On the Origins of Self-Modeling
This work addresses the motivation for self-modeling in complex robotic systems and its origins in animals and humans, but it appears incremental as it quantifies known benefits rather than introducing new methods.
The paper tackled the problem of quantifying the benefits of self-modeling for agents by analyzing its correlation with robot complexity, finding a strong correlation (R2=0.90) between the number of degrees of freedom and the added value compared to a baseline.
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.