Miguel Ángel Sotelo Vázquez

Tracking multiple and dynamic objects with an extended particle filter and an adapted k-means clustering algorithm

The work presented is related to the research area of autonomous navigation for mobile robots in unstructured, heavy crowded and highly dynamic environments. One of the main involved tasks in this researching area is the obstacle tracking module that has been successfully developed with different kind of probabilistic algorithms. The reliability that these techniques have shown estimating position with noisy measurements make them the most adequate to the mentioned problem, but their high computational cost has made them only useful with few and structured objects. In this paper a computational simple solution based on a multimodal (or extended) particle filter is proposed to track multiple and dynamic obstacles in an unstructured environment and based on the noisy position measurements taken from sonar sensors.