检索结果-内蒙古大学图书馆

15th Genetic and evolutionary Computation Conference (GECCO)

作者： Dinu, Cristian M. Dimitrov, Plamen Weel, Berend Eiben, A. E. Vrije Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781450319638

This paper is concerned with on-line evolutionary robotics, where robot controllers are being evolved during a robots' operative time. This approach offers the ability to cope with environmental changes without human intervention, but to be effective it needs an automatic parameter control mechanism to adjust the evolutionary algorithm (EA) appropriately. In particular, mutation step sizes (sigma) and the time spent on fitness evaluation (tau) have a strong influence on the performance of an EA. In this paper, we introduce and experimentally validate a novel method for self-adapting tau during runtime. The results show that this mechanism is viable: the EA using this self-adaptative control scheme consistently shows decent performance without a priori tuning or human intervention during a run.

关键词： evolutionary robotics Swarm robotics On-line Evolution Embodied Evolution Dynamic Environments

来源：评论

学校读者我要写书评

暂无评论

Evolution of a jump in an articulated leg with series-elastic actuation

Evolution of a jump in an articulated leg with series-elasti...

引用

IEEE International Conference on robotics and Automation

作者： Curran, Simon Orin, David E. Ohio State Univ Dept Elect & Comp Engn Columbus OH 43210 USA

ISBN: (纸本)9781424416462

The remarkable ability of humans and animals to perform dynamic maneuvers, such as a jump, is largely attributed to series-elastic elements in skeletal muscle. Both the degree of elasticity and the coordination of muscular contractions have been shown to impact jump performance. The objective of this paper is to use a genetic algorithm (GA) to optimize the control and actuator parameters of a series-elastic actuator (SEA), which is functionally analogous to skeletal muscle, in an articulated leg to produce the highest jump. Similar to skeletal muscle, the control and stiffness of the SEA is found by the GA to affect jump performance, yielding solutions with biological properties. In particular, the jumps evolved by the GA made use of the stretch and shortening cycle of the series-elasticity, which is contmonly seen in nature to increase the force of an explosive movement. The model studied in this paper is of a prototype leg with series-elastic actuation. A detailed leg and actuator model was developed to include the important electrical and mechanical properties of the DC motors as well as the characteristics of the motor amplifiers.

关键词： dynamic maneuvers jump legged robot series-elastic actuation (SEA) evolutionary robotics

来源：评论

学校读者我要写书评

暂无评论

Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots 27th

Investigating Premature Convergence in Co-optimization of Mo...

引用

27th European Conference on Genetic Programming (EuroGP) Held as Part of EvoStar Conference27th European Conference on Genetic Programming (EuroGP)

作者： Mertan, Alican Cheney, Nick Univ Vermont Burlington VT 05401 USA

ISBN: (纸本)9783031569562;9783031569579

Evolving virtual creatures is a field with a rich history and recently it has been getting more attention, especially in the soft robotics domain. The compliance of soft materials endows soft robots with complex behavior, but it also makes their design process unintuitive and in need of automated design. Despite the great interest, evolved virtual soft robots lack the complexity, and co-optimization of morphology and control remains a challenging problem. Prior work identifies and investigates a major issue with the co-optimization process - fragile co-adaptation of brain and body resulting in premature convergence of morphology. In this work, we expand the investigation of this phenomenon by comparing learnable controllers with proprioceptive observations and fixed controllers without any observations, whereas in the latter case, we only have the optimization of the morphology. Our experiments in two morphology spaces and two environments that vary in complexity show, concrete examples of the existence of high-performing regions in the morphology space that are not able to be discovered during the co-optimization of the morphology and control, yet exist and are easily findable when optimizing morphologies alone. Thus this work clearly demonstrates and characterizes the challenges of optimizing morphology during co-optimization. Based on these results, we propose a new body-centric framework to think about the co-optimization problem which helps us understand the issue from a search perspective. We hope the insights we share with this work attract more attention to the problem and help us to enable efficient brain-body co-optimization.

