@conference {2561, title = {Diversification Techniques and Distance Measures in Evolutionary Design of 3D Structures}, booktitle = {Genetic and Evolutionary Computation Conference Companion (GECCO {\textquoteright}22)}, year = {2022}, publisher = {ACM}, organization = {ACM}, address = {Boston, USA}, abstract = {Evolutionary algorithms are among the most successful metaheuristics for hard optimization problems. Nonetheless, there is still much room for improvement of their effectiveness, especially in the multimodal problems, where the algorithms are prone to falling into unsatisfactory local optima. One of the solutions to this problem may be to encourage a broader exploration of the solution space. Motivated by this premise, we compare the evolutionary algorithm without niching, with niching, the novelty search, and the two-criteria optimization (NSGA-II) where the criteria of fitness and diversity are not aggregated. We investigate these methods in the context of automated design of three-dimensional structures, which is one of the hardest optimization problems, often characterized by a rugged fitness landscape arising from a complex genotype to phenotype mapping. In the experiments we optimize 3D structures towards two different goals, height and velocity, using two genetic encodings and three distance measures: two phenetic ones and a genetic one. We demonstrate how different distance measures and diversity promotion mechanisms influence the fitness of the obtained solutions.}, doi = {10.1145/3520304.3528948}, author = {Adam Klejda and Maciej Komosinski and Agnieszka Mensfelt} } @conference {2562, title = {Fitness Diversification in the Service of Fitness Optimization: a Comparison Study}, booktitle = {Genetic and Evolutionary Computation Conference Companion (GECCO {\textquoteright}22)}, year = {2022}, publisher = {ACM}, organization = {ACM}, address = {Boston, USA}, abstract = {Blindly chasing after fitness is not the best strategy for optimization of hard problems, as it usually leads to premature convergence and getting stuck in low-quality local optima. Several techniques such as niching or quality-diversity algorithms have been established that aim to alleviate the selective pressure present in evolutionary algorithms and to allow for greater exploration. Yet another group of methods which can be used for that purpose are fitness diversity methods. In this work we compare the standard single-population evolution against three fitness diversity methods: fitness uniform selection scheme (FUSS), fitness uniform deletion scheme (FUDS), and convection selection (ConvSel). We compare these methods on both mathematical and evolutionary design benchmarks over multiple parametrizations. We find that given the same computation time, fitness diversity methods regularly surpass the performance of the standard single-population evolutionary algorithm.}, doi = {10.1145/3520304.3528949}, url = {http://www.framsticks.com/files/common/FitnessDiversity.pdf}, author = {Kamil Basiukajc and Maciej Komosinski and Konrad Miazga} } @conference {2557, title = {Automated development of latent representations for optimization of sequences using autoencoders}, booktitle = {2021 IEEE Congress on Evolutionary Computation (CEC)}, year = {2021}, publisher = {IEEE}, organization = {IEEE}, abstract = {In this paper, we propose an automated method for the development of new representations of sequences. For this purpose, we introduce a two-way mapping from variable length sequence representations to a latent representation modelled as the bottleneck of an LSTM (long short-term memory) autoencoder. Desirable properties of such mappings include smooth fitness landscapes for optimization problems and better evolvability. This work explores the capabilities of such latent encodings in the context of optimization of 3D structures. Various improvements are adopted that include manipulating the autoencoder architecture and its training procedure. The results of evolutionary algorithms that use different variants of automatically developed encodings are compared.}, doi = {10.1109/CEC45853.2021.9504910}, url = {http://www.framsticks.com/files/common/LatentRepresentationsForSequencesOptimization.pdf}, author = {Kaszuba, Piotr and Komosinski, Maciej and Mensfelt, Agnieszka} } @conference {2558, title = {Diversity control in evolution of movement}, booktitle = {Artificial Life Conference Proceedings}, year = {2021}, publisher = {MIT Press}, organization = {MIT Press}, abstract = {In this work we investigate how various techniques of diversity control employed during evolution of 3D agents influence the velocity they achieve, and how these techniques influence the diversity of behaviors across multiple independent evolutionary runs. Three evolutionary settings are compared: a standard generational evolutionary process where fitness is velocity, a niching technique, and pure novelty search. Two genetic encodings (lower and higher level) and two environments (land and water) are used in experiments. To diversify behaviors, seven properties of movement introduced earlier are calculated for each individual during evolution. Best individuals obtained from evolution in each setting are compared both in terms of their fitness and the similarity of their movement patterns.}, doi = {10.1162/isal_a_00456}, author = {Komosinski, Maciej and Miazga, Konrad} } @article {2555, title = {Type A and Type B Effects, Time-Order Error and Weber{\textquoteright}s Law in Human Timing {\textendash} Simulations and Synthesis}, year = {2021}, institution = {Poznan University of Technology, Institute of Computing Science}, abstract = {This article presents a computational approach to the theoretical integration of the psychophysical phenomena in human timing. While there are many useful models of human timing, analyses are scarce on how these models explain the relationships between several phenomena at the same time. The presented research is an attempt to primarily explain and integrate the time-order error with the Type A and Type B phenomena. The final result of this work also encompasses Weber{\textquoteright}s law property and relates it to the aforementioned order-related effects. The theoretical framework used is the Clock-Counter Timing Network (CCTN), an artificial neural network timing model which has been constructed to explain the process of comparing durations of stimuli. Extensive simulations performed with the use of this model revealed that the considered psychophysical properties may be strongly interrelated and dependent on a simple perceptual mechanism. The obtained results allow to formulate specific experimentally testable predictions.