Real-time localisation and mapping with wearable active vision
We present a general method for real-time, vision-only single-camera simultaneous localisation and mapping (SLAM) - an algorithm which is applicable to the localisation of any camera moving through a scene - and study its application to the localisation of a wearable robot with active vision. Starti...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2003
|
| _version_ | 1826264348515893248 |
|---|---|
| author | Davison, A Mayol, W Murray, D SOCIETY, IC SOCIETY, IC |
| author_facet | Davison, A Mayol, W Murray, D SOCIETY, IC SOCIETY, IC |
| author_sort | Davison, A |
| collection | OXFORD |
| description | We present a general method for real-time, vision-only single-camera simultaneous localisation and mapping (SLAM) - an algorithm which is applicable to the localisation of any camera moving through a scene - and study its application to the localisation of a wearable robot with active vision. Starting from very sparse initial scene knowledge, a map of natural point features spanning a section of a room is generated on-the-fly as the motion of the camera is simultaneously estimated in full 3D. Naturally this permits the annotation of the scene with rigidly-registered graphics, but further it permits automatic control of the robot's active camera: for instance, fixation on a particular object can be maintained during extended periods of arbitrary user motion, then shifted at will to another object which has potentially been out of the field of view. This kind of functionality is the key to the understanding or «management» of a workspace which the robot needs to have in order to assist its wearer usefully in tasks. We believe that the techniques and technology developed are of particular immediate value in scenarios of remote collaboration, where a remote expert is able to annotate, through the robot, the environment the wearer is working in. |
| first_indexed | 2024-03-06T20:06:21Z |
| format | Conference item |
| id | oxford-uuid:2907dbad-e608-4404-9e91-54e55b447474 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:06:21Z |
| publishDate | 2003 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | oxford-uuid:2907dbad-e608-4404-9e91-54e55b4474742022-03-26T12:16:39ZReal-time localisation and mapping with wearable active visionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:2907dbad-e608-4404-9e91-54e55b447474Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers Inc.2003Davison, AMayol, WMurray, DSOCIETY, ICSOCIETY, ICWe present a general method for real-time, vision-only single-camera simultaneous localisation and mapping (SLAM) - an algorithm which is applicable to the localisation of any camera moving through a scene - and study its application to the localisation of a wearable robot with active vision. Starting from very sparse initial scene knowledge, a map of natural point features spanning a section of a room is generated on-the-fly as the motion of the camera is simultaneously estimated in full 3D. Naturally this permits the annotation of the scene with rigidly-registered graphics, but further it permits automatic control of the robot's active camera: for instance, fixation on a particular object can be maintained during extended periods of arbitrary user motion, then shifted at will to another object which has potentially been out of the field of view. This kind of functionality is the key to the understanding or «management» of a workspace which the robot needs to have in order to assist its wearer usefully in tasks. We believe that the techniques and technology developed are of particular immediate value in scenarios of remote collaboration, where a remote expert is able to annotate, through the robot, the environment the wearer is working in. |
| spellingShingle | Davison, A Mayol, W Murray, D SOCIETY, IC SOCIETY, IC Real-time localisation and mapping with wearable active vision |
| title | Real-time localisation and mapping with wearable active vision |
| title_full | Real-time localisation and mapping with wearable active vision |
| title_fullStr | Real-time localisation and mapping with wearable active vision |
| title_full_unstemmed | Real-time localisation and mapping with wearable active vision |
| title_short | Real-time localisation and mapping with wearable active vision |
| title_sort | real time localisation and mapping with wearable active vision |
| work_keys_str_mv | AT davisona realtimelocalisationandmappingwithwearableactivevision AT mayolw realtimelocalisationandmappingwithwearableactivevision AT murrayd realtimelocalisationandmappingwithwearableactivevision AT societyic realtimelocalisationandmappingwithwearableactivevision AT societyic realtimelocalisationandmappingwithwearableactivevision |