-an intersting paper, it would be nice to see some code how different modules are implemented

-is it possible to give by an example that the proposed hierarchical approach outperforms authoritative system by imposed rules

-the authors claim that there system is dynamic, this means that the system is able to handle dynamic changes in the environment? but how?

-currently some robot systems use a probabilistic way of reasoning, a Bayesian approach. Next futur the authors plan to use a probabilistic approach?  

It would be nice to apply methods and algorithms in the field of Machine Learning.

A nice paper on actual topic.

There is an interesting approach to decision-making by an autonomous mobile agent.

A six-legged robot application is described in detail.

A minor question: “The selection of the specific coordinator is done in the coordinator block.” - it would be interesting to briefly mention what the coordinator block is?