检索结果-内蒙古大学图书馆

Sequential U-Net Architecture for Automatic Femoral Artery Segmentation in Ultrasound Images

Current Directions in Biomedical Engineering 2021年第1期7卷 158-161页

作者： Estrada Lugo, Ana Bockelmann, Niclas Haxthausen, Felix Von University of Lübeck Lübeck Germany Institute for Robotics and Cognitive Systems University of Lübeck Lübeck Germany

This work compares three different approaches to automatically segment the femoral artery from 2D ultrasound images. Two of the architectures follow a sequential structure, where each ultrasound image is considered a slice of the whole vessel volume, and its previous segmentation result will be part of the input, thus leading to a spatial prior. The Dice score on test data show a better performance on the baseline U-Net (0.819) compared to the sequential U-Net approaches (0.633, 0.725) for the femoral artery segmentation. This could be attributed to the misalignment of the slices being used in those networks. A possible improvement could be assumed in the implementation of a spatially calibrated and tracked ultrasound probe. Overall, these results indicate promising approaches for an automatic segmentation of the femoral artery using 2D ultrasound data. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Superimposing holograms on real world objects using HoloLens 2 and its depth camera

Superimposing holograms on real world objects using HoloLens...

引用

作者： Haxthausen, Felix Von Chen, Yenjung Ernst, Floris Institute for Robotics and Cognitive Systems University of Lübeck Lübeck Germany

Augmented Reality glasses such as HoloLens 2 may provide visual guidance during surgical interventions. To superimpose the holograms on real world objects (RWO), for instance a patient, spatial registration is required. In this work, we propose an approach to automatically register a hologram to the according RWO. To this end, the framework utilizes the depth camera of HoloLens 2 to acquire the point cloud (PC) of the RWO. A novel and recently published PC registration algorithm allows to register the PC of the RWO and the hologram after a rough initial placement without any need for pre-processing or outlier removal. The approach is evaluated by measuring displacements between certain known positions of the hologram and the RWO. The first metric relies on measuring points using an optically tracked stylus while the second is based on visually perceived positions. The median displacements were 22.3 mm, 35.6 mm, and 13.3 mm for the x-, y-, and z-axes in the first metric and 8.1 mm, 4.3 mm, and 11.9 mm for the second metric. Even though the accuracy is not yet adequate for many surgical interventions, the framework provides an initial step for a convenient marker less registration of holograms to an RWO. © 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

Learning Low-Dimensional Strain Models of Soft Robots by Looking at the Evolution of Their Shape with Application to Model-Based Control

Learning Low-Dimensional Strain Models of Soft Robots by Loo...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Ricardo Valadas Maximilian Stölzle Jingyue Liu Cosimo Della Santina Cognitive Robotics Department Delft University of Technology Delft Netherlands Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge USA

ISBN: (数字)9798331520205

ISBN: (纸本)9798331520212

Obtaining dynamic models of continuum soft robots is central to the analysis and control of soft robots, and researchers have devoted much attention to the challenge of proposing both data-driven and first-principle solutions. Both avenues have, however, shown their limitations; the former lacks structure and performs poorly outside training data, while the latter requires significant simplifications and extensive expert knowledge to be used in practice. This paper introduces a streamlined method for learning low-dimensional, physicsbased models that are both accurate and easy to interpret. We start with an algorithm that uses image data (i.e., shape evolutions) to determine the minimal necessary segments for describing a soft robot’s movement. Following this, we apply a dynamic regression and strain sparsification algorithm to identify relevant strains and define the model’s dynamics. We validate our approach through simulations with various planar soft manipulators, comparing its performance against other learning strategies, showing that our models are both computationally efficient and 25x more accurate on out-of-training distribution inputs. Finally, we demonstrate that thanks to the capability of the method of generating physically compatible models, the learned models can be straightforwardly combined with model-based control policies.

关键词： Training Accuracy Transmission line matrix methods Shape Computational modeling Heuristic algorithms Training data Soft robotics Aerodynamics Strain

来源：评论

学校读者我要写书评

暂无评论

One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion 8

One Policy to Run Them All: an End-to-end Learning Approach ...

引用

8th Conference on Robot Learning, CoRL 2024

作者： Bohlinger, Nico Czechmanowski, Grzegorz Krupka, Maciej Kicki, Piotr Walas, Krzysztof Peters, Jan Tateo, Davide Department of Computer Science Technical University of Darmstadt Germany Institute of Robotics and Machine Intelligence Poznan University of Technology Poland Research Department: Systems AI for Robot Learning Germany IDEAS NCBR Warsaw Poland Hessian.AI Germany Centre for Cognitive Science Germany

Deep Reinforcement Learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world. © 2024 Proceedings of Machine Learning Research.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Representation Learning of Multivariate Time Series using Attention and Adversarial Training

arXiv

引用

arXiv 2024年

作者： Scharwächter, Leon Otte, Sebastian Neuro-Cognitive Modeling Group Department of Computer Science University of Tübingen Germany Adaptive AI Lab Institute of Robotics and Cognitive Systems University of Lübeck Germany

A critical factor in trustworthy machine learning is to develop robust representations of the training data. Only under this guarantee methods are legitimate to artificially generate data, for example, to counteract imbalanced datasets or provide counterfactual explanations for blackbox decision-making systems. In recent years, Generative Adversarial Networks (GANs) have shown considerable results in forming stable representations and generating realistic data. While many applications focus on generating image data, less effort has been made in generating time series data, especially multivariate signals. In this work, a Transformer-based autoencoder is proposed that is regularized using an adversarial training scheme to generate artificial multivariate time series signals. The representation is evaluated using t-SNE visualizations, Dynamic Time Warping (DTW) and Entropy scores. Our results indicate that the generated signals exhibit higher similarity to an exemplary dataset than using a convolutional network approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Global Trajectory Optimization for Autonomous Driving using Nonlinear Programming with Topology Classes*

Global Trajectory Optimization for Autonomous Driving using ...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Maryam Nezami Ngoc Thinh Nguyen Georg Schildbach Institute for Electrical Engineering in Medicine University of Lübeck (UzL) Lübeck Germany Institute for Robotics and Cognitive Systems UzL Lübeck Germany

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Obstacle avoidance is an essential characteristic of autonomous driving cars. This paper presents a new method for efficiently determining possible routes that a vehicle can follow for overtaking obstacles and classifying them into different topology classes of paths. Impossible routes are eliminated based on the physical constraints of the vehicle. To evaluate each topology class and pick the one with the lowest cost as the globally optimal path, we run several topology-aided Nonlinear Programming (NLP) problems. For each topology-aided NLP problem to overtake the obstacles from the prespecified side determined by the topology class, corresponding auxiliary halfspace constraints are activated in the optimization problem. Through simulation results and comparisons with a standard NLP planner, we show that the overall computation time for solving several topology-aided NLP problems is faster than that of the standard NLP planner. Additionally, in complex driving scenarios, where the standard planner gets stuck in a sub-optimal solution due to internal faults or a local optimum, our proposed topology-aided planner can still find the globally optimal path.

关键词： Costs Simulation Roads Programming Topology Planning Collision avoidance Standards Autonomous vehicles Trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

Extraction of Semantically Rich High-Definition Maps from Spatial Representations of an Open Pit Mine

Extraction of Semantically Rich High-Definition Maps from Sp...

引用

International Conference on Intelligent Transportation

作者： Andreas Braining Gjorgji Nikolovski Michael Reke Alexander Ferrein The Mobile Autonomous Systems & Cognitive Robotics Institute FH Aachen University of Applied Science Aachen Germany

Hauling of material by automated vehicles can be one of the sustainable solutions for the increasing economic and environmental challenges in the mining industry. For this, vehicles of various sizes must drive through an ever-changing environment, due to the destructive nature of resource extraction. Therefore, we show our solution to create automatically semantically rich high-definition maps, which can be used for efficient and safe navigation within the mine. In contrast to navigation on pure spatial geometry-based data like point clouds, high-definition maps have the advantage, that semantic information is recognised by the navigation system. But manually created high-definition maps need frequent updates due to the terrain changes, which makes them inflexible for most applications. In this paper, we will show, how Lanelet2- maps can be generated automatically from point clouds with a multistep algorithm and how these maps are adjusted to the long-term changes of the environment. For evaluation, we present our findings in some real-world examples and synthetically generated point clouds of the main edge-case situations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-predictive Control with Parallelised Optimisation for the Navigation of Autonomous Mining Vehicles

Model-predictive Control with Parallelised Optimisation for ...

引用

IEEE Symposium on Intelligent Vehicle

作者： Gjorgji Nikolovski Nicolas Limpert Hendrik Nessau Michael Reke Alexander Ferrein The Mobile Autonomous Systems & Cognitive Robotics Institute FH Aachen University of Applied Science Aachen Germany

The work in modern open-pit and underground mines requires the transportation of large amounts of resources between fixed points. The navigation to these fixed points is a repetitive task that can be automated. The challenge in automating the navigation of vehicles commonly used in mines is the systemic properties of such vehicles. Many mining vehicles, such as the one we have used in the research for this paper, use steering systems with an articulated joint bending the vehicle’s drive axis to change its course and a hydraulic drive system to actuate axial drive components or the movements of tippers if available. To address the difficulties of controlling such a vehicle, we present a model-predictive approach for controlling the vehicle. While the control optimisation based on a parallel error minimisation of the predicted state has already been established in the past, we provide insight into the design and implementation of an MPC for an articulated mining vehicle and show the results of real-world experiments in an open-pit mine environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards a Lifelong Mapping Approach Using Lanelet 2 for Autonomous Open-Pit Mine Operations

Towards a Lifelong Mapping Approach Using Lanelet 2 for Auto...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Julian Eichenbaum Gjorgji Nikolovski Leon Mülhens Michael Reke Alexander Ferrein Ingrid Scholl The Mobile Autonomous Systems & Cognitive Robotics Institute FH Aachen University of Applied Science Aachen Germany

Autonomous agents require rich environment models for fulfilling their missions. High-definition maps are a well-established map format which allows for representing semantic information besides the usual geometric information of the environment. These are, for instance, road shapes, road markings, traffic signs or barriers. The geometric resolution of HD maps can be as precise as of centimetre level. In this paper, we report on our approach of using HD maps as a map representation for autonomous load-haul-dump vehicles in open-pit mining operations. As the mine undergoes constant change, we also need to constantly update the map. Therefore, we follow a lifelong mapping approach for updating the HD maps based on camera-based object detection and GPS data. We show our mapping algorithm based on the Lanelet 2 map format and show our integration with the navigation stack of the Robot Operating System. We present experimental results on our lifelong mapping approach from a real open-pit mine.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ECG Matching: An Approach to Synchronize ECG Datasets for Data Quality Comparisons

ECG Matching: An Approach to Synchronize ECG Datasets for Da...

引用

68th Annual Meeting of the German Association of Medical Informatics, Biometry, and Epidemiology: Science. Close to People, GMDS 2023

作者： Alhaskir, Mohamed Tschesche, Matteo Linke, Florian Schriewer, Elisabeth Weber, Yvonne Wolking, Stefan Röhrig, Rainer Koch, Henner Kutafina, Ekaterina Institute for Medical Informatics Medical Faculty Rwth Aachen University Aachen Germany Institute for Mobile Autonomous Systems and Cognitive Robotics Fh Aachen University of Applied Sciences Aachen Germany Department of Epileptology Neurology Medical Faculty Rwth Aachen University Aachen Germany

ISBN: (纸本)9781643684284

Clinical assessment of newly developed sensors is important for ensuring their validity. Comparing recordings of emerging electrocardiography (ECG) systems to a reference ECG system requires accurate synchronization of data from both devices. Current methods can be inefficient and prone to errors. To address this issue, three algorithms are presented to synchronize two ECG time series from different recording systems: Binned R-peak Correlation, R-R Interval Correlation, and Average R-peak Distance. These algorithms reduce ECG data to their cyclic features, mitigating inefficiencies and minimizing discrepancies between different recording systems. We evaluate the performance of these algorithms using high-quality data and then assess their robustness after manipulating the R-peaks. Our results show that R-R Interval Correlation was the most efficient, whereas the Average R-peak Distance and Binned R-peak Correlation were more robust against noisy data. © 2023 The authors and IOS Press.

关键词： Electrocardiography

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：