检索结果-内蒙古大学图书馆

IEEE International Workshop on Safety, Security, and Rescue Robotics (SSRR)

作者： Jan Quenzel Linus T. Mallwitz Benedikt T. Arnold Sven Behnke Autonomous Intelligent Systems Group Computer Science Institute VI - Intelligent Systems and Robotics Center for Robotics and Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany Fraunhofer FIT Germany Fraunhofer IAIS Germany

ISBN: (数字)9798331510954

ISBN: (纸本)9798331510961

Modern unmanned aerial vehicles (UAVs) are irreplaceable in search and rescue (SAR) missions to obtain a situational overview or provide closeups without endangering personnel. However, UAVs heavily rely on global navigation satellite system (GNSS) for localization which works well in open spaces, but the precision drastically degrades in the vicinity of buildings. These inaccuracies hinder aggregation of diverse data from multiple sources in a unified georeferenced frame for SAR operators. In contrast, CityGML models provide approximate building shapes with accurate georeferenced poses. Besides, LiDAR works best in the vicinity of 3D structures. Hence, we refine coarse GNSS measurements by registering LiDAR maps against CityGML and digital elevation map (DEM) models as a prior for allocentric mapping. An intuitive plausibility score selects the best hypothesis based on occupancy using a 2D height map. Afterwards, we integrate the registration results in a continuous-time spline-based pose graph optimizer with LiDAR odometry and further sensing modalities to obtain globally consistent, georeferenced trajectories and maps. We evaluate the viability of our approach on multiple flights captured at two distinct testing sites. Our method successfully reduced GNSS offset errors from up-to 16 m to below 0.5 m on multiple flights. Furthermore, we obtain globally consistent maps w.r.t. prior 3D geospatial models.

关键词： Global navigation satellite system Solid modeling Laser radar Three-dimensional displays Buildings Data models Trajectory Geospatial analysis Splines (mathematics) Testing

来源：评论

学校读者我要写书评

暂无评论

LiDAR-based Registration against Georeferenced Models for Globally Consistent Allocentric Maps

arXiv

引用

arXiv 2024年

作者： Quenzel, Jan Mallwitz, Linus T. Arnold, Benedikt T. Behnke, Sven Autonomous Intelligent Systems Group Computer Science Institute VI – Intelligent Systems and Robotics Germany Center for Robotics Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany Fraunhofer FIT Germany Fraunhofer IAIS Germany

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping

Learning Embeddings with Centroid Triplet Loss for Object Id...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Anas Gouda Max Schwarz Christopher Reining Sven Behnke Alice Kirchheim TU Dortmund Lamarr Institute for Machine Learning and Artificial Intelligence Autonomous Intelligent Systems - Computer Science VI & Center for Robotics University of Bonn Germany Fraunhofer IML

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Foundation models are a strong trend in deep learning and computer vision. These models serve as a base for applications as they require minor or no further fine-tuning by developers to integrate into their applications. Foundation models for zero-shot object segmentation such as Segment Anything (SAM) output segmentation masks from images without any further object information. When they are followed in a pipeline by an object identification model, they can perform object detection without training. Here, we focus on training such an object identification model. A crucial practical aspect for an object identification model is to be flexible in input size (number of input images). As object identification is an image retrieval problem, a suitable method should handle multi-query multigallery situations without constraining the number of input images (e.g. by having fixed-size aggregation layers). The key solution to train such a model is the centroid triplet loss (CTL), which aggregates image features to their centroids. CTL yields high accuracy, avoids misleading training signals and keeps the model input size flexible. In our experiments, we establish a new state of the art on the ArmBench object identification task, which shows general applicability of our model. We furthermore demonstrate an integrated unseen object detection pipeline on the challenging HOPE dataset, which requires finegrained detection. There, our pipeline matches and surpasses related methods which have been trained on dataset-specific data. Code and pretrained models are available. 5

关键词： Training Location awareness Image segmentation Accuracy Pipelines Object detection Object segmentation Market research Object recognition Proposals

