检索结果-内蒙古大学图书馆

作者： Chamzas, Constantinos Rice University

学位级别：Ph.D., Doctor of Philosophy

Sampling-based planners are effective in many real-world applications such as robotics manipulation, navigation, and even protein modeling. However, in the absence of any prior information, sampling-based planners are forced to explore uniformly or heuristically, which can lead to degraded performance. One way to improve performance is to use prior knowledge of environments to adapt the sampling strategy. In this thesis, we propose Pyre, a retrieval-based framework for learning sampling distributions for high-dimensional motion planning. Pyre decomposes the workspace into local primitives, memorizing local experiences by these primitives in the form of local samplers, and storing them in a database. Pyre synthesizes a global sampler by learning to retrieve local experiences relevant to the given situation. This method transfers knowledge between diverse environments that share local primitives and significantly speeds up planning. Pyre learns incrementally and significantly improves performance with only a handful of examples, achieving better generalization over diverse tasks and environments as compared to prior approaches. We demonstrate the effectiveness of Pyre on 2D and 3D environments as well as with a simulated and real Fetch Robot tasked with challenging pick-and-place manipulation problems. Additionally, in this thesis, we also contribute motionBENCHMAKER, an open-source benchmarking tool for realistic robot manipulation problems. It is an extensible, easy-to-use tool that allows users to both generate datasets and benchmark them by comparing motion planning algorithms.

关键词： Robotic motion planning Machine learning Pyre motion planning algorithms Sampling distributions

来源：评论

学校读者我要写书评

暂无评论

Data Fusion in Autonomous Vehicles Research, Literature Tracing from Imaginary Idea to Smart Surrounding Community 5

Data Fusion in Autonomous Vehicles Research, Literature Trac...

引用

5th International Conference on Fog and Mobile Edge Computing (FMEC)

作者： AlZu'bi, Shadi Jararweh, Yaser Al Zaytoonah Univ Jordan Comp Sci Dept Amman Jordan Jordan Univ Sci & Technol Dept Comp Sci Irbid Jordan

ISBN: (纸本)9781728172163

Many significant challenges related to transportation systems have been raised recently, these include the high accidents rate, road congestion, emission of gases, and environment pollution. Furthermore, transportation crashes caused injuries in accident. Researchers investigated virtual methodologies to automate the transportation process that known as Intelligent Transport System (ITS). In the last 20 years, ITS have been employed efficiently to enhance the performance of transportation systems, improve security of travel, and provide several choices for travelers. The idea of virtual technologies integration is a novel in transportation field. Collecting data from multi-sources played a significant improvement in ITS, this can help stakeholders for processing different forms of data. This huge amount of data can significantly help in the revolution of ITS. This paper focused on several Autonomous vehicles (AVs) related technologies that employed efficiently in ITS. This review integrates and synthesizes monitoring AVs using data fusion from different data sources. Furthermore, recent technologies and software toolboxes are presented in this paper to facilitate the researchers job in improving the data and sensor fusion in AVs.

关键词： Autonomous Vehicles Intelligent Transportation Systems Data and sensor fusion Multisource Data Assistive motion motion planning algorithms

来源：评论

学校读者我要写书评

暂无评论

The Topological Complexity of Spaces of Digital Images

The Topological Complexity of Spaces of Digital Images

引用

作者： Kandola, Shelley Burrows University of Minnesota

学位级别：Ph.D.

The motivation of this dissertation is to study image processing algorithms through a topological lens. The images we focus on here are those that have been segmented by digital Jordan curves as a means of image compression. The algorithms of interest are those that continuously morph one digital image into another digital image. Digital Jordan curves have been studied in a variety of forms for decades now. Our contribution to this field is interpreting the set of digital Jordan curves that can exist within a given digital plane as a finite topological space. Computing the topological complexity of this space determines the minimal number of continuous motion planning rules required to transform one image into another, and determining the motion planners associated to topological complexity provides the specific algorithms for doing so. In Chapter 2, we develop tools for computing the topological complexity of finite spaces, with an emphasis on spheres, joins, and wedge sums. The main result of Chapter 4 is that our space of digital Jordan curves is connected, hence, its topological complexity is finite. To build up to that, we use Chapter 3 to prove some results about paths and distance functions that are obvious in Hausdorff spaces, yet surprisingly elusive in T0 spaces. We end with Chapter 5, in which we study applications of these results. In particular, we prove that our interpretation of the space of digital Jordan curves is the only topologically correct interpretation.

