1. Visually-guided robot navigation: From artificial to natural landmarks
- Author
-
Celaya, Enric, Albarral García, José Luís, Jiménez Schlegl, Pablo, Torras, Carme, Ministerio de Ciencia y Tecnología (España), European Commission, Institut de Robòtica i Informàtica Industrial, Institut de Robòtica i Informàtica Industrial (IRI), Consejo Superior de Investigaciones Científicas [Madrid] (CSIC)-Universitat Politècnica de Catalunya [Barcelona] (UPC), Universitat Politècnica de Catalunya. KRD - Cinemàtica i Disseny de Robots, Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI, and Documentation, Inria Rhône-Alpes
- Subjects
0209 industrial biotechnology ,Informàtica::Automàtica i control [Àrees temàtiques de la UPC] ,Computer science ,Navigation task ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,02 engineering and technology ,Bottleneck ,Automation ,020901 industrial engineering & automation ,0202 electrical engineering, electronic engineering, information engineering ,Turn-by-turn navigation ,[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO] ,Computer vision ,Legged robot ,Automatització ,Landmark ,business.industry ,Salient region ,ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.9: Robotics ,[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO] ,Navigation system ,Mobile robot navigation ,Salient ,Robot ,Input pixel ,020201 artificial intelligence & image processing ,Artificial intelligence ,Automation [Classificació INSPEC] ,Mahalanobis distance ,Legged tobot ,business - Abstract
Presentado a la 6th International Conference on Field and Service Robotics (FSR) celebrada en 2007 en Chamonix (Francia)., Landmark-based navigation in unknown unstructured environments is far from solved. The bottleneck nowadays seems to be the fast detection of reliable visual references in the image stream as the robot moves. In our research, we have decoupled the navigation issues from this visual bottleneck, by first using artificial landmarks that could be easily detected and identified. Once we had a navigation system working, we developed a strategy to detect and track salient regions along image streams by just performing on-line pixel sampling. This strategy continuously updates the mean and covariances of the salient regions, as well as creates, deletes and merges regions according to the sample flow. Regions detected as salient can be considered as potential landmarks to be used in the navigation task., This work was supported by projects: 'Sistema reconfigurable para la navegación basada en visión de robots caminantes y rodantes en entornos naturales.' (00), 'Perception, action & cognition through learning of object-action complexes.' (4915)., This work has been supported by the Spanish Ministerio de Ciencia y Tecnología and FEDER under the project SIRVENT (DPI2003-05193-C02-01), as well as the European Union under the project PACO-PLUS (FP6-2004-IST-4-27657).
- Published
- 2007