Evolutionary Robotics

Floreano, Dario; Husbands, Phil; Nolfi, Stefano

doi:10.1007/978-3-540-30301-5_62

Cited by 125 publications

(88 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This paper focuses on the design of a control architecture for an autonomous mobile robot in an unknown environment. For this type of set-up, design approaches can range from hand-crafted reactive behavior [3] to optimal control approaches [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Embedded Evolutionary Robotics: The (1+1)-Restart-Online Adaptation Algorithm

Montanier

Bredèche

2011

New Horizons in Evolutionary Robotics

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

“…Evolutionary Robotics [9,16] ("ER") takes inspiration from nature by combining two partly antagonist mechanisms. On the one hand, selection of the most fitted individuals tends to ensure convergence of the algorithm toward the most fitted solution.…”

Section: Introductionmentioning

confidence: 99%

Embedded Evolutionary Robotics: The (1+1)-Restart-Online Adaptation Algorithm

Montanier

Bredèche

2011

New Horizons in Evolutionary Robotics

View full text Add to dashboard Cite

“…Exploratory and exploitative behaviors were thus achieved with the most basic Hebbian model. While such learning problems as those analyzed in this paper have been employed for decades to test the bottom-up emergence of intelligent behaviors in fields such as artificial life (Langton, 1990) and evolutionary robotics (Floreano and Nolfi, 2004;Floreano and Mattiussi, 2008), the results presented here show that very small structures can serve as exemplary paradigms of adaptive behavior (Staddon, 1983). The final experiment suggests that this plasticity rule maintains its problem-solving properties in multiple-input multiple output-networks in the face of highly stochastic signals, an important capability for the real world.…”

Section: Resultsmentioning

confidence: 99%

From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation

Soltoggio¹,

Stanley²

2012

Neural Networks

View full text Add to dashboard Cite

Citation: SOLTOGGIO, A. and STANLEY, K.O., 2012. From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks, 34 pp. 28-41.Additional Information:• NOTICE: this is the author's version of a work that was accepted for publication in Neural Networks. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neural Networks, vol. 34 (2012) AbstractSynaptic plasticity is a major mechanism for adaptation, learning and memory. Yet current models struggle to link local synaptic changes to the acquisition of behaviors. The aim of this paper is to demonstrate a computational relationship between local Hebbian plasticity and behavior learning by exploiting two traditionally unwanted features: neural noise and synaptic weight saturation. A modulation signal is employed to arbitrate the sign of plasticity: when the modulation is positive, the synaptic weights saturate to express exploitative behavior; when it is negative, the weights converge to average values and neural noise reconfigures the network's functionality. This process is demonstrated through simulating neural dynamics in the autonomous emergence of fearful and aggressive navigating behaviors and in the solution to reward-based problems. The neural model learns, memorizes and modifies different behaviors that lead to positive modulation in a variety of settings. The algorithm establishes a simple relationship between local plasticity and behavior learning by demonstrating the utility of noise and weight saturation. Moreover it provides a new tool to simulate adaptive behavior and contributes to bridging the gap between synaptic changes and behavior in neural computation.

show abstract

“…Evolutionary robotics (Nolfi and Floreano, 2000;Sims, 1994;Floreano et al, 2008;Doncieux et al, 2015) applies concepts derived from biology to the design of robotic systems. It has demonstrated an ability to address challenging problems in many task domains including: gaits (Clune et al, 2009), object manipulation (Bongard, 2008), biological study (Crespi et al, 2013;Doorly et al, 2009), and the optimization of morphology (Auerbach and Bongard, 2010;Bongard, 2010;Cheney et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Lexicase selection outperforms previous strategies for incremental evolution of virtual creature controllers

Moore¹,

Stanton²

2017

Proceedings of the 14th European Conference on Artificial Life ECAL 2017

View full text Add to dashboard Cite

Evolving robust behaviors for robots has proven to be a challenging problem. Determining how to optimize behavior for a specific instance, while also realizing behaviors that generalize to variations on the problem often requires highly customized algorithms and problem-specific tuning of the evolutionary platform. Algorithms that can realize robust, generalized behavior without this customization are therefore highly desirable. In this paper, we examine the Lexicase selection algorithm as a possible general algorithm for a wall crossing robot task. Previous work has resulted in specialized strategies to evolve robust behaviors for this task. Here, we show that Lexicase selection is not only competitive with these strategies but after parameter tuning, actually exceeds the performance of the specialized algorithms.

show abstract

Evolutionary Robotics

Cited by 125 publications

References 107 publications

Embedded Evolutionary Robotics: The (1+1)-Restart-Online Adaptation Algorithm

Embedded Evolutionary Robotics: The (1+1)-Restart-Online Adaptation Algorithm

From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation

Lexicase selection outperforms previous strategies for incremental evolution of virtual creature controllers

Contact Info

Product

Resources

About