In this work, we describe the evolutionary training of artificial neural network controllers for competitive team game playing behaviors by teams of real mobile robots. This research emphasized the development of methods to automate the production of behavioral robot controllers. We seek methods tha
Evolution of spiking neural circuits in autonomous mobile robots
โ Scribed by Dario Floreano; Yann Epars; Jean-Christophe Zufferey; Claudio Mattiussi
- Publisher
- John Wiley and Sons
- Year
- 2006
- Tongue
- English
- Weight
- 341 KB
- Volume
- 21
- Category
- Article
- ISSN
- 0884-8173
No coin nor oath required. For personal study only.
โฆ Synopsis
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.
๐ SIMILAR VOLUMES
The paper considers a consensus seeking problem for a multirobot system with limited communication. Multirobot systems with limited communication are modelled as hybrid dynamical systems. The proposed model is a modification of some mathematical models introduced in physics and biology. We derive a
This study investigated location-, movement-, and directional-selectivity of action potential discharges of hippocampal neurons in awake rats subjected to passive displacements in order to estimate vestibular contributions to this activity. Water-deprived rats were habituated to being restrained in