检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yin, Xiaoting Shi, Hao Bao, Yuhan Bing, Zhenshan Liao, Yiyi Yang, Kailun Wang, Kaiwei State Key Laboratory of Modern Optical Instrumentation Zhejiang University China School of Robotics National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Information Science and Electronic Engineering Zhejiang University China The Chair of Robotics AI and Real-Time Systems Technical University of Munich Germany

Estimating Neural Radiance Fields (NeRFs) from images captured under optimal conditions has been extensively explored in the vision community. However, robotic applications often face challenges such as motion blur, insufficient illumination, and high computational overhead, which adversely affect downstream tasks like navigation, inspection, and scene visualization. To address these challenges, we propose E-3DGS, a novel event-based approach that partitions events into motion (from camera or object movement) and exposure (from camera exposure), using the former to handle fast-motion scenes and using the latter to reconstruct grayscale images for high-quality training and optimization of event-based 3D Gaussian Splatting (3DGS). We introduce a novel integration of 3DGS with exposure events for high-quality reconstruction of explicit scene representations. Our versatile framework can operate on motion events alone for 3D reconstruction, enhance quality using exposure events, or adopt a hybrid mode that balances quality and effectiveness by optimizing with initial exposure events followed by high-speed motion events. We also introduce EME-3D, a real-world 3D dataset with exposure events, motion events, camera calibration parameters, and sparse point clouds. Our method is faster and delivers better reconstruction quality than event-based NeRF while being more cost-effective than NeRF methods that combine event and RGB data by using a single event sensor. By combining motion and exposure events, E-3DGS sets a new benchmark for event-based 3D reconstruction with robust performance in challenging conditions and lower hardware demands. The source code and dataset will be available at https://***/MasterHow/E-3DGS. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Gerchberg-Saxton Algorithm to Retrieve Phase of Laguerre-Gaussian Beams that Carry OAM

Gerchberg-Saxton Algorithm to Retrieve Phase of Laguerre-Gau...

引用

Propagation Through and Characterization of Atmospheric and Oceanic Phenomena, pcAOP 2024 - Part of Optica Imaging Congress

作者： O’Malley, Owen Avramov-Zamurovic, Svetlana Ferlic, Nathaniel A. Judd, K. Peter Weapons Robotics and Control Engineering Department United States Naval Academy 597 McNair Rd. Hopper Hall AnnapolisMD21402 United States Naval Air Warfare Center Aircraft Division 22347 Cedar Point Road Patuxent RiverMD20670 United States United States Naval Research Laboratory 4555 Overlook Ave. SW WashingtonDC20375 United States

We estimate the phase of laser beams using the Gerchberg-Saxton algorithm after propagation through experimental and simulated optical turbulence. Synchronous pupil-plane and focal-plane intensities of Gaussian and La... 详细信息

关键词： Laser beams

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Based Multi-Perception Safety Strategy for Human-Robot Collaboration

Transfer Learning Based Multi-Perception Safety Strategy for...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Chongyi Wei Changcong Wang Shaoping Bai Yibin Li Xincheng Tian Lelai Zhou Center for Robotics School of Control Science and Engineering Shandong University Jinan China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan China Department of Materials and Production Aalborg University Aalborg Denmark

Human-robot collaboration (HRC) is vital to adapt to the significant change in manufacturers’ demands for automation, and safety is a primary and major challenge that must be addressed for it. In this paper, a muti-perception safety strategy and framework are introduced to ensure human safety while trying to avoid reducing the work efficiency of the robot by taking human activity intentions and human-robot distance into account. To realize the safety strategy, an LSTM-CNN based neural network is built for human activity classification. To improve the generalization ability and performance of the network with data scarcity for existing deep learning-based human activity recognition methods, transfer learning-enabled activity recognition is proposed. Based on the studies, a feasible security system is implemented in the human-robot collaboration scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial and Temporal Study of controlled Underwater Optical Turbulence from Synchronous Measurements

Spatial and Temporal Study of Controlled Underwater Optical ...

