Adaptive, neural control architecture for the walking machine LAURON

As presented in many papers neural networks are adequate for special control tasks because of their real-time processing capability, their fault-tolerance and their high adaptivity. The following paper aims to demonstrate how to build up a neural control architecture, consisting only of control algorithms based on neural networks. A further aspect is how to teach such control algorithms. As a testbed, a six-legged walking machine is selected. Due to the use of neural control architecture, the requirements to the hardware concept of the walking machine is described.<>