检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Xu, Yihong Ban, Yutong Delorme, Guillaume Gan, Chuang Rus, Daniela Alameda-Pineda, Xavier Inria Grenoble Rhône-Alpes Montbonnot Saint-Martin France Distributed Robotics Lab CSAIL Massachusetts Institute of Technology United States MIT-IBM Watson AI Lab United States

Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries – is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets’ locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenter exhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and comparisons to more naive alternatives and concurrent works. For scientific interest, the code is made publicly available at https://***/yihongxu/transcenter. © 2021, CC BY-NC-ND.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Planning Motions for a Planar Robot Attached to a Stiff Tether

Planning Motions for a Planar Robot Attached to a Stiff Teth...

引用

IEEE International Conference on robotics and Automation

作者： Reza H. Teshnizi Dylan A. Shell Distributed AI and Robotics Lab Dept. of Computer Science and Engineering Texas A&M University College Station 77843 USA

ISBN: (纸本)9781467380270

There are several practical reasons to endow a mobile robot with a tether, but doing so adds considerable complexity to the problem of moving the robot. The feasibility of a particular motion in such systems depends on topological constraints imposed by the interplay of the robot's tether and its environment. The physical properties of the tether may also rule out configurations that would be possible otherwise. Little work has addressed these latter constraints, despite the considerable interest in motion planning for tethered robots recently. We examine the problem of planning motions of a planar robot connected via a cable of limited length to a fixed point in R~2 when the tether has a constraint on its curvature, which adds appreciably to the realism of the cable model over existing work. We incorporate Dubins's theory of curves with work on planning with topological constraints to concisely represent the configuration space manifold, leading to an atlas of the manifold consisting of locally continuous charts that represent the cable's curvature limits conveniently. Any configuration of the tether and the robot is described in our representation with two elements: (1) a discrete structure that characterizes the cable's position and (2) an element within a single continuous chart. We provide an algorithm that explores the necessary parts of this atlas on-the-fly to locate paths efficiently.

关键词： Motions Planar Robot

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：