In this paper we present a novel framework for unsupervised topological clustering resulting in improved loop detection and closure for SLAM. A navigating mobile robot clusters its traversal into visually similar topologies where each cluster (topology) contains a set of similar looking images typically observed from spatially adjacent locations. Each such set of spatially adjacent and visually similar grouping of images constitutes a topology obtained without any supervision. We formulate a hierarchical loop discovery strategy that first detects loops at the level of topologies and subsequently at the level of images between the looped topologies. We show over a number of traversals across different Habitat environments that such a hierarchical pipeline significantly improves SOTA image based loop detection and closure methods. Further, as a consequence of improved loop detection, we enhance the loop closure and backend SLAM performance. Such a rendering of a traversal into topological segments is beneficial for downstream tasks such as navigation that can now build a topological graph where spatially adjacent topological clusters are connected by an edge and navigate over such topological graphs.
Hierarchical Unsupervised Topological SLAM
24.09.2023
2086044 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Unsupervised learning to detect loops using deep neural networks for visual SLAM system
British Library Online Contents | 2017
|Real-Time Hierarchical Outdoor SLAM Based on Stereovision and GPS Fusion
Online Contents | 2009
|Hierarchical Bayesian models for unsupervised scene understanding
British Library Online Contents | 2015
|