Implementation and optimization of ORB-SLAM2 algorithm based on ROS on mobile robots

Guimao Zhang; Bo Liu; Zhihong Liang

doi:10.1117/12.2675118

25 May 2023 Implementation and optimization of ORB-SLAM2 algorithm based on ROS on mobile robots

Guimao Zhang, Bo Liu, Zhihong Liang

Proceedings Volume 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022); 126364M (2023) https://doi.org/10.1117/12.2675118
Event: Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 2022, Shenyang, China

Abstract

ORB-SLAM2 based on depth camera cannot run directly in ROS operating system, and when the algorithm is implemented through PC, it does not efficiently carry computer resources, and reduces the flexibility of mobile robots. By building a ROS operating system in the embedded system, porting the ORB-SLAM2 algorithm in the system, optimizing the algorithm, adjusting the CPU usage of the algorithm operation, and using a mobile robot based on depth camera for mapping. The results show that the grid map generated by the ROS operating system can meet the needs of robot autonomous navigation, the SLAM effect is more intuitive, the system is more flexible, and the cost and hardware configuration requirements are greatly reduced. It is proved that the optimized algorithm is closer to the actual usage requirements.

Citation Download Citation

Guimao Zhang, Bo Liu, and Zhihong Liang "Implementation and optimization of ORB-SLAM2 algorithm based on ROS on mobile robots", Proc. SPIE 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 126364M (25 May 2023); https://doi.org/10.1117/12.2675118

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available