Multi-Platform Teach-and-Repeat Navigation by Visual Place Recognition Based on Deep-Learned Local Features
This work addresses the problem of reliable navigation for mobile robots in diverse environments, representing an incremental improvement with novel components in a specific domain.
The paper tackles the challenge of stable visual localization and mapping in uniform and variable environments for mobile robot navigation by introducing an appearance-based teach-and-repeat navigation system using visual place recognition. The results show that the new system outperforms existing state-of-the-art methods in several testing scenarios, operates indoors and outdoors, and is robust to day and night variations.
Uniform and variable environments still remain a challenge for stable visual localization and mapping in mobile robot navigation. One of the possible approaches suitable for such environments is appearance-based teach-and-repeat navigation, relying on simplified localization and reactive robot motion control - all without a need for standard mapping. This work brings an innovative solution to such a system based on visual place recognition techniques. Here, the major contributions stand in the employment of a new visual place recognition technique, a novel horizontal shift computation approach, and a multi-platform system design for applications across various types of mobile robots. Secondly, a new public dataset for experimental testing of appearance-based navigation methods is introduced. Moreover, the work also provides real-world experimental testing and performance comparison of the introduced navigation system against other state-of-the-art methods. The results confirm that the new system outperforms existing methods in several testing scenarios, is capable of operation indoors and outdoors, and exhibits robustness to day and night scene variations.