On the limited memory BFGS method for large scale optimization
Mathematical Programming: Series A and B
Iterative point matching for registration of free-form curves and surfaces
International Journal of Computer Vision
Computation with infinite neural networks
Neural Computation
Bayesian Classification With Gaussian Processes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian Learning for Neural Networks
Bayesian Learning for Neural Networks
Improved Occupancy Grids for Map Building
Autonomous Robots
Tracking Multiple Moving Objects for Real-Time Robot Navigation
Autonomous Robots
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)
WiFi-SLAM using Gaussian process latent variable models
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Gaussian process modeling of large-scale terrain
Journal of Field Robotics - Three-Dimensional Mapping, Part 1
Contextual occupancy maps using Gaussian processes
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Some new results on neural network approximation
Neural Networks
| Hi-index | 0.00 |
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.