关键词： digital topology image processing motion planning algorithms robotics topological complexity

来源：评论

学校读者我要写书评

暂无评论

An Interval-based Sliding Horizon motion planning Method

引用

IFAC-PapersOnLine 2018年第16期51卷 296-301页

作者： dit Sandretto, Julien Alexandre Brendel, Elliot Chapoutot, Alexandre U2IS ENSTA ParisTech Université Paris-Saclay 828 bd des marechaux Palaiseau91762 France ONERA The French Aerospace Lab PalaiseauF-91761 France

A new algorithm of motion planning based on set-membership approach is presented. The goal of this algorithm is to find a safe and optimal path taking into account various sources of bounded uncertainties on the dynamical model of the plant, on the model of the environment, while being robust with respect to the numerical approximations introduced by numerical integration methods. The main approach is based on a sliding horizon method to predict the behavior of the system allowing the computation of an optimal path. As an example, the motion planning algorithm is applied to an Autonomous Underwater Vehicle (AUV) case study, showing the benefit of the proposed approach. © 2018

关键词： motion planning Approximation algorithms Autonomous underwater vehicles Numerical methods Robust control Autonomous underwater vehicles (AUV) Formal synthesis motion planning algorithms Numerical approximations Numerical integration methods Reachability Safety analysis Set membership approach

来源：评论

学校读者我要写书评

暂无评论

On One Approach to Robot motion planning

On One Approach to Robot Motion Planning

引用

International Conference on Braverman Readings in Machine Learning - Key Ideas from Inception to Current State

作者： Lumelsky, Vladimir Univ Wisconsin Madison WI 53706 USA

ISBN: (纸本)9783319994925;9783319994918

As this essay is meant for a book devoted to the memory of Dr. E. Braverman, a few words about my relation to him seem in order. Professor Braverman was my PhD thesis advisor in 1964-1967 at the Institute of Control Problems of the USSR National Academy, in Moscow. After graduation I had stayed at the same Institute, first as junior and then as senior research fellow, and we remained close, up until my emigration to USA in 1975. His sharp intellect, incredible human warmth, and wide cultural and scientific interests were there for us, a circle of friends which I, a younger man, was generously accepted to. This essay presents a big-picture description of a scientific approach to theory and practice of automatic moving machinery such as robots, and directions it has led to - all developed later on, in my years in America. What connects it to my time in the circle around M. Braverman is the skill for structured thinking that I was lucky to have been schooled in while associated with that circle.

关键词： Robotics Topology Sensing motion planning algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of autonomous humanoid robot control for competitive environment using fuzzy logic and heuristic search

引用

IFAC-PapersOnLine 2016年第1期49卷 373-378页

作者： Samant, Raj Nair, Saurabh Kazi, Faruk Electrical Engineering Department Indian Institute of Technology Kanpur India Electrical Engineering Department V.J.T.I Mumbai India

In this paper, we propose a novel method for interaction between humanoid robots in a competitive environment based on fuzzy logic and its implementation on an experimental platform which was validated using soccer gameplay. The proposed methodology employs vision-based feedback of the humanoid's workspace. The position of the humanoids and other objects are expressed in a newly proposed diagonal coordinate system. Hough transform with moment strategy is used to obtain odometric data of humanoids. The proposed motion planning algorithm is a combination of IDA∗ and linear interpolation which accounts to a major part of the path estimator. Post the path estimator, the motion execution is achieved by a fuzzy-based control system. © 2016, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Fuzzy logic Anthropomorphic robots Computer circuits Heuristic algorithms Hough transforms Iterative methods motion planning Visual servoing Autonomous humanoid robots Competitive environment Experimental platform Fuzzy logic controllers Humanoid robot Iterative deepening motion planning algorithms Vision based feedbacks

来源：评论

学校读者我要写书评

暂无评论

Determining the Nonexistence of Evasive Trajectories for Collision Avoidance Systems 18

Determining the Nonexistence of Evasive Trajectories for Col...

引用

18th IEEE International Conference on Intelligent Transportation Systems

作者： Soentges, Sebastian Althoff, Matthias Tech Univ Munich Dept Comp Sci Boltzmannstr 3 D-85748 Garching Germany

ISBN: (纸本)9781467365963

It is of utmost importance for automatic collision avoidance systems to correctly evaluate the risk of a current situation and constantly decide, if and what kind of evasive maneuver must be initiated. Most motion planning algorithms find such maneuver by searching a deterministic or random subset of the state space or input space. These approaches can be designed to be complete in the sense that they converge to a feasible solution as sampling is made denser. However, they are not suitable to determine whether a solution exists. In this paper, we present an approach which overapproximates the reachable set of the host vehicle considering workspace obstacles. Thus, it provides an upper bound of the solution set and it can report if no solution exists. Furthermore, the calculated set can be used for guiding the search of an underlying planning algorithm to find a solution as each trajectory of the host vehicle is ensured to be contained within this set.

