Research ArticleNew validation algorithm for data association in SLAM

- A novel algorithm for data validation in SLAM robotics is proposed.
- The algorithm checks for the compatibility of matches based in a quality metric distance.
- The C++ implementation gives better execution times than other validation techniques.
- All the experiments have been carried out with real data meeting real-time constraints at 15 fps.
- The proposed data validation algorithm is more efficient than previous approaches.

In this work, a novel data validation algorithm for a single-camera SLAM system is introduced. A 6-degree-of-freedom monocular SLAM method based on the delayed inverse-depth (DI-D) feature initialization is used as a benchmark. This SLAM methodology has been improved with the introduction of the proposed data association batch validation technique, the highest order hypothesis compatibility test, HOHCT. This new algorithm is based on the evaluation of statistically compatible hypotheses, and a search algorithm designed to exploit the characteristics of delayed inverse-depth technique. In order to show the capabilities of the proposed technique, experimental tests have been compared with classical methods. The results of the proposed technique outperformed the results of the classical approaches.