Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2011 | Clinical Orthopaedics and Related Research | dynamic systems theory,boolean network,evolutionary computing,gene regulation,proof of concept,artificial intelligent |
Field | DocType | Volume |
Boolean network,Computer science,Theoretical computer science,Compact space,Dynamical systems theory,Proof of concept,Artificial intelligence,Local search (optimization),Robot,Spite,Machine learning,Robotics | Journal | abs/1101.6 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andrea Roliand | 1 | 0 | 0.34 |
Mattia Manfroni | 2 | 24 | 1.90 |
Carlo Pinciroli | 3 | 419 | 30.54 |
Mauro Birattari | 4 | 2021 | 146.61 |