检索结果-内蒙古大学图书馆

Field robotics 2025年 4卷 99-137页

作者： Ayoub Raji Danilo Caporale Francesco Gatti Andrea Giove Micaela Verucchi Davide Malatesta Nicola Musiu Alessandro Toschi Silviu Roberto Popitanu Fabio Bagni Massimiliano Bosi Alexander Liniger Marko Bertogna Daniele Morra Francesco Amerotti Luca Bartoli Federico Martello Riccardo Porta University of Modena and Reggio Emilia Italy University of Parma Italy Technology Innovation Institute-Autonomous Robotics Research Center UAE HIPERT srl University of Pisa Italy HIPERT srl Computer Vision Lab ETH Zurich Switzerland

The Indy Autonomous Challenge (IAC) brought together for the first time in history nine autonomous racing teams competing at an unprecedented speed and in a head-to-head scenario, using independently developed software on open-wheel race cars. This paper presents the complete software architecture used by the team TII EuroRacing (TII-ER), covering all the modules needed to avoid static obstacles, perform active overtakes, and reach speeds above 75m/s (270km/h). In addition to the most common modules related to perception, planning, and control, we discuss the approaches used for vehicle dynamics modeling, simulation, telemetry, and safety. Overall results and the performance of each module are described, as well as the lessons learned during the first two events of the competition on oval tracks, where the team placed second and third, respectively.

关键词： Automobiles Cameras Laser radar Autonomous vehicles Location awareness Safety Planning Vehicle dynamics Testing Sports Motion planning Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

FrontierNet: Learning Visual Cues to Explore

引用

IEEE robotics and Automation Letters 2025年第7期10卷 6576-6583页

作者： Sun, Boyang Chen, Hanzhi Leutenegger, Stefan Cadena, Cesar Pollefeys, Marc Blum, Hermann ETH Zurich Computer Vision and Geometry Group Zurich 8092 Switzerland Technical University of Munich Mobile Robotics Lab München 80333 Germany ETH Zurich Mobile Robotics Lab Zurich 8092 Switzerland ETH Zurich Robotic Systems Lab Zurich 8092 Switzerland AI Lab Microsoft Mixed Reality Zurich 8038 Switzerland University of Bonn Lamarr Institute for ML and AI Robot Perception and Learning Lab Bonn 53115 Germany

Exploration of unknown environments is crucial for autonomous robots;it allows them to actively reason and decide on what new data to acquire for different tasks, such as mapping, object discovery, and environmental assessment. Existing solutions, such as frontier-based exploration approaches, rely heavily on 3D map operations, which are limited by map quality and, more critically, often overlook valuable context from visual cues. This work aims at leveraging 2D visual cues for efficient autonomous exploration, addressing the limitations of extracting goal poses from a 3D map. We propose a visual-only frontier-based exploration system, with FrontierNet as its core component. FrontierNet is a learning-based model that (i) proposes frontiers, and (ii) predicts their information gain, from posed RGB images enhanced by monocular depth priors. Our approach provides an alternative to existing 3D-dependent goal-extraction approaches, achieving a 15% improvement in early-stage exploration efficiency, as validated through extensive simulations and real-world experiments. © 2016 IEEE.

关键词： Deep Learning Motion and Path Planning Perception and Autonomy

来源：评论

学校读者我要写书评

暂无评论

LiCAR: pseudo-RGB LiDAR image for CAR segmentation

arXiv

引用

arXiv 2025年

作者： de Loyola Páez-Ubieta, Ignacio Velasco-Sánchez, Edison P. Puente, Santiago T. AUtomatics RObotics and Artificial Vision Lab IUII: University Institute for Computer Research University of Alicante Crta. San Vicente s/n San Vicente del Raspeig AlicanteE-03690 Spain

