检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Adam Misik Driton Salihu Xin Su Heike Brock Eckehard Steinbach Siemens Technology Munich Germany School of Computation Information and Technology Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich Munich Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Given its wide application in robotics, point cloud registration is a widely researched topic. Conventional methods aim to find a rotation and translation that align two point clouds in 6 degrees of freedom (DoF). However, certain tasks in robotics, such as category-level pose estimation, involve non-uniformly scaled point clouds, requiring a 9DoF transform for accurate alignment. We propose HEGN, a novel equivariant graph neural network for 9DoF point cloud registration. HEGN utilizes equivariance to rotation, translation, and scaling to estimate the transformation without relying on point correspondences. Based on graph representations for both point clouds, we extract equivariant node features aggregated in their local, cross-, and global context. In addition, we introduce a novel node pooling mechanism that leverages the cross-context importance of nodes to pool the graph representation. By repeating the feature extraction and node pooling, we obtain a graph hierarchy. Finally, we determine rotation and translation by aligning equivariant features aggregated over the graph hierarchy. To estimate scaling, we leverage scale information in the vector norm of the equivariant features. We evaluate the effectiveness of HEGN through experiments with the synthetic ModelNet40 dataset and the real-world ScanObjectNN dataset. The results show the superior performance of HEGN in 9DoF point cloud registration and its competitive performance in conventional 6DoF point cloud registration.

关键词： Point cloud compression Three-dimensional displays Pose estimation Transforms Feature extraction Graph neural networks Vectors

来源：评论

学校读者我要写书评

暂无评论

A Novel Information-Theoretic Metric for Evaluating LiDAR Setups of Autonomous Vehicles

A Novel Information-Theoretic Metric for Evaluating LiDAR Se...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Philipp Hafemann Xulin Song David Brecht Technical University of Munich Germany Department of Mobility Systems Engineering School of Engineering & Design Institute of Automotive Technology and Munich Institute of Robotics and Machine Intelligence (MIRMI)

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The sensor configuration of an autonomous vehicle (AV) is determined in the early development phase when specific perception algorithms are not yet available. Therefore, approaches based on synthetic raw data are necessary to evaluate different configurations. One sensor type used in AV is LiDAR, but developers should carefully consider the amount and placement of the sensors due to their high costs. In this contribution, we propose the Omni-Lidar Evaluation Score (OLES), a novel metric to evaluate different LiDAR configurations based on their simulated raw data. Our OLES metric combines information-theoretic quantities with coverage-based metrics, considering both the spatial coverage and the uniformity of a LiDAR point cloud distribution. We show the need for a new metric and provide details on implementing OLES using the open-source simulator CARLA. We demonstrate the effectiveness of our new metric in a simulation study and highlight its usefulness in the early phases of vehicle development. This research provides a means to evaluate the quality of LiDAR configurations and provides a basis for further optimizing sensor setups for AVs.

关键词： Measurement Point cloud compression Laser radar Costs Autonomous vehicles Cybernetics Information theory

来源：评论

学校读者我要写书评

暂无评论

Camera-LiDAR Inconsistency Analysis for Active Learning in Object Detection

Camera-LiDAR Inconsistency Analysis for Active Learning in O...

引用

IEEE Symposium on Intelligent Vehicle

作者： Esteban Rivera Ana Clara Serra Do Nascimento Markus Lienkamp Technical University of Munich Germany Department of Mobility Systems Engineering School of Engineering and Design Institute of Automotive Technology Munich Institute of Robotics and Machine Intelligence (MIRMI)

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Today, deep learning detectors for autonomous driving are delivering impressive results on public datasets and in real-world applications. However, these detectors require large amounts of data, especially labeled data, to achieve the performance needed to ensure safe driving. The process of collecting and tagging data is expensive and cumbersome. Therefore, the recent focus of the industry has been on how to achieve similar performance while limiting the amount of labeled data required to train such models. Within the cross-modal active learning paradigm, we propose and analyze new strategies to exploit the inconsistencies between camera and LiDAR detectors to improve sampling efficiency and label only the samples that promise improvements for model training. For this, we leverage the 2D projection of the bounding boxes to equalize the output quality of camera and LiDAR detections. Finally, we achieve up to 0.6% AP improvement for camera and 2% improvement for LiDAR over random sampling on the KITTI dataset using a sampling strategy based on the number of detected objects.

关键词： Training Industries Laser radar Three-dimensional displays Limiting Detectors Object detection

来源：评论

学校读者我要写书评

暂无评论

LEMON: Localized Editing with Mesh Optimization and Neural Shaders

arXiv

引用

arXiv 2024年

作者： Algan, Furkan Mert Yazgan, Umut Salihu, Driton Eteke, Cem Steinbach, Eckehard Technical University of Munich Chair of Media Technology Munich Institute of Robotics and Machine Intelligence MIRMI School of Computation Information and Technology Department of Computer Engineering Germany

In practical use cases, polygonal mesh editing can be faster than generating new ones, but it can still be challenging and time-consuming for users. Existing solutions for this problem tend to focus on a single task, either geometry or novel view synthesis, which often leads to disjointed results between the mesh and view. In this work, we propose LEMON, a mesh editing pipeline that combines neural deferred shading with localized mesh optimization. Our approach begins by identifying the most important vertices in the mesh for editing, utilizing a segmentation model to focus on these key regions. Given multi-view images of an object, we optimize a neural shader and a polygonal mesh while extracting the normal map and the rendered image from each view. By using these outputs as conditioning data, we edit the input images with a text-to-image diffusion model and iteratively update our dataset while deforming the mesh. This process results in a polygonal mesh that is edited according to the given text instruction, preserving the geometric characteristics of the initial mesh while focusing on the most significant areas. We evaluate our pipeline using the DTU dataset, demonstrating that it generates finely-edited meshes more rapidly than the current state-of-the-art methods. We include our code and additional results in the supplementary material. © 2024, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

VLP-KAN: Low-Complexity and Interpretable RSS-Based VLP Using Kolmogorov-Arnold Networks

VLP-KAN: Low-Complexity and Interpretable RSS-Based VLP Usin...

引用

Annual Conference on Wireless On Demand Network systems and Services (WONS)

作者： Fabian Seguel Driton Salihu Stefan Hägele Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich School of Computation Information and Technology München Germany

ISBN: (数字)9783903176713

ISBN: (纸本)9798331522025

Received signal strength (RSS)-based Visible Light Positioning (VLP) has gained attention due to its relatively easy infrastructure deployment and high localization accuracy. Different low-complexity geometrical and machine learning (ML)-based models have been proposed for localization because of their robustness against the uncertainty produced by tilted devices, non-Lambertian sources, and the low dimensionality of RSS-vector. Inspired by the Kolmogorov-Arnold representation theorem, Kolmogorov-Arnold Networks (KANs) have been proposed as a promising alternative to Multi-Layer Perceptrons (MLPs). This paper evaluates the use and performance of KANs in VLP systems for the first time. Results show that in the proposed scenario, KANs achieve below cm-level accuracy. Moreover, symbolic regression (SR) can be implemented straightforwardly to find a function that relates RSS with distance. It is shown in this paper that both KANs and SR-KAN models outperform MLP and Weighted K-nearest neighbors based approaches.

关键词： Location awareness Wireless communication Performance evaluation Deep learning Accuracy Uncertainty Nearest neighbor methods Fingerprint recognition Robustness Network systems

来源：评论

学校读者我要写书评

暂无评论

Bio-Inspired Spherical Joints for a Soft Articulated Artificial Hand

Bio-Inspired Spherical Joints for a Soft Articulated Artific...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Theophil Spiegeler Castañeda Patricia Capsi-Morales Xiaoqian Zhang Cristina Piazza School of Computation Information and Technology Technical University of Munich (TUM) Munich Germany Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich (TUM) Munich Germany Independent research

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

The introduction of soft robotics technologies represents a promising direction to enhance system robustness and natural interaction. However, the inherent flexibility in joint designs can pose challenges in achieving both precise and repeatable gripping. This work introduces a soft artificial hand design with constrained ball joints, inspired by the anatomical structure of bones and tendons in the human hand. The key innovation lies in the integration of selectable stiffness levels in the spherical joints, enabling distinct stiffness characteristics to achieve both power and precision grasps. Through a set of contact simulations, this study characterize different behaviors in the finger model according to the stiffness level of its joints. The final hand design encompasses 15 degrees of freedom (DoF) actuated by a unique tendon and a single motor, and a passive proximal thumb joint. The developed prototype was preliminarily tested to assess its manipulation taxonomy and demonstrated the ability to grasp everyday objects in different configurations. Results show the potential of the proposed joint design in achieving a trade-off between precision and adaptability in grasping.

关键词： Technological innovation Taxonomy Thumb Prototypes Grasping Soft robotics Motors Robustness Joints Tendons

来源：评论

学校读者我要写书评

暂无评论

The impact of dwell time on the contextual effect of visual and passive lead-in movements

引用

Journal of Neurophysiology 2025年第5期133卷 1520-1537页

作者： Alvarez-Hidalgo, Laura Franklin, David W. Howard, Ian S. School of Computing Engineering and Mathematics University of Plymouth Plymouth United Kingdom Neuromuscular Diagnostics TUM School of Medicine and Health Technical University of Munich Munich Germany Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich Munich Germany Munich Data Science Institute (MDSI) Technical University of Munich Munich Germany

Contextual cues arising from distinct movements are crucial in shaping control strategies for human movement. Here, we examine the impact of visual and passive lead-in movement cues on unimanual motor learning, focusing on the influence of “dwell time,” where two-part movements are separated by the interval between the end of the first movement and the start of the second. We used a robotic manipulandum to implement a point-to-point interference task with switching opposing viscous curl fields in male and female human participants. Consistent with prior research, in both visual and passive lead-in conditions, participants showed significant adaptation to opposing dynamics with short dwell times. As dwell time increased for both visual and passive signals, past movement information had less contextual influence. However, the efficacy of visual movement cues declined more rapidly as dwell times increased. At dwell times greater than 800 ms, the contextual influence of prior visual movement was small, whereas the effectiveness of passive lead-in movement was found to be significantly greater. This indicates that the effectiveness of sensory movement cues in motor learning is modality dependent. We hypothesize that such differences may arise because proprioceptive signals directly relate to arm movements, whereas visual inputs exhibit longer latency and, in addition, can relate to many aspects of movement in the environment and not just to our own arm movements. Therefore, the motor system may not always find visual movement cues as relevant for predictive control of dynamics. Copyright © 2025 The Authors.

关键词： dynamic learning lead-in context motor memory predictive compensation temporal decay

来源：评论

学校读者我要写书评

暂无评论

NPRF: Neural Painted Radiosity Fields for Neural Implicit Rendering and Surface Reconstruction

NPRF: Neural Painted Radiosity Fields for Neural Implicit Re...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Driton Salihu Adam Misik Yuankai Wu Constantin Patsch Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich School of Computation Information and Technology Siemens Technology

In recency, neural signed distance fields have become more popular for reconstructing 3D indoor environments. While great improvements have been made due to missing incident radiance and materials in the surface estimation, current methods cannot reconstruct high-quality surfaces. To address this issue, we propose Neural Painted Radiosity Fields (NPRF), consisting of Neural Radiosity Fields for volumetric surface representation and Neural Painted Scenes for novel view synthesis. Neural Radiosity Fields combine the radiative transfer equation with neural radiosity to estimate 3D surfaces, thus leveraging raytracing to improve the volumetric representation. Neural Painted Scenes employs sparsification and projection of 3D points into 2D images in conjunction with a generative, context-aware inpainting network to produce high-quality novel views. We show that NPRF leads to overall improvements in F-score on the popular ScanNet dataset. Finally, we show that NPRF improves novel view synthesis by a significant margin, giving improvements of up to 25% on PSNR, 53% on LPIPS, and 3% on SSIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating Virtual Fixture Parameters in Digital Twin Environments for Robot Manipulation Tasks using Reinforcement Learning

Estimating Virtual Fixture Parameters in Digital Twin Enviro...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Diego Fernandez Prado Eckehard Steinbach Technical University of Munich / School of Computation Information and Technology / Chair of Media Technology and Munich Institute of Robotics and Machine Intelligence (MIRMI) Munich Germany

In recent years, the idea of teleoperating robots to perform manipulation tasks has gained popularity. Being able to take remote control of a robotic system performing an assembly task provides exciting possibilities for industry, not only operating the robot in hazardous environments, but also facilitating the accessibility of human workers, requesting help from a remote expert, or even teaching skills. With the rise of teleoperated manipulators, it is expected that tools that facilitate the interaction of humans with the remote environment will be more prevalent in industry, leading to a greater availability of them. This is the case with Virtual Fixtures (VFs), which are collections of abstract sensory information overlaid on top of reflected sensory feedback from a remote environment. Other ever more prevalent tools are Digital Twins (DTs), virtual representations of systems that facilitate bidirectional communication between the real and the virtual worlds. Being more likely than ever that factories have both an implemented Digital Twin of a system and VFs for a particular manipulation system, we propose a method to leverage both tools. In this paper, methods to integrate already existing VFs in a Reinforcement Learning (RL) pipeline and to use RL to construct an optimal VF to aid the human user in a telemanipulation task are proposed, tackling the cumbersome problems of reward function and VF design. The results show that this approach is able to correctly estimate the right parameters of predefined VFs and open the possibility to future work in this topic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessing Perceived Discomfort and Proxemic Behavior towards Robots: A Comparative Study between Real and Augmented Reality Presentations

Assessing Perceived Discomfort and Proxemic Behavior towards...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Olivia Herzog Simone Nertinger Katharina Wenzel Abdeldjallil Naceri Sami Haddadin Klaus Bengler Chair of Ergonomics School of Engineering and Design Technical University of Munich Germany Munich Institute of Robotics and Machine Intelligence Technical University of Munich Germany

This paper assesses the usefulness of immersive technology to evaluate perceived discomfort and proxemic behavior towards a robot depending on its size. Therefore, we compared a real and an augmented reality (AR) robot presentation. In a within-subject design, a service humanoid approached participants (N = 32) in four trials in a counterbalanced order. One trial presented a real robot, another showed a same-sized AR version, and two trials showed down-scaled AR versions of the robot. The perceived discomfort and the comfort distance were measured. For the presentation mode comparison, the distance estimation error was measured additionally. The results show that the comfort distance was greater for the AR robot than for the real one. The comfort distance was also greater for the largest robot compared to the smaller sizes, while there was no difference when comparing the smaller ones. There was no difference in perceived discomfort between the presentation modes or the robot sizes. The distance estimation error was greater in AR. The study indicates that results obtained with the AR and real robot are comparable relative to each other. Therefore, utilizing AR could effectively evaluate various versions of robots in terms of the discomfort they induce—a critical prerequisite prior to the manufacturing process. Finally, AR might provide better validity for the evaluation of subjective measures.

关键词：

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：