This paper improves the most widely used nearest neighbor method in SLAM data association, and uses the Euclidean distance calculation between the feature estimated position and the carrier predicted position to replace the Mahalanobis distance calculation between all features and each measurement, avoiding a large number of matrix multiplication calculations. The algorithm is simple and easy to implement, reduces the computational complexity of the algorithm, is conducive to the real-time execution of the SLAM algorithm, and the association effect is the same as the global nearest neighbor method.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore