检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

314 篇 期刊文献
310 篇 会议
9 篇 学位论文
2 册 图书

馆藏范围

635 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

587 篇 工学
- 503 篇 计算机科学与技术...
- 171 篇 控制科学与工程
- 107 篇 电气工程
- 52 篇 软件工程
- 12 篇 机械工程
- 6 篇 信息与通信工程
- 4 篇 材料科学与工程（可...
- 4 篇 交通运输工程
- 4 篇 安全科学与工程
- 2 篇 力学（可授工学、理...
- 2 篇 土木工程
- 1 篇 仪器科学与技术
137 篇 理学
- 104 篇 生物学
- 33 篇 数学
- 2 篇 系统科学
- 2 篇 科学技术史(分学科...
- 1 篇 物理学
- 1 篇 化学
- 1 篇 地质学
- 1 篇 统计学（可授理学、...
128 篇 管理学
- 127 篇 管理科学与工程(可...
- 2 篇 图书情报与档案管...
39 篇 教育学
- 37 篇 心理学(可授教育学...
- 3 篇 教育学
28 篇 法学
- 28 篇 社会学
25 篇 农学
- 6 篇 作物学
20 篇 医学
- 17 篇 基础医学(可授医学...
- 10 篇 临床医学
4 篇 哲学
- 4 篇 哲学
1 篇 经济学
- 1 篇 应用经济学

主题

635 篇 evolutionary rob...
70 篇 swarm robotics
35 篇 genetic algorith...
30 篇 neural networks
30 篇 genetic algorith...
27 篇 novelty search
27 篇 artificial neura...
26 篇 neuroevolution
25 篇 evolutionary com...
24 篇 artificial life
22 篇 embodied evoluti...
19 篇 soft robotics
19 篇 evolutionary alg...
18 篇 genetic programm...
18 篇 evolutionary alg...
16 篇 simulation
15 篇 modular robots
14 篇 embodied cogniti...
14 篇 robotics
13 篇 artificial intel...

机构

24 篇 vrije univ amste...
13 篇 inst telecomunic...
12 篇 univ vermont dep...
11 篇 inst univ lisboa...
10 篇 vrije univ amste...
8 篇 cnr inst cognit ...
8 篇 biomachines lab ...
7 篇 univ trieste dep...
7 篇 univ libre bruxe...
7 篇 univ oslo oslo
6 篇 michigan state u...
6 篇 nelson mandela u...
5 篇 univ amsterdam
5 篇 hiroshima univ h...
5 篇 connecticut coll...
5 篇 connecticut coll...
5 篇 sorbonne univ cn...
4 篇 univ oslo dept i...
4 篇 ohio state univ ...
4 篇 univ sussex sch ...

作者

33 篇 eiben a. e.
20 篇 christensen ande...
19 篇 ohkura kazuhiro
17 篇 haasdijk evert
15 篇 glette kyrre
14 篇 doncieux stephan...
14 篇 tuci elio
13 篇 nolfi stefano
13 篇 hiraga motoaki
12 篇 gomes jorge
12 篇 du plessis mathy...
12 篇 bongard josh c.
11 篇 medvet eric
11 篇 bredeche nicolas
10 篇 miras karine
10 篇 bongard josh
10 篇 mouret jean-bapt...
9 篇 de carlo matteo
9 篇 nolfi s
8 篇 husbands p

语言

617 篇 英文
16 篇 其他
2 篇 中文

检索条件"主题词=evolutionary robotics"

共 635 条记录，以下是351-360 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Epistemic autonomy through adaptive sensing

Epistemic autonomy through adaptive sensing

引用

Joint Conference on the Science and Technology of Intelligent Systems ISIC/CIRA/ISAS

作者： Cariani, P Massachusetts Eye & Ear Infirm Eaton Peabody Lab Auditory Physiol Boston MA 02114 USA

ISBN: (纸本)0780344235

Sensors and effecters determine how events in the world at large are related to the internal informational states of organisms and robotic devices. Sensors determine what kinds of distinctions (perceptual categories, features, primitives) can be made on the environment. By "evolving the sensors" perceptual repertoires can be adaptively altered and/or enlarged. To the extent that devices can adaptively choose their own feature primitives for themselves, they gain a greater measure of "epistemic autonomy" vis-a-vis their designers. Such devices are useful in ill-defined situations where the designer does not know a priori what feature primitives are adequate or optimum for solving a particular task. Several general strategies for adaptively altering or augmenting sensor function are proposed: 1) prosthesis: adaptive fabrication of new front-ends for existing sensors (e.g. telescopes), 2) active sensing: using motor-actions to alter what is sensed through interaction (poking, pushing, bending), 3) sensory evolution: adaptive construction of entirely new sensors (adaptive antibody construction, Gordon Pask's electrochemical device) and 4) internalized sensing: "bringing the world into the device" by creating internal, analog representations of the world out of which internal sensors extract newly-relevant properties (perceptual learning). Since many neural sensory representations appear to be analog and iconic in nature, neural assemblies can be adaptively formed to function as internal sensors that can switch behavior according to new perceptual categories.

