SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
A dynamical systems perspective on agent-environment interaction
Artificial Intelligence - Special volume on computational research on interaction and agency, part 1
Understanding intelligence
SO(2)-networks as neural oscillators
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Homeotaxis: Coordination with Persistent Time-Loops
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Emergence of Interaction among Adaptive Agents
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Creating and modulating rhythms by controlling the physics of the body
Autonomous Robots
Guided self-organisation for autonomous robot development
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Taming the beast: guided self-organization of behavior in autonomous robots
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Intrinsic adaptation in autonomous recurrent neural networks
Neural Computation
SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
| Hi-index | 0.00 |
Dynamical systems offer intriguing possibilities as a substrate for the generation of behavior because of their rich behavioral complexity. However this complexity together with the largely covert relation between the parameters and the behavior of the agent is also the main hindrance in the goal oriented design of a behavior system. This paper presents a general approach to the self-regulation of dynamical systems so that the design problem is circumvented. We consider the controller (a neural net work) as the mediator for changes in the sensor values over time and define a dynamics for the parameters of the controller by maximizing the dynamical complexity of the sensorimotor loop under the condition that the consequences of the actions taken are still predictable. This very general principle is given a concrete mathematical formulation and is implemented in an extremely robust and versatile algorithm for the parameter dynamics of the controller. We consider two different applications, a mechanical device called the rocking stamper and the ODE simulations of a "snake" with five degrees of freedom. In these and many other examples studied we observed various behavior modes of high dynamical complexity