title: Robot Self-Characterisation of Experience Using Trajectories in Sensory-Motor Phase Space creator: Mirza, Naeem A. creator: Nehaniv, Chrystopher creator: te Boekhorst, Rene creator: Dautenhahn, Kerstin subject: Machine Learning subject: Robotics description: We describe sensorimotor phase-plots constructed using information theoretical methods from raw sensor data as a way for a robotic agent to characterise its interactions and interaction history. Measurements of the position and shape of the trajectories, including fractal dimension, can be used to characterise the agent-environment interaction. publisher: Lund University Cognitive Studies contributor: Berthouze, Luc contributor: Kaplan, Frédéric contributor: Kozima, Hideki contributor: Yano, Hiroyuki contributor: Konczak, Jürgen contributor: Metta, Giorgio contributor: Nadel, Jacqueline contributor: Sandini, Giulio contributor: Stojanov, Georgi contributor: Balkenius, Christian date: 2005 type: Conference Poster type: PeerReviewed format: application/pdf identifier: http://cogprints.org/4992/1/mirza.pdf identifier: Mirza, Naeem A. and Nehaniv, Chrystopher and te Boekhorst, Rene and Dautenhahn, Kerstin (2005) Robot Self-Characterisation of Experience Using Trajectories in Sensory-Motor Phase Space. [Conference Poster] relation: http://cogprints.org/4992/