Abstract | ||
---|---|---|
We describe evolution of spiking neural architectures to control navigation of autonomous mobile robots. Experimental results with simple fitness functions indicate that evolution can rapidly generate spiking circuits capable of navigating in textured environments with simple genetic representations that encode only the presence or absence of synaptic connections. Building on those results, we then describe a low-level implementation of evolutionary spiking circuits in tiny microcontrollers that capitalizes on compact genetic encoding and digital aspects of spiking neurons. The implementation is validated on a sugar-cube robot capable of developing functional spiking circuits for collision-free navigation. (c) 2006 Wiley Periodicals, Inc. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1002/int.20173 | INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS |
Keywords | Field | DocType |
genetics,fitness function | Evolutionary algorithm,Evolutionary robotics,Artificial intelligence,Autonomous system (mathematics),Robot,Artificial neural network,Spiking neural network,Mathematics,Mobile robot,Robotics | Journal |
Volume | Issue | ISSN |
21 | 9 | 0884-8173 |
Citations | PageRank | References |
17 | 0.93 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dario Floreano | 1 | 3400 | 284.98 |
Yann Epars | 2 | 98 | 8.05 |
Jean-Christophe Zufferey | 3 | 467 | 46.55 |
Claudio Mattiussi | 4 | 739 | 36.42 |