Mobile robot localization based on multi target tracking

In this article, a multi-sensor cooperation approach between an omnidirectional vision system and a panoramic range finder is presented. The aim is to localize dynamically a mobile robot. These two sensors provide some complementary and redundant data which enable to construct a robust sensorial model which integrates all important number of significant primitives. Based on this model, we treat the problem of maintaining a matching and propagating uncertainties on each matched primitive. Indeed, our localization method is based on the tracking of significant landmarks of the environment and integrates a multilevel uncertainty propagation stage based on the use of the Dempster-Shafer theory.