Using embodiment theory to train a set of actuators with different expertise to accomplish a duty: An application to train a quadruped robot for walking

In recent years, there have been many efforts for distributing a big and complex duty among some agents in order to do it more simply. One of the theories that has received attention recently is called Embodiment. According to this theory, in cooperation of a set of agents for performing a particular task, expertise might not be integrated in a centralized controller; rather it gradually spreads to component and agents. Based on this theory and despite the fact that the human brain is the main controller, expertise is integrated in the body organs gradually. In multi-agent systems a central controller controls and programs whole duties and jobs that agents should perform, this leads to have a very complicated central controller. While in embodiment systems, initially each agent with different structures are fed with some knowledge in the specific duty and then are placed together to accomplish a common task. Now, we will examine this issue that how much improvement is earned when every agent has got a specific amount of partial knowledge separately in comparison with whole structure is defined beforehand. We try to implement embodied system on legs of a quadruped and compare result with the multi-agent system.