}, issn = {RA{\textendash}2/2021}, url = {http://www.framsticks.com/files/common/HumanTimingSimulation-TypeA-TypeB-TOE-WebersLaw.pdf}, author = {Komosinski, Maciej and Kups, Adam} } @article {2553, title = {Human perception of similarity of 3D graph structures}, year = {2020}, abstract = {This report describes the study of how humans perceive similarity of simple three-dimensional graph structures. Participants of this study were required to align pairs of 3D structures the best they could, then match all vertices of these structures, evaluate their perceived similarity on a numerical scale, and justify their decisions as a textual response. The outcomes of this process were analyzed and compared to the outcomes of a heuristic computer algorithm that maximized the alignment of pairs of 3D structures and matched their vertices. The influence of personal characteristics of participants such as their gender, age, handedness, education, but also time required to complete each task, on the quality of the matching of vertices was evaluated. The consistency of human responses was also verified. The participants turned out to be more consistent (both between themselves and with the algorithm) in the degree of similarity estimated than in matching of vertices. Personal characteristics of the subjects did not have an influence on their similarity assessments.}, issn = {RA-07/2020}, author = {Maciej Komosinski and Agnieszka Mensfelt} } @conference {2344, title = {A Flexible Dissimilarity Measure for Active and Passive 3D Structures and Its Application in the Fitness{\textendash}Distance Analysis}, booktitle = {Applications of Evolutionary Computation}, year = {2019}, publisher = {Springer}, organization = {Springer}, abstract = {Evolutionary design of 3D structures {\textendash} either static structures, or equipped with some sort of a control system {\textendash} is one of the hardest optimization tasks. One of the reasons are rugged fitness landscapes resulting from complex and non-obvious genetic representations of such structures and their genetic operators. This paper investigates global convexity of fitness landscapes in optimization tasks of maximizing velocity and height of both active and passive structures. For this purpose, a new dissimilarity measure for 3D active and passive structures represented as undirected graphs is introduced. The proposed measure is general and flexible {\textendash} any vertex properties can be easily incorporated as dissimilarity components. The new measure was compared against the previously introduced measure in terms of triangle inequality satisfiability, changes in raw measure values and the computational cost. The comparison revealed improvements for triangle inequality and raw values at the expense of increased computational complexity. The investigation of global convexity of the fitness landscape, involving the fitness{\textendash}distance correlation analysis, revealed negative correlation between the dissimilarity of the structures and their fitness for most of the investigated cases.}, isbn = {978-3-030-16692-2}, doi = {10.1007/978-3-030-16692-2_8}, url = {http://www.framsticks.com/files/common/DissimilarityMeasure3DStructuresFitnessDistance.pdf}, author = {Komosinski, Maciej and Mensfelt, Agnieszka}, editor = {Kaufmann, Paul and Castillo, Pedro A.} } @article {2342, title = {Mappism: formalizing classical and artificial life views on mind and consciousness}, journal = {Foundations of Computing and Decision Sciences}, volume = {44}, number = {1}, year = {2019}, pages = {55{\textendash}99}, doi = {10.2478/fcds-2019-0005}, url = {http://www.framsticks.com/files/common/MappismConsciousness.pdf}, author = {Iwo B{\l}{\k a}dek and Maciej Komosinski and Konrad Miazga} } @inbook {2349, title = {Measuring properties of movement in populations of evolved 3D agents}, booktitle = {Artificial Life Conference Proceedings}, year = {2019}, pages = {485{\textendash}492}, publisher = {MIT Press}, organization = {MIT Press}, doi = {10.1162/isal_a_00208}, author = {Maciej Komosinski and Konrad Miazga}, editor = {Harold Fellermann and Jaume Bacardit and Angel Goni-Moreno and Rudolf M. F{\"u}chslin} } @inbook {2350, title = {Parametrizing Convection Selection: Conclusions from the Analysis of Performance in the NKq Model}, booktitle = {Genetic and Evolutionary Computation Conference (GECCO {\textquoteright}19), July 13{\textendash}17, 2019, Prague, Czech Republic}, year = {2019}, pages = {804{\textendash}811}, publisher = {ACM}, organization = {ACM}, doi = {10.1145/3321707.3321864}, url = {http://www.framsticks.com/files/common/ConvectionSelectionNKqModel.pdf}, author = {Maciej Komosinski and Konrad Miazga} } @article {2348, title = {Properties of movement of 3D agents}, number = {RA-1/2019}, year = {2019}, institution = {Poznan University of Technology, Institute of Computing Science}, url = {http://www.framsticks.com/files/common/PropertiesOfMovementOf3DAgents.pdf}, author = {Krzysztof Gorgolewski and Maciej Komosinski and Konrad Miazga and Krzysztof Rosinski and Pawe{\l} Rych{\l}y} } @article {2343, title = {Comparison of the tournament-based convection selection with the island model in evolutionary algorithms}, journal = {Journal of Computational Science}, volume = {32}, year = {2018}, pages = {106{\textendash}114}, abstract = {Convection selection is an approach to multipopulational evolutionary algorithms where solutions are assigned to subpopulations based on their fitness values. Although it is known that convection selection can allow the algorithm to find better solutions than it would be possible with a standard single population, the convection approach was not yet compared to other, commonly used architectures of multipopulational evolutionary algorithms, such as the island model. In this paper we describe results of experiments which facilitate such a comparison, including extensive multi-parameter analyses. We show that approaches based on convection selection can obtain better results than the island model, especially for difficult optimization problems such as those existing in the area of evolutionary design. We also introduce and test a generalization of the convection selection which allows for adjustable overlapping of fitness ranges of subpopulations; the amount of overlapping influences the exploration vs. exploitation balance.}, issn = {1877-7503}, doi = {10.1016/j.jocs.2018.10.001}, url = {http://www.framsticks.com/files/common/ConvectionSelectionVsIslandModel.pdf}, author = {Maciej Komosinski and Konrad Miazga} } @mastersthesis {2351, title = {Development and comparison of genetic representations for evolving 3D structures}, year = {2018}, school = {Poznan University of Technology, Institute of Computing Science}, url = {http://www.framsticks.com/files/common/MSc_Latosinski_GeneticRepresentations.pdf}, author = {Grzegorz Latosi{\'n}ski} } @article {2347, title = {Tournament-based convection selection in evolutionary algorithms}, journal = {PPAM 2017 proceedings, Lecture Notes in Computer Science}, volume = {10778}, year = {2018}, pages = {466{\textendash}475}, abstract = {One of the problems that single-threaded (non-parallel) evolutionary algorithms encounter is premature convergence and the lack of diversity in the population. To counteract this problem and improve the performance of evolutionary algorithms in terms of the quality of optimized solutions, a new subpopulation-based selection scheme - the convection selection - is introduced and analyzed in this work. This new selection scheme is compared against traditional selection of individuals in a single-population evolutionary processes. The experimental results indicate that the use of subpopulations with fitness-based assignment of individuals yields better results than both random assignment and a traditional, non-parallel evolutionary architecture.