PRISM-TopoMap: Online Topological Mapping With Place Recognition and Scan Matching

Mapping is one of the crucial tasks enabling autonomous navigation of a mobile robot. Conventional mapping methods output a dense geometric map representation, e.g. an occupancy grid, which is not trivial to keep consistent for prolonged runs covering large environments. Meanwhile, capturing the topological structure of the workspace enables fast path planning, is typically less prone to odometry error accumulation, and does not consume much memory. Following this idea, this letter introduces PRISM-TopoMap – a topological mapping method that maintains a graph of locally aligned locations not relying on global metric coordinates. The proposed method involves original learnable multimodal place recognition paired with the scan matching pipeline for localization and loop closure in the graph of locations. The latter is updated online, and the robot is localized in a proper node at each time step. We conduct a broad experimental evaluation of the suggested approach in a range of photo-realistic environments and on a real robot, and compare it to state of the art. The results of the empirical evaluation confirm that PRISM-Topomap consistently outperforms competitors computationally-wise, achieves high mapping quality and performs well on a real robot.

I. Introduction

Building an accurate map of the environment is crucial for mobile robots navigation. Common mapping methods such as RTAB-Map [1] or Cartographer [2] build maps as dense metric structures like occupancy grids or point clouds. However, such dense metric maps require significant memory for maintenance and optimization, which can potentially lead to memory overflow when the robot navigates large environments [3]. Coupled with odometry error accumulation, this may cause mapping and loop closure failures with map size growth.