检索结果-内蒙古大学图书馆

Lessons from Speciation Dynamics: How to Generate Selective Pressure Towards Diversity

ARTIFICIAL LIFE 2015年第4期21卷 464-480页

作者： Hamann, Heiko Univ Paderborn Paderborn Germany

Recent approaches in evolutionary robotics (ER) propose to generate behavioral diversity in order to evolve desired behaviors more easily. These approaches require the definition of a behavioral distance, which often includes task-specific features and hence a priori knowledge. Alternative methods, which do not explicitly force selective pressure towards diversity (SPTD) but still generate it, are known from the field of artificial life, such as in artificial ecologies (AEs). In this study, we investigate how SPTD is generated without task-specific behavioral features or other forms of a priori knowledge and detect how methods of generating SPTD can be transferred from the domain of AE to ER. A promising finding is that in both types of systems, in systems from ER that generate behavioral diversity and also in the investigated speciation model, selective pressure is generated towards unpopulated regions of search space. In a simple case study we investigate the practical implications of these findings and point to options for transferring the idea of self-organizing SPTD in AEs to the domain of ER.

关键词： evolutionary robotics speciation selection

来源：评论

学校读者我要写书评

暂无评论

Behavioral diversity measures for evolutionary robotics

Behavioral diversity measures for Evolutionary Robotics

引用

2010 IEEE World Congress on Computational Intelligence

作者： Doncieux, Stephane Mouret, Jean-Baptiste Univ Paris 06 ISIR CNRS UMR 7222 F-75005 Paris France

ISBN: (纸本)9781424481262

In evolutionary robotics (ER), explicitly rewarding for behavioral diversity recently revealed to generate efficient results without recourse to complex fitness functions. The principle of such approaches is to explicitly encourage diversity in the robot behavior space instead of in the space of genotypes (the space explored by the evolutionary algorithm) or the space of phenotypes (the space of robot controllers and morphologies). To implement such approaches, a similarity between behaviors needs to be evaluated but, up to now, used similarity measures are problem-specific. The goal of this work is to explore generic behavioral similarity measures that only rely on sensori-motor values. With such a measure, we managed to evolve the topology and the parameters of neuro-controllers that make a simulated robot go towards a ball, take it, find a basket, put the ball into the basket, perform a half-turn, search and take another ball, put it into the basket, etc. In this experiment, two objectives were simultaneously optimized with NSGA-II: the number of collected balls and the generic behavioral diversity objective. Several generic behavioral measures are compared. To confirm the interpretation of behavioral diversity objective and in an attempt to characterize behavioral similarity measures, they are also compared to human-made behavioral similarity evaluations. They reveal to classify behaviors globally as humans did, but with no clear correlation between the closeness to human classification and the efficiency within an evolutionary run.

关键词： NSGA-II evolutionary algorithm evolutionary robotics generic behavioral diversity measures generic behavioral similarity measures genetic algorithms human-made behavioral similarity evaluations neurocontrollers robot behavior space robot controllers robot morphologies robots sensori-motor values

来源：评论

学校读者我要写书评

暂无评论

Supplanting Neural Networks with ODEs in evolutionary robotics

Supplanting Neural Networks with ODEs in Evolutionary Roboti...

引用

8th International Conference of Simulated Evolution and Learning

作者： Grouchy, Paul D'Eleuterio, Gabriele M. T. Univ Toronto Inst Aerosp Studies Toronto ON Canada

ISBN: (纸本)9783642172977

A new approach to evolutionary robotics is presented. Neural networks are abstracted and supplanted by a system of ordinary differential equations that govern the changes in controller outputs. The equations are evolved as trees using an evolutionary algorithm based on symbolic regression in genetic programming. Initial proof-of-concept experiments are performed using a simulated two-wheeled robot that must drive a straight line while wheel response properties vary. Evolved controllers demonstrate the ability to learn and adapt;to a changing environment, as well as the ability to generalize and perform well in novel situations.

关键词： evolutionary robotics Genetic Programming evolutionary Algorithms Genetic Algorithms evolutionary Computing Learning

来源：评论

学校读者我要写书评

暂无评论

A Case Study on the Scalability of Online Evolution of Robotic Controllers 17th

A Case Study on the Scalability of Online Evolution of Robot...