With the advancement of computing resources, an increasing number of Neural Networks (NNs) are appearing for image detection and segmentation appear. However, these methods usually accept as input a RGB 2D image. On the other side, Light Detection And Ranging (LiDAR) sensors with many layers provide images that are similar to those obtained from a traditional low resolution RGB camera. Following this principle, a new dataset for segmenting cars in pseudo-RGB images has been generated. This dataset combines the information given by the LiDAR sensor into a Spherical Range Image (SRI), concretely the reflectivity, near infrared and signal intensity 2D images. These images are then fed into instance segmentation NNs. These NNs segment the cars that appear in these images, having as result a Bounding Box (BB) and mask precision of 88% and 81.5% respectively with You Only Look Once (YOLO)-v8 large. By using this segmentation NN, some trackers have been applied so as to follow each car segmented instance along a video feed, having great performance in real world experiments. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification

arXiv

引用

arXiv 2025年

作者： Yang, Wennuo Wu, Shiling Zhou, Yuzhi Luo, Cheng He, Xilin Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China HBUG Lab University of Exeter United Kingdom

Multivariate Time Series Classification (MTSC) enables the analysis if complex temporal data, and thus serves as a cornerstone in various real-world applications, ranging from healthcare to finance. Since the relationship among variables in MTS usually contain crucial cues, a large number of graph-based MTSC approaches have been proposed, as the graph topology and edges can explicitly represent relationships among variables (channels), where not only various MTS graph representation learning strategies but also different Graph Neural Networks (GNNs) have been explored. Despite such progresses, there is no comprehensive study that fairly benchmarks and investigates the performances of existing widely-used graph representation learning strategies/GNN classifiers in the application of different MTSC tasks. In this paper, we present the first benchmark which systematically investigates the effectiveness of the widely-used three node feature definition strategies, four edge feature learning strategies and five GNN architecture, resulting in 60 different variants for graph-based MTSC. These variants are developed and evaluated with a standardized data pipeline and training/validation/testing strategy on 26 widely-used suspensor MTSC datasets. Our experiments highlight that node features significantly influence MTSC performance, while the visualization of edge features illustrates why adaptive edge learning outperforms other edge feature learning methods. The code of the proposed benchmark is publicly available at https://***/CVI-yangwn/*** Codes 68T10 © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

NON-RIGID BODY MOTION.

NON-RIGID BODY MOTION.

引用

Proceedings - Graphics Interface '85.

作者： Dill, Andreas R. Levine, Martin D. McGill Univ Computer Vision & Robotics Lab Montreal Que Can McGill Univ Computer Vision & Robotics Lab Montreal Que Can

During the last few years motion analysis has developed into a major field of interest in image analysis and understanding. Considerable progress has been made as evidenced by the number of publications. However, most of these have been confined to the study of rigid body motion. Very few have addressed the issue of non-rigid body motion which poses many interesting and difficult problems. We propose a new technique for analyzing non-rigid body motion of closed boundary shapes that is based on the computation of skeletons at multiple resolutions. This technique is used for analyzing the structural changes in the morphology of locomoting lymphocytes and, in particular, of their pseudopods.

关键词： IMAGE PROCESSING

来源：评论

学校读者我要写书评

暂无评论

RECEPTIVE FIELDS AND THE REPRESENTATION OF VISUAL INFORMATION.

RECEPTIVE FIELDS AND THE REPRESENTATION OF VISUAL INFORMATIO...

引用

Proceedings - Seventh International Conference on Pattern Recognition.

作者： Zuker, Steven W. Hummel, Robert A. McGill Univ Computer Vision & Robotics Lab Montreal Que Can McGill Univ Computer Vision & Robotics Lab Montreal Que Can

ISBN: (纸本)0818605456

A scheme is presented by which a precise visual image can be reconstructed from a combination of these multiple-size representations. The scheme, which supports the position that image analysis begins in the cortex, differs in basic technical ways from other schemes proposed to account for the communication gap and hyperacuity. One such class of schemes is based on (sin chi )/ chi reconstruction filters. The numerical analysis of such filters shows that they require too much spatial support (i. e. , several lobes on either side) to function properly with the limited support apparently available. The present scheme is based on local (Hermite) polynomials. A completely different theoretical position is that the receptive field operators are participating in 'edge detection', but both computational experiments and mathematical analysis provide evidence that this position in untenable.

关键词： vision

来源：评论

学校读者我要写书评

暂无评论

LOCAL STRUCTURE OF IMAGE DISCONTINUITIES IN ONE DIMENSION.

LOCAL STRUCTURE OF IMAGE DISCONTINUITIES IN ONE DIMENSION.