来源：评论

学校读者我要写书评

暂无评论

Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping

arXiv

引用

arXiv 2024年

作者： Gouda, Anas Schwarz, Max Reining, Christopher Behnke, Sven Kirchheim, Alice TU Dortmund Germany Autonomous Intelligent Systems - Computer Science VI Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany Fraunhofer IML Germany

Foundation models are a strong trend in deep learning and computer vision. These models serve as a base for applications as they require minor or no further fine-tuning by developers to integrate into their applications. Foundation models for zero-shot object segmentation such as Segment Anything (SAM) output segmentation masks from images without any further object information. When they are followed in a pipeline by an object identification model, they can perform object detection without training. Here, we focus on training such an object identification model. A crucial practical aspect for an object identification model is to be flexible in input size (number of input images). As object identification is an image retrieval problem, a suitable method should handle multi-query multigallery situations without constraining the number of input images (e.g. by having fixed-size aggregation layers). The key solution to train such a model is the centroid triplet loss (CTL), which aggregates image features to their centroids. CTL yields high accuracy, avoids misleading training signals and keeps the model input size flexible. In our experiments, we establish a new state of the art on the ArmBench object identification task, which shows general applicability of our model. We furthermore demonstrate an integrated unseen object detection pipeline on the challenging HOPE dataset, which requires fine-grained detection. There, our pipeline matches and surpasses related methods which have been trained on dataset-specific data. Code and pretrained models are available. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards a companion system for collision avoidance during robot-assisted needle placement

Towards a companion system for collision avoidance during ro...

引用

作者： Currle, Eva Hemm, Johannes Schäfer, Armin Beckerle, Philipp Horsch, Johannes Stallkamp, Jan Kühne, Markus Fraunhofer IPA Project Group for Automation in Medicine and Biotechnology Mannheim Germany FAU Erlangen Institution for Autonomous Systems und Mechatronics Erlangen Germany Mannheim Institute of Intelligent Systems MIISM Dpt. for Automation in Medicine and Biotechnology Mannheim Germany DB Systemtechnik GmbH Frankfurt Germany

Robotic assistance systems for surgery enable fast and precise interventions with reduced complication rates. However, these benefits are accompanied by a more complex operating room (OR) and the risk of collision with robotic assistance systems. Current strategies for collision avoidance and minimizing possible injuries require the adaptation of robotic trajectories and a computational model of the surroundings. In contrast, this work presents a novel companion system for collision avoidance without influencing robotic trajectories. The companion system consists of a preoperative planning application and an augmented reality application for intraoperative support. The companion system visualizes the workflow within the OR and allows robot movements to be seen virtually, before they are executed by the actual robotic assistance system. Preliminary experiments with users imply that the companion system leads to a positive user experience, enables users to follow a predefined workflow in the OR, but requires further refinement to improve accuracy for practical collision avoidance. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Composing complex and hybrid AI solutions

arXiv

引用

arXiv 2022年

作者： Schüller, Peter Costeira, João Paulo Crowley, James Grosinger, Jasmin Ingrand, Félix Köckemann, Uwe Saffotti, Alessandro Welss, Martin Knowledge-based Systems Group Technische Universität Wien Vienna Austria Institute for Systems and Robotics Técnico Lisboa Lisbon Portugal Univ. Grenoble Alpes CNRS Inria Grenoble France Center for Applied Autonomous Sensor Systems Örebro University Sweden LAAS-CNRS University of Toulouse France Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Germany

Progress in several areas of computer science has been enabled by comfortable and efficient means of experimentation, clear interfaces, and interchangable components, for example using OpenCV for computer vision or ROS for robotics. We describe an extension of the Acumos system towards enabling the above features for general AI applications. Originally, Acumos was created for telecommunication purposes, mainly for creating linear pipelines of machine learning components. Our extensions include support for more generic components with gRPC/Protobuf interfaces, automatic orchestration of graphically assembled solutions including control loops, sub-component topologies, and event-based communication, and provisions for assembling solutions which contain user interfaces and shared storage areas. We provide examples of deployable solutions and their interfaces. The framework is deployed at http://***/ and its source code is managed as an open source Eclipse project. © 2022, CC BY.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Towards a companion system for collision avoidance during robot-assisted needle placement