引用

Propagation Through and Characterization of Atmospheric and Oceanic Phenomena, pcAOP 2024 - Part of Optica Imaging Congress

作者： Avramov-Zamurovic, Svetlana Ferlic, Nathaniel A. Kelly, Thomas O’Malley, Owen Judd, K. Peter Weapons Robotics and Control Engineering Department United States Naval Academy 597 McNair Rd. Hopper Hall AnnapolisMD21402 United States Naval Air Warfare Center Aircraft Division 22347 Cedar Point Road Patuxent RiverMD20670 United States United States Naval Research Laboratory 4555 Overlook Ave. SW WashingtonDC20375 United States

We experimentally record intensity of laser light at the pupil and focal planes after propagation through underwater optical turbulence. We study the temporal and spatial properties of intensity correlations and angle...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forward Kinematics Development of a 3-RRS Parallel Manipulator for Real-Time control

Forward Kinematics Development of a 3-RRS Parallel Manipulat...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： S. Ali A. Moosavian Omid Mahdizadeh Sina Hallajian Sara Ashrafi Mohammad Jamali Vahid Akbari Department of Mechanical Engineering Center of Excellence in Robotics and Control Advanced Robotics and Automated Systems (ARAS) Lab. K. N. Toosi University of Technology Tehran Iran

ISBN: (纸本)9781665454537

In control of parallel robots, forward kinematics calculation is mainly required. In some studies, obtained equations are solved numerically with massive calculations that is not acceptable for control implementations. This paper introduces a new method to extract forward kinematics for a 3- RRS robot. This method calculates the kinematics of passive joints with two separated equations, which can be solved to decrease the total computation demands. Also, a new weight compensation mechanism is proposed to improve the dynamic response by a linear pneumatic actuator placed between the ground and the end-effector. On the other hand, to use various control algorithms, the position of the rolling ball on the end- effector (moving platform) must be measured. This is performed using Convolutional Neural Networks (CNNs) as image processing algorithms. Since the system must work quickly for a high-frequency task, the proposed image processing algorithm can provide the desired fast feedback. Experimental results reveal the merits of the above-described proposed modules.

关键词： Pneumatic actuators Image processing Heuristic algorithms Kinematics Position measurement Pneumatic systems Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Cascaded Model Predictive control of Underactuated Bipedal Walking with Impact and Friction Considerations

Cascaded Model Predictive Control of Underactuated Bipedal W...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Sait Sovukluk Christian Ott M. Mert Ankaralı Automation and Control Institute (ACIN) TU Wien Vienna Austria Department of Electrical and Electronics Engineering Middle East Technical University (METU) Ankara Turkey Institute of Robotics and Mechatronics German Aerospace Center (DLR) Wessling Germany METU Robotics and AI Technologies Application and Research Center (METU-ROMER) Ankara Turkey

This study demonstrates a cascaded model predictive control (C-MPC) method for input constrained control of underactuated planar bipedal walking with any predefined sta-bilizable trajectory. Our approach aims to increase the trajectory tracking performance of the system and produce realistic and applicable responses while respecting friction constraints and considering impact dynamics. Primarily focusing on zero dynamics with PD (ZD+PD) control, this proposed control method constitutes a second layer controller on top of the well-known trajectory tracking controllers for underactuated bipedal walking systems. We successfully implement this model-based controller and test against large modeling errors, noises, and disturbances, where the conventional ZD+PD control fails to maintain stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts

arXiv

引用

arXiv 2025年

作者： Huang, Yizhou Yang, Fan Zhu, Guoliang Li, Gen Shi, Hao Zuo, Yukun Chen, Wenrui Li, Zhiyong Yang, Kailun School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China School of Informatics University of Edinburgh United Kingdom State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China

Affordance refers to the functional properties that an agent perceives and utilizes from its environment, and is key perceptual information required for robots to perform actions. This information is rich and multimodal in nature. Existing multimodal affordance methods face limitations in extracting useful information, mainly due to simple structural designs, basic fusion methods, and large model parameters, making it difficult to meet the performance requirements for practical deployment. To address these issues, this paper proposes the BiT-Align image-depth-text affordance mapping framework. The framework includes a Bypass Prompt Module (BPM) and a Text Feature Guidance (TFG) attention selection mechanism. BPM integrates the auxiliary modality depth image directly as a prompt to the primary modality RGB image, embedding it into the primary modality encoder without introducing additional encoders. This reduces the model’s parameter count and effectively improves functional region localization accuracy. The TFG mechanism guides the selection and enhancement of attention heads in the image encoder using textual features, improving the understanding of affordance characteristics. Experimental results demonstrate that the proposed method achieves significant performance improvements on public AGD20K and HICO-IIF datasets. On the AGD20K dataset, compared with the current state-of-the-art method, we achieve a 6.0% improvement in the KLD metric, while reducing model parameters by 88.8%, demonstrating practical application values. The source code will be made publicly available at https://***/DAWDSE/BiT-Align. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Lin, Jiacheng Chen, Jiajun Peng, Kunyu He, Xuan Li, Zhiyong Stiefelhagen, Rainer Yang, Kailun The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics Hunan University Changsha410012 China The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The Institute for Robotics and An-Thropomatics Karlsruhe Institute of Technology Karlsruhe76131 Germany

This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving. Due to the lack of semantic modeling capacity in audio and video, existing works have mainly focused on text-based multiobject tracking, which often comes at the cost of tracking quality, interaction efficiency, and even the safety of assistance systems, limiting the application of such methods in autonomous driving. In this paper, we delve into the problem of AR-MOT from the perspective of audio-video fusion and audio-video tracking. We put forward EchoTrack, an end-to-end AR-MOT framework with dual-stream vision transformers. The dual streams are intertwined with our Bidirectional Frequency-domain Cross-attention Fusion Module (Bi-FCFM), which bidirectionally fuses audio and video features from both frequency- and spatiotemporal domains. Moreover, we propose the Audio-visual Contrastive Tracking Learning (ACTL) regime to extract homogeneous semantic features between expressions and visual objects by learning homogeneous features between different audio and video objects effectively. Aside from the architectural design, we establish the first set of large-scale AR-MOT benchmarks, including Echo-KITTI, Echo-KITTI+, and Echo-BDD. Extensive experiments on the established benchmarks demonstrate the effectiveness of the proposed EchoTrack and its components. The source code and datasets are available at https://***/lab206/EchoTrack. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LDFCDet: Boosting 3D Object Detectors with Low-High level Feature Crosses Using Laplace Distribution

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： He, Zhenyu Mao, Jianxu Wang, Yaonan Yu, Junlong Tao, Ziming Yi, Junfei Zhang, Hui Wang, Shaoyuan Hunan University College of Electrical and Information Engineering Hunan Changsha410012 China Hunan University School of Robotics Changsha410082 China National Engineering Reseach Center for Robot Visual Perception and Control Technology Changsha410082 China

Highly accurate 3D object detection is critical for autonomous driving and robotic sensing system. However, some objects with few foreground points significantly affect the accuracy of 3D object detection. As the network depth increases, the low-level features of these objects are gradually lost, especially for the hard object. Due to this issue, current LiDAR-only based and multimodal methods often misclassify background as foreground. Therefore, how to leverage the low-level feature that contain information about these objects in the high layer of the network becomes the key to optimizing the issue. In this paper, we propose LDFCDet, a framework boosting 3D object detectors with low-high level feature crosses using Laplace distribution(LD). In our proposed method, we design a low-high level feature crosses module(LHFCM) to embed low-level feature into high-level feature in the deeper layer of the network, and use Laplace distribution to obtain a new low-high level feature that includes information about these objects with few foreground points. In addition, we propose a res-gated feature aggregation module(RGFAM) to fuse the mutli-scale features. Our approach is well-suited for both LiDAR-based and multimodal *** evaluate the LDFCDet on the widely used KITTI dataset, and our method outperforms almost current 3D object detection methods on the challenging KITTI test set. Moreover, we conducted comparative experiments on the ONCE dataset, and the results further demonstrate the effectiveness and superiority of our method. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Teng, Fei Zhang, Jiaming Peng, Kunyu Wang, Yaonan Stiefelhagen, Rainer Yang, Kailun The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany The Institute for Visual Computing ETH Zurich Zurich8092 Switzerland

Light field cameras are capable of capturing intricate angular and spatial details. This allows for acquiring complex light patterns and details from multiple angles, significantly enhancing the precision of image semantic segmentation. However, two significant issues arise: (1) The extensive angular information of light field cameras contains a large amount of redundant data, which is overwhelming for the limited hardware resources of intelligent agents. (2) A relative displacement difference exists in the data collected by different micro-lenses. To address these issues, we propose an Omni-Aperture Fusion model (OAFuser) that leverages dense context from the central view and extracts the angular information from sub-aperture images to generate semantically consistent results. To simultaneously streamline the redundant information from the light field cameras and avoid feature loss during network propagation, we present a simple yet very effective Sub-Aperture Fusion Module (SAFM). This module efficiently embeds sub-aperture images in angular features, allowing the network to process each sub-aperture image with a minimal computational demand of only (∼1GFlops). Furthermore, to address the mismatched spatial information across viewpoints, we present a center Angular Rectification Module (CARM) to realize feature resorting and prevent feature occlusion caused by misalignment. The proposed OAFuser achieves state-of-the-art performance on four UrbanLF datasets in terms of all evaluation metrics and sets a new record of 84.93% in mIoU on the UrbanLF-Real Extended dataset, with a gain of +3.69%. The source code for OAFuser is available at https://***/FeiBryantkit/OAFuser. Impact Statement-To solve the data abundance problem, we have reduced the significant computational consumption of light field cameras while not introducing any additional parameters. The proposed method has practical value for the deployment and application of light field cameras. The proposed

关键词： Semantic Segmentation

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：