检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Schwingshackl, Michael Oberweger, Fabio Francisco Murschitz, Markus AIT Austrian Institute of Technology Center for Vision Automation & Control Australia

This paper proposes a novel approach to few-shot semantic segmentation for machinery with multiple parts that exhibit spatial and hierarchical relationships. Our method integrates the foundation models CLIPSeg and Segment Anything Model (SAM) with the interest point detector SuperPoint and a graph convolutional network (GCN) to accurately segment machinery parts. By providing 1 to 25 annotated samples, our model, evaluated on a purely synthetic dataset depicting a truck-mounted loading crane, achieves effective segmentation across various levels of detail. Training times are kept under five minutes on consumer GPUs. The model demonstrates robust generalization to real data, achieving a qualitative synthetic-to-real generalization with a J&F score of 92.2 on real data using 10 synthetic support samples. When benchmarked on the DAVIS 2017 dataset, it achieves a J&F score of 71.5 in semi-supervised video segmentation with three support samples. This method’s fast training times and effective generalization to real data make it a valuable tool for autonomous systems interacting with machinery and infrastructure, and illustrate the potential of combined and orchestrated foundation models for few-shot segmentation tasks. © 2025, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimal torque control with radial force compensation for multiphase PMSMs under an open-circuit fault

引用

IFAC-PapersOnLine 2023年第2期56卷 4412-4417页

作者： René Lenz Andreas Kugi Wolfgang Kemmetmüller Automation and Control Institute TU Wien Vienna Austria Center for Vision Automation & Control Austrian Institute of Technology Vienna Austria

Open-circuit (OC) faults of permanent magnet synchronous machines (PMSM) yield deviations from the desired torque and result in undesired radial forces, which cause vibrations and noise. Multiphase PMSMs give additional degrees of freedom for the control of the machine, which allow to (partially) mitigate the impacts of an OC fault. Therefore, a fault-tolerant control strategy with radial force compensation under single open-circuit (OC) faults is developed in this paper for multiphase PMSMs. It is based on a magnetic equivalent circuit (MEC) model, which ensures a high model accuracy even for motors with non-fundamental wave behavior and magnetic saturation, and which is applicable to arbitrary multiphase PMSM designs both for the healthy-circuit (HC) and the OC fault case. The proposed method allows to minimize the torque tracking error, the power losses and the radial forces. The results of the proposed fault-tolerant control strategy, which are presented for an experimentally validated model, prove that almost complete mitigation of an OC fault is possible.

关键词： Permanent magnet synchronous machine magnetic equivalent circuit optimal control multiphase drives open-circuit fault radial force compensation

来源：评论

学校读者我要写书评

暂无评论

Monocular 3D Detection and reID-enhanced Tracking of Multiple Traffic Participants 14th

Monocular 3D Detection and reID-enhanced Tracking of Multipl...

引用

14th International Joint Conference on Computational Intelligence, IJCCI 2022

作者： Sing, Alexander Beleznai, Csaba Göbel, Kai Center for Vision Automation and Control AIT Austrian Institute of Technology Giefinggasse 6 Vienna1210 Austria

ISBN: (纸本)9789897586118

Autonomous driving is becoming a major scientific challenge and applied domain of significant impact, also triggering a demand for the enhanced safety of vulnerable road users, such as cyclists and pedestrians. The recent developments in Deep Learning have demonstrated that monocular 3D pose estimation is a potential detection modality in safety related task domains such as perception for autonomous driving and automated traffic monitoring. Deep Learning offers enhanced ways to represent targets in terms of their location, shape, appearance and motion. Learning can capture the significant variations seen in the training data while retaining class- or target-specific cues. Learning even allows for discovering specific correlations within an image of a 3D scene, as a perspective image contains many hints about an object's 3D location, orientation, size and identity. In this paper we propose an attention-based representational enhancement to enhance the spatial accuracy of 3d pose and the temporal stability of multi-target tracking. The presented methodology is evaluated on the KITTI multi-target tracking benchmark. It demonstrates competitive results against other recent techniques, and when compared to a baseline relying solely on a Kalman-Filter-based kinematic association step. Copyright © 2022 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Singularity Avoidance with Application to Online Trajectory Optimization for Serial Manipulators

引用

IFAC-PapersOnLine 2023年第2期56卷 284-291页

作者： F. Beck M.N. Vu C. Hartl-Nesic A. Kugi Automation and Control Institute (ACIN) TU Wien Vienna Austria Center for Vision Automation and Control AIT Austrian Institute of Technology Vienna Austria

This work proposes a novel singularity avoidance approach for real-time trajectory optimization based on known singular configurations. The focus of this work lies on analyzing kinematically singular configurations for three robots with different kinematic structures, i.e., the Comau Racer 7-1.4, the KUKA LBR iiwa 14 R820, and the Franka Emika Panda, and exploiting these configurations in form of tailored potential functions for singularity avoidance. Monte Carlo simulations of the proposed method and the commonly used manipulability maximization approach are performed for comparison. The numerical results show that the average computing time can be reduced and shorter trajectories in both time and path length are obtained with the proposed approach.

