noeperez
commented
2 years ago Hello,
the ideas implemented here are very basic, so they are not based on any paper. We just perform a very very simple clustering of the points of the laser scan. Then, we discard some of the clusters based on the number of points. Finally, we use a Kalman Filter to track the clusters, so that we follow only the clusters (dynamic obstacles) that exceed a minimum-velocity threshold. If you are interested, you could take a look to different clustering algorithm that could be applied, and the theory behind Kalman Filters.
I would like to ask, what is the basic principle of the implementation of the function package? Do you have any relevant papers or materials to recommend? Thank you！