The World of Framsticks: Simulation, Evolution, Interaction

Komosiński, Maciej

doi:10.1007/3-540-45016-5_20

Cited by 37 publications

(34 citation statements)

References 16 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The joint angle sensors return continuous values in radians whereas the touch sensors return discrete values, 0 if no contact with the ground and 1 if contact is made. The choice of inputs was decided upon after a review of the literature where joint angle and touch sensors were the most commonly used types of input to the controller (e.g., [4,13,15,20,21,26]). The eight actuators (y 1 Ày 8 ) represent the motors that control each of the eight articulated joints of the creature.…”

Section: Creature Morphologymentioning

confidence: 99%

An information-theoretic landscape analysis of neuro-controlled embodied organisms

Teo

Abbass

2004

Neural Computing & Applications

View full text Add to dashboard Cite

Recently, there has been a lot of interest in evolving controllers for both physically simulated creatures as well as for real physical robots. However, a range of different ANN architectures are used for controller evolution, and, in the majority of the work conducted, the choice of the architecture used is made arbitrarily. No fitness landscape analysis was provided for the underlying fitness landscape of the controller's search space. As such, the literature remains largely inconclusive as to which ANN architecture provides the most efficient and effective space for searching the range of possible controllers through evolutionary methods. This represents the motivation for this paper where we compare the search space for four different types of ANN architecture for controller evolution through an information-theoretic analysis of the fitness landscape associated with each type of architecture.

show abstract

Section: Creature Morphologymentioning

confidence: 99%

An information-theoretic landscape analysis of neuro-controlled embodied organisms

Teo

Abbass

2004

Neural Computing & Applications

View full text Add to dashboard Cite

show abstract

“…Brain is made from neurons and their elements called neuroitems (these are receptors, effectors, and neural connections). For more detailed description of the model mechanics and neural network refer to [9,8,1].…”

Section: Simulationmentioning

confidence: 99%

Taxonomy in Alife. Measures of Similarity for Complex Artificial Organisms

Komosiński

Kubiak

2001

Advances in Artificial Life

View full text Add to dashboard Cite

Abstract. In this paper a formal approach to construction of a similarity measure for complex creatures is presented. The simulation model is described, and a Framsticks agent is expressed in a formal way. This helps in defining a dissimilarity measure. Two main ideas are discussed with reference to biology, namely genotypic and phenotypic methods. The holistic phenotypic measure is then proposed, where a fast, heuristic algorithm is used. Examples of its application are shown, including mutation and crossing over analysis, and a clustering tree based on distances between pairs of seven artificial individuals.

show abstract

“…Researchers construct various models of life, which serve diverse purposes, ranging from entertainment to medicine. One of such models is Framsticks, a system developed since 1997 (Komosiński andRotaru-Varga, 2000, 2001;Komosiński and Ulatowski, 1997). It is different from most other models in that it does not address a single purpose or a single research problem.…”

Section: Introductionmentioning

confidence: 98%

The Framsticks system: versatile simulator of 3D agents and their evolution

́ski

2003

Kybernetes

View full text Add to dashboard Cite

If you would like to write for this, or any other Emerald publication, then please use our Emerald for Authors service information about how to choose which publication to write for and submission guidelines are available for all. Please visit www.emeraldinsight.com/authors for more information. About Emerald www.emeraldinsight.comEmerald is a global publisher linking research and practice to the benefit of society. The company manages a portfolio of more than 290 journals and over 2,350 books and book series volumes, as well as providing an extensive range of online products and additional customer resources and services.Emerald is both COUNTER 4 and TRANSFER compliant. The organization is a partner of the Committee on Publication Ethics (COPE) and also works with Portico and the LOCKSS initiative for digital archive preservation.Abstract Various aspects of the Framsticks system are described. The system is a universal tool for modeling, simulating and optimizing virtual agents, with three-dimensional body and embedded control system. Simulation model is described first. Then features of the system framework are presented, with typical and potential applications. Specific tools supporting human understanding of evolutionary processes, control and behaviors are also outlined. Finally, the most interesting research experiments are summarized.

show abstract

The World of Framsticks: Simulation, Evolution, Interaction

Cited by 37 publications

References 16 publications

An information-theoretic landscape analysis of neuro-controlled embodied organisms

An information-theoretic landscape analysis of neuro-controlled embodied organisms

Taxonomy in Alife. Measures of Similarity for Complex Artificial Organisms

The Framsticks system: versatile simulator of 3D agents and their evolution

Contact Info

Product

Resources

About