Learning Continuous Occupancy Maps with the Ising Process Model
This work addresses the need for efficient continuous occupancy mapping in robotics, offering an incremental improvement over existing methods by reducing computational cost and hyperparameter complexity.
The authors tackled the problem of learning continuous occupancy maps for robot navigation by generalizing the Ising model and introducing a unique kernel for range measurements, resulting in a computationally efficient method with few hyperparameters that was demonstrated on simulated and real datasets.
We present a new method of learning a continuous occupancy field for use in robot navigation. Occupancy grid maps, or variants of, are possibly the most widely used and accepted method of building a map of a robot's environment. Various methods have been developed to learn continuous occupancy maps and have successfully resolved many of the shortcomings of grid mapping, namely, priori discretisation and spatial correlation. However, most methods for producing a continuous occupancy field remain computationally expensive or heuristic in nature. Our method explores a generalisation of the so-called Ising model as a suitable candidate for modelling an occupancy field. We also present a unique kernel for use within our method that models range measurements. The method is quite attractive as it requires only a small number of hyperparameters to be trained, and is computationally efficient. The small number of hyperparameters can be quickly learned by maximising a pseudo likelihood. The technique is demonstrated on both a small simulated indoor environment with known ground truth as well as large indoor and outdoor areas, using two common real data sets.