Exploring New Object Recognition Techniques for Online Robots

P.J. Sanz, R. Marín, and J.S. Sánchez (Spain)


Object recognition; Online Robots; Neural Networks.


Within the context of robots controlled through the web (i.e. online robots), research has traditionally focused on the global system functionality, including the way of interaction between the user and the robot (in general, only very simple ways of interaction have been considered). Recent results in different robotics areas have demonstrated the potential role of several techniques from the Pattern Recognition and Machine Learning domains, although very few work has been specifically addressed to online robots, where the object recognition is directly performed by the user. In this paper, we investigate the feasibility of using a neural network approach to object recognition in the context of online robots, and discuss the main advantages over the application of statistical learning methods. A experimental validation, by means of neural networks with the "UJI (i.e. University of Jaume-I) Online Robot" system is presented, showing a better performance than previous distance-based recognition algorithms implemented.

Important Links:

Go Back