Some new results on neural network approximation
Neural Networks
Iterative point matching for registration of free-form curves and surfaces
International Journal of Computer Vision
Learning metric-topological maps for indoor mobile robot navigation
Artificial Intelligence
Artificial intelligence and mobile robots
Computation with infinite neural networks
Neural Computation
Bayesian Learning for Neural Networks
Bayesian Learning for Neural Networks
Improved Occupancy Grids for Map Building
Autonomous Robots
An Evidential Approach to Probabilistic Map-Building
RUR '95 Proceedings of the International Workshop on Reasoning with Uncertainty in Robotics
Occupancy grids: a probabilistic framework for robot perception and navigation
Occupancy grids: a probabilistic framework for robot perception and navigation
Learning Occupancy Grid Maps with Forward Sensor Models
Autonomous Robots
Information Theory, Inference & Learning Algorithms
Information Theory, Inference & Learning Algorithms
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Probabilistic multi-level maps from LIDAR data
International Journal of Robotics Research
Gaussian process occupancy maps*
International Journal of Robotics Research
Semi-parametric learning for visual odometry
International Journal of Robotics Research
Hi-index | 0.00 |
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 robot's environment is classified into regions of occupancy and unoccupancy. Our model provides both a continuous representation of the robot's 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.