}, doi = {10.1007/978-3-319-78054-2_44}, url = {http://www.framsticks.com/files/common/TournamentBasedConvectionSelectionEvolutionary.pdf}, author = {Maciej Komosinski and Konrad Miazga} } @article {2341, title = {Universes and simulations: civilizational development in nested embedding}, journal = {Foundations of Computing and Decision Sciences}, volume = {43}, number = {3}, year = {2018}, pages = {181{\textendash}205}, abstract = {The rapid development of technology has allowed computer simulations to become routinely used in an increasing number of fields of science. These simulations become more and more realistic, and their energetic efficiency grows due to progress in computer hardware and software. As humans merge with machines via implants, brain-computer interfaces and increased activity involving information instead of material objects, philosophical concepts and theoretical considerations on the nature of reality are beginning to concern practical, working models and testable virtual environments. This article discusses how simulation is understood and employed in computer science today, how software, hardware and the physical universe unify, how simulated realities are embedded one in another, how complicated it can get in application, practical scenarios, and the possible consequences of these situations. A number of basic properties of universes and simulations in such multiply nested structures are reviewed, and the relationship of these properties with a level of civilizational development is explored.}, url = {http://www.framsticks.com/files/common/DevelopmentNestedUniverses.pdf}, author = {Maciej Komosinski} } @article {Komosinski-2016, title = {Applications of a similarity measure in the analysis of populations of 3D agents}, journal = {Journal of Computational Science}, volume = {21}, year = {2017}, pages = {407{\textendash}418}, abstract = {Research in complex collective and multi-agent systems often involves building models of three-dimensional biological life or evolving such structures in virtual environments. Applications stemming from evolutionary design, engineering, robotics, and artificial life require processing of large numbers of such agents that are encoded in some form of a "genotype". However, what is important in evaluation is the "phenotype", i.e. the actual 3D body and its properties. This work introduces a number of ways in which a measure of similarity of 3D agents can support researchers in recognizing the link between the genotype and phenotype spaces, building taxonomies of 3D bodies and automatically selecting representative agents. The measure of similarity employed here is based on phenotypes and places few restrictions on the compared designs, so it can be applied independently of genetic representation.}, issn = {1877-7503}, doi = {10.1016/j.jocs.2016.10.004}, url = {http://www.framsticks.com/files/common/SimilarityPopulations3DAgents.pdf}, author = {Maciej Komosinski} } @article {Komosinski-and-Kups-2017r, title = {Evolutionary construction of derivations in classical propositional logic using a symbolic-connectionist representation}, number = {RA{\textendash}3/17}, year = {2017}, institution = {Poznan University of Technology, Institute of Computing Science}, type = {Research report}, abstract = {This report introduces a way derivations in classical propositional logic can be constructed using evolutionary algorithms. The derivations are represented by connectionist systems. There are three kinds of nodes constituting these systems: formula nodes that generate signal in the form of strings of symbols, "modus ponens" nodes that transform incoming signal according to the "modus ponens" rule, and substitution nodes that transform incoming signal by applying the substitution rule. This work presents initial research on an approach that is a part of our quest for efficient construction of derivations using various logics and constrained in various ways. The final part of this report outlines limitations encountered in our initial experiments and the ways the proposed approach can be improved.}, url = {http://www.framsticks.com/files/common/EvolutionOfDerivationsInLogic.pdf}, author = {Maciej Komosinski and Adam Kups} } @article {Komosinski-et-al-2016, title = {Multi-agent simulation of benthic foraminifera response to annual variability of feeding fluxes}, journal = {Journal of Computational Science}, volume = {21}, year = {2017}, pages = {419{\textendash}431}, abstract = {In this work we describe a novel simulation model of foraminifera and their microhabitat. The simulations reported here are focused on the response of foraminiferal populations to environmental feeding fluxes. The experiments allowed to calibrate the model and to simulate realistic population patterns known from culture experiments, as well as from oceanographic and paleoecologic studies. Variability of annual food flux has a direct impact on productivity of foraminifera: population sizes closely follow the intensity of constant and seasonal food fluxes in both scenarios. This correlation between the food influx and population size is interpreted as the consequence of changing the carrying capacity of the system. Seasonal pulses of particulate organic matter enhance the population size which is represented by a higher number of fossilized shells. Our model offers a flexible experimental design to run sophisticated in silico experiments. This approach reveals a novel methodology for testing sensitivity of fossil and recent foraminiferal assemblages to environmental changes. Furthermore, it facilitates predictive applications for monitoring studies based on simulation of various scenarios.}, issn = {1877-7503}, doi = {10.1016/j.jocs.2016.09.009}, url = {http://www.framsticks.com/files/common/SimulationForaminiferaFeedingFluxes.pdf}, author = {Maciej Komosinski and Agnieszka Mensfelt and Jaros{\l}aw Tyszka and Jan Gole{\'n}} } @article {Komosinski-and-Ulatowski-2016, title = {Multithreaded computing in evolutionary design and in artificial life simulations}, journal = {The Journal of Supercomputing}, volume = {73}, year = {2017}, pages = {2214{\textendash}2228}, chapter = {5}, abstract = {This article investigates low-level and high-level multithreaded performance of evolutionary processes that are typically employed in evolutionary design and artificial life. Computations performed in these areas are specific because evaluation of each genotype usually involves time-consuming simulation of virtual environments and physics. Computational experiments have been conducted using the Framsticks simulator running a multithreaded version of a standard evolutionary experiment. Tests carried out on five diverse machines and two operating systems demonstrated how low-level performance depends on the number of physical and logical CPU cores and on the number of threads. Two string implementations have been compared, and their raw performance turned out to fundamentally differ in a multithreading setup. To improve high-level performance of parallel evolutionary algorithms, i.e. the quality of optimized solutions, a new distribution scheme that is especially useful and efficient for complex representations of solutions {\textendash} the convection distribution {\textendash} has been introduced. This new distribution scheme has been compared against a random distribution of genotypes among threads that carry out evolutionary processes.