Skip to Main Content
Robust object recognition is a crucial requirement for many robotic applications. We propose a method towards increasing reliability and flexibility of object recognition for robotics. This is achieved by the fusion of diverse recognition frameworks and algorithms on score level which use characteristics like shape, texture and color of the objects. Machine Learning allows for the automatic combination of the respective recognition methods' outputs instead of having to adapt their hypothesis metrics to a common basis. We show the applicability of our approach through several real-world experiments in a service robotics environment. Great importance is attached to robustness, especially in varying environments.
Date of Conference: 13-15 Sept. 2012