Computer Science – Artificial Intelligence
Scientific paper
2011-01-31
Computer Science
Artificial Intelligence
11 pages, 6 figures
Scientific paper
Dynamical systems theory and complexity science provide powerful tools for analysing artificial agents and robots. Furthermore, they have been recently proposed also as a source of design principles and guidelines. Boolean networks are a prominent example of complex dynamical systems and they have been shown to effectively capture important phenomena in gene regulation. From an engineering perspective, these models are very compelling, because they can exhibit rich and complex behaviours, in spite of the compactness of their description. In this paper, we propose the use of Boolean networks for controlling robots' behaviour. The network is designed by means of an automatic procedure based on stochastic local search techniques. We show that this approach makes it possible to design a network which enables the robot to accomplish a task that requires the capability of navigating the space using a light stimulus, as well as the formation and use of an internal memory.
Birattari Mauro
Manfroni Mattia
Pinciroli Carlo
Roli Andrea
No associations
LandOfFree
Boolean network robotics: a proof of concept does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Boolean network robotics: a proof of concept, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Boolean network robotics: a proof of concept will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-648370