Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
In this paper, we investigate by means of statistical and information-theoretic measures, to what extent sensory-motor coordinated activity can generate and structure information in the sensory channels of a simulated agent interacting with its surrounding environment. We show how the usage of correlation, entropy, and mutual information can be employed (a) to segment an observed behavior into distinct behavioral states, (b) to quantify (fingerprint) the agent-environment interaction, and (c) to analyze the informational relationship between the different components of the sensory-motor apparatus. We hypothesize that a deeper understanding of the information-theoretic implications of sensory-motor coordination can help us endow our robots with better sensory morphologies, and with better strategies for exploring their surrounding environment.