Reactive Neural Control for Phototaxis and Obstacle Avoidance Behavior of Walking Machines

This paper describes reactive neural control used to generate phototaxis and obstacle avoidance behavior of walking machines. It utilizes discrete-time neurodynamics and consists of two main neural modules: neural preprocessing and modular neural control. The neural preprocessing network acts as a sensory fusion unit. It filters sensory noise and shapes sensory data to drive the corresponding reactive behavior. On the other hand, modular neural control based on a central pattern generator is applied for locomotion of walking machines. It coordinates leg movements and can generate omnidirectional walking. As a result, through a sensorimotor loop this reactive neural controller enables the machines to explore a dynamic environment by avoiding obstacles, turn toward a light source, and then stop near to it.

Authors:

• Poramate Manoonpong
• Frank Pasemann
• Florentin Wörgötter

Keywords:

• Recurrent neural networks
• Walking robots
• Modular neural control
• Phototaxis
• Obstacle avoidance behavior.

References:

[1] S. Fujii and T. Nakamura, "Development of an amphibious hexapod robot
based on a water strider," in Proc. 10th International Conference on
Climbing and Walking Robots, pp. 135-143, 2007.
[2] A. J. Ijspeert, A. Crespi, D. Ryczko, and J. M. Cabelguen, "From
swimming to walking with a salamander robot driven by a spinal cord
model," Science, vol. 315, pp. 1416-1420, 2007.
[3] R. A. Brooks, "A robot that walks: emergent behaviors from a carefully
evolved network," Neural Computation, vol. 12, pp. 253-262, 1989.
[4] H. Cruse, T. Kindermann, M. Schumm, J. Dean, and J. Schmitz,
"Walknet-A biologically inspired network to control six-legged walking,"
Neural Networks, vol. 11, pp. 1435-1447, 1998.
[5] H. Kimura, Y. Fukuoka, and A. H. Cohen, "Adaptive dynamic walking
of a quadruped robot on natural ground based on biological concepts,"
International Journal of Robotics Research, vol. 26, pp. 475-490, 2007.
[6] R. C. Arkin, K. Ali, A. Weitzenfeld, and F. Cervantes-Perez, "Behavior
models of the praying matis as a basis for robotic behavior," Robotics
and Autonomous Systems, vol. 32, pp. 39-60, 2000.
[7] W. G. Walter, The Living Brain, New York: Norton, 1953.
[8] P. Manoonpong, Neural Preprocessing and Control of Reactive Walking
Machines: Towards Versatile Artificial Perception-Action Systems, Cognitive
Technologies, Springer, 2007.
[9] P. Manoonpong, F. Pasemann, and F. Woergoetter, "Sensor-driven neural
control for omnidirectional locomotion and versatile reactive behaviors
of walking machines," Robotics and Autonomous Systems,
doi:10.1016/j.robot.2007.07.004, 2007, in press.
[10] F. Pasemann, M. Huelse, and K. Zahedi, "Evolved neurodynamics
for robot control," in Proc. European Symposium on Artificial Neural
Networks, vol. 2, pp. 439-444, 2003.
[11] F. Pasemann, "Discrete dynamics of two neuron networks," Open
Systems and Information Dynamics, vol. 2, pp. 49-66, 1993.
[12] M. Huelse, S. Wischmann, and F. Pasemann, "The role of non-linearity
for evolved multifunctional robot behavior," in Proc. 6th International
Conference on Evolvable Systems-ICES 2005, LNCS vol. 3637, pp. 108-
118, 2005.
[13] S. L. Hooper, "Central pattern generators," Current Biology, vol. 10, pp.
R176-R177, 2000.
[14] P. Manoonpong, F. Pasemann, J. Fischer, and H. Roth, "Neural processing
of auditory signals and modular neural control for sound tropism of
walking machines," International Journal of Advanced Robotic Systems
(ARS), vol. 2, no. 3, pp. 223-234.