Memory-enhanced Evolutionary Robotics: The Echo State Network Approach

Hartland, Cédric; Bredèche, Nicolas; Sebag, Michèle

doi:10.1109/cec.2009.4983292

Cited by 8 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, the objective function and the constraint in Equation 10 are integrated into a single evaluation function And subsequently, PSO algorithm is called to solve Equation 11. The swarm has s N particles; each particle has a position p and a velocity V in the N dimensional space.…”

Section: Training Methods Based On Pso Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Stable trajectory generator-echo state network trained by particle swarm optimization

Song

Feng

2009

2009 IEEE International Symposium on Computational Intelligence in Robotics and Automation - (CIRA)

View full text Add to dashboard Cite

Recurrent neural networks (RNNs) have good modeling capability for nonlinear dynamic systems, but due to the difficulties for training this superiority is discounted. Echo state network (ESN) is a new paradigm for using RNNs with a simpler training method, where an RNN is generated randomly and only a readout is trained. ESN method has quickly become popular in robotics, such as for motor control, for navigation. However, the classical training method for ESNs can not ensure the dynamics asymptotic stability if the trained ESNs run in a closed-loop self-generative mode. The reason is analyzed at first. We then consider the ESN training problem as an optimization problem with a nonlinear constraint, and take a particle swarm optimization (PSO) algorithm solve it. In our simulation experiments, the ESNs are trained as "figure-eight" trajectory generators. The results show that the proposed PSO-based training method can effectively ensure the dynamics asymptotic stability as well as the precision of generating trajectories of the trained ESNs.

show abstract

Section: Training Methods Based On Pso Algorithmmentioning

confidence: 99%

“…), such as slow or non-convergence, local minimum, and time-consuming [9]. Though ESN is initially proposed for time series predictions and indeed performs remarkably well on this kind of data, it has been generalized to many other application domains, of which one is in robotics [10,11,12].…”

mentioning

confidence: 99%

Stable trajectory generator-echo state network trained by particle swarm optimization

Song

Feng

2009

2009 IEEE International Symposium on Computational Intelligence in Robotics and Automation - (CIRA)

View full text Add to dashboard Cite

show abstract

“…Is it possible to generate such complex systems without going through specific stepping stones? For intelligent systems endowed with cognitive abilities, counting may be a stepping stone [80], as well as having a memory [147] or internal representations [144]. These questions suggest a trend of research in which, for a goal recognized to be important, e.g., a robot with significant cognitive, motor or perception abilities, the corresponding stepping stones are proposed and studied.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

Evolutionary robotics is often viewed as the application of a family of black-box optimization algorithms -evolutionary algorithms -to the design of robots, or parts of robots. When considering evolutionary robotics as black-box optimization, the selective pressure is mainly driven by a user-defined, black-box fitness function, and a domain-independent selection procedure. However, most evolutionary robotics experiments face similar challenges in similar setups: the selective pressure, and, in particular, the fitness function, is not a pure user-defined black box. The present review shows that, because evolutionary robotics experiments share common features, selective pressures for evolutionary robotics are a subject of research on their own. The literature has been split into two categories: goal refiners, aimed at changing the definition of a good solution, and process helpers, designed to help the search process. Two subcategories are further considered: task-specific approaches, which require knowledge on how to solve the task and taskagnostic ones, which do not need it. Besides highlighting the diversity of the approaches and their respective goals, the present review shows that many task-agnostic process helpers have been proposed during the last years, thus bringing us closer to the goal of a fully automated robot behavior design process.

show abstract

“…In the field of agent (robot) control, robot navigation/localization [305,306], robotics trajectory control [307,308,20] and evolutionary Robotics [309] have been the applications of ESNs.…”

Section: Real-world Tasks Orientatedmentioning

confidence: 99%

A Review of Designs and Applications of Echo State Networks

Sun¹,

Song²,

Hong³

et al. 2020

Preprint

View full text Add to dashboard Cite

Recurrent Neural Networks (RNNs) have demonstrated their outstanding ability in sequence tasks and have achieved state-of-the-art in wide range of applications, such as industrial, medical, economic and linguistic. Echo State Network (ESN) is simple type of RNNs and has emerged in the last decade as an alternative to gradient descent training based RNNs. ESN, with a strong theoretical ground, is practical, conceptually simple, easy to implement. It avoids non-converging and computationally expensive in the gradient descent methods. Since ESN was put forward in 2002, abundant existing works have promoted the progress of ESN, and the recently introduced Deep ESN model opened the way to uniting the merits of deep learning and ESNs. Besides, the combinations of ESNs with other machine learning models have also overperformed baselines in some applications. However, the apparent simplicity of ESNs can sometimes be deceptive and successfully applying ESNs needs some experience. Thus, in this paper, we categorize the ESN-based methods to basic ESNs, DeepESNs and combinations, then analyze them from the perspective of theoretical studies, network designs and specific applications. Finally, we discuss the challenges and opportunities of ESNs by summarizing the open questions and proposing possible future works.

show abstract

Memory-enhanced Evolutionary Robotics: The Echo State Network Approach

Cited by 8 publications

References 34 publications

Stable trajectory generator-echo state network trained by particle swarm optimization

Stable trajectory generator-echo state network trained by particle swarm optimization

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

A Review of Designs and Applications of Echo State Networks

Contact Info

Product

Resources

About