关键词： singularity avoidance motion planning trajectory optimization manipulability redundant manipulators

来源：评论

学校读者我要写书评

暂无评论

Investigating Visual Localization Using Geospatial Meshes 8

Investigating Visual Localization Using Geospatial Meshes

引用

8th International ISPRS Workshop LowCost 3D - Sensors, Algorithms, Applications

作者： Vultaggio, Francesco Fanta-Jende, Phillipp Schörghuber, Matthias Kern, Alexander Gerke, Markus Austrian Institute of Technology Center for Vision Automation and Control Unit Assistive and Autonomous Systems Austria Technische Universität Braunschweig Institute of Flight Guidance Germany Technische Universität Braunschweig Institute of Geodesy and Photogrammetry Germany

This paper investigates the use of geospatial mesh data for visual localization, focusing on city-scale aerial meshes as map representations for locating ground-level query images captured by smartphones. Visual localization, essential for applications such as robotics and augmented reality, traditionally relies on Structure-from-Motion (SfM) reconstructions or image collections as maps. However, mesh-based approaches offer dense spatial representation, memory efficiency, and real-time rendering capabilities. In this work, we evaluate initialization strategies, image matching techniques, and pose refinement methods for mesh-based localization pipelines, comparing the performance of both traditional and deep-learning-based techniques in image matching between real and synthetic views. We created a dataset from nadir and oblique aerial imagery and accurately georeferenced smartphone images to test cross-modal localization. Our findings demonstrate that combining global feature retrieval with GNSS-based spatial filtering yields significant improvements in accuracy and efficiency, achieving submeter positional and subdegree rotational errors. This study advances scalable visual localization using meshes and highlights the potential of integrating smartphone GNSS data for improved performance in urban environments. Copyright: © 2024 Francesco Vultaggio et al.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Visual Quality Inspection Planning: A Model-Based Framework for Generating Optimal and Feasible Inspection Poses

Visual Quality Inspection Planning: A Model-Based Framework ...

引用

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

作者： Vanessa Staderini Tobias Glück Philipp Schneider Andreas Kugi Center for Vision Automation and Control AIT Austrian Institute of Technology GmbH Vienna Austria Automation and Control Institute Technische Universität Wien Vienna Austria

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Automatic visual quality inspection is pivotal in both computer vision and robotics. It plays a crucial role in manufacturing, where robotic systems are increasingly employed to enhance the speed and efficiency of visual quality assessments. Several inspection planning methodologies have been developed; however, they often address the inspection challenge from a singular perspective of robotics or computer vision. This work introduces a comprehensive approach that synergistically integrates principles from both domains. We present an innovative algorithm designed to generate optimal inspection poses by considering the interplay between the inspected object’s geometry and the kinematics of the robotic setup used for inspection. This is accomplished by taking advantage of the concept of visibility. The effectiveness of our algorithm is demonstrated through simulations and experiments, revealing complete coverage for diverse geometries and materials with a small number of inspection poses. Moreover, we benchmark our framework against box constraints and workspace sampling techniques to generate feasible inspection poses. The results indicate superior performance in achieving extensive coverage and reducing the number of required optimal inspection poses, enhancing the overall inspection process.

关键词： Geometry Visualization Computer vision Technological innovation Robot vision systems Reinforcement learning Inspection Planning Bayes methods Optimization

来源：评论

学校读者我要写书评

暂无评论

BoundPlanner: A convex-set-based approach to bounded manipulator trajectory planning

arXiv

引用

arXiv 2025年

作者： Oelerich, Thies Hartl-Nesic, Christian Beck, Florian Kugi, Andreas TU Wien Vienna Austria The center for Vision Automation & Control AIT Austrian Institute of Technology GmbH Vienna Austria

Online trajectory planning enables robot manipulators to react quickly to changing environments or tasks. Many robot trajectory planners exist for known environments but are often too slow for online computations. Current methods in online trajectory planning do not find suitable trajectories in challenging scenarios that respect the limits of the robot and account for collisions. This work proposes a trajectory planning framework consisting of the novel Cartesian path planner based on convex sets, called BoundPlanner, and the online trajectory planner BoundMPC [1]. BoundPlanner explores and maps the collision-free space using convex sets to compute a reference path with bounds. BoundMPC is extended in this work to handle convex sets for path deviations, which allows the robot to optimally follow the path within the bounds while accounting for the robot's kinematics. Collisions of the robot's kinematic chain are considered by a novel convex-set-based collision avoidance formulation independent on the number of obstacles. Simulations and experiments with a 7-DoF manipulator show the performance of the proposed planner compared to state-of-the-art methods. The source code is available at ***/Thieso/BoundPlanner and videos of the experiments can be found at ***/42d4. © 2025, CC BY-NC-ND.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

vision-based mobile analysis of roadside guardrail structures 23

Vision-based mobile analysis of roadside guardrail structure...

