Gaussian Process Occupancy Maps for Dynamic Environments

We present a continuous Bayesian occupancy representation for dynamic environments. The method builds on Gaussian processes classifiers and addresses the main limitations of occupancy grids such as the need to discretise the space, strong assumptions of independence between cells, and difficulty to represent occupancy in dynamic environments. We develop a novel covariance function (or kernel) to capture space and time statistical dependencies given a motion map of the environment. This enables the model to perform predictions on how the occupancy state of the environment will be in the future given past observations. We show results on a simulated environment with multiple dynamic objects, and on a busy urban intersection.