}, issn = {1573-0484}, doi = {10.1007/s11227-016-1923-4}, url = {http://www.framsticks.com/files/common/MultithreadedEvolutionaryDesign.pdf}, author = {Maciej Komosinski and Szymon Ulatowski} } @inbook {Komosinski-et-al-2015, title = {Application of a morphological similarity measure to the analysis of shell morphogenesis in Foraminifera}, booktitle = {Man{\textendash}Machine Interactions 4}, series = {Advances in Intelligent Systems and Computing}, volume = {391}, year = {2016}, pages = {215{\textendash}224}, publisher = {Springer}, organization = {Springer}, abstract = {This work evaluates the genotype-to-phenotype mapping defined by one of the models of growth of foraminifera. Foraminifera are simple unicellular organisms with very diverse morphologies. To analyze the mapping, a morphological similarity measure is needed that compares 3D structures. One of the key components of the similarity estimation algorithm is Singular Value Decomposition (SVD). Since this algorithm is heavily used and its performance is important, four SVD implementations have been compared in this work. Distance matrices of the phenotypes obtained for equally distant genotypes were computed using the similarity measure. For the visualization of the phenotype space, multidimensional scaling techniques were used. Visual comparison of the genotype and the phenotype spaces revealed characteristics and potential weaknesses of the analyzed model of foraminifera growth, and demonstrated usefulness of the proposed approach.}, isbn = {978-3-319-23436-6}, doi = {10.1007/978-3-319-23437-3_18}, url = {http://www.framsticks.com/files/common/ForaminiferaGenotypePhenotypeMapping.pdf}, author = {Maciej Komosinski and Agnieszka Mensfelt and Topa, Pawe{\l} and Jaros{\l}aw Tyszka}, editor = {Gruca, Aleksandra and Brachman, Agnieszka and Kozielski, Stanis{\l}aw and Czach{\'o}rski, Tadeusz} } @conference {gajda2016connectionist, title = {A connectionist approach to abductive problems: employing a learning algorithm}, booktitle = {Proceedings of the 2016 Federated Conference on Computer Science and Information Systems (FedCSIS)}, year = {2016}, pages = {353{\textendash}362}, publisher = {ACSIS}, organization = {ACSIS}, abstract = {This paper presents preliminary results of an application of artificial neural networks and Backpropagation learning algorithm to solve logical abductive problems. To represent logic programs in the form of artificial neural networks CIL2P approach proposed by Garcez et al. is employed. Our abductive procedure makes use of translation of a logic program representing a knowledge base into a neural network, training of the neural network with an example representing an abductive goal and translation of the trained network back to the form of a logic program. An abductive hypothesis is represented as the symmetric difference between the initial logic program and the one obtained after training of the network. The first part of the paper introduces formal description of the tools used to model the abductive process, while the second part illustrates our contribution with results of a few computational experiments and discusses the ways of possible improvements of the proposed procedure.}, doi = {10.15439/2016F484}, author = {Andrzej Gajda and Adam Kups and Mariusz Urba{\'n}ski}, editor = {M. Ganzha and L. Maciaszek and M. Paprzycki} } @inbook {2346, title = {eVolutus: a configurable platform designed for ecological and evolutionary experiments tested on Foraminifera}, booktitle = {Man{\textendash}Machine Interactions 4}, year = {2016}, publisher = {Springer}, organization = {Springer}, isbn = {978-3-319-23436-6}, doi = {10.1007/978-3-319-23437-3_23}, url = {http://dx.doi.org/10.1007/978-3-319-23437-3_23}, author = {Pawe{\l} Topa and Maciej Komosinski and Maciej Bassara and Jaros{\l}aw Tyszka}, editor = {Gruca, Aleksandra and Brachman, Agnieszka and Kozielski, Stanis{\l}aw and Czach{\'o}rski, Tadeusz} } @booklet {2340, title = {Nesting}, year = {2016}, url = {http://www.framsticks.com/nesting}, author = {Maciej Komosinski} } @article {Komosinski-and-Kups-2015, title = {Time-order error and scalar variance in a computational model of human timing: simulations and predictions}, journal = {Computational Cognitive Science}, volume = {1}, number = {1}, year = {2015}, pages = {1{\textendash}24}, publisher = {Springer}, abstract = {This work introduces a computational model of human temporal discrimination mechanism - the Clock-Counter Timing Network. It is an artificial neural network implementation of a timing mechanism based on the informational architecture of the popular Scalar Timing Model. The model has been simulated in a virtual environment enabling computational experiments which imitate a temporal discrimination task - the two-alternative forced choice task. The influence of key parameters of the model (including the internal pacemaker speed and the variability of memory translation) on the network accuracy and the time-order error phenomenon has been evaluated. The results of simulations reveal how activities of different modules contribute to the overall performance of the model. These results can be compared and verified in empirical experiments with human participants, especially when the modes of activity of the internal timing mechanism are changed because of some external conditions, or are impaired due to some kind of a neural degradation process.}, doi = {10.1186/s40469-015-0002-0}, url = {http://dx.doi.org/10.1186/s40469-015-0002-0}, author = {Maciej Komosinski and Adam Kups} } @booklet {Foraminifera-framsticks, title = {Foraminifera: genetics, morphology, simulation, evolution}, year = {2014}, url = {http://www.framsticks.com/foraminifera}, author = {Maciej Komosinski and Agnieszka Mensfelt and Topa, Pawe{\l} and Jaros{\l}aw Tyszka and Szymon Ulatowski} } @article {Komosinski-et-al-2014, title = {Identifying efficient abductive hypotheses using multi-criteria dominance relation}, journal = {ACM Transactions on Computational Logic}, volume = {15}, number = {4}, year = {2014}, pages = {28:1{\textendash}28:20}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, abstract = {In this article, results of the automation of an abductive procedure are reported. This work is a continuation of our earlier research, where a general scheme of the procedure has been proposed. Here, a more advanced system developed to generate and evaluate abductive hypotheses is introduced. Abductive hypotheses have been generated by the implementation of the Synthetic Tableau Method. Before the evaluation, the set of hypotheses has undergone several reduction phases. To assess usefulness of abductive hypotheses in the reduced set, several criteria have been employed. The evaluation of efficiency of the hypotheses has been provided by the multi-criteria dominance relation. To comprehend the abductive procedure and the evaluation process more extensively, analyses have been conducted on a number of artificially generated abductive problems.