Probabilistic ego-motion estimation using multiple automotive radar sensors

For automotive applications, an accurate estimation of the ego-motion is required to make advanced driver assistant systems work reliably. The proposed framework for ego-motion estimation involves two components: The first component is the spatial registration of consecutive scans. In this paper, the reference scan is represented by a sparse Gaussian Mixture model. This structural representation is improved by incorporating clustering algorithms. For the spatial matching of consecutive scans, a normal distributions transform-based optimization is used. The second component is a likelihood model for the Doppler velocity. Using a hypothesis for the ego-motion state, the expected radial velocity can be calculated and compared to the actual measured Doppler velocity. The ego-motion estimation framework of this paper is a joint spatial and Doppler-based optimization function which shows reliable performance on real world data and compared to state-of-the-art algorithms.