Expectation-Maximization for Adaptive Mixture Models in Graph Optimization
This addresses robust sensor fusion for applications like GNSS and indoor localization, with incremental improvements in parametrization.
The paper tackles the problem of robust sensor fusion by proposing an adaptive mixture model to approximate real error distributions, outperforming state-of-the-art static parametrization approaches on GNSS and indoor localization datasets.
Non-Gaussian and multimodal distributions are an important part of many recent robust sensor fusion algorithms. In difference to robust cost functions, they are probabilistically founded and have good convergence properties. Since their robustness depends on a close approximation of the real error distribution, their parametrization is crucial. We propose a novel approach that allows to adapt a multi-modal Gaussian mixture model to the error distribution of a sensor fusion problem. By combining expectation-maximization and non-linear least squares optimization, we are able to provide a computationally efficient solution with well-behaved convergence properties. We demonstrate the performance of these algorithms on several real-world GNSS and indoor localization datasets. The proposed adaptive mixture algorithm outperforms state-of-the-art approaches with static parametrization. Source code and datasets are available under https://mytuc.org/libRSF.