关键词： evolutionary robotics epistemic autonomy adaptive sensing active sensing semiotics sensory coding sensory prosthesis

来源：评论

学校读者我要写书评

暂无评论

Environment induced emergence of collective behavior in evolving swarms with limited sensing

Environment induced emergence of collective behavior in evol...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： van Diggelen, Fuda Luo, Jie Karaguzel, Tugay Alperen Cambier, Nicolas Ferrante, Eliseo Eiben, A. E. Vrije Univ Amsterdam Noord Holland Netherlands Technol Innovat Inst Abu Dhabi U Arab Emirates

ISBN: (纸本)9781450392372

Designing controllers for robot swarms is challenging, because human developers have typically no good understanding of the link between the details of a controller that governs individual robots and the swarm behavior that is an indirect result of the interactions between swarm members and the environment. In this paper we investigate whether an evolutionary approach can mitigate this problem. We consider a very challenging task where robots with limited sensing and communication abilities must follow the gradient of an environmental feature and use Differential Evolution to evolve a neural network controller for simulated robots. We conduct a systematic study to measure the flexibility and scalability of the method by varying the size of the arena and number of robots in the swarm. The experiments confirm the feasibility of our approach, the evolved robot controllers induced swarm behavior that solved the task. We found that solutions evolved under the harshest conditions (where the environmental clues were the weakest) were the most flexible and that there is a sweet spot regarding the swarm size. Furthermore, we observed collective motion of the swarm, showcasing truly emergent behavior that was not represented in-and selected for during evolution.

关键词： evolutionary robotics Embodied AI Differential evolution evolutionary swarm robotics

来源：评论

学校读者我要写书评

暂无评论

Novelty Search makes Evolvability Inevitable

Novelty Search makes Evolvability Inevitable

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Doncieux, Stephane Paolo, Giuseppe Laflaquiere, Alban Coninx, Alexandre Sorbonne Univ CNRS Inst Syst Intelligents & Robot ISIR F-75005 Paris France SoftBank Robot Europe AI Lab Paris France

ISBN: (纸本)9781450371285

Evolvability is an important feature that impacts the ability of evolutionary processes to find interesting novel solutions and to deal with changing conditions of the problem to solve. The estimation of evolvability is not straight-forward and is generally too expensive to be directly used as selective pressure in the evolutionary process. Indirectly promoting evolvability as a side effect of other easier and faster to compute selection pressures would thus be advantageous. In an unbounded behavior space, it has already been shown that evolvable individuals naturally appear and tend to be selected as they are more likely to invade empty behavior niches. Evolvability is thus a natural byproduct of the search in this context. However, practical agents and environments often impose limits on the reachable behavior space. How do these boundaries impact evolvability? In this context, can evolvability still be promoted without explicitly rewarding it? We show that Novelty Search implicitly creates a pressure for high evolvability even in bounded behavior spaces, and explore the reasons for such a behavior. More precisely we show that, throughout the search, the dynamic evaluation of novelty rewards individuals which are very mobile in the behavior space, which in turn promotes evolvability.

关键词： Novelty search evolutionary robotics evolvability behavior space

来源：评论

学校读者我要写书评

暂无评论

Towards developing micro-scale robots for inaccessible fluidic environments

Towards developing micro-scale robots for inaccessible fluid...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Colley, M de Souza, G Hagras, H Pounds-Cornish, A Clarke, G Callaghan, V Univ Essex Dept Comp Sci Colchester CO4 3SQ Essex England

ISBN: (纸本)0780385667

In this paper we introduce the development of dedicated hardware capable of controlling autonomous micro-scale robots for fault detection/repair in complex inaccessible fluidic environments. This work is part of a European Union funded project entitled SOCIAL, (Self-Organized societies of Connectionist Intelligent Agents capable of Learning No IST-2001-38911). The project's aim is to produce a swarm of micro-scale (5cm(3)) autonomous robots that, through indirect communication, are capable of achieving fault detection and reparation in difficult, challenging and inaccessible environments. An application benchmark for this project is the on-line monitoring and maintenance of underwater pipelines like those found in the oil industry or desalination plants. The robots would move through the fluidic environment, continuously sensing for corrosion and scaling faults in the pipeline.

