dates de séjour
projet de recherche
Curious robots: Developing an integrated architecture for self-motivated robot learning, categorization and prediction.
In a realistic environment, a robot is continually flooded with multiple streams of perceptual information. In order to use this information effectively for determining actions, the robot must have the ability to focus its attention on the most relevant features of the world by making abstractions and categorizing its experiences. Based on these categories, it must be able to anticipate new experiences and predict how the world will change over time, possibly as a result of its own actions. Most importantly, this process of learning must be driven by the robot's own intrinsic motivation to explore its world, to extend and refine its repertoire of categories, and to choose its own tasks and goals, rather than relying on a set of pre-specified learning tasks. The objective of this project is to design a developmental architecture for a robot that integrates the mechanisms of categorization, prediction, and intrinsic motivation, which will enable the robot to function autonomously in a rich, dynamic environment through an open-ended process of self-driven learning.
Cette résidence a bénéficié d'une aide de l'État gérée par l'Agence nationale de la recherche dans le cadre des programmes d'Investissements d'avenir au titre du Laboratoire d'excellence RFIEA+.
James Marshall is a faculty member at Sarah Lawrence College in Bronxville, New York, where he teaches computer science and does research in robotics and artificial intelligence. He did his undergraduate work at Cornell, and obtained a PhD in Computer Science and Cognitive Science from Indiana University, Bloomington, where he studied with Douglas Hofstadter and developed the Metacat computer model of analogy-making and self-perception, as the successor to the earlier Copycat model. He has held academic positions at Swarthmore College and Pomona College, and spent a year in the Developmental Robotics research group at Bryn Mawr College in 2003-04. His current research interests focus on biologically-inspired artificial intelligence, and include developmental and epigenetic robotics, neural networks, complex adaptive systems, and evolutionary computation.