Extending the Temporal Horizon of Autonomous Robots

Abstract. We introduce mathematically rigorous metrics on agent experiences having various temporal horizons. Sensorimotor variables accessible to the agent are treated as information-theoretic sources modelled as random variables. The time series from the sensorimotor variables over a given temporal region for different behavioural contexts ground an agent-based view of the agent’s own experiences, and the information-theoretic differences between sensorimotor experiences induce a metric space structure on the set of the agent’s possible experiences. This could allow an autonomous mobile robot to locate and navigate between its sensorimotor experiences on a geometric landscape (an experiential metric space) whose points are its possible experiences of a given temporal scope and in which nearby points are similar experiences. 1 Motivation and Overview In order to mathematically formalize and exploit the notion of temporally extended episodes of experience for autonomous robots, we ...

• Type: Conference
• Year: 2005
• Where: AMIRE
• Authors: Chrystopher L. Nehaniv, Naeem Assif Mirza, Kerstin Dautenhahn, I. René J. A. te Boekhorst
• Keywords: AMIRE 2005, Possible Experiences, Random Variable, Robotics, Sensorimotor Experiences