Home Publications Modular Reactive Neurocontrol for Biologically-Inspired Walking Machines.
Personal tools

Poramate Manoonpong, Frank Pasemann, and Hubert Roth (2006)

Modular Reactive Neurocontrol for Biologically-Inspired Walking Machines.

International Journal of Robotics Research (IJRR).  (export entry)

Computational Neuroscience
In this article, a neurocontroller is presented which generates the basic locomotion and controls the sensor-driven behavior of a four-legged and a six-legged walking machine. The controller utilizes discrete-time neurodynamics, and it is of modular structure. One module is for processing sensor signals, one is a neural oscillator network serving as a central pattern generator, and the third one is a so-called velocity regulating network. These modules are small and their structures and their functionalities are analyzable. In combination, they enable the machines to autonomously explore an unknown environment, to avoid obstacles, and to escape from corners or deadlock situations. The neurocontroller was developed and tested first using a physical simulation environment, and then it was successfully transferred to the physical walking machines. Locomotion is based on a gait where the diagonal legs are paired and move together, e.g. trot gait for the four-legged walking machine and tripod gait for the six-legged walking machine. The developed controller is universal in the sense that it can be easily adapted to different types of even-legged walking machines without changing the internal structure and its parameters. Keywords—autonomous robots, walking machines, recurrent neural networks, neural control, reactive behavior