}, doi = {10.1145/2629669}, url = {http://www.framsticks.com/files/common/IdentifyingEfficientAbductiveHypotheses.pdf}, author = {Maciej Komosinski and Adam Kups and Dorota Leszczy{\'n}ska-Jasion and Mariusz Urba{\'n}ski} } @mastersthesis {Sniegowski-2013, title = {Development of the environment for distributed computing in the Framsticks system}, year = {2013}, school = {Institute of Computing Science, Poznan University of Technology}, type = {masters}, url = {http://www.framsticks.com/files/common/MSc_Sniegowski_DistributedFramsticks.pdf}, author = {Piotr Sniegowski} } @article {Komosinski-and-Ulatowski-2013r, title = {Parallel computing in Framsticks}, number = {RA-18/2013}, year = {2013}, institution = {Poznan University of Technology, Institute of Computing Science}, abstract = {This report demonstrates how parallel computation can be implemented in the Framsticks environment. A number of possible multithreaded and distributed architectures and configurations is shown. The main part of this report discusses and explains two experiment definitions (prime-mt and standard-mt) that exploit multithreading. These experiment definitions are included in the official Framsticks distribution. The first one serves as a minimal example of how parallelization can be implemented in Framsticks. The second one is more complex: it shows how to deal with Slave experiments that do not have an internal stop condition, how to migrate the evolved genotypes between Slaves, and how to use Slave checkpoint events to monitor the progress of evolution.}, url = {http://www.framsticks.com/files/common/ParallelComputingFramsticks.pdf}, author = {Maciej Komosinski and Szymon Ulatowski} } @article {2352, title = {Evolutionary design of tall structures}, year = {2012}, institution = {Poznan University of Technology, Institute of Computing Science}, issn = {RA-06/12}, url = {http://www.framsticks.com/files/common/EvolutionaryDesignOfTallStructures.pdf}, author = {Maciej Komosinski} } @mastersthesis {Templeton-2011, title = {On the origin of robotic species}, year = {2011}, type = {masters}, url = {http://www.framsticks.com/files/common/MSc_Templeton_RoboticSpecies.pdf}, author = {Matthew Templeton} } @article {Komosinski-and-Kubiak-2011, title = {Quantitative measure of structural and geometric similarity of 3D morphologies}, journal = {Complexity}, volume = {16}, number = {6}, year = {2011}, pages = {40{\textendash}52}, publisher = {Wiley}, abstract = {This work describes a new heuristic algorithm that estimates structural and geometric similarity of three-dimensional morphologies. It is an extension to previously developed measure of similarity (Komosinski et al., 2001) that was only able to consider the structure of 3D constructs. Morphologies are modeled as graphs with vertices as points in a 3D space, and edges connecting these vertices. This model is very general, therefore the proposed algorithm can be applied in (and across) a number of disciplines including artificial life, evolutionary design, engineering, robotics, biology and chemistry. The primary areas of application of this fast numerical similarity measure are artificial life and evolutionary design, where great numbers of morphologies result from simulated evolutionary processes, and both structural and geometric aspects are significant. Geometry of 3D constructs (i.e., locations of body parts in space) is as important as the structure (i.e., connections of body parts), because both determine behavior of creatures or designs and their fitness in a particular environment. In this work both morphological aspects are incorporated in a single, highly discriminative measure of similarity.}, issn = {1099-0526}, doi = {10.1002/cplx.20367}, url = {http://www.framsticks.com/files/common/Komosinski_Kubiak_MeasureSimilarity3DMorphologies.pdf}, author = {Maciej Komosinski and Marek Kubiak} } @article {2345, title = {Estimating similarity of neural network dynamics}, number = {RA-10/10}, year = {2010}, institution = {Poznan University of Technology, Institute of Computing Science}, abstract = {This report concerns estimation of the similarity between neural networks of any topology. Motivations and benefits of having an automated and quantitative network comparison mechanism are presented. The concept of neural network dynamics (neuron output signal) is considered. A measure is proposed for estimating similarity of active (i.e., working) neural networks. Properties of the measure are analyzed theoretically and verified empirically. The experiments have been performed on a set of evolved networks responsible for controlling 3D structures (agents, robots). These experiments demonstrate the capabilities and the limitations of the proposed measure as a mechanism to support humans in analyzing large sets of neural networks.}, url = {http://www.framsticks.com/files/common/SimilarityNeuralNetworkDynamics.pdf}, author = {Maciej Komosinski and Krzysztof Rosinski} } @book {Adamatzky-and-Komosinski-2009, title = {Artificial Life Models in Hardware}, year = {2009}, publisher = {Springer}, organization = {Springer}, abstract = {Hopping, climbing and swimming robots, nano-size neural networks, motorless walkers, slime mould and chemical brains {\textendash} this book offers unique designs and prototypes of life-like creatures in conventional hardware and hybrid bio-silicon systems. Ideas and implementations of living phenomena in non-living substrates cast a colourful picture of state-of-the-art advances in hardware models of artificial life. Focusing on topics and areas based on non-traditional thinking, and new and emerging paradigms in bio-inspired robotics, this book has a unifying theme: the design and real-world implementation of artificial life robotic devices. Students and researchers will find this coverage of topics such as robotic energy autonomy, multi-locomotion of robots, biologically inspired autonomous robots, evolution in colonies of robotic insects, neuromorphic analog devices, self-configurable robots, and chemical and biological controllers for robots, will considerably enhance their understanding of the issues involved in the development of not-traditional hardware systems at the cusp of artificial life and robotics.