Adaptive Behavior current issue

A Hierarchical Autonomous Robot Controller for Learning and Memory: Adaptation in a Dynamic Environment

Alnajjar, F., Bin Mohd Zin, I., Murase, K. — 2009-06-09

This work concerns practical issues surrounding the application of learning and memory in a real mobile robot with the goal of optimal navigation in dynamic environments. A novel hierarchical adaptive controller that contains two-level units was developed and trained in a physical mobile robot "e-Puck." In the low-level unit, the robot holds a number of biologically inspired Aplysia -like spiking neural networks that have the property of spike time-dependent plasticity. Each of these networks is trained to become an expert in a particular local environment(s). All the trained networks are stored in a tree-type memory structure that is located in the high-level unit. These stored networks are used as experiences for the robot to enhance its navigation ability in both new and previously trained environments. The robot's memory is designed to hold memories of various lengths and has a simple searching mechanism. Forgetting and dynamic clustering techniques are used to control the memory size. Experimental results show that the proposed model can produce a robot with learning and memorizing capabilities that enable it to survive in complex and highly dynamic environments.

A Steering Taxis Model and the Qualitative Analysis of its Trajectories

Rano, I. — 2009-06-09

Taxis is a well-known steering technique used by simple animals to approach a stimulus in the real world. However, no mathematical motion model of taxis can be found in the literature. This article derives the differential ordinary equations describing the motion of a Braitenberg vehicle, a widely used taxis model. A qualitative technique for non-linear dynamical systems analysis is applied to investigate the motion generated by the model. Validation of the analysis is performed through several simulations, and conditions for the stimulus source to be reached are obtained. This work fills the theoretical hole in formal models of Braitenberg vehicles and thereby provides theoretical support for the many previous experimental uses of those vehicles for steering tasks.

The Iterated Classification Game: A New Model of the Cultural Transmission of Language

Swarup, S., Gasser, L. — 2009-06-09

The iterated classification game (ICG) combines the classification game with the iterated learning model (ILM) to create a more realistic model of the cultural transmission of language through generations. It includes both learning from parents and learning from peers. Further, it eliminates some of the chief criticisms of the ILM: that it does not study grounded languages, that it does not include peer learning, and that it builds in a bias for compositional languages. We show that, over the span of a few generations, a stable linguistic system emerges that can be acquired very quickly by each generation, is compositional, and helps the agents to solve the classification problem with which they are faced. The ICG also leads to a different interpretation of the language acquisition process. It suggests that the role of parents is to initialize the linguistic system of the child in such a way that subsequent interaction with peers results in rapid convergence to the correct language.

Re-embodiment of Honeybee Aggregation Behavior in an Artificial Micro-Robotic System

Kernbach, S., Thenius, R., Kernbach, O., Schmickl, T. — 2009-06-09

In this article we describe the re-embodiment of biological aggregation behavior of honeybees in Jasmine micro-robots. The observed insect behavior, in the context of the insect's sensor—actor system, is formalized as behavioral and motion-sensing meta-models. These meta-models are transformed into a sensor—actor system of micro-robots by means of a sensors virtualization technique. This allows us to keep the efficiency and scalability of the bio-inspired approach. We also demonstrate the systematic character of this re-embodiment procedure on collective aggregation in a real robotic swarm.