Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
doc:environment_map_meta_information [2014/06/05 11:38]
127.0.0.1 external edit
doc:environment_map_meta_information [2014/12/07 08:57] (current)
admin
Line 1: Line 1:
 ====== Meta-information about environment maps ====== ====== Meta-information about environment maps ======
 ~~NOTOC~~ ~~NOTOC~~
-In particular in the context of the RoboEarth project, which deals with the exchange of knowledge between robots, ​robots face the problem how to represent which environment is described in a map in such a way that robots ​can query for a map and retrieve the right one? The following approach has been chosen in the RoboEarth context:+ 
 +Robots sometimes face the problem how to represent which environment is described inside a map. In the context of the RoboEarth project, which dealt with the exchange of knowledge between robots, ​this was required ​to enable ​robots ​to query for a map based on a specification of which environment it describes. ​The following approach has been chosen in the RoboEarth context:
   * Hierarchical,​ symbolic description similar to human-readable addresses: Country, city, street, building, floor, room (described by room number or room type)   * Hierarchical,​ symbolic description similar to human-readable addresses: Country, city, street, building, floor, room (described by room number or room type)
-  * These upper-level categories are described as instances (e.g. Munich as instance of City) which are linked by the transitive properPhysicalParts-relation +  * These upper-level categories are described as instances (e.g. Munich as instance of City) which are linked by the transitive properPhysicalParts-relation. This effectively extends the hierarchical structure intrinsic of semantic maps (map -> objects -> object parts). 
-  * This allows to query based on a conjunction of class restrictions,​ e.g. for a room 3006 in a building in Karlstrasse in Munich.+  * The representation ​allows to query based on a conjunction of class restrictions,​ e.g. for a room 3006 in a building in Karlstrasse in Munich.
  
 {{ :​map-representations.png?​nolink&​ |}} {{ :​map-representations.png?​nolink&​ |}}
  
-There can be multiple maps describing the same environment in different ways, for example a 2D occupancy grid, used e.g. for laser-based localization,​ or a semantic environment map, consisting of object instances and their properties. These can all be assigned to the same room/​floor/​building,​ and the downloading robot can decide which one to use based on its properties and requirements.+There can be multiple maps describing the same environment in possibly ​different ways, for example a 2D occupancy grid, used e.g. for laser-based localization,​ or a semantic environment map, consisting of object instances and their properties. These can all be assigned to the same room/​floor/​building,​ and the downloading robot can decide which one to use based on its properties and requirements. 
 + 
  
 ====== ​ Objects in the map  ====== ====== ​ Objects in the map  ======
Line 78: Line 81:
     owl_has(R, knowrob:​roomNumber,​ literal(type(_,​ '​3001'​))), ​     owl_has(R, knowrob:​roomNumber,​ literal(type(_,​ '​3001'​))), ​
     owl_has(R, knowrob:​describedInMap,​ Map).     owl_has(R, knowrob:​describedInMap,​ Map).
- M = '​http://​ias.cs.tum.edu/​kb/​ias_hospital_room.owl#​Munich',​ + M = '​http://​knowrob.org/​kb/​ias_hospital_room.owl#​Munich',​ 
- R = '​http://​ias.cs.tum.edu/​kb/​ias_hospital_room.owl#​Room7635',​ + R = '​http://​knowrob.org/​kb/​ias_hospital_room.owl#​Room7635',​ 
- Map = '​http://​ias.cs.tum.edu/​kb/​ias_hospital_room.owl#​SemanticEnvironmentMap7635'​+ Map = '​http://​knowrob.org/​kb/​ias_hospital_room.owl#​SemanticEnvironmentMap7635'​
 </​code>​ </​code>​