检索结果-内蒙古大学图书馆

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Caleb Chuck Supawit Chockchowwat Scott Niekum The University of Texas at Austin Personal Robotics and Automation Lab.

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample efficiency, partially because they aim to be entirely problem-agnostic. In this work, we introduce a novel approach to exploration and hierarchical skill learning that derives its sample efficiency from intuitive assumptions it makes about the behavior of objects both in the physical world and simulations which mimic physics. Specifically, we propose the Hypothesis Proposal and Evaluation (HyPE) algorithm, which discovers objects from raw pixel data, generates hypotheses about the controllab.lity of observed changes in object state, and learns a hierarchy of skills to test these hypotheses. We demonstrate that HyPE can dramatically improve the sample efficiency of policy learning in two different domains: a simulated robotic blockpushing domain, and a popular benchmark task: Breakout. In these domains, HyPE learns high-scoring policies an order of magnitude faster than several state-of-the-art reinforcement learning methods.

关键词： Transfer learning Reinforcement learning Proposals Task analysis Standards Physics Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

What is the basic semantic unit of chinese language? A computational approach based on topic models

What is the basic semantic unit of chinese language? A compu...

引用

12th Meeting on Mathematics of Language, MOL 12

作者： Zhao, Qi Qin, Zengchang Wan, Tao Intelligent Computing and Machine Learning Lab. School of Automation Science and Electrical Engineering Beihang University Beijing China Robotics Institute Carnegie Mellon University United States

ISBN: (纸本)9783642232107

Chinese language has been generally regarded as a Subject-Verb -Object (SVO) language and the basic semantic unit is the Chinese word that is usually consisted by two or more Chinese characters. However, word-centered structure of Chinese language has been controversial in linguistics. Some recent research in computational linguistics in Chinese language suggests that the character-based models perform better than the word-based models in some applications such word segmentation. In this paper, the word-based topic models and the character-based models are tested for modeling Chinese language, respectively. By empirical studies, we demonstrated the effectiveness of using Chinese characters as the basic semantic units. These two models have close performance in text classifications while the character-based model has a better quality in language modeling and a much smaller vocabulary. By testing on a bilingual corpus, three independent topic models based on Chinese words, Chinese characters and English words are trained and compared to each other. we verify the capability of topic models in modeling semantics by experiments across Chinese and English. The classification accuracy can also be boosted up by aggregating the classification results from the three independent topic models. © 2011 Springer-Verlag.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Behavior of Smith predictor in teleoperation systems with modeling and delay time errors

Behavior of Smith predictor in teleoperation systems with mo...

引用

Proceedings of 2003 IEEE Conference on Control Applications

作者： Ganjefar, S. Momeni, H. Sharifi, F. Janabi Beheshti, M.T. Hamidi Department of Electrical Engineering Tarbiat Modares University Tehran Iran Robotics and Mfg. Automation Lab. Department of MAIE Ryerson University Toronto Ont. Canada

In this paper, behavior of teleoperation systems with modeling error and error of delay time in Smith predictor is discussed. In teleoperation systems usually there is a large distance between Master system and Slave system. In this case there is always an error in modeling of system. The condition for stability of teleoperation systems with modeling error is derived by introducing of a theorem. This theorem can assist a designer in ensuring the stability of the teleoperation system. Also, error of delay time and stability of teleoperation systems by using of Internet as communication channel are discussed. The effect of delay time prediction on the system stability and performance is studied and it is shown that delay time prediction could improve system performance. Simulation results are presented to verify the obtained results.

关键词： Control system analysis

来源：评论

学校读者我要写书评

暂无评论

Generation of new robot skills from learned skills 19

Generation of new robot skills from learned skills

引用

19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014

作者： García, Daniel Hernández Monje, Concepción A. Balaguer, Carlos Universidad Carlos III de Madrid Robotics Lab. Department of Systems and Automation Engineering Av. de la Universidad 30 Leganés Madrid28911 Spain

ISBN: (纸本)9783902823625

Future humanoid robots, working beside humans in complex dynamic environments, would be required to perform a wide repertoire of task. To this end traditional methods for deriving a control policy won't succeed, learning approaches are fundamental. Learning from demonstrations (LfD) techniques have appear as a means for developing intuitive control methods and generalize a skill based on a set of demonstrations. However, learning appropriate skills for every conceivable scenario the robot may encounter would still be a daunting undertaking. In this work we propose a framework for the generation and adaptation of new robot skills from previously learned skill models. Using previously learned models of a robot skill, and knowledge of the current task, the models of a skill is adapted to generate a new task by a merger or combination operation over the given robot skill models. © IFAC.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Knowledge base representation for humanoid robot skills 19

Knowledge base representation for humanoid robot skills

引用

19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014

ISBN: (纸本)9783902823625

The ultimate goal for humanoid robotics research is to develop humanoid robotic systems capable and flexible enough to handle the challenge of working alongside human in complex natural environments performing everyday tasks. To reach this goal it is key to develop appropriate structures in which to organize the acquire knowledge in a manner that allows the system to retrieve it in order to use it to fulfil its missions. In this work a knowledge base representation of the robot skills knowledge organized in terms of the relationships between objects, actions and event frames is proposed. © IFAC.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Design and realization of a wireless drive microrobot