}, url = {http://www.springer.com/978-1-84882-529-1}, editor = {Andrew Adamatzky and Maciej Komosinski} } @book {Komosinski-and-Adamatzky-2009, title = {Artificial Life Models in Software}, year = {2009}, publisher = {Springer}, organization = {Springer}, edition = {second}, abstract = {Artificial Life Models in Software provides an introduction and guide to modern software tools for modeling and simulating life-like phenomena, written by those who personally design and develop software, hardware, and art installations in artificial life, simulated complex systems and virtual worlds. This timely volume offers a nearly exhaustive overview and original analysis of major non-profit software packages that are actively developed and supported by experts in artificial life and software design. The carefully selected topics include: simulation and evolution of real and artificial life forms, natural and artificial morphogenesis, self-organization, models of communication and social behaviors, emergent collective behaviors and swarm intelligence, agent-based simulations, autonomous and evolutionary robotics, adaptive, complex and biologically inspired ecosystems, artificial chemistries, and creative computer art. The models of life presented here are essential components in undergraduate and post-graduate courses in complex adaptive systems, multi-agent systems, collective robotics and nature-inspired computing. Readers interested in artificial life, evolutionary biology, simulation, cybernetics, computer graphics and animation, neuroscience, cognitive science, and philosophy will find this monograph a valuable guide and an excellent resource for supplementary reading.}, url = {http://www.springer.com/978-1-84882-284-9}, editor = {Maciej Komosinski and Andrew Adamatzky} } @conference {Komosinski-and-Polak-2009, title = {Evolving free-form stick ski jumpers and their neural control systems}, booktitle = {Proceedings of the National Conference on Evolutionary Computation and Global Optimization}, year = {2009}, pages = {103--110}, address = {Poland}, abstract = {This paper concerns evolution of stick agents in a simplified ski-jumping task. Both body morphologies and control systems are optimized. Evolutionary processes are performed in a range of conditions: the air drag and the friction of the ramp varies. Qualitative and quantitative analyses are presented that show how jump distance, jump height, and flight trajectory depend on environmental conditions. Jumping and landing strategies are investigated, and the most interesting evolved behaviors are reported.}, url = {http://www.framsticks.com/files/common/Komosinski_Polak_EvolvedSkiJumping.pdf}, author = {Maciej Komosinski and Jan Polak} } @inbook {Komosinski-and-Ulatowski-2009, title = {Framsticks: Creating and Understanding Complexity of Life}, booktitle = {Artificial Life Models in Software}, year = {2009}, pages = {107{\textendash}148}, publisher = {Springer}, organization = {Springer}, edition = {second}, chapter = {5}, address = {New York}, abstract = {This chapter describes Framsticks, a three-dimensional life simulation project. Both mechanical structures ("bodies") and control systems ("brains") of creatures are modeled. It is possible to design various kinds of experiments in this environment, including simple optimization (by evolutionary algorithms), coevolution, open-ended and spontaneous evolution, distinct gene pools and populations, diverse genotype-phenotype mappings, and modeling of species and ecosystems. Framsticks is employed in evolutionary computation, artificial intelligence, neural networks, biology, robotics and simulation, cognitive science, neuroscience, medicine, philosophy, virtual reality, graphics, and art. It is a versatile tool for research and education.}, url = {http://www.springer.com/978-1-84882-284-9}, author = {Maciej Komosinski and Szymon Ulatowski}, editor = {Maciej Komosinski and Andrew Adamatzky} } @article {Komosinski-and-Kups-2009r, title = {Models and implementations of timing processes using Artificial Life techniques}, number = {RA-05/09}, year = {2009}, institution = {Poznan University of Technology, Institute of Computing Science}, type = {Research report}, abstract = {This work presents implementation of the Scalar Timing Model (STM) in the neural networks environment. STM is rather popular and commonly used model in the perception of time intervals in humans and animals fields of study. Currently many experiments are conducted in order to verify and research STM parameters and attributes. One of the goal of the implementation was to check whether theoretical model will cope with constraints of artificial neural networks. During implementation process it turned out, that scheme of the model should be revised (by adding extra components) in order to maintain it{\textquoteright}s functional adequacy. Another case was to check how does manipulations of certain parameters will influence collected representation of the real time within model. In this preliminary research we focus on the pacemaker module. Conclusion of this research is that appropriate choice of distribution form of impulses generated by pacemaker make it simulation of the model more congruent with the experimentally collected data then with formal assumptions of STM.}, url = {http://www.framsticks.com/files/common/HumanTimingModelsSimulations.pdf}, author = {Maciej Komosinski and Adam Kups} } @article {pyles2009neural, title = {Neural adaptation for novel objects during dynamic articulation}, journal = {Neuropsychologia}, volume = {47}, number = {5}, year = {2009}, pages = {1261{\textendash}1268}, publisher = {Elsevier}, author = {Pyles, J.A. and Grossman, E.D.} } @article {Hapke-and-Komosinski-2008, title = {Evolutionary Design of Interpretable Fuzzy Controllers}, journal = {Foundations of Computing and Decision Sciences}, volume = {33}, number = {4}, year = {2008}, pages = {351{\textendash}367}, abstract = {This paper presents an approach that allows to evolve fuzzy controllers that can be expressed as fuzzy rules in human-readable form and interpreted. For comparison, the evolution is also performed on simple neural controllers. The control task considered here is a balancing problem, where a construct made of articulated elastic elements is equipped with sensors and actuators. The goal of the construct is to keep the top heavy part from touching the ground. Evolved controllers are evaluated using computer simulation. Control systems process signals from tilt sensors to actuators fixed in the construct. During evolution, fuzzy controllers (including their fuzzy sets and rules) are reconfigured by genetic operators in order to maximize fitness of the control. The article compares evolvability of neural and fuzzy controllers and demonstrates how additional, comprehensible knowledge can be gained which explains the work of the fuzzy controller. The representation for the fuzzy control system, evolutionary operators, various evaluation functions, and the best evolved control systems are presented. A sample evolved fuzzy control system is analyzed in detail to explain its behavior.}, url = {http://www.framsticks.com/files/common/Komosinski_EvolveInterpretableFuzzy.pdf}, author = {Maciej Hapke and Maciej Komosinski} } @conference {2339, title = {Imitation and mirror neurons: an evolutionary robotics model}, booktitle = {BNAIC 2008: 20th Belgian-Dutch Conference on Artificial Intelligence}, year = {2008}, address = {Enschede}, abstract = {The involvement of the mirror neuron system (MNS) in both imitation and action understanding has been firmly established. Various authors have claimed that the MNS{\textquoteright}s function in facilitating imitation builds upon its role in action understanding and is a phylogenetically later development. We argue that this hypothesis lacks sufficient evidence and present support for the reverse: the phylogenetically primary function of the MNS is imitation and the MNS could have evolved in response to a selective pressure for imitative behavior. This hypothesis was tested using evolutionary robotics simulation techniques. The simulation was conducted with embodied and embedded agents with a lifetime-adapting neural network for which the learning parameters were evolutionarily optimized. The agents had to perform an imitation task. Analysis of the resulting controller revealed artificial neurons showing clear mirror characteristics, suggesting that, indeed, mirror neurons evolve due to a selective pressure for imitative behavior.