Poisson Multi-Bernoulli Mapping Using Gibbs Sampling
This work addresses the mapping problem for robotics or autonomous systems, offering an incremental improvement by extending existing methods with a novel Gibbs sampling approach for more efficient posterior sampling.
This paper tackles the mapping problem by deriving the exact theoretical batch multi-object posterior density for landmarks modeled as extended objects, using a Poisson process prior and measurements as a conditioned Poisson process, and proposes a Gibbs sampling algorithm to sample from this posterior. The method outperforms a state-of-the-art approach on synthetic data, handling uncertainties in data associations and landmark cardinality while being parallelizable for large-scale applications.
This paper addresses the mapping problem. Using a conjugate prior form, we derive the exact theoretical batch multi-object posterior density of the map given a set of measurements. The landmarks in the map are modeled as extended objects, and the measurements are described as a Poisson process, conditioned on the map. We use a Poisson process prior on the map and prove that the posterior distribution is a hybrid Poisson, multi-Bernoulli mixture distribution. We devise a Gibbs sampling algorithm to sample from the batch multi-object posterior. The proposed method can handle uncertainties in the data associations and the cardinality of the set of landmarks, and is parallelizable, making it suitable for large-scale problems. The performance of the proposed method is evaluated on synthetic data and is shown to outperform a state-of-the-art method.