Regularized Maximum-Correntropy Criterion Kalman Filter for uncalibrated visual servoing in the presence of non-gaussian feature tracking noise

Monte Carlo experiments to test RMCKF with non-gaussian Kalman Filter based techniques. The first scenario compares the estimation algorithms in a simple feature translation task. The second scenario is harder than the first, because the robot starts at different configurations, requiring translation and rotation of the features. Whereas in previous scenarios, all techniques use simulated annealing, the third scenario evaluates the relevance of the simulated annealing approach for the kernel bandwidth, compared to tests with a fixed kernel bandwidth.