Gusz Eiben

Vrije Universiteit Amsterdam, Computer Science, Faculty Member

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by Gusz Eiben

2009 IEEE Congress on Evolutionary Computation (CEC 2009) [Conference Reports

IEEE Computational Intelligence Magazine, 2009

downloadDownload free PDF

Living Technology Artificial Systems Embodied Evolution Fet Consultation Workshop @bullet@bullet@bullet Future and Emerging Technologies Fet Consultation Meeting: Living Technology – Artificial Systems – Embodied Evolution Fet Consultation Meeting: Living Technology – Artificial Systems – Embodied E

Executive Summary Future and Emerging Technologies − Proactive Initiatives (FET − Proactive) is p... more Executive Summary Future and Emerging Technologies − Proactive Initiatives (FET − Proactive) is preparing the next work programme for 2013 and later. As part of the process to identify new research challenges, the European Commission organised a workshop on 10 November 2011, in Brussels, to brainstorm and elaborate novel candidates for future FET proactive initiatives in the area of Living Technologies. The meeting was attended by 12 researchers and covered a broad range of topics linked to this theme. The objective was to identify specific topics as suitable candidates for future proactive initiatives. In discussion following the presentations of the individual participants, the group identified a single broad challenge which they felt captured most of the key components of the individual challenges proposed. This single challenge was then further explored and elaborated as a potential seed theme for a future proactive initiative. The initial description offered here (detailed in S...

Towards Augmented Humanity: Tuning Bionic Man

SoundICTs: Endowing human auditory capacities and embodying audition faculties into artificial sy... more

SOKS: Self-Organising Knowledge Systems

Chapter 10 How to Handle Constraints with Evolutionary Algorithms

In this chapter we describe evolutionary algorithms (EAs) for constraint handling. Constraint han... more In this chapter we describe evolutionary algorithms (EAs) for constraint handling. Constraint handling is not straightforward in an EA because the search operators mutation and recombination are “blind” to constraints. Hence, there is no guarantee that if the parents satisfy some constraints the offspring will satisfy them as well. This suggests that the presence of constraints in a problem makes EAs intrinsically unsuited to solve this problem. This should especially hold when the problem does not contain an objective function to be optimized, but only constraints – the category of constraint satisfaction problems. A survey of related literature, however, indicates that there are quite a few successful attempts to evolutionary constraint satisfaction. Based on this survey, we identify a number of common features in these approaches and arrive at the conclusion that EAs can be effective constraint solvers when knowledge about the constraints is incorporated either into the genetic o...

Evolutionary Swarm Computing the Semantic Web

The Semantic Web has become a dynamic and enormous network of typed links between data sets store... more The Semantic Web has become a dynamic and enormous network of typed links between data sets stored on different machines. These data sets are machine readable and unambiguously interpretable, thanks to their underlying standard representation languages. The expressiveness and flexibility of the publication model of Linked Data has led to its widespread adoption and an ever increasing publication of semantically rich data on the Web. This success however has started to create serious problems as the scale and complexity of information outgrows the current methods in use, which are mostly based on data- base technology, expressive knowledge representation formalism and high-performance computing. We argue that methods from computa- tional intelligence can play an important role in solving these prob- lems. In this paper we introduce and systemically discuss the typical application problems on the Semantic Web and argue that the existing approaches to address their underlying reasoning...

Hardware Design for Autonomous Robot Evolution

2020 IEEE Symposium Series on Computational Intelligence (SSCI), 2020

The long term goal of the Autonomous Robot Evolution (ARE) project is to create populations of ph... more The long term goal of the Autonomous Robot Evolution (ARE) project is to create populations of physical robots, in which both the controllers and body plans are evolved. The transition for evolutionary designs from purely simulation environments into the real world creates the possibility for new types of system able to adapt to unknown and changing environments. In this paper, a system for creating robots is introduced in order to allow for their body plans to be designed algorithmically and physically instantiated using the previously introduced Robot Fabricator. This system consists of two types of components. Firstly, skeleton parts are created bespoke for each design by 3D printing, allowing the overall shape of the robot to include almost infinite variety. To allow for the shortcomings of 3D printing, the second type of component are organs which contain components such as motors and sensors, and can be attached to the skeleton to provide particular functions. Specific organ designs are presented, with discussion of the design challenges for evolutionary robotics in hardware. The Robot Fabricator is extended to allow for robots with joints, and some example body plans shown to demonstrate the diversity possible using this system of robot generation.

downloadDownload free PDF

Special Issue on Toward Autonomous Evolution, (Re)production, and Learning in Robotic Ecosystems

