Adaptive behavior control with self-regulating neurons

  • Authors:
  • Keyan Zahedi;Frank Pasemann

  • Affiliations:
  • MPI for Mathematics in the Sciences, Leipzig, Germany;Fraunhofer Institute IAIS, Sankt Augustin, Germany

  • Venue:
  • 50 years of artificial intelligence
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is claimed that synaptic plasticity of neural controllers for autonomous robots can enhance the behavioral properties of these systems. Based on homeostatic properties of so called self-regulating neurons, the presented mechanism will vary the synaptic strength during the robot interaction with the environment, due to driving sensor inputs and motor outputs. This is exemplarily shown for an obstacle avoidance behavior in simulation.