We introduce a new statistical modelling technique for building occupancy maps. The problem of mapping is addressed as a classification task where the robot's environment is classified into regions of occupancy and free space. This is obtained by employing a modified Gaussian process as a non-parametric Bayesian learning technique to exploit the fact that realworld environments inherently possess structure. This structure introduces dependencies between points on the map which are not accounted for by many common mapping techniques such as occupancy grids. Our approach is an 'anytime' algorithm that is capable of generating accurate representations of large environments at arbitrary resolutions to suit many applications. It also provides inferences with associated variances into occluded regions and between sensor beams, even with relatively few observations. Crucially, the technique can handle noisy data, potentially from multiple sources, and fuse it into a robust common probabilistic representation of the robot's surroundings. We demonstrate the benefits of our approach on simulated datasets with known ground truth and in outdoor urban environments.

Knowing the patterns of distribution of sediments in the global ocean is critical for understanding biogeochemical cycles and how deep-sea deposits respond to environmental change at the sea surface. We present the first digital map of seafloor lithologies based on descriptions of nearly 14,500 samples from original cruise reports, interpolated using a support vector machine algorithm. We show that sediment distribution is more complex, with significant deviations from earlier hand-drawn maps, and that major lithologies occur in drastically different proportions globally. By coupling our digital map to oceanographic data sets, we find that the global occurrence of biogenic oozes is strongly linked to specific ranges in seasurface parameters. In particular, by using recent computations of diatom distributions from pigment-calibrated chlorophyll-a satellite data, we show that, contrary to a widely held view, diatom oozes are not a reliable proxy for surface productivity. Their global accumulation is instead strongly dependent on low surface temperature (0.9-5.7 °C) and salinity (33.8-34.0 PSS, Practical Salinity Scale 1978) and high concentrations of nutrients. Under these conditions, diatom oozes will accumulate on the seafloor regardless of surface productivity as long as there is limited competition from biogenous and detrital components, and diatom frustules are not significantly dissolved prior to preservation. Quantifying the link between the seafloor and the sea surface through the use of large digital data sets will ultimately lead to more robust reconstructions and predictions of climate change and its impact on the ocean environment.

Abstract-Observing human motion patterns is informative for social robots that share the environment with people. This paper presents a methodology to allow a robot to navigate in a complex environment by observing pedestrian positional traces. A continuous probabilistic function is determined using Gaussian process learning and used to infer the direction a robot should take in different parts of the environment. The approach learns and filters noise in the data producing a smooth underlying function that yields more natural movements. Our method combines prior conventional planning strategies with most probable trajectories followed by people in a principled statistical manner, and adapts itself online as more observations become available. The use of learning methods are automatic and require minimal tuning as compared to potential fields or spline function regression. This approach is demonstrated testing in cluttered office and open forum environments using laser and vision sensing modalities. It yields paths that are similar to the expected human behaviour without any a priori knowledge of the environment or explicit programming.