As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
This work presents methods for tracking a ball from noisy data taken by robots. In robotic soccer, getting a good estimation of a ball's position is a critical. In addition, accurate ball tracking enables robots to play well, for example, efficiently passing to other robots, fine saves by the goalie, good team play, and so on. In this paper, we present new ball tracking technique based on Monte-Carlo localization. The key idea of our technique is to consider two kinds of samples, one for position and the other for velocity. As a result of this technique, it enables us to estimate trajectory of the ball even when it goes out of view.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.