Visual procedures especially tailored to the constraints and requirements of a legged robot are presented. They work for an uncalibrated camera, with pan and zoom, freely moving towards a stationary target in an unstructured environment that may contain independently moving objects. The goal is to dynamically analyse the image sequence in order to extract information about the robot motion, the target position and the environment structure. The development is based on the deformations of an active contour fitted to the target. Experimental results confirm that the proposed approach constitutes a promising alternative to the prevailing trend based on the costly computation of displacement or velocity fields. ; This work was supported by the project 'Navegación basada en visión de robots autónomos en entornos no estructurados.' (070-724). ; Peer Reviewed
Qualitative vision for the guidance of legged robots in unstructured environments
2001-01-01
doi:10.1016/S0031-3203(00)00093-5
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Multi-contact Stability of Multi-legged Robots Operating in Unstructured Terrains
Springer Verlag | 2022
|Legged robots and methods for controlling legged robots
Europäisches Patentamt | 2023
|LEGGED ROBOTS AND METHODS FOR CONTROLLING LEGGED ROBOTS
Europäisches Patentamt | 2019
|