关键词： Spiking Neural Networks evolutionary robotics FPGA hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

Exploration Of Unknown Environments Via Evolution Of Behavioral And Morphological Properties Of Miniaturized Sensory Agents 22

Exploration Of Unknown Environments Via Evolution Of Behavio...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Sariman, Cagatay Hallawa, Ahmed Sayar, Erdi Peine, Arne Martin, Lukas Schmeink, Anke Univ Hosp RWTH Aachen Aachen Germany Tech Univ Munich Munich Germany Rhein Westfal TH Aachen Aachen Germany

ISBN: (纸本)9781450392686

In this work, we propose a framework to evolve morphology and behavior of resource-constrained miniaturized sensory agents. One key application of this framework is the exploration of unknown environments. Consequently, we demonstrate its ability to solve multi-objective optimization problem by applying it to an environment exploration task. The goal is to find the position of a pollution source in a U-shaped fluid pipe with unknown fluid dynamics properties. Firstly, morphological evolution is set to find the optimal physical shape for an agent so that it passes through six target points inside the pipe, i.e. it follows a certain trajectory. Based on that, behavioral evolution optimizes then the sensor controller of an agent and tries to solve a Pareto-optimization problem where the objectives are (1) to measure accurately chemical particle concentrations, (2) to measure depth of the agent while in the environment and (3) to minimize power consumption while using the sensors by altering their operation frequencies. We executed 24000 simulations and the best agent hit the target points with accuracy 91% and reached the maximum performance possible in first and second objectives while reducing the power usage by 86.6%, compared to fixed frequency rate.

关键词： evolutionary robotics earth sciences and the environment morphological evolution

来源：评论

学校读者我要写书评

暂无评论

Encouraging Creative Thinking in Robots Improves Their Ability to Solve Challenging Problems 14

Encouraging Creative Thinking in Robots Improves Their Abili...

引用

16th Genetic and evolutionary Computation Conference (GECCO)

作者： Li, Jingyu Stone, Jed Clune, Jeff Univ Wyoming Laramie High Sch Dept Comp Sci Evolving AI Lab Laramie WY 82071 USA Univ Wyoming Evolving AI Lab Dept Comp Sci Laramie WY 82071 USA

ISBN: (纸本)9781450326629

evolutionary algorithms frequently get stuck on local optima and fail to find the global optimum when local gradients do not point the search process toward the direction of the global optimum. A recent breakthrough called Novelty Search ameliorates this problem by enabling the search process to explore in every direction by encouraging the production of novel, or not-yet-seen, phenotypes (e.g. new robot behaviors). However, a problem with Novelty Search is that it can get lost on "novelty plateaus" wherein novel behaviors in offspring are not immediately produced by mutation and crossover (e.g. when a sequence of specific mutations is required to produce new behaviors, but the intermediate mutations are not rewarded because they do not produce novel behaviors). In such cases, Novelty Search and related approaches that reward behavioral diversity can get stuck. Here we introduce a new approach, borrowed from human psychology, that mitigates this problem: encouraging creative thinking. In addition to rewarding novel behavior, we encourage evolving neural networks to "think differently" by rewarding not-yet-seen firing patterns in hidden neurons, which we call the "Creative Thinking Approach." We hypothesize that encouraging novel thinking can reward stepping stones toward new behaviors. On a variety of challenging robotic control problems from previous publications we demonstrate that, as problem difficulty increases, adding the Creative Thinking Approach increasingly improves performance over simply encouraging novel behaviors. Our results suggest that the Creative Thinking Approach could help improve the scale and complexity of problems that can be solved by evolutionary algorithms.

关键词： Novelty Search Behavioral Diversity evolutionary robotics Creative Thinking Approach

来源：评论

学校读者我要写书评

暂无评论

What You Choose to See Is What You Get: An Experiment with Learnt Sensory Modulation in a Robotic Foraging Task 17

引用

17th European Conference on Applications of evolutionary Computation (EvpApplications)

作者： Rodrigues, Tiago Duarte, Miguel Oliveira, Sancho Christensen, Anders Lyhne Inst Telecomunicacoes Lisbon Portugal Inst Univ Lisboa ISCTE IUL Lisbon Portugal

ISBN: (纸本)9783662455234;9783662455227

In evolutionary robotics, the mapping from raw sensory input to neural network input is typically decided by the experimenter or encoded in the genome. Either way, the mapping remains fixed throughout a robot's lifetime. Inspired by biological sensory organs and the mammalian brain's capacity for selective attention, we evaluate an alternative approach in which a robot has active, real-time control over the mapping from sensory input to neural network input. We augment the neural controllers with additional output neurons that control key sensory parameters and evolve solutions for a single-robot foraging task. The results show that the capacity to control the mapping from raw input to neural network input is exploited by evolution and leads to novel solutions with higher fitness compared to traditional approaches.

