(Co)evolution of (de)centralized neural control for a gravitationally driven machine

Authors:
Steffen Wischmann;Martin Hülse;Frank Pasemann
Affiliations:
Fraunhofer Institute for Autonomous Intelligent Systems, Sankt Augustin, Germany;Fraunhofer Institute for Autonomous Intelligent Systems, Sankt Augustin, Germany;Fraunhofer Institute for Autonomous Intelligent Systems, Sankt Augustin, Germany
Venue:
ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life
Year:
2005

Citing 7
Cited 4

Turtles, termites, and traffic jams: explorations in massively parallel microworlds

Turtles, termites, and traffic jams: explorations in massively parallel microworlds
Understanding intelligence

Understanding intelligence
Being There: Putting Brain, Body, and World Together Again

Being There: Putting Brain, Body, and World Together Again
Cooperative Mobile Robotics: Antecedents and Directions

Autonomous Robots
Collaboration Through the Exploitation of Local Interactions in Autonomous Collective Robotics: The Stick Pulling Experiment

Autonomous Robots
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines

Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Evolutionary Robotics: A New Scientific Tool for Studying Cognition

Artificial Life

YARS: A Physical 3D Simulator for Evolving Controllers for Real Robots

SIMPAR '08 Proceedings of the 1st International Conference on Simulation, Modeling, and Programming for Autonomous Robots
Evolving morphology and control: a distributed approach

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Dynamical systems in the sensorimotor loop: on the interrelation between internal and external mechanisms of evolved robot behavior

50 years of artificial intelligence
Neural control of a modular multi-legged walking machine: Simulation and hardware

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using decentralized control structures for robot control can offer a lot of advantages, such as less complexity, better fault tolerance and more flexibility. In this paper the evolution of recurrent artificial neural networks as centralized and decentralized control architectures will be demonstrated. Both designs will be analyzed concerning their structure-function relations and robustness against lesion experiments. As an application, a gravitationally driven robotic system will be introduced. Its task can be allocated to a cooperative behavior of five subsystems. A co-evolutionary strategy for generating five autonomous agents in parallel will be described.