}, author = {Spaak, Eelke and Haselager, Pim F. G.}, editor = {Anton Nijholt and Maja Pantic and Mannes Poel and Hendri Hondorp} } @article {Komosinski-and-Jaskowski-2008, title = {The Numerical Measure of Symmetry for 3D Stick Creatures}, journal = {Artificial Life Journal}, volume = {14}, number = {4}, year = {2008}, month = {Fall}, pages = {425{\textendash}443}, publisher = {MIT Press}, abstract = {This work introduces a numerical, continuous measure of symmetry for 3D stick creatures and solid 3D objects. Background information about the property of symmetry is provided, and motivations to developing symmetry measure are described. Three approaches are mentioned, and two of them are presented in detail using a formal mathematical language. The best approach is used to sort a set of creatures according to their symmetry. Experiments with a mixed set of 84 individuals originating from both human design and evolution are performed to examine symmetry within these two sources, and to determine if human designers and evolutionary processes prefer symmetry or asymmetry.}, doi = {10.1162/artl.2008.14.4.14402}, url = {http://www.framsticks.com/files/common/NumericalMeasureSymmetry3DCreatures.pdf}, author = {Wojciech Jaskowski and Maciej Komosinski} } @article {pyles2007visual, title = {Visual perception and neural correlates of novel {\textquoteright}biological motion{\textquoteright}}, journal = {Vision Research}, volume = {47}, number = {21}, year = {2007}, pages = {2786{\textendash}2797}, publisher = {Elsevier}, doi = {10.1016/j.visres.2007.07.017}, url = {http://dx.doi.org/10.1016/j.visres.2007.07.017}, author = {Pyles, J.A. and Garcia, J.O. and Hoffman, D.D. and Grossman, E.D.} } @inbook {Jelonek-and-Komosinski-2006, title = {Biologically-inspired Visual-motor Coordination Model in a Navigation Problem}, booktitle = {Knowledge-Based Intelligent Information and Engineering Systems. Lecture Notes in Computer Science 4253}, year = {2006}, pages = {341{\textendash}348}, publisher = {Springer-Verlag}, organization = {Springer-Verlag}, address = {Berlin}, abstract = {This work presents a biologically-inspired coordination model which associates motor actions with visual stimuli. The model is introduced and explained, and navigation experiments are reported that verify the implemented visual-motor system. Experiments demonstrate that the system can be trained to solve navigation problems consisting in moving around a 3D object to reach a specific location based on the visual information only. The model is flexible, as it is composed of an adjustable number of modules. It is also interpretable, i.e. it is possible to estimate the influence of visual features on the motor action.}, doi = {10.1007/11893011_44}, url = {http://www.framsticks.com/files/common/BiologicallyInspiredVisualMotorCoordinationModel.pdf}, author = {Jacek Jelonek and Maciej Komosinski}, editor = {B. Gabrys and R.J. Howlett and L.C. Jain} } @article {pyles2006brain, title = {Brain activity evoked by perception of novel "biological motion"}, journal = {Journal of Vision}, volume = {6}, number = {6}, year = {2006}, pages = {794{\textendash}794}, publisher = {Association for Research in Vision and Ophthalmology}, author = {Pyles, J.A. and Garcia, J.O. and Hoffman, D.D. and Grossman, E.D.} } @mastersthesis {Deback-2006thesis, title = {Eco-evolutionary experiments with situated agents}, year = {2006}, type = {masters}, url = {http://www.framsticks.com/files/common/MSc_deBack_EcologyEvolution.pdf}, author = {Walter de Back} } @article {Komosinski-and-Jaskowski-2006r, title = {Measuring symmetry of moving stick creatures}, year = {2006}, institution = {Poznan University of Technology, Institute of Computing Science}, issn = {RA{\textendash}20/06}, author = {Wojciech Jaskowski and Maciej Komosinski} } @article {Deback-2006, title = {Red Queen dynamics in a predator-prey ecosystem}, journal = {Proceedings of the 8th annual conference on genetic and evolutionary computation}, year = {2006}, pages = {381{\textendash}382}, publisher = {ACM New York, NY, USA}, url = {http://www.ai.rug.nl/~mwiering/GROUP/ARTICLES/redqueen.pdf}, author = {Walter de Back and M. Wiering and E. de Jong} } @mastersthesis {Hoffmann-2006thesis, title = {Structural coupling with environment and its modelling on neural driven agents}, year = {2006}, type = {masters}, url = {http://www.framsticks.com/files/common/MSc_Hoffmann_StructuralCoupling.pdf}, author = {Matej Hoffmann} } @book {Adamatzky-and-Komosinski-2005, title = {Artificial Life Models in Software}, year = {2005}, publisher = {Springer}, organization = {Springer}, edition = {first}, address = {New York}, url = {http://www.springer.com/978-1-84882-284-9}, editor = {Andrew Adamatzky and Maciej Komosinski} } @inbook {Komosinski-2005, title = {Framsticks: a platform for modeling, simulating and evolving {3D} creatures}, booktitle = {Artificial Life Models in Software}, year = {2005}, pages = {37{\textendash}66}, publisher = {Springer}, organization = {Springer}, edition = {first}, chapter = {2}, address = {New York}, author = {Maciej Komosinski}, editor = {Andrew Adamatzky and Maciej Komosinski} } @article {Komosinski-and-Ulatowski-2004, title = {Genetic mappings in artificial genomes}, journal = {Theory in Biosciences}, volume = {123}, number = {2}, year = {2004}, month = {September}, pages = {125{\textendash}137}, abstract = {This paper concerns processing of genomes of artificial (computer-simulated) organisms. Of special interest is the process of translation of genotypes into phenotypes, and utilizing the mapping information obtained during such translation. If there exists more than one genetic encoding in a single artificial life model, then the translation may also occur between different encodings. The obtained mapping information allows to present genes-phenes relationships visually and interactively to a person, in order to increase understanding of the genotype-to-phenotype translation process and genetic encoding properties. As the mapping associates parts of the source sequence with the translated destination, it may be also used to trace genes, phenes, and their relationships during simulated evolution. A mappings composition procedure is formally described, and a simple method of visual mapping presentation is established. Finally, advanced visualizations of gene-phene relationships are demonstrated as practical examples of introduced techniques. These visualizations concern genotypes expressed in various encodings, including an encoding which exhibits polygenic and pleiotropic properties.