A Vision Based Multi-robot Cooperative Semantic SLAM Algorithm

Abstract

The large-scale environmental SLAM which is based on visual information, is an important technical field of mobile robot application. However, a single robot is difficult to achieve the semantic SLAM tasks because of the limited sensing range and the low computing efficiency. This problem can be effectively solved by multi-robot cooperation that is using their collected visual information to model together. In this paper, a vision based multi-robot cooperative semantic SLAM algorithm is proposed. Moreover, to achieve the distributed map splicing that is constructed by several heterogeneous robot, a cloud computing method is also proposed detailedly. Besides, to satisfy the demand of low bandwidth and data transmission between robots and cloud, a high density information representation and a transmission strategy against spatiotemporal delay are designed. On this basis, the LEDNET model is used to obtain the semantic information of environmental feature points. Then, the centroid of map points is obtained to calculate the position information of objects in the environment, the attitude information of objects in the environment is determined by principal component analysis, and a multi map stitching method based on key frame is established to realize the collaborative slam of multi robots. Through the map mosaic test of three robots on KITTI data set, the multi-robot cooperative SLAM algorithm proposed in this paper can quickly and accurately construct the semantic map of large-scale environment.