SLAM) framework for environment modelling using 2D and 3D features. The proposed solution is using a team of mobile robots which are exploring unknown environment with unknown poses. Each team member is allowed to build its independent features based SLAM solution and to share the local map model among other mates. By matching the overlapping tendency of any two mates, a map merging strategy is introduced which in result is building global map. The overall approach has tested in 2D and 3D features based environment and results have shown.