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

2024-04-02

arXiv.org

AI Summary

To address poor map consistency, accumulated odometry drift, and high memory overhead in long-duration, large-scale autonomous navigation, this paper proposes an online topological mapping framework. It abandons global metric coordinates and instead constructs a lightweight, robust locally aligned pose graph. We introduce the first learnable multimodal place recognition mechanism synergistically integrated with laser scan matching (ICP/NDT), enabling end-to-end feature matching and geometric calibration. Combined with graph optimization and incremental topological updates, the framework supports real-time localization, loop closure detection, and dynamic graph evolution. Extensive evaluations on both simulation and real-world robotic platforms demonstrate that our method outperforms state-of-the-art approaches in mapping accuracy, computational efficiency, and memory footprint. The implementation is open-sourced and has been validated in practical deployment.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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 paper 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. The code of PRISM-Topomap is open-sourced and is available at: https://github.com/kirillMouraviev/prism-topomap.

Problem

• Develops online topological mapping for robots
• Integrates place recognition and scan matching
• Ensures consistent mapping in large environments

Innovation

• Online topological mapping
• Learnable multimodal recognition
• Scan matching pipeline