关键词： evolutionary robotics Soft robotics Brain-body co-optimization

来源：评论

学校读者我要写书评

暂无评论

Effect of Animat Complexity on the Evolution of Hierarchical Control 17

Effect of Animat Complexity on the Evolution of Hierarchical...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Moore, Jared M. Clark, Anthony J. McKinley, Philip K. Grand Valley State Univ Sch Comp & Informat Syst Allendale MI 49401 USA Missouri State Univ Comp Sci Dept Springfield MO USA Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA

ISBN: (纸本)9781450349208

Animal movements are realized by a combination of high-level control from the nervous system and joint-level movement provided by the musculoskeletal system. The digital muscle model (DMM) emulates the low-level musculoskeletal system and can be combined with a high-level artificial neural network (ANN) controller forming a hybrid control strategy. Previous work has shown that, compared to ANN-only controllers, hybrid ANN/DMM controllers exhibit similar performance with fewer synapses, suggesting that some computation is offloaded to the low-level DMM. An open question is how the complexity of the robot, in terms of the number of joints, affects the evolution of the ANN control structure. We explore this question by evolving both hybrid controllers and ANN-only controllers for worm-like animats of varying complexity. Specifically, the number of joints in the worms ranges from 1 to 12. Consistent with an earlier study, the results demonstrate that, in most cases, hybrid ANN/DMM controllers exhibit equal or better performance than ANN-only controllers. In addition, above a threshold for animat complexity (number of joints), the ANNs for one variant of the hybrid controllers have significantly fewer connections than the ANN-only controllers.

关键词： evolutionary robotics artificial neural networks digital muscle model animats controller evolution

来源：评论

学校读者我要写书评

暂无评论

A Species-based Approach to Brain-Body Co-Evolution of Modular Robots 12

A Species-based Approach to Brain-Body Co-Evolution of Modul...

引用

14th International Conference on Genetic and evolutionary Computation Conference (GECCO)

作者： Zhang, Yuyang Meng, Yan Stevens Inst Technol Hoboken NJ 07030 USA

ISBN: (纸本)9781450311786

Compared with fixed morphology robotic systems, self-reconfigurable modular (SRM) robots can reconfigure themselves to form a variety of morphologies, and carry on various types of motions. Recently, some co-evolutionary approaches have been proposed to co-evolve the robot morphology and associated controller simultaneously for locomotion tasks. However, these co-evolution approaches don't consider some physical limitations of SRM robots and usually request longer evolution process due to extensive searching space. To address these issues, we proposed a species-based co-evolution (S-CoE) algorithm. The S-CoE algorithm is applied on a simulated modular robot system and evaluated under two testing scenarios.

关键词： evolutionary robotics Self-Reconfigurable Modular Robots Brain-Body Co-Evolution

来源：评论

学校读者我要写书评

暂无评论

Sensitivity to social contingency or stability of interaction? Modelling the dynamics of perceptual crossing

引用

NEW IDEAS IN PSYCHOLOGY 2008年第2期26卷 278-294页

作者： Di Paolo, Ezequiel A. Rohde, Marieke Iizuka, Hiroyuki Univ Sussex Ctr Computat Ncurosci & Robot Dept Informat Brighton BN1 9QH E Sussex England Future Univ Hakodate Dept Media Architecture Hakodate Hokkaido 0418655 Japan

We introduce a series of evolutionary robotics simulations that address the behaviour of individuals in socially contingent interactions. The models are based on a recent study by Auvray, Lenay and Stewart [(2006). The attribution of intentionality in a simulated environment: The case of minimalist devices. In Tenth meeting of the association for the scientific study of consciousness, Oxford, UK, 23-26 June, 2006] on tactile perceptual crossing in a minimal virtual environment. In accordance, both the empirical experiments and our simulations point out the essential character of global embodied interaction dynamics for the sensitivity to contingency to arise. Rather than being individually perceived by any of the interactors, sensitivity to contingency arises from processes of circular causality that characterise the collective dynamics. Such global dynamical aspects are frequently neglected when studying social cognition. Furthermore, our synthetic studies point out interesting aspects of the task that are not immediately obvious in the empirical data. They, in addition, generate new hypotheses for further experiments. We conclude by promoting a minimal but tractable, dynamic and embodied account to social interaction, combining synthetic and empirical findings as well as concrete predictions regarding sensorimotor strategies, the role of time-delays and robustness to perturbations in interactive dynamics. (C) 2007 Elsevier Ltd. All rights reserved.

关键词： perceptual crossing social contingency agency interaction dynamics evolutionary robotics simulation modelling

来源：评论

学校读者我要写书评

暂无评论

Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds 1

引用

22nd International Conference on Applications of evolutionary Computation (EvoApplications) Held as Part of EvoStar Conference

作者： Nygaard, Tonnes F. Martin, Charles P. Torresen, Jim Glette, Kyrre Univ Oslo Oslo Norway

ISBN: (数字)9783030166922

ISBN: (纸本)9783030166915;9783030166922

The complexity of a legged robot's environment or task can inform how specialised its gait must be to ensure success. Evolving specialised robotic gaits demands many evaluations-acceptable for computer simulations, but not for physical robots. For some tasks, a more general gait, with lower optimization costs, could be satisfactory. In this paper, we introduce a new type of gait controller where complexity can be set by a single parameter, using a dynamic genotype-phenotype mapping. Low controller complexity leads to conservative gaits, while higher complexity allows more sophistication and high performance for demanding tasks, at the cost of optimization effort. We investigate the new controller on a virtual robot in simulations and do preliminary testing on a real-world robot. We show that having variable complexity allows us to adapt to different optimization budgets. With a high evaluation budget in simulation, a complex controller performs best. Moreover, real-world evolution with a limited evaluation budget indicates that a lower gait complexity is preferable for a relatively simple environment.

