An Evolvable Hardware Tutorial

Tørresen, Jim

doi:10.1007/978-3-540-30117-2_83

Cited by 22 publications

(22 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional interpretation of the evolution of an engineered system considers the changes to a system, which are made by the system designers at design time as a result of changed requirements from one release of the system to the next. Evolvability is studied based on the assumption that systems have intelligence and self-adaptability to adapt themselves automatically, either of which based on run-time environmental changes, and it has received attention in the context of hardware systems (Torresen, 2004), embedded systems (van de Laar et al, 2011), and software systems (Cheng et al, 2009). …”

Section: Adaptronics Of Systemsmentioning

confidence: 99%

An initial categorization of foundational research in complex technical systems

Horváth

2015

J. Zhejiang Univ. Sci. A

View full text Add to dashboard Cite

There has been intense foundational research in complex technical systems (CTSs) over the last half century. These systems are exemplified by advanced mechatronics systems, embedded control systems, real-time systems, agent-based smart systems, distributed software systems, internet of things systems, and cyber-physical systems. The objective of this paper is to offer an initial cataloguing of the various research domains and to identify the major research issues. The paper has an ontological flavour, because it concentrates on what research has been and is being done, rather than on why and how research is done. The underpinning study has been done in three stages: (i) intuition-driven exploration of a reference set of related academic publications, (ii) evidence-based specification of a categorization of the domains and subdomains of research, and (iii) refinement and validation of the proposed classification based on a control set of related academic publications. The proposed reasoning model identifies three categories of research domains. The 'intellectualizations' category includes research domains such as: (i) philosophy, (ii) ontology, and (iii) epistemology of CTSs. The research domains included in the 'realizations' category are: (iv) methodology, and (v) creation of CTSs. The domains considered in the 'influences' category are: (vi) manifestations, and (vii) axiology of CTSs. Based on the proposed reasoning model a landscape of foundational research in CTSs is proposed for public debate. Our follow-up study focuses on the extension of the proposed classification to other families of complex engineered systems such as sociotechnical systems and social ecosystems.

show abstract

Section: Adaptronics Of Systemsmentioning

confidence: 99%

An initial categorization of foundational research in complex technical systems

Horváth

2015

J. Zhejiang Univ. Sci. A

View full text Add to dashboard Cite

show abstract

“…To analyse the diverse EHW research, EHW systems can be classified, as suggested by Torresen [12], into the following categories: evolutionary algorithm, evolution level, target platform/architecture, degree of evolution and scope. The evolutionary algorithm and target platform was previously discussed.…”

Section: Variety Of Researchmentioning

confidence: 99%

“…EHW systems make use of evolutionary algorithms (EA), usually genetic algorithms (GA), to evolve digital circuits on devices such as field-programmable gate arrays (FPGAs) [11,12,13]. These systems are particularly useful in adaptive control systems, fault-tolerant systems and the automatic design of low-cost hardware [4].…”

Section: Introductionmentioning

confidence: 99%

Hardware Genetic Algorithm Optimization by Critical Path Analysis using a Custom VLSI Architecture

Smith¹,

Berg²

2015

SACJ

View full text Add to dashboard Cite

This paper propose a Virtual-Field Programmable Gate Array (V-FPGA) architecture that allows direct access to its configuration bits to facilitate hardware evolution, thereby allowing any combinational or sequential digital circuit to be realized. By using the V-FPGA, this paper investigates two possible ways of making evolutionary hardware systems more scalable: by optimizing the system’s genetic algorithm (GA); and by decomposing the solution circuit into smaller, evolvable sub-circuits. GA optimization is done by: omitting a canonical GA’s crossover operator (i.e. by using a 1+λ algorithm); applying evolution constraints; and optimizing the fitness function. A noteworthy contribution this research has made is the in-depth analysis of the phenotypes’ CPs. Through analyzing the CPs, it has been shown that a great amount of insight can be gained into a phenotype’s fitness. We found that as the number of columns in the Cartesian Genetic Programming array increases, so the likelihood of an external output being placed in the column decreases. Furthermore, the number of used LEs per column also substantially decreases per added column. Finally, we demonstrated the evolution of a state-decomposed control circuit. It was shown that the evolution of each state’s sub-circuit was possible, and suggest that modular evolution can be a successful tool when dealing with scalability.

show abstract

“…The genetic algorithm then creates a population of solutions and applies genetic operators to evolve the solutions in order to find the best one(s). In the simple GA approach [4], [12] the chromosomes are randomly initiated and the only genetic operators used are mutation and crossover. The selection process is done by roulette wheel selection.…”

Section: Simple Gamentioning

confidence: 99%

Robot gaits evolved by combining genetic algorithms and binary hill climbing

Garder

Høvin

2006

Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

In this paper an evolutionary algorithm is used for evolving gaits in a walking biped robot controller. The focus is fast learning in a real-time environment. An incremental approach combining a genetic algorithm (GA) with hill climbing is proposed. This combination interacts in an efficient way to generate precise walking patterns in less than 15 generations. Our proposal is compared to various versions of GA and stochastic search, and finally tested on a pneumatic biped walking robot.

show abstract

An Evolvable Hardware Tutorial

Cited by 22 publications

References 30 publications

An initial categorization of foundational research in complex technical systems

An initial categorization of foundational research in complex technical systems

Hardware Genetic Algorithm Optimization by Critical Path Analysis using a Custom VLSI Architecture

Robot gaits evolved by combining genetic algorithms and binary hill climbing

Contact Info

Product

Resources

About