Simon Timothy O'Callaghan

Gaussian process occupancy maps

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 real-world 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.

Contextual occupancy maps using Gaussian processes

In this paper we introduce a new statistical modeling technique for building occupancy maps. The problem of mapping is addressed as a classification task where the robots environment is classified into regions of occupancy and unoccupancy. Our model provides both a continuous representation of the robots surroundings and an associated predictive variance. This is obtained by employing a Gaussian process as a non-parametric Bayesian learning technique to exploit the fact that real-world environments inherently possess structure. This structure introduces a correlation between points on the map which is not accounted for by many common mapping techniques such as occupancy grids. Using a trained neural network covariance function to model the highly non-stationary datasets, it is possible to generate accurate representations of large environments at resolutions which suit the desired applications while also providing inferences into occluded regions, between beams, and beyond the range of the sensor, even with relatively few sensor readings. We demonstrate the benefits of our approach in a simulated data set with known ground-truth, and in an outdoor urban environment covering an area of 120,000 m2.

Learning navigational maps by observing human motion patterns

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.

Contextual occupancy maps incorporating sensor and location uncertainty

This paper describes a method of incorporating sensor and localisation uncertainty into contextual occupancy maps to provide for robust mapping. This paper builds on a recently proposed application of the Gaussian process (GP) to occupancy mapping. An extension of GPs is employed which incorporates uncertain inputs into the covariance function. In turn, this allows statistically consistent, multi-resolution maps to be constructed which exploit the spatial inference properties of GPs while correctly accounting for sensor and localisation errors. Experiments are described, with both synthetic and real data, which show the benefits of complete uncertainty modeling and how contextual occupancy maps may be constructed by fusing data from different sensors on different robots in a common probabilistic representation.

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.

Learning highly dynamic environments with stochastic variational inference

Understanding the dynamics of urban environments is crucial for path planning and safe navigation. However, the dynamics might be extremely complex making learning the environment an unfathomable task. Within the methods available for learning dynamic environments, dynamic Gaussian process occupancy maps (DGPOM) are very attractive because they can produce spatially-continuous occupancy maps taking into account neighborhood information, and provide probabilistic estimates, naturally inferring the uncertainty of predictions. Despite these properties, they are extremely slow, especially in dynamic mapping where the parameters of the map have to be updated as new data arrive from range sensors such as LiDARs. In this work, we leverage recent advancements in stochastic variational inference (SVI) to quickly learn dynamic areas in an online fashion. Further, we propose an information-driven technique to “intelligently” select inducing points required for SVI without relying on any object trackers which essentially improves computational time as well as robustness. These long-term occupancy maps entertain all attractive properties of DGPOM while the learning process is significantly faster, yet accurate. Our experiments with both simulation and real robot data on road intersections show a significant improvement in speed while maintaining a comparable or better accuracy.