Visual navigation around curved obstacles
An approach to path-planning around smooth obstacles that exploits visually derived geometry is proposed. A moving robot can scan the silhouette or apparent contour of an obstacle and estimate a minimum length path. This is done by seeking geodesics which can be extrapolated smoothly, around the obs...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
1991
|
| _version_ | 1826317650190401536 |
|---|---|
| author | Blake, A Brady, M Cipolla, R Xie, Z Zisserman, A |
| author_facet | Blake, A Brady, M Cipolla, R Xie, Z Zisserman, A |
| author_sort | Blake, A |
| collection | OXFORD |
| description | An approach to path-planning around smooth obstacles that exploits visually derived geometry is proposed. A moving robot can scan the silhouette or apparent contour of an obstacle and estimate a minimum length path. This is done by seeking geodesics which can be extrapolated smoothly, around the obstacle and towards the goal. Preliminary implementation of this idea uses a real-time visual contour tracker running at 16 Hz, with a camera mounted on an Adept robot arm. The camera first dithers to generate visual motion, a safe path is estimated, and the robot steers the camera around the obstacle with a clearance of a few millimeters. |
| first_indexed | 2025-03-11T16:57:16Z |
| format | Conference item |
| id | oxford-uuid:bd1d91e2-1ccf-415c-af4d-c967d0780edb |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-03-11T16:57:16Z |
| publishDate | 1991 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:bd1d91e2-1ccf-415c-af4d-c967d0780edb2025-02-25T14:36:52ZVisual navigation around curved obstaclesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:bd1d91e2-1ccf-415c-af4d-c967d0780edbEnglishSymplectic ElementsIEEE1991Blake, ABrady, MCipolla, RXie, ZZisserman, AAn approach to path-planning around smooth obstacles that exploits visually derived geometry is proposed. A moving robot can scan the silhouette or apparent contour of an obstacle and estimate a minimum length path. This is done by seeking geodesics which can be extrapolated smoothly, around the obstacle and towards the goal. Preliminary implementation of this idea uses a real-time visual contour tracker running at 16 Hz, with a camera mounted on an Adept robot arm. The camera first dithers to generate visual motion, a safe path is estimated, and the robot steers the camera around the obstacle with a clearance of a few millimeters. |
| spellingShingle | Blake, A Brady, M Cipolla, R Xie, Z Zisserman, A Visual navigation around curved obstacles |
| title | Visual navigation around curved obstacles |
| title_full | Visual navigation around curved obstacles |
| title_fullStr | Visual navigation around curved obstacles |
| title_full_unstemmed | Visual navigation around curved obstacles |
| title_short | Visual navigation around curved obstacles |
| title_sort | visual navigation around curved obstacles |
| work_keys_str_mv | AT blakea visualnavigationaroundcurvedobstacles AT bradym visualnavigationaroundcurvedobstacles AT cipollar visualnavigationaroundcurvedobstacles AT xiez visualnavigationaroundcurvedobstacles AT zissermana visualnavigationaroundcurvedobstacles |