引用

6th International Conference on Machine vision and Applications, ICMVA 2023

作者： Beleznai, Csaba Göbel, Kai Stefan, Christian Dorninger, Peter Pusica, Aleksandra Center for Vision Automation & Control AIT Austrian Institute of Technology GmbH Austria Center for Low-Emission Transport AIT Austrian Institute of Technology GmbH Austria 4D-IT GmbH Austria DTV-Verkehrsconsult GmbH Germany

ISBN: (纸本)9781450399531

vision-based analysis of the roadside infrastructure is a research field of growing relevance, since autonomous driving, roadside asset digitization and mapping are key emerging applications. The advancement of Deep Learning for vision-based environment perception represents a core enabling technology to interpret scenes in terms of its objects and their spatial relations. In this paper we present a multi-sensory mobile analysis systemic concept, which targets the structural classification of roadside guardrail structures, and allows for digital measurements within the scene surrounding the guardrail objects. We propose an RGB-D vision-based analysis pipeline to perform semantic segmentation and metric dimension estimation of key structural elements of a given guardrail segment. We demonstrate that the semantic segmentation task can be fully learned in the synthetic domain and deployed with a high accuracy in the real domain. Based on guardrail structural measurements aggregated and tracked over time, our pipeline estimates one or several type-labels for the observed guardrail structure, based on a prior catalog of all possible types. The paper presents qualitative and quantitative results from experiments using our measurement vehicle and covering 100km in total. Obtained results demonstrate that the presented mobile analysis framework can well delineate roadside guardrail structures spatially, and able to propose a limited set of type-candidates. The paper also discusses failure modes and possible future improvements towards accomplishing digital mapping and recognition of safety-critical roadside assets. © 2023 Owner/Author.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Role of Trajectory Planners in Lane Change Tracking control: A Monte Carlo Evaluation of Four controllers under Uncertainty

The Role of Trajectory Planners in Lane Change Tracking Cont...

引用

European control Conference (ECC)

作者： Markus Gurtner Jakob Weber Patrik Zips Andreas Kugi Center for Vision Automation & Control AIT Austrian Institute of Technology GmbH Vienna Austria Automation and Control Institute TU Wien and AIT Austrian Institute of Technology GmbH Vienna Austria

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

In the realm of autonomous transportation, executing vehicle manoeuvres accurately and reliably is paramount. The usual separation of trajectory planning and tracking, due to diverse origins and complexities, can lead to limitations in the closed-loop tracking behaviour. Nonlinear vehicle dynamics, stemming from nonholonomic constraints and tyre-road interactions demand simplified models for realtime planning. This paper comprehensively evaluates the combination of three trajectory planners with four tracking controllers using Monte Carlo analysis, considering scenario and model uncertainties. While planners use simplified or no models, tracking controllers based on nominal models can deviate due to uncertain parameters and environmental variations. Our study systematically evaluates tracking performance under uncertainty, supposing feasible planned trajectories adhering to physics-based constraints. We explore tracking error consistency across trajectory planners, assessing if feasibility alone can limit tracking errors.

关键词： Analytical models Uncertainty Monte Carlo methods Trajectory planning Trajectory tracking Transportation Trajectory

来源：评论

学校读者我要写书评

暂无评论

Two-Step Online Trajectory Planning of a Quadcopter in Indoor Environments with Obstacles

引用

IFAC-PapersOnLine 2023年第2期56卷 11002-11009页

作者： M. Zimmermann M.N. Vu F. Beck A. Nguyen A. Kugi Automation and Control Institute (ACIN) TU Wien Vienna Austria Center for Vision Automation and Control AIT Austrian Institute of Technology Vienna Austria Department of Computer Science University of Liverpool Liverpool England

This paper presents a two-step algorithm for online trajectory planning in indoor environments with unknown obstacles. In the first step, sampling-based path planning techniques such as the optimal Rapidly exploring Random Tree (RRT*) algorithm and the Line-of-Sight (LOS) algorithm are employed to generate a collision-free path consisting of multiple waypoints. Then, in the second step, constrained quadratic programming is utilized to compute a smooth trajectory that passes through all computed waypoints. The main contribution of this work is the development of a flexible trajectory planning framework that can detect changes in the environment, such as new obstacles, and compute alternative trajectories in real time. The proposed algorithm actively considers all changes in the environment and performs the replanning process only on waypoints that are occupied by new obstacles. This helps to reduce the computation time and realize the proposed approach in real time. The feasibility of the proposed algorithm is evaluated using the Intel Aero Ready-to-Fly (RTF) quadcopter in simulation and in a real-world experiment.

关键词： quadcopter motion planning optimal rapidly exploring random tree (RRT*) constrained quadratic programming differential flatness trajectory planning

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：