title: Simulating development in a real robot: on the concurrent increase of sensory, motor, and neural complexity creator: Gomez, Gabriel creator: Lungarella, Max creator: Eggenberger Hotz, Peter creator: Matsushita, Kojiro creator: Pfeifer, Rolf subject: Machine Learning subject: Neural Nets subject: Robotics description: We present a quantitative investigation on the effects of a discrete developmental progression on the acquisition of a foveation behavior by a robotic hand-arm-eyes system. Development is simulated by (a) increasing the resolution of visual and tactile systems, (b) freezing and freeing mechanical degrees of freedom, and (c) adding neuronal units to the neural control architecture. Our experimental results show that a system starting with a low-resolution sensory system, a low precision motor system, and a low complexity neural structure, learns faster that a system which is more complex at the beginning. publisher: Lund University Cognitive Studies contributor: Berthouze, Luc contributor: Kozima, Hideki contributor: Prince, Christopher G. contributor: Sandini, Giulio contributor: Stojanov, Georgi contributor: Metta, Giorgio contributor: Balkenius, Christian date: 2004 type: Conference Paper type: PeerReviewed format: application/pdf identifier: http://cogprints.org/4064/1/gomez.pdf identifier: Gomez, Gabriel and Lungarella, Max and Eggenberger Hotz, Peter and Matsushita, Kojiro and Pfeifer, Rolf (2004) Simulating development in a real robot: on the concurrent increase of sensory, motor, and neural complexity. [Conference Paper] relation: http://cogprints.org/4064/