This paper presents new methods for the representation of a vehicle's contour by an oriented rectangle, also known as the bounding box. The parameters of this bounding box are originally modeled probabilistically by a single multivariate Gaussian distribution. This approach incorporates the sensor uncertainties, where the problem of estimating the parameters of this distribution from range measurements is addressed. Additionally, a transformation of the parameters into the measurement space is introduced. This representation is used to perform probabilistic updates by new measurements. The proposed method can handle strong parameter changes which might be affected by object occlusion. Experiments on real-world data demonstrate the robustness and accuracy of the probabilistic approach integrated in a tracking framework incorporating the Doppler measurements of automotive radars and laser measurements.

Grid map registration is an important field in mobile robotics. Applications in which multiple robots are involved benefit from multiple aligned grid maps as they provide an efficient exploration of the environment in parallel. In this paper, a normal distribution transform (NDT)-based approach for grid map registration is presented. For simultaneous mapping and localization approaches on laser data, the NDT is widely used to align new laser scans to reference scans. The original grid quantization-based NDT results in good registration performances but has poor convergence properties due to discontinuities of the optimization function and absolute grid resolution. This paper shows that clustering techniques overcome disadvantages of the original NDT by significantly improving the convergence basin for aligning grid maps. A multi-scale clustering method results in an improved registration performance which is shown on real world experiments on radar data.