引用

17th Portuguese Conference on Artificial Intelligence (EPIA)

作者： Silva, Fernando Correia, Luis Christensen, Anders Lyhne BioMachines Lab Lisbon Portugal Inst Telecomunicacoes Lisbon Portugal Inst Univ Lisboa ISCTE IUL Lisbon Portugal Univ Lisbon Fac Ciencias BioISI Lisbon Portugal

ISBN: (纸本)9783319234854;9783319234847

Online evolution of controllers on real robots typically requires a prohibitively long evolution time. One potential solution is to distribute the evolutionary algorithm across a group of robots and evolve controllers in parallel. No systematic study on the scalability properties and dynamics of such algorithms with respect to the group size has, however, been conducted to date. In this paper, we present a case study on the scalability of online evolution. The algorithm used is odNEAT, which evolves artificial neural network controllers. We assess the scalability properties of odNEAT in four tasks with varying numbers of simulated e-puck-like robots. We show how online evolution algorithms can enable groups of different size to leverage their multiplicity, and how larger groups can: (i) achieve superior task performance, and (ii) enable a significant reduction in the evolution time and in the number of evaluations required to evolve controllers that solve the task.

关键词： evolutionary robotics Artificial neural network evolutionary algorithm Online evolution Robot control Scalability

来源：评论

学校读者我要写书评

暂无评论

Devising Effective Novelty Search Algorithms: A Comprehensive Empirical Study 15

Devising Effective Novelty Search Algorithms: A Comprehensiv...

引用

17th Genetic and evolutionary Computation Conference (GECCO)

作者： Gomes, Jorge Mariano, Pedro Christensen, Anders Lyhne Univ Lisbon BioISI BioMachines Lab P-1699 Lisbon Portugal Univ Lisbon BioISI Inst Telecomunicacoes P-1699 Lisbon Portugal Univ Lisbon Fac Ciencias BioISI Lisbon Portugal BioMachines Lab Lisbon Portugal Inst Telecomunicacoes Lisbon Portugal Inst Univ Lisboa ISCTE IUL Lisbon Portugal

ISBN: (纸本)9781450334723

Novelty search is a state-of-the-art evolutionary approach that promotes behavioural novelty instead of pursuing a static objective. Along with a large number of successful applications, many different variants of novelty search have been proposed. It is still unclear, however, how some key parameters and algorithmic components influence the evolutionary dynamics and performance of novelty search. In this paper, we conduct a comprehensive empirical study focused on novelty search's algorithmic components. We study the k parameter - the number of nearest neighbours used in the computation of novelty scores;the use and function of an archive;how to combine novelty search with fitness-based evolution;and how to con figure the mutation rate of the underlying evolutionary algorithm. Our study is conducted in a simulated maze navigation task. Our results show that the con figuration of novelty search can have a significant impact on performance and behaviour space exploration. We conclude with a number of guidelines for the implementation and con figuration of novelty search, which should help future practitioners to apply novelty search more effectively.

关键词： Novelty search evolutionary robotics neuroevolution premature convergence empirical study

来源：评论

学校读者我要写书评

暂无评论

Three-fold Adaptivity in Groups of Robots: The Effect of Social Learning 15

Three-fold Adaptivity in Groups of Robots: The Effect of Soc...

引用

17th Genetic and evolutionary Computation Conference (GECCO)

作者： Heinerman, Jacqueline Drupsteen, Dexter Eiben, A. E. Vrije Univ Amsterdam Amsterdam Netherlands Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781450334723

Adapting the control systems of robots on the fly is important in robotic systems of the future. In this paper we present and investigate a three-fold adaptive system based on evolution, individual and social learning in a group of robots and report on a proof-of-concept study based on e-pucks. We distinguish inheritable and learnable components in the robots' makeup, specify and implement operators for evolution, learning and social learning, and test the system in an arena where the task is to learn to avoid obstacles. In particular, we make the sensory layout evolvable, the locomotion control system learnable and investigate the effects of including social learning in the 'adaptation engine'. Our simulation experiments demonstrate that the full mix of three adaptive mechanisms is practicable and that adding social learning leads to better controllers faster.