Design and realization of a wireless drive microrobot

引用

WCICA 2004 - Fifth World Congress on Intelligent Control and automation, Conference Proceedings

作者： Zhu, Tao Tan, Dalong Shi, Pu Yan, Chunli Robotics Lab. Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Liaoning Province China Traffic and Transport Institute Northeast Forestry University Harbin Heilongjiang Province China

ISBN: (纸本)0780382730

With the increasing of micro parts, much attention has been paid to development of micro devices, which can handle those micro parts. We present a novel wireless microrobot based on the deformation of piezoelectric. The microrobot can fulfill both long distance transport and precise positioning. With three drive units arranged at apexes of an equilateral triangle, omnidirectional motion can be achieved. The author mainly discusses its driving principle and wireless control strategies. Some experimental results are also given to examine the effects of related parameters on its kinematics characteristics.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Generation and adaptation of robot skills models 14

Generation and adaptation of robot skills models

引用

2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014

作者： García, Daniel Hernández Monje, Concepción A. Balaguer, Carlos Robotics Lab. Department of Systems and Automation Engineering Universidad Carlos III de Madrid Av. de la Universidad 30 Leganés Madrid28911 Spain

ISBN: (纸本)9781479971749

Humanoid robots are required to perform a wide repertoire of task working beside humans in complex dynamic environments. Learning mechanism are important for building up this type of repertoires of robot skills, however, despite the clear advantages of this approaches it would be impractical to teach the robot skills for every needed task and for every foreseen situation. Robot skills learning approaches to develop humanoid robotic systems would have greater impact if the models of the skill can be operated upon to generate new behaviours of increasing levels of complexity. A framework that allows the adaptation of a robot previously learned motion skills to new unseen contexts is necessary. In this work we present different modalities for the adaptation and generation of new skill models based on the already learned models of skills. Experimental results are presented to validate this approach. © 2014 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Advanced Methods for Evolutionary Optimisation

引用

IFAC Proceedings Volumes 1998年第20期31卷 1121-1128页

作者： P. Adamidis S. Kazarlis V. Petridis Automation and Robotics Lab. Dept. of Electrical & Computer Eng. Aristotle University of Thessaloniki Greece

In this paper we present two advanced methods for evolutionary optimisation. One method is based on Parallel Genetic Algorithms. It is called Cooperating Populations with Different Evolution Behaviours (CoPDEB), and allows each population to exhibit a different evolution behaviour. Results from two problems show the advantage of using different evolution behaviour on each population. The other method concerns application of GAs on constrained optimisation problems. It is called the Varying Fitness Function (VFF) method and implements a fitness function with varying penalty tenns, added to the objective function for penalising infeasible solutions, in order to assist the GA to easily locate the area of the global optimum. Simulation results on two real world problems show that the VFF method outperfonns the classic static fitness function implementations.

关键词： Genetic Algorithms Parallel Algorithm Behaviour Optimization Methodology

来源：评论

学校读者我要写书评

暂无评论

Visual Odometry for autonomous robot navigation through efficient outlier rejection

Visual Odometry for autonomous robot navigation through effi...

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Ioannis Kostavelis Evangelos Boukas Lazaros Nalpantidis Antonios Gasteratos Robotics and Automation Lab. Democritus University of Thrace Xanthi Greece Robotics Vision and Machine Intelligence Lab. Aalborg University Copenhagen Denmark

The ability of autonomous robots to precisely compute their spatial coordinates constitutes an important attribute. In this regard, Visual Odometry (VO) becomes a most appropriate tool, in estimating the full pose of a camera, placed onboard a robot by analyzing a sequence of images. The paper at hand proposes an accurate computationally-efficient VO algorithm relying exclusively on stereo vision. A non-iterative outlier detection technique capable of efficiently discarding outliers of matched features is suggested. The developed technique is combined with an incremental motion estimation approach to estimate the robot's trajectory. The accuracy of the proposed system has been evaluated both on simulated data and using a real robotic platform. Experimental results from rough terrain routes show remarkable accuracy with positioning errors as low as 1.1%.

关键词： Robot kinematics Estimation Three-dimensional displays Cameras Feature extraction Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Utilisation of soft computing techniques to model abstract manufacturing information

引用

IFAC Proceedings Volumes 2000年第20期33卷 153-158页

作者： Chrysostomos D. Stylios Peter P. Groumpos Lab. for Automation & Robotics Dep. of Electrical & Computer Engineering University of Patras26500 Rion Patras Greece

The paper examines the usefulness of Fuzzy Cognitive Maps in modeling complex systems and specifically their use in modeling manufacturing systems and information from an abstract point of view. Aspects such as Fuzzy Cognitive Map representation and development are presented and PCM use to develop a behavioral model of the system is discussed. Fuzzy Cognitive Maps applicability in modeling complex systems and their use to aggregate different models for the complex system is discussed. A hierarchical structure is proposed, where a Fuzzy Cognitive Map models the supervisor of the system.

关键词： Fuzzy Cognitive Map Modeling Complex Systems Manufacturing Systems

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：