引用

Current Directions in Biomedical Engineering 2021年第1期7卷

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

NAT: Noise-Aware Training for Robust Neural Sequence Labeling

arXiv

引用

arXiv 2020年

作者： Namysl, Marcin Behnke, Sven Köhler, Joachim Fraunhofer IAIS Sankt Augustin Germany Autonomous Intelligent Systems Computer Science Institute VI University of Bonn Germany

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs—as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the noisy sequence labeling problem, where the input may undergo an unknown noising process and propose two Noise-Aware Training (NAT) objectives that improve robustness of sequence labeling performed on perturbed input: Our data augmentation method trains a neural model using a mixture of clean and noisy samples, whereas our stability training algorithm encourages the model to create a noise-invariant latent representation. We employ a vanilla noise model at training time. For evaluation, we use both the original data and its variants perturbed with real OCR errors and misspellings. Extensive experiments on English and German named entity recognition benchmarks confirmed that NAT consistently improved robustness of popular sequence labeling models, preserving accuracy on the original input. We make our code and data publicly available for the research community. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Search-based 3d planning and trajectory optimization for safe micro aerial vehicle flight under sensor visibility constraints

arXiv

引用

arXiv 2019年

作者： Nieuwenhuisen, Matthias Behnke, Sven Fraunhofer Institute for Communication Information Processing and Ergonomics FKIE Wachtberg Germany Autonomous Intelligent Systems Group Computer Science VI University of Bonn Germany

Safe navigation of Micro Aerial Vehicles (MAVs) requires not only obstacle-free flight paths according to a static environment map, but also the perception of and reaction to previously unknown and dynamic objects. This implies that the onboard sensors cover the current flight direction. Due to the limited payload of MAVs, full sensor coverage of the environment has to be traded off with flight time. Thus, often only a part of the environment is covered. We present a combined allocentric complete planning and trajectory optimization approach taking these sensor visibility constraints into account. The optimized trajectories yield flight paths within the apex angle of a Velodyne Puck Lite 3D laser scanner enabling low-level collision avoidance to perceive obstacles in the flight direction. Furthermore, the optimized trajectories take the flight dynamics into account and contain the velocities and accelerations along the path. We evaluate our approach with a DJI Matrice 600 MAV and in simulation employing hardware-in-the-loop. Copyright © 2019, The Authors. All rights reserved.

关键词： Micro air vehicle (MAV)

来源：评论

学校读者我要写书评

暂无评论

Robust extrinsic calibration of multiple stationary laser range finders

Robust extrinsic calibration of multiple stationary laser ra...

引用

2016 IEEE International Conference on Automation Science and Engineering, CASE 2016

作者： Quenzel, Jan Papenberg, Nils Behnke, Sven Autonomous Intelligent Systems Group University of Bonn 53113 Germany Fraunhofer MEVIS Project Group Image Registration Institute of Mathematics and Image Computing University of Luebeck Luebeck23562 Germany

ISBN: (纸本)9781509024094

Laser range finders are used in industrial safety and surveillance applications, e.g. to track persons. The relative position between two sensors is needed for the correct operation of such a system. In order to reduce costs, sensors are positioned to have minimal overlap while extending the combined field of view. The necessary calibration is often done in a time-consuming manual process. To automate this, moving objects are tracked in the laser scans and used to find the relative sensor poses. We present a novel approach to pairwise calibration using shared observations in a RANSAC-based fashion to estimate the relative transformation between two sensors. Afterwards, we apply robust pose graph optimization that deals with possibly faulty pairwise estimates. Our method uses 1-norm minimization in the tangential space of the rotation matrices under transitivity constraints and, thus, does not need a further initial guess to obtain the final sensor poses. The complete system is evaluated with simulated and real data in very challenging situations. To emphasize the robustness of the proposed calibration, we show results using a very simple non-robust tracking. The overall accuracy is further improved when ellipse fitting of the tracked targets is used. © 2016 IEEE.

关键词： Calibration

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：