关键词： evolutionary robotics on-line evolution individual learning social learning obstacle avoidance neural networks

来源：评论

学校读者我要写书评

暂无评论

Evolving Generalised Maze Solvers 18

引用

18th European Conference on Applications of evolutionary Computation (EvoApplications) as part of EvoSTAR Conference

作者： Shorten, David Nitschke, Geoff Univ Cape Town Dept Comp Sci ZA-7700 Cape Town South Africa

ISBN: (纸本)9783319165486;9783319165493

This paper presents a study of the efficacy of comparative controller design methods that aim to produce generalised problem solving behaviours. In this case study, the goal was to use neuro-evolution to evolve generalised maze solving behaviours. That is, evolved robot controllers that solve a broad range of mazes. To address this goal, this study compares objective, non-objective and hybrid approaches to direct the search of a neuro-evolution controller design method. The objective based approach was a fitness function, the non-objective based approach was novelty search, and the hybrid approach was a combination of both. Results indicate that, compared to the fitness function, the hybrid and novelty search evolve significantly more maze solving behaviours that generalise to larger and more difficult maze sets. Thus this research provides empirical evidence supporting novelty and hybrid novelty-objective search as approaches for potentially evolving generalised problem solvers.

关键词： Neuro-Evolution evolutionary robotics Novelty search Maze solving

来源：评论

学校读者我要写书评

暂无评论

Crowdseeding: A Novel Approach for Designing Bioinspired Machines 4th

引用

4th International Conference on Biomimetic and Biohybrid Systems (Living Machines)

作者： Wagy, Mark D. Bongard, Josh C. Univ Vermont Dept Comp Sci Burlington VT 05405 USA

ISBN: (纸本)9783319229799;9783319229782

Crowdsourcing is a popular technique for distributing tasks to a group of anonymous workers over the web. Similarly, crowdseeding is any mechanism that extracts knowledge from the crowd, and then uses that knowledge to guide an automated process. Here we demonstrate a method that automatically distills features from a set of robot body plans designed by the crowd, and then uses those features to guide the automated design of robot body plans and controllers. This approach outperforms past work in which one feature was detected and distilled manually. This provides evidence that the crowd collectively possesses intuitions about the biomechanical advantages of certain body plans;we hypothesize that these intuitions derive from their experiences with biological organisms.

关键词： evolutionary robotics Biomimetics Crowdsourcing Data mining Machine learning

来源：评论

学校读者我要写书评

暂无评论

Decentralized Innovation Marking for Neural Controllers in Embodied Evolution 15

Decentralized Innovation Marking for Neural Controllers in E...

引用

17th Genetic and evolutionary Computation Conference (GECCO)

作者： Perez, Inaki Fernandez Boumaza, Amine Charpillet, Francois Univ Lorraine Loria UMR 7503 F-54500 Vandoeuvre Les Nancy France CNRS Loria UMR 7503 F-54500 Vandoeuvre Les Nancy France Inria F-54600 Villers Les Nancy France

ISBN: (纸本)9781450334723

We propose a novel innovation marking method for Neuro-Evolution of Augmenting Topologies in Embodied evolutionary robotics. This method does not rely on a centralized clock, which makes it well suited for the decentralized nature of EE where no central evolutionary process governs the adaptation of a team of robots exchanging messages locally. This method is inspired from event dating algorithms, based on logical clocks, that are used in distributed systems, where clock synchronization is not possible. We compare our method to odNEAT, an algorithm in which agents use local time clocks as innovation numbers, on two multi-robot learning tasks: navigation and item collection. Our experiments showed that the proposed method performs as well as odNEAT, with the added benefit that it does not rely on synchronization of clocks and is not affected by time drifts.

关键词： evolutionary robotics Swarm robotics Online algorithms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Evolving Robot Controllers for Structured Environments Through Environment Decomposition 18

引用

18th European Conference on Applications of evolutionary Computation (EvoApplications) as part of EvoSTAR Conference

作者： Moreno, Rodrigo Faina, Andres Stoy, Kasper Univ Nacl Colombia Bogota Colombia IT Univ Copenhagen Copenhagen Denmark

ISBN: (纸本)9783319165486;9783319165493

In this paper we aim to develop a controller that allows a robot to traverse an structured environment. The approach we use is to decompose the environment into simple sub-environments that we use as basis for evolving the controller. Specifically, we decompose a narrow corridor environment into four different sub-environments and evolve controllers that generalize to traverse two larger environments composed of the sub-environments. We also study two strategies for presenting the sub-environments to the evolutionary algorithm: all sub-environments at the same time and in sequence. Results show that by using a sequence the evolutionary algorithm can find a controller that performs well in all sub-environments more consistently than when presenting all sub-environments together. We conclude that environment decomposition is an useful approach for evolving controllers for structured environments and that the order in which the decomposed sub-environments are presented in sequence impacts the performance of the evolutionary algorithm.

关键词： evolutionary robotics Environment decomposition Sequential evolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：