RWT-SLAM: Robust Visual SLAM for Highly Weak-textured Environments
This addresses a specific problem for intelligent robots operating in low-texture settings, representing an incremental improvement over existing methods.
The paper tackles the challenge of robust visual SLAM in highly weak-textured environments by proposing RWT-SLAM, which modifies the LoFTR network for dense point matching and integrates it into ORB-SLAM with feature masks and KNN strategies, showing promising performance on datasets like TUM and OpenLORIS.
As a fundamental task for intelligent robots, visual SLAM has made great progress over the past decades. However, robust SLAM under highly weak-textured environments still remains very challenging. In this paper, we propose a novel visual SLAM system named RWT-SLAM to tackle this problem. We modify LoFTR network which is able to produce dense point matching under low-textured scenes to generate feature descriptors. To integrate the new features into the popular ORB-SLAM framework, we develop feature masks to filter out the unreliable features and employ KNN strategy to strengthen the matching robustness. We also retrained visual vocabulary upon new descriptors for efficient loop closing. The resulting RWT-SLAM is tested in various public datasets such as TUM and OpenLORIS, as well as our own data. The results shows very promising performance under highly weak-textured environments.