Evolutionary robotics: The next-generation-platform for on-line and on-board artificial evolution

Kernbach, Serge; Meister, Eugen; Scholz, Oliver; Humza, Raja; Liedke, Jens; Ricotti, Leonardo; Jemai, J.; Havlik, Jiri; Liu, W.

doi:10.1109/cec.2009.4983066

Cited by 33 publications

(27 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The individual modules that make up our organism are simpler than those being developed in the SYMBRION project [5] but for the purposes of organism locomotion have a similar degrees of freedom and sensors.…”

Section: Modules and Organismmentioning

confidence: 99%

“…We used Jason Gauci's publicly available C++ implementation of HyperNEAT, version 2.6. 5 Apart from a population size of 10, we used the settings as found in that implementation's TicTacToe experiment. We did not engage in further tuning of parameters or thorough analysis of alternative fitness calculations since the experiments provide a proof of concept rather than a comprehensive analysis.…”

Section: Task and Evolutionmentioning

confidence: 99%

See 1 more Smart Citation

HyperNEAT for Locomotion Control in Modular Robots

Haasdijk

Rusu

Eiben

2010

Evolvable Systems: From Biology to Hardware

View full text Add to dashboard Cite

Abstract. In an application where autonomous robots can amalgamate spontaneously into arbitrary organisms, the individual robots cannot know a priori at which location in an organism they will end up. If the organism is to be controlled autonomously by the constituent robots, an evolutionary algorithm that evolves the controllers can only develop a single genome that will have to suffice for every individual robot. However, the robots should show different behaviour depending on their position in an organism, meaning their phenotype should be different depending on their location. In this paper, we demonstrate a solution for this problem using the HyperNEAT generative encoding technique with differentiated genome expression. We develop controllers for organism locomotion with obstacle avoidance as a proof of concept. Finally, we identify promising directions for further research.

show abstract

Section: Modules and Organismmentioning

confidence: 99%

Section: Task and Evolutionmentioning

confidence: 99%

HyperNEAT for Locomotion Control in Modular Robots

Haasdijk

Rusu

Eiben

2010

Evolvable Systems: From Biology to Hardware

View full text Add to dashboard Cite

show abstract

“…A "reality gap" mostly exists between system simulations and physical reality, which makes the development of the various aspects of robotic systems difficult. A mixed system, combining simulation and physical controllers, may help engineers overcome the reality gap [36]. It provides the possibility to approximate the global system state using local sensors, to use information provided by robot-to-robot interactions, and the robots' internal states.…”

Section: A U T H O R C O P Ymentioning

confidence: 99%

“…Platforms such as the one developed for the Symbrion and Replicator projects [36] provide a distributed computational system, able to run learning and evolutionary algorithms. Such robotic systems can run autonomously or with human influence.…”

Section: A U T H O R C O P Ymentioning

confidence: 99%

The future of complexity engineering

Frei

Serugendo

2012

Open Engineering

View full text Add to dashboard Cite

AbstractComplexity Engineering encompasses a set of approaches to engineering systems which are typically composed of various interacting entities often exhibiting self-* behaviours and emergence. The engineer or designer uses methods that benefit from the findings of complexity science and often considerably differ from the classical engineering approach of “divide and conquer”.This article provides an overview on some very interdisciplinary and innovative research areas and projects in the field of Complexity Engineering, including synthetic biology, chemistry, artificial life, self-healing materials and others. It then classifies the presented work according to five types of nature-inspired technology, namely: (1) using technology to understand nature, (2) nature-inspiration for technology, (3) using technology on natural systems, (4) using biotechnology methods in software engineering, and (5) using technology to model nature. Finally, future trends in Complexity Engineering are indicated and related risks are discussed.

show abstract

“…Temporal : Online evolution is proposed as a mechanism to produce functional behaviour to solve a task, as opposed to a study of evolution in of itself. This applies pressure to generate solutions at a rate comparable to the dynamic change within the task environment [8]. Selection : The migration of solutions across the group of robots is non-deterministic since the robots are mobile.…”

Section: Introductionmentioning

confidence: 99%

The distributed co-evolution of an on-board simulator and controller for swarm robot behaviours

2014

View full text Add to dashboard Cite

The distributed co-evolution of an on-board simulator and controller for swarm robot behaviours. Evolutionary Intelligence, 7 (2). pp. 95-106. ISSN 1864-5909 Available from: http://eprints.uwe.ac.uk/23450We recommend you cite the published version. The publisher's URL is: http://dx.doi.org/10.1007/s12065-014-0112-8 Refereed: YesThe final publication is available at Springer via http://dx.doi.org/doi:10.1007/s12065?014?0112?8 Disclaimer UWE has obtained warranties from all depositors as to their title in the material deposited and as to their right to deposit such material. UWE makes no representation or warranties of commercial utility, title, or fitness for a particular purpose or any other warranty, express or implied in respect of any material deposited.UWE makes no representation that the use of the materials will not infringe any patent, copyright, trademark or other property or proprietary rights. UWE accepts no liability for any infringement of intellectual property rights in any material deposited but will remove such material from public view pending investigation in the event of an allegation of any such infringement. PLEASE SCROLL DOWN FOR TEXT.Noname manuscript No. Abstract We investigate the reality gap, specifically the environmental correspondence of an on-board simulator. We describe a novel distributed co-evolutionary approach to improve the transference of controllers that co-evolve with an on-board simulator. A novelty of our approach is the the potential to improve transference between simulation and reality without an explicit measurement between the two domains. We hypothesise that a variation of on-board simulator environment models across many robots can be competitively exploited by comparison of the real controller fitness of many robots. We hypothesise that the real controller fitness values across many robots can be taken as indicative of the varied fitness in environmental correspondence of on-board simulators, and used to inform the distributed evolution an on-board simulator environment model without explicit measurement of the real environment. Our results demonstrate that our approach creates an adaptive relationship between the onboard simulator environment model, the real world behaviour of the robots, and the state of the real environment. The results indicate that our approach is sensitive to whether the real behavioural performance of the robot is informative on the state real environment.

show abstract

Evolutionary robotics: The next-generation-platform for on-line and on-board artificial evolution

Cited by 33 publications

References 7 publications

HyperNEAT for Locomotion Control in Modular Robots

HyperNEAT for Locomotion Control in Modular Robots

The future of complexity engineering

The distributed co-evolution of an on-board simulator and controller for swarm robot behaviours

Contact Info

Product

Resources

About