2013 | OriginalPaper | Buchkapitel
Object Recognition Using Tactile Sensors
verfasst von : Jürgen Sturm
Erschienen in: Approaches to Probabilistic Model Learning for Mobile Manipulation Robots
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
So far, we have considered monocular and stereo vision to perceive the state of the world. However, vision alone is in some cases not sufficient: for example, a robot that picks up an object from a box cannot see which object it grasps because the robot partially occludes its view with its own gripper. In particular for robotic manipulation tasks, tactile sensing provides another sensor modality that can reveal relevant aspects about the object being manipulated, for example, to infer its identity, pose, and internal state.