Time Experiencing by Robotic Agents

Biological organisms perceive and act in the world based on spatiotemporal experiences and interpretations. However, artificial agents consider mainly the spatial relationships that exist in the world, typically ignoring its temporal aspects. In an attempt to direct research interest towards the fundamental issue of time experiencing, the current work explores two temporally different versions of a robotic rule switching task. An evolutionary process is employed to design a neural network controller capable of accomplishing both versions of the task. The systematic exploration of neural network dynamics revealed a self-organized time perception capacity in the agent’s cognitive system that significantly facilitates the accomplishment of tasks, through modulation of the supplementary behavioural and cognitive processes.