An Approach to Evolutionary Robotics Using a Genetic Algorithm with a Variable Mutation Rate Strategy

Katada, Yoshiaki; Ohkura, Kazuhiro; Ueda, Kanji

doi:10.1007/978-3-540-30217-9_96

Cited by 8 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some useful techniques have also been proposed to analyse the neutrality present in fitness landscapes using GAs as shown by Katada et al [46]. In their work, the authors noticed how the mutation rate plays a key element in evolutionary search and, in specific, they focused their attention on its effects when neutrality is present.…”

Section: Previous Work On Neutrality In Genetic Algorithmsmentioning

confidence: 99%

Neutrality in evolutionary algorithms… What do we know?

et al. 2011

View full text Add to dashboard Cite

Publication informationEvolving Systems, 2 (3): 145-163Publisher Springer Abstract Over the last years, the effects of neutrality have attracted the attention of many researchers in the Evolutionary Algorithms (EAs) community. A mutation from one gene to another is considered as neutral if this modification does not affect the phenotype. This article provides a general overview on the work carried out on neutrality in EAs. Using as a framework the origin of neutrality and its study in different paradigms of EAs (e.g., Genetic Algorithms, Genetic Programming), we discuss the most significant works and findings on this topic. This work points towards open issues, which the community needs to address.

show abstract

Section: Previous Work On Neutrality In Genetic Algorithmsmentioning

confidence: 99%

Neutrality in evolutionary algorithms… What do we know?

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Evolved spiking neural networks have been used in the last few years for the control of simulated or real robots, but more rarely than other types of neural networks [8,13,14,15,16,17,18,9,19,20,21,22,23,24,10,11,25,26,27]. Among previous evolutionary studies, only one explored the properties of a plastic spiking neural network [18,9,19].…”

Section: Introductionmentioning

confidence: 99%

Spiking Neural Controllers for Pushing Objects Around

Florian¹

2006

From Animals to Animats 9

View full text Add to dashboard Cite

We evolve spiking neural networks that implement a seekpush-release drive for a simple simulated agent interacting with objects. The evolved agents display minimally-cognitive behavior, by switching as a function of context between the three sub-behaviors and by being able to discriminate relative object size. The neural controllers have either static synapses or synapses featuring spike-timing-dependent plasticity (STDP). Both types of networks are able to solve the task with similar efficacy, but networks with plastic synapses evolved faster. In the evolved networks, plasticity plays a minor role during the interaction with the environment and is used mostly to tune synapses when networks start to function.

show abstract

“…This would be explained as follows; In the process of evolution, no error threshold effects were observed 1 . This implies that the effective mutation rate at q = 1/L would be below the error threshold under each condition [29][34] [35]. In addition, 1 Generally, an error threshold sets the upper limit for a mutation rate that will enable efficient search [10][27] [33].…”

Section: Simulation Resultsmentioning

confidence: 99%

“…The control task used in this experiment was motion pattern discrimination [28] [29], and is based on a task originally implemented by Beer [30]. The agent must discriminate between two types of vertically falling object based on the object's period of horizontal oscillation; it must catch (i.e., move close to) falling objects that have a long period whilst avoiding those with a short period (see Fig.…”

Section: B the Task And The Fitness Functionmentioning

confidence: 99%

Estimating the Degree of Neutrality in Fitness Landscapes by the Nei’s Standard Genetic Distance – An Application to Evolutionary Robotics –

Katada

Ohkura²

2006 IEEE International Conference on Evolutionary Computation

View full text Add to dashboard Cite

In recent years, not only ruggedness but also neutrality has been recognized as an important feature of a fitness landscape for genetic search. As it has been reported that the evolutionary dynamics on a fitness landscape with neutrality is clearly different from the canonical explanations, ruggedness alone might be inadequate describing it. Another measure, i.e., neutrality is required. In this paper, we proposed the use of the Nei's standard genetic distance, which originates from population genetics, for estimating the degree of neutrality in fitness landscapes after minor modifications. Several computer simulations were conducted with an evolutionary robotics problem in order to investigate the validity of the proposed approach. The results suggest to us that the Nei's genetic distance is a reliable method for estimating the degree of neutrality on realworld problems.0-7803-9487

show abstract

An Approach to Evolutionary Robotics Using a Genetic Algorithm with a Variable Mutation Rate Strategy

Cited by 8 publications

References 19 publications

Neutrality in evolutionary algorithms… What do we know?

Neutrality in evolutionary algorithms… What do we know?

Spiking Neural Controllers for Pushing Objects Around

Estimating the Degree of Neutrality in Fitness Landscapes by the Nei’s Standard Genetic Distance – An Application to Evolutionary Robotics –

Contact Info

Product

Resources

About