Evolution of a Cognitive Architecture for Social Robots: Integrating Behaviors and Symbolic Knowledge
Round 1
Reviewer 1 Report
The authors describe the evolution of a cognitive architecture for social robots.
In its original form, this architecture was based on low level behaviors, based on a finite state machine. The authors describe how the successive requirements of the system had necessitated the addition of planning capabilities and symbolic representation. These two components of the robot cognitive architecture are integrated through a working memory that is implemented as a distributed graph. The system made it possible for the authors to reuse it across different robot hardware types such as four legged Aibo robots or wheeled robots such as Pepper or TIAGo.
Overall, this is a well written paper that presents the evolution and the rationale of the design of a robot cognitive architecture. As the paper is an overview, its focus is not on novel algorithmic content but on the insights gained through the evolution of the system.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The paper is well written, however it would be useful for the reader if the authors laid out the disadvantages of the current state of the art and the improvements with the proposed approach
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
