**5. Neural controllers**

**4. Autonomy**

**4.1. Artificial neural networks**

Our approach to autonomous robots is based in autonomous controllers, constructed with artificial neural nets, and incorporating basic rules of living brains in terms of energy usage, default mode network (DMN), and the orchestrated, autonomous transitions forms default

**Figure 2.** The basic robotic joint with sensors, muscles, and neural driver. The joint can be snapped into long chains.

**Figure 3.** Modular robot with 16 joints and dedicated driven neurons in its working environment.

The neural networks used in this chapter are sigmoidal neurons trained with backpropaga-

mode to other operative behaviors in reaction to stimuli.

Muscles are driven by the output neurons of an associate network.

130 Human-Robot Interaction - Theory and Application

tion [17]. Other functioning details are given in [12, 13].
