FC-SLAM: Federated Learning Enhanced Distributed Visual-LiDAR SLAM In Cloud Robotic System

SLAM has shown great values in many fields such as self-driving cars, virtual reality and robotic localization, etc. Cloud robot based collaborative SLAM can effectively improve the efficiency of mapping tasks. However, place recognition and matching accuracy among different robots can greatly affect the map fusion performance of the entire SLAM system. Therefore, this paper presents a learning architecture for cooperative SLAM named FC-SLAM, a distributed SLAM in cloud robotic systems by taking advantage of federated learning to enhance the performance of visual-LiDAR SLAM. Additionally, we propose a federated deep learning algorithm for feature extraction and dynamic vocabulary designation which works in real-time on cloud workstation. FC-SLAM can ensure real-time collaborative SLAM by keep the original images on robot side instead of sending them to the cloud server. We test our system on open datasets and in simulated environment. The results show that it has better feature extraction performance than SIFT and ORB under illumination and viewpoint changes. Besides, map fusion is conducted to generate a global map according to place matching relation of distributed robots.