IEEE Transactions on Cognitive and Developmental Systems, 2020

downloadDownload free PDF

Boosting Genetic Algorithms with Self-Adaptive Selection

2006 IEEE International Conference on Evolutionary Computation

In this paper we evaluate a new approach to selection in Genetic Algorithms (GAs). The basis of o... more In this paper we evaluate a new approach to selection in Genetic Algorithms (GAs). The basis of our approach is that the selection pressure is not a superimposed parameter defined by the user or some Boltzmann mechanism. Rather, it is an aggregated parameter that is determined collectively by the individuals in the population. We implement this idea in two different ways and experimentally evaluate the resulting genetic algorithms on a range of fitness landscapes. We observe that this new style of selection can lead to 30-40% performance increase in terms of speed.

downloadDownload free PDF

Parameter control

Proceedings of the 15th annual conference companion on Genetic and evolutionary computation, 2013

Parameter control mechanisms in evolutionary algorithms (EAs) dynamically change the values of th... more Parameter control mechanisms in evolutionary algorithms (EAs) dynamically change the values of the EA parameters during a run. Research over the last two decades has delivered ample examples where an EA using a parameter control mechanism outperforms its static version with fixed parameter values. However, very few have investigated why such parameter control approaches perform better. In principle, it could be the case that using different parameter values alone is already sufficient and EA performance can be improved without sophisticated control strategies. This paper investigates whether very simple random variation in parameter values during an evolutionary run can already provide improvements over static values.

downloadDownload free PDF

Extreme distributed systems: from large scale to complexity

Computing, 2012

downloadDownload free PDF

Comparing adaptive and traditional techniques for direct marketing

: The paper contains results of a research project aimed at application and evaluation of modernd... more : The paper contains results of a research project aimed at application and evaluation of moderndata analysis techniques in the field of marketing. The investigated techniques were: neural networks, evolutionaryalgorithms, CHAID and logistic regression analysis. All techniques were applied to the problem of makingoptimal selections for direct mailing and the resulting models were compared w.r.t. accuracy, interpretability,transparency and time and expertise needed for their construction.1...

SAW-ing EAs: Adapting the fitness function for solving constrained problems

... 32, Learning Short-Term Weights for GSAT Frank - 1997. 30, A new representation and operato... more

Evolution of Diverse, Manufacturable Robot Body Plans

2020 IEEE Symposium Series on Computational Intelligence (SSCI)

Advances in rapid prototyping have opened up new avenues of research within Evolutionary Robotics... more Advances in rapid prototyping have opened up new avenues of research within Evolutionary Robotics in which not only controllers but also the body plans (morphologies) of robots can evolve in real-time and real-space. However, this also introduces new challenges, in that robot models that can be instantiated from an encoding in simulation might not be manufacturable in practice (due to constraints associated with the 3D printing and/or automated assembly processes). We introduce a representation for evolving (wheeled) robots with a printed plastic skeleton, and evaluate three variants of a novelty-search algorithm in terms of their ability to produce populations of manufacturable but diverse robots. While the set of manufacturable robots discovered represent only a small fraction of the overall search space of all robots, all methods are shown to be capable of generating a diverse population of manufacturable robots that we conjecture is large enough to seed an evolving robotic ecosystem.

format_quoteThe highest diversity of robots occurred without manufacturability constraints, yielding a mere fraction being manufacturable.format_quote

downloadDownload free PDF

The ARE Robot Fabricator: How to (Re)produce Robots that Can Evolve in the Real World

The 2019 Conference on Artificial Life, 2019

The long term vision of the Autonomous Robot Evolution (ARE) project is to create an ecosystem of... more The long term vision of the Autonomous Robot Evolution (ARE) project is to create an ecosystem of both virtual and physical robots with evolving brains and bodies. One of the major challenges for such a vision is the need to construct many unique individuals without prior knowledge of what designs evolution will produce. To this end, an autonomous robot fabrication system for evolutionary robotics, the Robot Fabricator, is introduced in this paper. Evolutionary algorithms can create robot designs without direct human interaction; the Robot Fabricator will extend this to create physical copies of these designs (phenotypes) without direct human interaction. The Robot Fabricator will receive genomes and produce populations of physical individuals that can then be evaluated, allowing this to form part of the evolutionary loop, so robotic evolution is not confined to simulation and the reality gap is minimised. In order to allow the production of robot bodies with the widest variety of shapes and functional parts, individuals will be produced through 3D printing, with prefabricated actuators and sensors autonomously attached in the positions determined by evolution. This paper presents details of the proposed physical system, including a proof-ofconcept demonstrator, and discusses the importance of considering the physical manufacture for evolutionary robotics.

