This book presents biologically inspired walking machines interacting with their physical environment. It describes how the designs of the morphology and the behavior control of walking machines can benefit from biological studies. The purpose of this book is to develop a modular structure of neural control generating different reactive behaviors of the physical walking machines, to analyze the neural mechanisms underlying the reactive behaviors, and to demonstrate the sensor fusion technique leading to smooth switching between appropriate behaviors, like obstacle avoidance and sound tropism. The author offers an example of artificial perception-action systems and emphasizes the close relationship between biological studies, computational neuroscience and engineering. The book will be of interest to researchers, engineers and students in the fields of robotics, biologically inspired mechatronics, electronics engineering, control, and artificial intelligence.