关键词： evolutionary robotics dynamic sensors sensor evolution genome-encoding

来源：评论

学校读者我要写书评

暂无评论

Adaptive Team Cooperative Co-Evolution for a Multi-Rover Distribution Problem 23

Adaptive Team Cooperative Co-Evolution for a Multi-Rover Dis...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Fontbonne, Nicolas Maudet, Nicolas Bredeche, Nicolas Sorbonne Univ CNRS ISIR LIP6 F-F75005 Paris France Sorbonne Univ LIP6 F-75005 Paris France Sorbonne Univ CNRS ISIR F-75005 Paris France

ISBN: (纸本)9798400701191

This paper deals with policy learning for a team of heterogeneous robotic agents when the whole team shares a single reward. We address the problem of providing an accurate estimation of the contribution of each agent in tasks where coordination between agents requires joint policy updates of two (or more) agents. This is typically the case when two agents must simultaneously modify their behaviors to perform a joint action that leads to a performance gain for the whole team. We propose a cooperative co-evolutionary algorithm extended with a multi-armed bandit algorithm that dynamically adjusts the number of agents that should update their policies simultaneously, aiming both for performance and learning speed. We use a realistic robotic multi-rover task where agents must physically distribute themselves on points of interest of different natures to complete the task. Results show that the algorithm is able to select the best group size for policy updates that reflects the task's coordination requirements. Surprisingly, we also reveal that coupling between agents' actions in a realistic setup can also emerge from interactions at the phenotypical level, hinting at subtle interactions during learning between the control parameter space and the behavioral space.

关键词： multi-robots multi-agent systems evolutionary robotics multiagent reinforcement learning multi-armed bandits marginal contribution fitness evaluation cooperative coevolution EA

来源：评论

学校读者我要写书评

暂无评论

Evolving Controllers for Robots with Multimodal Locomotion 14th

Evolving Controllers for Robots with Multimodal Locomotion

引用

14th International Conference on the Simulation of Adaptive Behavior (SAB)

作者： Ramos, Rita Duarte, Miguel Oliveira, Sancho Moura Christensen, Anders Lyhne Inst Telecomunicacoes BioMachines Lab Lisbon Portugal IUL ISCTE Lisbon Portugal

ISBN: (纸本)9783319434889;9783319434872

Animals have inspired numerous studies on robot locomotion, but the problem of how autonomous robots can learn to take advantage of multimodal locomotion remains largely unexplored. In this paper, we study how a robot with two different means of locomotion can effective learn when to use each one based only on the limited information it can obtain through its onboard sensors. We conduct a series of simulation-based experiments using a task where a wheeled robot capable of jumping has to navigate to a target destination as quickly as possible in environments containing obstacles. We apply evolutionary techniques to synthesize neural controllers for the robot, and we analyze the evolved behaviors. The results show that the robot succeeds in learning when to drive and when to jump. The results also show that, compared with unimodal locomotion, multimodal locomotion allows for simpler and higher performing behaviors to evolve.

关键词： evolutionary robotics Multimodal locomotion Navigation task

来源：评论

学校读者我要写书评

暂无评论

Learning behaviour-performance maps with meta-evolution

Learning behaviour-performance maps with meta-evolution

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Bossens, David M. Mouret, Jean-Baptiste Tarapore, Danesh Univ Southampton Southampton Hants England Univ Lorraine INRIA CNRS Nancy France

ISBN: (纸本)9781450371285

The MAP-Elites quality-diversity algorithm has been successful in robotics because it can create a behaviorally diverse set of solutions that later can be used for adaptation, for instance to unanticipated damages. In MAP-Elites, the choice of the behaviour space is essential for adaptation, the recovery of performance in unseen environments, since it defines the diversity of the solutions. Current practice is to hand-code a set of behavioural features, however, given the large space of possible behaviour-performance maps, the designer does not know a priori which behavioural features maximise a map's adaptation potential. We introduce a new meta-evolution algorithm that discovers those behavioural features that maximise future adaptations. The proposed method applies Covariance Matrix Adaptation Evolution Strategy to evolve a population of behaviour-performance maps to maximise a meta-fitness function that rewards adaptation. The method stores solutions found by MAP-Elites in a database which allows to rapidly construct new behaviour-performance maps on-the-fly. To evaluate this system, we study the gait of the RHex robot as it adapts to a range of damages sustained on its legs. When compared to MAP-Elites with user-defined behaviour spaces, we demonstrate that the meta-evolution system learns high-performing gaits with or without damages injected to the robot.

关键词： quality-diversity algorithms behavioural diversity meta-learning evolutionary robotics damage recovery

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共64页 << < 32 33 34 35 36 37 38 39 40 41 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：