downloadDownload free PDF

Evo-RL

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2021

In this work, we propose a novel approach for reinforcement learning driven by evolutionary compu... more In this work, we propose a novel approach for reinforcement learning driven by evolutionary computation. Our algorithm, dubbed as Evolutionary-Driven Reinforcement Learning (Evo-RL), embeds the reinforcement learning algorithm in an evolutionary cycle, where we distinctly differentiate between purely evolvable (instinctive) behaviour versus purely learnable behaviour. Furthermore, we propose that this distinction is decided by the evolutionary process, thus allowing Evo-RL to be adaptive to different environments. In addition, Evo-RL facilitates learning on environments with rewardless states, which makes it more suited for real-world problems with incomplete information. To show that Evo-RL leads to state-of-the-art performance, we present the performance of different state-of-the-art reinforcement learning algorithms when operating within Evo-RL and compare it with the case when these same algorithms are executed independently. Results show that reinforcement learning algorithms embedded within our Evo-RL approach significantly outperform the stand-alone versions of the same RL algorithms on OpenAI Gym control problems with rewardless states constrained by the same computational budget.

downloadDownload free PDF

Tutorials at PPSN 2016

Lecture Notes in Computer Science, 2016

PPSN 2016 hosts a total number of 16 tutorials covering a broad range of current research in evol... more PPSN 2016 hosts a total number of 16 tutorials covering a broad range of current research in evolutionary computation. The tutorials range from introductory to advanced and specialized but can all be attended without prior requirements. All PPSN attendees are cordially invited to take this opportunity to learn about ongoing research activities in our field!

downloadDownload free PDF

Using Entropy for Parameter Analysis of Evolutionary Algorithms

Experimental Methods for the Analysis of Optimization Algorithms, 2010

Evolutionary Algorithms (EA) form a rich class of stochastic search methods that share the basic ... more Evolutionary Algorithms (EA) form a rich class of stochastic search methods that share the basic principles of incrementally improving the quality of a set of candidate solutions by means of variation and selection [10], [8]. Such variation and selection operators often require parameters to be specified. Finding a good set of parameter values is a nontrivial problem in itself, furthermore some EA parameters are more relevant than others in the sense that choosing different values for them affects EA performance more than for the other parameters. In this chapter we explain the notion of entropy and discuss how entropy can disclose important information on EA parameters, in particular, about their relevance. We describe an algorithm that is able to estimate the entropy of EA parameters and we present a showcase, based on extensive experimentation, to demonstrate the usefulness of this approach and some interesting insights that are gained.

downloadDownload free PDF

The Triangle of Life: Evolving Robots in Real-time and Real-space

Advances in Artificial Life, ECAL 2013, 2013

Evolutionary robotics is heading towards fully embodied evolution in real-time and real-space. In... more Evolutionary robotics is heading towards fully embodied evolution in real-time and real-space. In this paper we introduce the Triangle of Life, a generic conceptual framework for such systems in which robots can actually reproduce. This framework can be instantiated with different hardware approaches and different reproduction mechanisms, but in all cases the system revolves around the conception of a new robot organism. The other components of the Triangle capture the principal stages of such a system; the Triangle as a whole serves as a guide for realizing this anticipated breakthrough and building systems where robot morphologies and controllers can evolve in real-time and real-space. After discussing this framework and the corresponding vision, we present a case study using the SYMBRION research project that realized some fragments of such a system in modular robot hardware.

downloadDownload free PDF

Evolutionary Robotics: What, Why, and Where to

Frontiers in Robotics and AI, 2015

Evolutionary robotics applies the selection, variation, and heredity principles of natural evolut... more Evolutionary robotics applies the selection, variation, and heredity principles of natural evolution to the design of robots with embodied intelligence. It can be considered as a subfield of robotics that aims to create more robust and adaptive robots. A pivotal feature of the evolutionary approach is that it considers the whole robot at once, and enables the exploitation of robot features in a holistic manner. Evolutionary robotics can also be seen as an innovative approach to the study of evolution based on a new kind of experimentalism. The use of robots as a substrate can help to address questions that are difficult, if not impossible, to investigate through computer simulations or biological studies. In this paper, we consider the main achievements of evolutionary robotics, focusing particularly on its contributions to both engineering and biology. We briefly elaborate on methodological issues, review some of the most interesting findings, and discuss important open issues and promising avenues for future work.

downloadDownload free PDF

Gusz Eiben

Uploads

Papers by Gusz Eiben

Log In