Spatial tessellations: concepts and applications of Voronoi diagrams
Spatial tessellations: concepts and applications of Voronoi diagrams
Learning metric-topological maps for indoor mobile robot navigation
Artificial Intelligence
Rapid Concept Learning for Mobile Robots
Machine Learning - Special issue on learning in autonomous robots
Bayesian Landmark Learning for Mobile Robot Localization
Machine Learning
Hidden Markov Models for Speech Recognition
Hidden Markov Models for Speech Recognition
Automatic Mapping of Dynamic Office Environments
Autonomous Robots
On convergence properties of the em algorithm for gaussian mixtures
Neural Computation
Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
| Hi-index | 0.00 |
This article presents a new algorithm to recognize natural distinctive places such as corridors, halls, narrowings, corridors with doors opening on the left side, etc., from indoor environments using Hidden Markov Models (HMM). HMM give a stochastic solution which can be used to make decisions on localization, navigation and path-planning. The environment is modeled as a topo-geometric map which combines topological and geometric information. This map is obtained from a Voronoi diagram using measurements of a laser telemeter. The characteristics of topo-geometric map (nodes, number of edges adjacent to nodes, slope of edges, etc.) are used to learn and to recognize the different places typical of indoor environments. This map can be used in order to resolve several problems in robotics such as localization, navigation and path-planning. Our method of place recognition is a fast and effective way for a robot to recognize typical places of indoor environments from a topo-geometric map.