Print Email Facebook Twitter Active Affordance Learning in Continuous State and Action Spaces Title Active Affordance Learning in Continuous State and Action Spaces Author Wang, C. Hindriks, K.V. Babuska, R. Faculty Electrical Engineering, Mathematics and Computer Science Department Intelligent Systems Date 2014-11-18 Abstract Learning object affordances and manipulation skills is essential for developing cognitive service robots. We propose an active affordance learning approach in continuous state and action spaces without manual discretization of states or exploratory motor primitives. During exploration in the action space, the robot learns a forward model to predict action effects. It simultaneously updates the active exploration policy through reinforcement learning, whereby the prediction error serves as the intrinsic reward. By using the learned forward model, motor skills are obtained in a bottom-up manner to achieve goal states of an object. We demonstrate that a humanoid robot NAO is able to learn how to manipulate garbage cans with different lids by using different motor skills. To reference this document use: http://resolver.tudelft.nl/uuid:59069258-f7aa-4ab2-8805-4303a97c62dc Source Active Learning in Robotics Workshop at IEEE-RAS International Conference on Humanoid Robots, Madrid, Spain, 18 November 2014 Part of collection Institutional Repository Document type conference paper Rights (c) 2014 The Author(s) Files PDF 319389.pdf 409.3 KB Close viewer /islandora/object/uuid:59069258-f7aa-4ab2-8805-4303a97c62dc/datastream/OBJ/view