Passively accepting measurements of the world is not enough, as the data we obtain is always incomplete, and the inferences made from it uncertain to a degree which is often unacceptable. If we are to build machines that operate autonomously they will always be faced with this dilemma, and can only be successful if they play a m uch more active role. This paper presents such a machine. It deliberately seeks out those parts of the world which maximize the delity of its internal representations, and keeps searching until those representations are acceptable. We call this paradigm autonomous exploration, and the machine an autonomous explorer. This paper has two major contributions. The rst is a theory that tells us how t o explore, and which con rms the intuitive ideas we h a ve put forward previously. The second is an implementation of that theory. In our laboratory we h a ve constructed a working autonomous explorer and here for the rst time show it in action. The system is entirely bottom-up and does not depend on any a priori knowledge of the environment. To our knowledge it is the rst to have successfully closed the loop between gaze planning and the inference of complex 3D models. R esum e Accepter passivement des mesures du monde est insu sant etant donn e que les donn ees obtenues sont toujours incomplêtes, et que les inf erences qui en d ecoulent sont incertaines a un degr e tel qu'elles sont souvent inacceptable. Si l'on construit des machines qui op erent d e fa con autonome, elles feront toujours face a ce dilemme et ne r eussiront que si elles jouent u n rôle beaucoup plus actif. Ce papier pr esente une telle machine. Elle cherche d elib er ement ces parties du monde qui permettent d'accrotre la d elit e de la repr esentation interne, et continue cette recherche jusqu' a ce que cette repr esentation soit acceptable. On appelle ce paradigme, l'exploration autonome; et on appelle la machine, l'explorateur autonome. Ce papier contient deux contributions majeures. La premi ere est une th eorie qui nous dit comment explorer, et qui con rme les id ees intuitives que nous avons mentionn ees pr ec edemment. La deuxi eme est une impl ementation de cette th eorie. Dans notre laboratoire, nous avons construit un explorateur autonome fonctionnel et ici pour la premi ere fois, nous pouvons le montrer en action. Le syst eme est enti erement guid e par les donn ees et ne d epend aucunement de connaissance sur l'environnement acquise a priori. A notre connaissance, c'est la premi ere fois que la boucle de la plani cation du regard et de l'inf erence de mod eles complexes tridimensionnels est complêt ee avec succ es.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.