关键词： collision avoidance road traffic control trajectory control advanced driver assistance systems collision avoidance system motion planning algorithms planning algorithm Acceleration Approximation methods Integrated circuit modeling planning Trajectory Upper bound Vehicles Collision avoidance trajectory integrated circuit modelling trajectory control Approximation method Upper bound vehicle airborne anticollision system Beacon collision avoidance systems advanced driver assistance systems (ADAS) state space acceleration Solution Set

来源：评论

学校读者我要写书评

暂无评论

Coarse-grained elastic networks, normal mode analysis and robotics-inspired methods for modeling protein conformational transitions

Coarse-grained elastic networks, normal mode analysis and ro...

引用

IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)

作者： Al-Bluwi, Ibrahim Vaisset, Marc Simeon, Thierry Cortes, Juan CNRS LAAS 7 Ave Colonel Roche F-31400 Toulouse France Univ Toulouse LAAS F-31400 Toulouse France

ISBN: (纸本)9781467327466;9781467327459

This paper presents a method, inspired by robot motion planning algorithms, to model conformational transitions in proteins. The capacity of normal mode analysis to predict directions of collective large-amplitude motions is exploited to bias the conformational exploration. A coarse-grained elastic network model built on short fragments of three residues is proposed for the rapid computation of normal modes. The accurate reconstruction of the all-atom model from the coarse-grained one is achieved using closed-form inverse kinematics. Results show the capacity of the method to model conformational transitions of proteins within a few hours of computing time on a single processor. Tests on a set of ten proteins demonstrate that the computing time scales linearly with the protein size, independently of the protein topology. Further experiments on adenylate kinase show that main features of the transition between the open and closed conformations of this protein are well captured in the computed path.

关键词： Protein conformational transitions elastic network models normal mode analysis motion planning algorithms inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Selection Of A UAV Orbit To Keep Multiple Targets In The Camera Field Of View

Selection Of A UAV Orbit To Keep Multiple Targets In The Cam...

引用

IEEE International Conference on Control Applications Part of 2010 IEEE Multi-Conference on Systems and Control

作者： Gans, N. R. Shen, J. Curtis, J. W. Univ Texas Dallas Dept Elect Engn Richardson TX 75080 USA US Air Force Res Lab Eglin AFB FL 32579 USA

ISBN: (纸本)9781424453610

Unmanned air vehicles (UAV's) are seeing increased use in many applications. One common problem is keeping a target or region in the view of a camera mounted on an UAV. Keeping multiple targets in view compounds the problem. For a fixed wing UAV, this is further complicated by the forward velocity constraints of the system. This paper presents an initial investigation into such to solve this problem with motion planning algorithms. We propose to search through the space of elliptical orbits that to find one that best keeps multiple targets in view. The search is performed using rapidly expanding trees in the space of possible ellipses. The choice of ellipse is predicated on a pair of cost functions based on the mean and variance of the targets' locations in the camera image. Simulations are performed to demonstrate the ability successfully find an ellipse.

关键词： UAV orbit selection aerospace robotics aircraft control camera field of view cameras elliptical orbits space forward velocity constraints mobile robots motion planning algorithms multiple targets path planning remotely operated vehicles unmanned air vehicles

来源：评论

学校读者我要写书评

暂无评论

THE COMPLEXITY OF THE FREE-SPACE FOR motion planning AMIDST FAT OBSTACLES

引用

JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 1994年第1-2期11卷 21-44页

作者： VANDERSTAPPEN, AF 1. Department of Computer Science Utrecht University PO Box 80.089 3508 TB Utrecht The Netherlands

The complexity of motion planning algorithms highly depends on the complexity of the robot's free space, i.e., the set of all collision-free placements of the robot. Theoretically, the complexity of the free space can be very high, resulting in bad worst-case time bounds for motion planning algorithms. In practice, the complexity of the free space tends to be much smaller than the worst-case complexity. motion planning algorithms with a running time that is determined by the complexity of the free space therefore become feasible in practical situations. We show that, under some realistic assumptions, the complexity of the free space of a robot with any fixed number of degrees of freedom moving around in a d-dimensional Euclidean workspace with fat obstacles is linear in the number of obstacles. The complexity results lead to highly efficient algorithms for motion planning amidst fat obstacles.

关键词： motion planning algorithms FATNESS FREE SPACE COMBINATORIAL COMPLEXITY

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：