Fast and Robust Teach-and-Repeat Navigation Using MixVPR Visual Place Recognition*

📅 2026-10-07
📈 Citations: 0
✨ Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the high computational overhead and deployment challenges of existing deep learning-based visual navigation systems on resource-constrained robotic platforms. To this end, we propose a lightweight "teach-and-repeat" navigation architecture that integrates MixVPR-based visual place recognition with efficient mobile robot navigation algorithms. This approach achieves robust localization across complex indoor and outdoor environments while effectively balancing positioning accuracy with computational efficiency. Experimental results demonstrate that the proposed system delivers navigation performance comparable to state-of-the-art methods while significantly reducing hardware dependencies and resource consumption. Furthermore, it exhibits strong cross-platform adaptability and substantial practical engineering value for real-world robotic applications.
📝 Abstract
Teach-and-repeat navigation systems employing advanced visual place recognition techniques for localization exhibit key attributes for long-term mobile robot navigation, such as the ability to operate in unstructured and dynamic environments. However, existing solutions based on deep-learning techniques are computationally demanding, limiting their applicability. This work introduces a novel and efficient teach-and-repeat system built on the modern visual place recognition method MixVPR. Real-world testing demonstrated its ability to operate both indoors and outdoors, achieving robustness and navigation precision comparable to other state-of-the-art systems. In addition, its lower hardware requirements make it suitable for a wide range of robotic platforms and practical applications.
Problem

Research questions and friction points this paper is trying to address.

Teach-and-Repeat Navigation
Visual Place Recognition
Computational Efficiency
Mobile Robot Navigation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Teach-and-Repeat Navigation
Visual Place Recognition
MixVPR
Computational Efficiency
Mobile Robot Localization
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
V
Václav Truhlařík
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague; and Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague
Tomáš Pivoňka
Tomáš Pivoňka
Researcher, Czech Technical Universiy in Prague
RoboticsComputer Vision
L
Libor Přeučil
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague