检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Sebastian Pütz Thomas Wiemann Malte Kleine Piening Joachim Hertzberg Knowledge Based Systems Institute of Computer Science Osnabrück University Plan-Based Robot Control German Research Center for Artificial Intelligence DFKI

We present a highly efficient approach to compute continuous shortest path vector fields on arbitrarily shaped 3D triangular meshes for robot navigation in complex real-world outdoor environments. The continuity of the vector field allows to query the shortest distance, direction and geodesic path to the goal at any point within the mesh triangles, resulting in accurate paths. In order to avoid impassable areas, our wavefront propagation method runs on a modular extendable multilayer map architecture taking different geometric cost layers into account. We describe the mathematical foundation of the geodesic distances and continuous vector field computation and demonstrate the performance in real-world and multilevel environments on our campus with a tunnel, ramps and stair- cases, and in a difficult, steep forest area with a stone quarry. For reproducibility, we provide a ready-to-use ROS software stack as well as Gazebo simulations.

关键词： Three-dimensional displays Runtime Costs Navigation robot kinematics Computational modeling Forestry

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Modeling with Neurodynamical Agglomerative Analysis 29th

Hierarchical Modeling with Neurodynamical Agglomerative Anal...

引用

29th International Conference on Artificial Neural Networks (ICANN)

作者： Marino, Michael Schroeter, Georg Heidemann, Gunther Hertzberg, Joachim Univ Osnabruck Wachsbleiche 27 D-49090 Osnabruck Germany DFKI Lab Niedersachsen Plan Based Robot Control Dept Berghoffstr 11 D-49090 Osnabruck Germany

ISBN: (纸本)9783030616090;9783030616083

We propose a new analysis technique for neural networks, Neurodynamical Agglomerative Analysis (NAA), an analysis pipeline designed to compare class representations within a given neural network model. The proposed pipeline results in a hierarchy of class relationships implied by the network representation, i.e. a semantic hierarchy analogous to a human-made ontological view of the relevant classes. We use networks pretrained on the ImageNet benchmark dataset to infer semantic hierarchies and show the similarity to human-made semantic hierarchies by comparing them with the WordNet ontology. Further, we show using MNIST training experiments that class relationships extracted using NAA appear to be invariant to random weight initializations, tending toward equivalent class relationships across network initializations in sufficiently parameterized networks.

关键词： Neural network theory Deep learning Cognitive models

来源：评论

学校读者我要写书评

暂无评论

Geometry-based Regularisation for Dense Image Matching Via Uncertainty-Driven Depth Propagation 24

Geometry-Based Regularisation for Dense Image Matching Via U...

引用

2020 24th ISPRS Congress on Technical Commission II

作者： Höllmann, M. Mehltretter, M. Heipke, C. Plan-Based Robot Control Group German Research Center for Artificial Intelligence Osnabrück Germany Institute of Photogrammetry and GeoInformation Leibniz University Hannover Germany

In the present work, an uncertainty-driven geometry-based regularisation for the task of dense stereo matching is presented. The objective of the regularisation is the reduction of ambiguities in the depth reconstruction process, which exist due to the ill-posed nature of this task. based on cost and uncertainty information computed beforehand, pixels are selected, whose depth information can be determined correctly with a high probability. This depth information assumed to be of high confidence is initially used to construct a triangle mesh, which is interpreted as surface approximation of the imaged scene and allows to propagate the confident depth information of the triangle vertices within local neighbourhoods. The proposed method further computes confidence scores for propagated depth estimates, which are used to fuse this depth information with the previously computed cost information, introducing a regularisation into the data term of global optimisation methods. Furthermore, based on the propagated depth information the local smoothness assumption of global optimisation methods is adjusted. Instead of fronto-parallel planes, the method presumes planes, which are parallel to the propagated depth information. The performance of the proposed regularisation approach is evaluated in combination with a global optimisation method. For a quantitative and qualitative evaluation two commonly employed and well-established stereo datasets are used. The proposed method shows significant improvements in accuracy on both datasets and for two different cost computation methods. Especially in unstructured areas, artefacts in the disparity maps are reduced. © 2020 Copernicus GmbH. All rights reserved.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

AI-TEST-FIELD - An Agricultural Test Environment for Semantic Environment Perception with Respect to Harsh And Changing Environmental Conditions

AI-TEST-FIELD - An Agricultural Test Environment for Semanti...

引用

2023 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2023

作者： Krause, Jan Christoph Martinez, Jaron Gennet, Henry Urban, Martin Herbers, Jens Menke, Stefan Röttgermann, Sebastian Hertzberg, Joachim Ruckelshausen, Arno DFKI GmbH Niedersachsen Plan-based Robot Control Hamburger Straße 24 Osnabrück49084 Germany Hochschule Osnabrück Labor für Mikro- und Optoelektronik Sedanstraße 26 Osnabrück49076 Germany UR Automation GmbH Hanauerstraße 6 Rodalben66976 Germany Maschinenfabrik Bernard KRONE GmbH and Co. KG Vorentwicklung Heinrich-Krone-Straße 10 Spelle48480 Germany LEMKEN GmbH and Co. KG Vorentwicklung Weseler Straße 5 Alpen46519 Germany Universität Osnabrück Knowledge-Based Systems Group Hamburger Straße 24 Osnabrück49084 Germany

ISBN: (纸本)9781713885887

Highly automated machines with sensor-based assistance systems can increase performance and efficiency while reducing environmental impact. Especially in agriculture, the environment is characterized by harsh and changing conditions such as weather and vegetation. However, for the safe operation of automated and autonomous machinery, robust environmental perception that works reliably in all environmental conditions is essential. Domain-specific test data is needed to validate the robustness of sensor systems that detect obstacles, such as humans, in an agricultural context. This paper presents a test environment to investigate the influence of different environmental conditions on the reliability of sensor systems used for semantic environment perception. Sensors, like cameras and LiDAR, are reproducibly moved on a 100-meter-long L-shaped rail-based carrier system. On three different cultivable field areas, e.g. row crop, grassland and fallow, different scenarios with a detection range of up to 30 meters are covered. With automated test runs, domain specific datasets with multiple environmental conditions can be generated to systematically evaluate the accuracy of AI algorithms for environment perception. Therefor the ground truth is automatically generated based on two surveyed pedestrian test targets and the localization of the carrier system. The test field described here is one of three test levels that forms a basis for the development of certification processes together with separate individual tests and a transfer to real agricultural machinery. © 2023 ASABE Annual International Meeting. All Rights Reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Modular Approach to the Embodiment of Hand Motions from Human Demonstrations

A Modular Approach to the Embodiment of Hand Motions from Hu...

引用

IEEE-RAS International Conference on Humanoid robots

作者： Alexander Fabisch Manuela Uliano Dennis Marschner Melvin Laux Johannes Brust Marco Controzzi Robotics Innovation Center DFKI GmbH Bremen Germany The BioRobotics Institute Scuola Superiore Sant’ Anna Pisa Italy Department of Excellence in Robotics & AI Pisa Italy Robotics Research Group University of Bremen Plan-Based Robot Control DFKI GmbH

ISBN: (纸本)9798350309805

Manipulating objects with robotic hands is a complicated task. Not only the fingers of the hand, but also the pose of the robot's end effector need to be coordinated. Using human demonstrations of movements is an intuitive and data-efficient way of guiding the robot's behavior. We propose a modular framework with an automatic embodiment mapping to transfer recorded human hand motions to robotic systems. In this work, we use motion capture to record human motion. We evaluate our approach on eight challenging tasks, in which a robotic hand needs to grasp and manipulate either deformable or small and fragile objects. We test a subset of trajectories in simulation and on a real robot and the overall success rates of about 70% are aligned.

关键词： robot kinematics robot vision systems Humanoid robots Reinforcement learning Grasping Cameras Motion capture

来源：评论

学校读者我要写书评

暂无评论

Which and How Many Soil Sensors are Ideal to Predict Key Soil Properties: A Case Study with Seven Sensors

SSRN

引用

SSRN 2024年

作者： Schmidinger, Jonas Barkov, Viacheslav Tavakoli, Hamed Correa, José Eduardo Ostermann, Markus Atzmueller, Martin Gebbers, Robin Vogel, Sebastian Osnabrück University Joint Lab Artificial Intelligence and Data Science Osnabrück Germany Department of Agromechatronics Potsdam Germany Process Analytical Technology Berlin Germany Research Department Plan-Based Robot Control Osnabrück Germany Osnabrück University Semantic Information Systems Group Osnabrück Germany Martin Luther University Halle-Wittenberg Institute of Agricultural and Nutritional Sciences Halle Germany

Soil sensing enables rapid and cost-effective soil analysis. However, a single sensor often does not generate enough information to reliably predict a wide range of soil properties. Within a case-study, our objective was to identify how many and which combinations of soil sensors prove to be suitable for high-resolution soil mapping. On a subplot of an agricultural field showing a high spatial soil variability, six in-situ proximal soil sensors (PSSs) next to remote sensing (RS) data from Sentinel-2 were evaluated based on their capabilities to predict a set of soil properties including: soil organic matter, pH, moisture as well as plant-available phosphorus, magnesium and potassium. The set of PSSs consisted of ion-selective pH electrodes, a capacitive soil moisture sensor, an apparent soil electrical conductivity measuring system as well as passive gamma-ray-, X-ray fluorescence- and near-infrared spectroscopy. All possible combinations of sensors were exhaustively evaluated and ranked based on their prediction performances. Over all soil properties, data fusion demonstrated a considerable increase in prediction accuracy. Five out of six soil properties were predicted with an R2 ≥ 0.80 with the best sensor fusion model. Nonetheless, the improvement derived from fusing an increasing number of PSSs was subject to diminishing returns. Sometimes adding more PSSs even decreased prediction performances for specific soil properties. Gamma-ray spectroscopy and near-infrared spectroscopy demonstrated to be most effective, both as single sensors or in combination with other sensors. As a single sensor, RS outperformed three out of six PSSs. RS showed especially potential for fusion with single PSSs but was of limited benefit when multiple PSSs were fused. © 2024, The Authors. All rights reserved.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Rmagine: 3D Range Sensor Simulation in Polygonal Maps via Raytracing for Embedded Hardware on Mobile robots

arXiv

引用

arXiv 2022年

作者： Mock, Alexander Wiemann, Thomas Hertzberg, Joachim Knowledge Based Systems Group Institute of Computer Science Osnabrück University Berghoffstraße 11 Osnabrück49090 Germany Autonomous Robotics Group Institute of Computer Science Osnabrück University Berghoffstraße 11 Osnabrück49090 Germany DFKI Niedersachsen Plan-based Robot Control Berghoffstraße 11 Osnabrück49090 Germany

Sensor simulation has emerged as a promising and powerful technique to find solutions to many real-world robotic tasks like localization and pose tracking. However, commonly used simulators have high hardware requirements and are therefore used mostly on high-end computers. In this paper, we present an approach to simulate range sensors directly on embedded hardware of mobile robots that use triangle meshes as environment map. This library called Rmagine allows a robot to simulate sensor data for arbitrary range sensors directly on board via raytracing. Since robots typically only have limited computational resources, the Rmagine aims at being flexible and lightweight, while scaling well even to large environment maps. It runs on several platforms like Laptops or embedded computing boards like Nvidia Jetson by putting an unified API over the specific proprietary libraries provided by the hardware manufacturers. This work is designed to support the future development of robotic applications depending on simulation of range data that could previously not be computed in reasonable time on mobile systems. Copyright © 2022, The Authors. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Monocular Localization in Feature-Annotated 3D Polygon Maps

Monocular Localization in Feature-Annotated 3D Polygon Maps

引用

European Conference on Mobile robots (ECMR)

作者： Alexander Mock Thomas Wiemann Joachim Hertzberg Knowledge Based Systems and Autonomous Robotics Groups at the Institute of Computer Science Osnabrück University Osnabrück Germany German Research Center for Artificial Intelligence (DFKI) Niedersachsen Lab Plan-Based Robot Control Group Osnabrück Germany

Localization in six degrees of freedom is becoming increasingly relevant, especially in indoor environments where GPS is not available. To localize autonomous vehicles like UAVs in such areas, reliable methods for self-localization with low-weight sensors are required. In this paper, we present an approach to precisely localize systems with monocular cameras in polygonal 3D maps annotated with keypoints and feature descriptors computed from LiDAR data and associated reference images. Our contribution consists of offline map computation from high resolution 3D point clouds with corresponding reference images as well as online localization within these maps using low cost sensors. During localization, features extracted from the vehicle’s camera image stream are matched against the reference map. The proposed method is capable of real-time localization and suitable for precise global localization. The evaluation shows comparable results to state of the art with high re-localization accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tools for Visualizing, Annotating and Storing Triangle Meshes in ROS and RViz

Tools for Visualizing, Annotating and Storing Triangle Meshe...

引用

European Conference on Mobile robots (ECMR)

作者： Puetz, Sebastian Wiemann, Thomas Hertzberg, Joachim Univ Osnabruck Knowledge Based Syst Grp Osnabruck Germany German Res Ctr Artificial Intelligence Res Unit Plan Based Robot Control Osnabruck Germany

ISBN: (纸本)9781728136059

Polygonal maps for robotic applications are becoming increasingly popular, but are currently not effectively supported in the robot Operating System (ROS). In this paper, we introduce the Mesh Tools package consisting of message definitions, RViz plugins and a persistence layer to make the benefits of annotated polygonal maps available in ROS. These tools allow to publish, edit and inspect such maps within the existing ROS context. Our persistence layer efficiently loads and stores large mesh maps. We discuss two application areas as a proof-of-concept: Labeling of triangle clusters for semantic mapping and robot navigation on triangle meshes in a typical outdoor environment by integrating our tools into an existing navigation stack.

关键词： Three-dimensional displays Tools Two dimensional displays Octrees robots Semantics Navigation

来源：评论

学校读者我要写书评

暂无评论

A Modular Approach to the Embodiment of Hand Motions from Human Demonstrations

arXiv

引用

arXiv 2022年

作者： Fabisch, Alexander Uliano, Manuela Marschner, Dennis Laux, Melvin Brust, Johannes Controzzi, Marco Robotics Innovation Center DFKI GmbH Robert-Hooke-Straße 1 BremenD-28359 Germany The BioRobotics Institute Scuola Superiore Sant'Anna Pisa Italy The Department of Excellence in Robotics & AI Scuola Superiore Sant'Anna Pisa Italy Robotics Research Group University of Bremen Germany Plan-Based Robot Control DFKI GmbH Germany

关键词： End effectors

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：