Paper Info
Title
AutoMoDe-Chocolate: automatic design of control software for robot swarms
Abstract
We present two empirical studies on the design of control software for robot swarms. In Study A, and , two previously published automatic design methods, are compared with human designers. The comparison is performed on five swarm robotics tasks that are different from those on which and have been previously tested. The results show that, under the experimental conditions considered, performs better than , but it is not able to outperform human designers. The results indicate that ’s weak element is the optimization algorithm employed to search the space of candidate designs. To improve over and with the final goal of obtaining an automatic design method that performs better than human designers, we introduce , which differs from only in the fact that it adopts a more powerful optimization algorithm. In Study B, we perform an assessment of . The results show that, under the experimental conditions considered, outperforms both and the human designers. is the first automatic design method for robot swarms that, at least under specific experimental conditions, is shown to outperform a human designer.
Year
DOI
Venue
2015
10.1007/s11721-015-0107-9
Swarm Intelligence
Keywords
Field
DocType
Swarm robotics,Automatic design,AutoMoDe
Control software,Computer science,Design methods,Artificial intelligence,Optimization algorithm,Robot,Machine learning,Empirical research,Swarm robotics
Journal
Volume
Issue
ISSN
9
2-3
1935-3812
Citations 
PageRank 
References 
11
0.51
42
Authors
13
Name
Order
Citations
PageRank
Gianpiero Francesca19111.26
Manuele Brambilla232515.84
Arne Brutschy325714.19
Lorenzo Garattoni4273.20
Roman Miletitch5273.28
Gaëtan Podevijn6192.37
Andreagiovanni Reina7537.24
Touraj Soleymani8163.04
Mattia Salvaro9172.05
Carlo Pinciroli1041930.54
Franco Mascia11967.24
Vito Trianni1277851.87
Mauro Birattari132021146.61