RALF SALOMON Department of Computer Science, University of Zurich Winterthurerstrasse 190, 8057 Zurich, Switzerland FAX: +41-1-635 68 09; Email: [email protected] ABSTRACT : This paper proposes a new self-organizing control architecture for mobile robots. It consists of a controller and a value system. The controller uses visual sensors to determine the motor commands, whereas the value syst...

This paper proposes a new self-organizing, biologically-inspired control architecture for mobile robots consisting of a controller and a value system. The controller uses activity patterns of visual sensors to determine the motor commands, whereas the value system receives stimuli from proprioceptive sensors. This design decision is justified by the following arguments: (1) the feedback of prop...

The Autonomous Robotics and Control Systems Laboratory at the University of Washington has developed a testbed consisting of seven K-Team Khepera II miniature robots, a global vision system and a custom-designed infrared communication structure. The purpose of the testbed is to provide a platform for the real-world testing of distributed and centralized control algorithms for groups of autonomo...

An evolutionary algorithm for the creation of recurrent network structures is presented. The aim is to develop neural networks controlling the behaviour of miniature robots. Two diierent tasks are solved with this approach. For the rst, the agents are required to move within an environment without colliding with obstacles. In the second task, the agents are required to move towards a light sour...

The aim of this thesis is to perform robot positioning, based on an odometry which is continuously corrected by different landmark detection systems demanding as less modifications as possible for the environment. Two independent correction systems (a supervised and an unsupervised) were implemented into two different experiences which represent the subject of this thesis. The supervised experi...

This paper is concerned with adaptation capabilities of evolved neural controllers. A method consisting of encoding a set of local adaptation rules that synapses obey while the robot freely moves in the environment [6] is compared to a standard xed-weight network. In the experiments presented here, the performance of the robot is measured in environments that are di erent in signi cant ways fro...

Abstract. Through the present paper, a new approach useful for solving the obstacle avoidance and trajectory optimization problems during robot navigation for certain tasks to be performed at minimum costs. In its real sense, the obstacle avoidance approach is based on the application of two fuzzy controllers, the first of which is designed to join the object, while the second is conceived to s...

The work presented in this paper deals with the development of a methodology for resource-efficient behaviour synthesis on autonomous systems. In this context, a definition of a maximal problem with respect to the resources of a given system is introduced. It is elucidated by means of an exemplary implementation of the solution to such a problem using the mini-robot Khepera as the experimental ...

In this paper we compare the evolution of simple behaviour patterns for both an individual and a group of simulated physical robots. An evolutionary algorithm with quite general objective function is used to study the ability to develop behaviour patterns such as the maze exploring ability. The group experiments demonstrate the development of collective behaviour where the group members follow ...

Due to their distributed architecture, artificial neural networks often show a graceful performance degradation to the loss of few units or connections. Living systems also display an additional source of fault-tolerance obtained through distributed processes of self-healing: defective components are actively regenerated. In this paper, we present results obtained with a model of development fo...