}, doi = {10.1016/j.thbio.2004.04.002}, url = {http://www.framsticks.com/files/common/GeneticMappingsInArtificialGenomes.pdf}, author = {Maciej Komosinski and Szymon Ulatowski} } @conference {Hapke-et-al-2003, title = {Application of Evolutionarily Optimized Fuzzy Controllers for Virtual Robots}, booktitle = {Proceedings of the 7th Joint Conference on Information Sciences}, year = {2003}, month = {September}, pages = {1605{\textendash}1608}, publisher = {Association for Intelligent Machinery}, organization = {Association for Intelligent Machinery}, address = {North Carolina, USA}, url = {http://www.framsticks.com/files/common/Komosinski_FuzzyControl_CINC2003.pdf}, author = {Maciej Hapke and Maciej Komosinski and Dawid Waclawski} } @article {Komosinski-2003, title = {The Framsticks system: versatile simulator of 3D agents and their evolution}, journal = {Kybernetes: The International Journal of Systems \& Cybernetics}, volume = {32}, number = {1/2}, year = {2003}, pages = {156{\textendash}173}, doi = {10.1108/03684920310452382}, url = {http://www.framsticks.com/files/common/Komosinski_FramsticksSystem_Kybernetes2003.pdf}, author = {Maciej Komosinski}, editor = {A. Adamatzky} } @article {mandik2003vre, title = {Varieties of Representation in Evolved and Embodied Neural Networks}, journal = {Biology and Philosophy}, volume = {18}, number = {1}, year = {2003}, pages = {95{\textendash}130}, publisher = {Springer}, url = {http://www.framsticks.com/files/common/Mandik_RepresentationsInNeuralNetworks.pdf}, author = {Pete Mandik} } @article {Hapke-et-al-2002, title = {Evolutionary optimization of fuzzy controllers for virtual robots}, number = {RA-010/02}, year = {2002}, institution = {Poznan University of Technology, Institute of Computing Science}, keywords = {EA, Fuzzy, Robotics}, author = {Maciej Hapke and Maciej Komosinski and Dawid Waclawski} } @article {mandik2002sn, title = {Synthetic Neuroethology}, journal = {Metaphilosophy}, volume = {33}, number = {1\&2}, year = {2002}, pages = {11{\textendash}29}, publisher = {Blackwell Synergy}, url = {http://www.petemandik.com/philosophy/papers/synthneur.pdf}, author = {Pete Mandik} } @article {Komosinski-and-Rotaru-Varga-2001, title = {Comparison of different genotype encodings for simulated 3D agents}, journal = {Artificial Life Journal}, volume = {7}, number = {4}, year = {2001}, month = {Fall}, pages = {395{\textendash}418}, publisher = {MIT Press}, address = {Cambridge, MA}, abstract = {This paper analyzes the effect of different genetic encodings used for evolving 3D agents with physical morphologies. The complex phenotypes used in such systems often require nontrivial encodings. Different encodings used in Framsticks - a system for evolving 3D agents - are presented. These include a low-level direct mapping and two higher-level encodings: a recurrent and a developmental one. Quantitative results are presented from three simple optimization tasks (active height, passive height, and locomotion speed). The low-level encoding produced solutions of lower fitness than the two higher-level encodings under similar conditions. Results from recurrent and developmental encodings had similar fitness values but displayed qualitative differences. Desirable advantages and some drawbacks of more complex encodings are established.}, keywords = {Agents, AL, Body and Brain evol., Genetics, Simulation, Theory}, doi = {10.1162/106454601317297022}, url = {http://www.framsticks.com/files/common/ComparisonGeneticEncodings3DAgents.pdf}, author = {Maciej Komosinski and Adam Rotaru-Varga} } @article {Komosinski-et-al-2001, title = {On estimating similarity of artificial and real organisms}, journal = {Theory in Biosciences}, volume = {120}, number = {3-4}, year = {2001}, month = {December}, pages = {271{\textendash}286}, keywords = {AL, Biology, EA, Theory}, url = {http://www.framsticks.com/files/common/Komosinski_Similarity_TheoryInBiosc2001.pdf}, author = {Maciej Komosinski and Grzegorz Koczyk and Marek Kubiak} } @book {Komosinski-and-Kubiak-2001, title = {Taxonomy in {A}life. {M}easures of similarity for complex artificial organisms}, series = {Advances in Artificial Life. Lecture Notes in Artificial Intelligence 2159}, year = {2001}, pages = {685{\textendash}694}, publisher = {Springer-Verlag}, organization = {Springer-Verlag}, keywords = {Agents, AL, Biology, EA, Simulation}, url = {http://www.framsticks.com/files/common/Komosinski_TaxonomyAlife_ECAL2001.pdf}, author = {Maciej Komosinski and Marek Kubiak}, editor = {Jozef Kelemen and Petr Sos{\'\i}k} } @book {Komosinski-and-Rotaru-Varga-2000, title = {From Directed to Open-Ended Evolution in a Complex Simulation Model}, series = {Artificial Life VII}, year = {2000}, pages = {293{\textendash}299}, publisher = {MIT Press}, organization = {MIT Press}, keywords = {Agents, AL, Simulation, Theory}, author = {Maciej Komosinski and Adam Rotaru-Varga}, editor = {Mark A. Bedau and John S. McCaskill and Norman H. Packard and Steen Rasmussen} } @book {Komosinski-2000, title = {The World of {F}ramsticks: Simulation, Evolution, Interaction}, series = {Virtual Worlds. Lecture Notes in Artificial Intelligence No. 1834}, year = {2000}, pages = {214{\textendash}224}, publisher = {Springer-Verlag}, organization = {Springer-Verlag}, address = {Berlin}, keywords = {Agents, AL, Simulation, Theory}, url = {http://www.framsticks.com/files/common/Komosinski_FramsticksSimul_VW2000.pdf}, author = {Maciej Komosinski}, editor = {Jean-Claude Heudin} } @conference {Komosinski-and-Ulatowski-1999a, title = {Framsticks: sztuczne {\.z}ycie {\textendash} z{\l}o{\.z}ona symulacja stworze{\'n} i ich ewolucji}, booktitle = {Materia{\l}y konferencyjne III Krajowej Konferencji Algorytmy Ewolucyjne i Optymalizacja Globalna KAEiOG (Proceedings of the National Conference on Evolutionary Computation and Global Optimization)}, year = {1999}, month = {May}, pages = {157{\textendash}166}, address = {Potok Z{\l}oty}, keywords = {Agents, AI, AL, Simulation}, url = {http://www.framsticks.com/files/common/Komosinski_Framsticks_KAEiOG1999.pdf}, author = {Maciej Komosinski and Szymon Ulatowski} } @book {Komosinski-and-Ulatowski-1999b, title = {Framsticks: towards a simulation of a nature-like world, creatures and evolution}, series = {Advances in Artificial Life. Lecture Notes in Artificial Intelligence 1674}, year = {1999}, pages = {261{\textendash}265}, publisher = {Springer-Verlag}, organization = {Springer-Verlag}, doi = {10.1007/3-540-48304-7_33}, url = {http://www.framsticks.com/files/common/Komosinski_FramsticksEvol_ECAL1999.pdf}, author = {Maciej Komosinski and Szymon Ulatowski}, editor = {Dario Floreano and Jean-Daniel Nicoud and Francesco Mondada} } @conference {Komosinski-and-Ulatowski-1998, title = {Framsticks {\textendash} Artificial Life}, booktitle = {ECML 98 Demonstration and Poster Papers}, year = {1998}, pages = {7{\textendash}9}, publisher = {Chemnitzer Informatik-Berichte}, organization = {Chemnitzer Informatik-Berichte}, address = {Chemnitz}, keywords = {Agents, AL, Simulation}, author = {Maciej Komosinski and Szymon Ulatowski}, editor = {C. N{\'e}dellec and C. Rouveirol} } @booklet {Komosinski-and-Ulatowski-1996, title = {Framsticks Web Site}, year = {1996}, note = {\url{http://www.framsticks.com/}}, url = {http://www.framsticks.com/}, author = {Maciej Komosinski and Szymon Ulatowski} }