关键词： evolutionary robotics Real-world evolution Legged robots

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Environments to Test the General Learning Capabilities of AI Agents 14

Automated Generation of Environments to Test the General Lea...

引用

16th Genetic and evolutionary Computation Conference (GECCO)

作者： Coleman, Oliver J. Blair, Alan D. Clune, Jeff Univ New S Wales Sch Comp Sci & Engn Sydney NSW 2052 Australia Univ Wyoming Dept Comp Sci Evolving AI Lab Laramie WY 82071 USA

ISBN: (纸本)9781450326629

Algorithms for evolving agents that learn during their lifetime have typically been evaluated on only a handful of environments. Designing such environments is labour intensive, potentially biased, and provides only a small sample size that may prevent accurate general conclusions from being drawn. In this paper we introduce a method for automatically generating MDP environments which allows the difficulty to be scaled in several ways. We present a case study in which environments are generated that vary along three key dimensions of difficulty: the number of environment configurations, the number of available actions, and the length of each trial. The study reveals interesting differences between three neural network models - Fixed-Weight, Plastic-Weight, and Modulated Plasticity - that would not have been obvious without sweeping across these different dimensions. Our paper thus introduces a new way of conducting reinforcement learning science: instead of manually designing a few environments, researchers will be able to automatically generate a range of environments across key dimensions of variation. This will allow scientists to more rigorously assess the general learning capabilities of an algorithm, and may ultimately improve the rate at which we discover how to create AI with general purpose learning.

关键词： Experimentation Algorithms evolutionary robotics Generative encodings Neural networks Learning Neuromodulation

来源：评论

学校读者我要写书评

暂无评论

Novelty Search: a Theoretical Perspective

Novelty Search: a Theoretical Perspective

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Doncieux, Stephane Laflaquiere, Alban Coninx, Alexandre Sorbonne Univ CNRS ISIR F-75005 Paris France SoftBank Robot Europe AI Lab Paris France

ISBN: (纸本)9781450361118

Novelty Search is an exploration algorithm driven by the novelty of a behavior. The same individual evaluated at different generations has different fitness values. The corresponding fitness landscape is thus constantly changing and if, at the scale of a single generation, the metaphor of a fitness landscape with peaks and valleys still holds, this is not the case anymore at the scale of the whole evolutionary process. How does this kind of algorithms behave? Is it possible to define a model that would help understand how it works? This understanding is critical to analyse existing Novelty Search variants and design new and potentially more efficient ones. We assert that Novelty Search asymptotically behaves like a uniform random search process in the behavior space. This is an interesting feature, as it is not possible to directly sample in this space: the algorithm has a direct access to the genotype space only, whose relationship to the behavior space is complex. We describe the model and check its consistency on a classical Novelty Search experiment. We also show that it sheds a new light on results of the literature and suggests future research work.

关键词： Novelty search evolutionary robotics theory behavior space

来源：评论

学校读者我要写书评

暂无评论

An Approach to Representation Learning in Morphological Robot Evolution

An Approach to Representation Learning in Morphological Robo...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Stuurman, Aart C. Yaman, Anil Eiben, A.E. Vrije Universiteit Amsterdam Netherlands

ISBN: (纸本)9781665430654

A key challenge for evolving complex physical ob-jects is to design a representation, that is, to devise suitable genotypes and a good mapping from genotypes to phenotypes (the objects to be evolved). This paper outlines a new approach to address this challenge for evolving robot morphologies and presents a proof-of-concept study to assess its feasibility. The key idea is to design genotype-phenotype mappings using variational autoencoders. This idea is implemented and tested for the evolution of modular robots for a locomotion task. The experiments show the practicability of this idea where the representation is not hand-designed, but algorithmically generated. This indicates a great future potential for the evolution of complex objects where there are no straightforward representations to use. © 2023 IEEE.

关键词： evolutionary robotics genotype-phenotype mapping morphological evolution representation

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：