On the Origins of Self-Modeling

TL;DR

This paper investigates the benefits of self-modeling in robots, demonstrating a strong correlation between robot complexity and the value of self-modeling, which may inform future developments in robotics and understanding of self-awareness.

Contribution

It quantifies the relationship between robot complexity and the benefits of self-modeling, providing insights into its origins and potential applications in complex systems.

Findings

High correlation (R2=0.90) between degrees of freedom and self-modeling benefits

Self-modeling enhances planning and evaluation in robots

Results suggest implications for understanding self-awareness in animals and humans

Abstract

Self-Modeling is the process by which an agent, such as an animal or machine, learns to create a predictive model of its own dynamics. Once captured, this self-model can then allow the agent to plan and evaluate various potential behaviors internally using the self-model, rather than using costly physical experimentation. Here, we quantify the benefits of such self-modeling against the complexity of the robot. We find a R2 =0.90 correlation between the number of degrees of freedom a robot has, and the added value of self-modeling as compared to a direct learning baseline. This result may help motivate self modeling in increasingly complex robotic systems, as well as shed light on the origins of self-modeling, and ultimately self-awareness, in animals and humans.