Purpose: The purpose of this paper is to present an artificial homeostatic system whose parameters are defined by means of an evolutionary process. The objective is to design a more biologically plausible system inspired by homeostatic regulations observed in nature, which is capable of exploring key issues in the context of robot behaviour adaptation and coordination. Design/methodology/approach: The proposed system consists of an artificial endocrine system that coordinates two spatially unconstrained GasNet artificial neural network models, called non-spatial GasNets. Both systems are dedicated to the definition of control actions in autonomous navigation tasks via the use of an artificial hormone and a hormone receptor. A series of experiments are performed in a real and simulated scenario in order to investigate the performance of the system and its robustness to novel environmental conditions and internal sensory disruptions. Findings: The designed system shows to be robust enough to self-adapt to a wider variety of disruptions and novel environments by making full use of its in-built homeostatic mechanisms. The system is also successfully tested on a real robot, indicating the viability of the proposed method for coping with the reality gap, a well-known issue for the evolutionary robotics community. Originality/value: The proposed framework is inspired by the homeostatic regulations and gaseous neuro-modulation that are intrinsic to the human body. The incorporation of an artificial hormone receptor stands for the novelty of this paper. This hormone receptor proves to be vital to control the network's response to the signalling promoted by the presence of the artificial hormone. It is envisaged that the proposed framework is a step forward in the design of a generic model for coordinating many and more complex behaviours in simulated and real robots, employing multiple hormones and potentially coping with further severe disruptions. © Emerald Group Publishing Limited.
|Number of pages||20|
|Journal||International Journal of Intelligent Computing and Cybernetics|
|Publication status||Published - 21 Aug 2009|
- Artificial intelligence
- Endocrine system
- Neural nets