引用

Proceedings - Seventh International Conference on Pattern Recognition.

作者： Leclerc, Yvan Zucker, Steven W. McGill Univ Computer Vision & Robotics Lab Montreal Que Can McGill Univ Computer Vision & Robotics Lab Montreal Que Can

ISBN: (纸本)0818605456

The authors present a new method for locating discontinuities in one-dimensional cuts through idealized images. The model for such a cut is a sampled, piecewise smooth (C**1) function corrupted by noise. The new method uses an extension of the mathematical definition that a function is discontinuous at a point if the left- and right-hand limits of the function (or any of its derivatives) are unequal. The extended definition is that a noisy function is discontinuous at a point if the difference in the estimates of the limits is statistically significant. It follows from this extended definition that locating discontinuities must be carried out at the same time as determining the structure of the uncorrupted function in a local neighbourhood about the discontinuity (we call this the local structure of the discontinuity). Determining this local structure is an important first step in interpreting the physical event causing the image discontinuity.

关键词： IMAGE PROCESSING

来源：评论

学校读者我要写书评

暂无评论

TRAJECTORY PLANNING IN TIME-VARYING ENVIRONMENTS, 1: TPP equals PPP plus VPP.

TRAJECTORY PLANNING IN TIME-VARYING ENVIRONMENTS, 1: TPP equ...

引用

Intelligent Robots and computer vision.

作者： Kamal Kant Zucker, Steven McGill Univ Computer Vision & Robotics Lab Montreal Que Can McGill Univ Computer Vision & Robotics Lab Montreal Que Can

ISBN: (纸本)0892525568

In this paper, the authors present a novel approach to solving the trajectory planning problem (TPP) in time-varying environments. The essence of our approach lies in a decomposition of the TPP into two sub-problems: (i) planning the path to avoid collision with the static obstacles, and then (ii) planning the velocity along the path to avoid collision with the moving obstacles. The authors call the first sub-problem, the path planning problem (PPP), and the second, the velocity planning problem (VPP). Thus, the decomposition is summarized by the equation TPP equals PPP plus VPP. A variation of an existing approach to solve the PPP is used. They transform the VPP to a 2-dimensional PPP in path-time space. The resulting 2-dimensional PPP is then solved to determine the collision-free velocity profile.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

TRAJECTORY PLANNING PROBLEMS. I: DETERMINING VELOCITY ALONG A FIXED PATH.

TRAJECTORY PLANNING PROBLEMS. I: DETERMINING VELOCITY ALONG ...

引用

Proceedings - Seventh International Conference on Pattern Recognition.

作者： Kant, Kamal Zucker, Steven W. McGill Univ Computer Vision & Robotics Lab Montreal Que Can McGill Univ Computer Vision & Robotics Lab Montreal Que Can

ISBN: (纸本)0818605456

In this paper, the authors generalize the path planning problem to that of the trajectory planning problem (TPP) in a time-varying environment. They present an algorithm to solve a special case of the TPP - the fixed path TPP. In this case, the path is a point set fixed in space and the aim is to determine the velocity of a robot vehicle moving along this path from an initial position to a final position while avoiding moving obstacles. The solution is essentially equivalent to a (static) 2-D path planning problem. Graph searching techniques are used to construct the velocity profile.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

MULTI-ROBOT ASSEMBLY OF IC'S.

MULTI-ROBOT ASSEMBLY OF IC'S.

引用

Proceedings - Graphics Interface '85.

作者： Michaud, C. Malowany, A.S. Levine, M.D. McGill Univ Computer Vision & Robotics Lab Montreal Que Can McGill Univ Computer Vision & Robotics Lab Montreal Que Can

This paper presents a multi-robot system which assembles integrated circuits. The problems addressed are the calibration of the robotic station, the control of several robots working concurrently, and pattern recognition. These problems are discussed in the context of a distributed system. The use of image processing is omnipresent. For instance, vision feedback is used to acknowledge almost every move of the robots and also to calibrate the camera itself. Pattern recognition techniques are employed to detect the exact orientation of an IC die. Several robots are used in order to give more flexibility to the system and allow us to acquire experience which could lead toward a multirobot multitasking system.

关键词： ROBOTS, INDUSTRIAL

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：