Abstract
This paper presents the evolution of a robotic architecture intended for controlling autonomous social robots. The first instance of this architecture was originally designed according to behavior-based principles. The building blocks of this architecture were behaviors designed as a finite state machine and organized in an ethological inspired way. However, the need of managing explicit symbolic knowledge in human–robot interaction required the integration of planning capabilities into the architecture and a symbolic representation of the environment and the internal state of the robot. A major contribution of this paper is the description of the working memory that integrates these two approaches. This working memory has been implemented as a distributed graph. Another contribution is the use of behavior trees instead of state machine for implementing the behavior-based part of the architecture. This late version of the architecture has been tested in robotic competitions (RoboCup or European Robotics League, among others), whose performance is also discussed in this paper.
Highlights
Organizing the capabilities of autonomous systems is an old, recurrent, and still open problem in artificial intelligence based systems, and in service robotics in particular, where this paper is focused. These different ways of organization are usually known as the architecture of the robot. Both software and cognitive architectures form the backbone of complete robotic systems [1]
This approach led to the emergence of behavior-based robotics during the 80 s and 90 s, that basically proposes that artificial intelligent systems should be decomposed into independent and parallel activity producers which interface directly to the world through perception and action, rather than interface to each other [4]
This paper presents the evolution of the cognitive and software architecture jointly developed by the robotics research group at the Universities of León and Rey Juan Carlos
Summary
Organizing the capabilities of autonomous systems is an old, recurrent, and still open problem in artificial intelligence based systems, and in service robotics in particular, where this paper is focused These different ways of organization are usually known as the architecture of the robot. According to Rodney Brooks [3], the problem was that Shakey’s cognitive architecture was based on the idea of decomposing the intelligent system into information processing units which had to interact with each other via a symbolic representation This approach led to the emergence of behavior-based robotics during the 80 s and 90 s, that basically proposes that artificial intelligent systems should be decomposed into independent and parallel activity producers which interface directly to the world through perception and action, rather than interface to each other [4].
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call