检索结果-内蒙古大学图书馆

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

PU-SDF: Arbitrary-Scale Uniformly Upsampling Point Clouds via Signed Distance Functions

PU-SDF: Arbitrary-Scale Uniformly Upsampling Point Clouds vi...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Shaohui Pan Yong Xu Ruotao Xu School of Computer Science and Engineering South China University of Technology Guangzhou China Peng Cheng Laboratory ShenZhen China Communication and Computer Network Laboratory of Guangdong Guangzhou China Institute of Super Robotics South China University of Technology Guangzhou China

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Point cloud upsampling is a crucial technique for improving the performance of 3D data understanding, enabling the creation of dense and uniform point clouds from raw and sparse input data. However, most existing methods exhibit limitations in dealing with different scaling factors, either requiring multiple networks or producing unevenly distributed points. To tackle this issue, this paper proposes a deep learning method called PU-SDF, which consists of a local-feature-based signed distance function network (LSDF-network) and a 3D-grid query points generation module (GPGM). The proposed LSDF-network can perform point cloud upsampling at arbitrary rates and can be easily adapted to handle unseen datasets. Additionally, we propose the GPGM that generates uniform and unlimited query points in sparse voxel space with arbitrary resolution. Extensive qualitative and quantitative evaluations demonstrate the superior performance of the PU-SDF method, achieving state-of-the-art point cloud upsampling performance.

关键词： Point cloud compression Training Deep learning Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

GelPixel: A Single-Pixel-Based Tactile Sensor

GelPixel: A Single-Pixel-Based Tactile Sensor

引用

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

作者： Binhua Huang Xiaoyu Li Putra Sumari Chaoxiang Ye Zhenning Zhou Meng Yin Zhengkun Yi Xinyu Wu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science Universiti Sains Malaysia Malaysia

In this paper, we present the design and development of a novel optical tactile sensor that uses a single-pixel color light-to-frequency converter (TCS3200) and spectral decoding to recognize presses at different positions. This innovative approach overcomes the limitations associated with camera-based sensors, such as increased manufacturing costs and shape restrictions, enabling potential integration as a skin-like layer over a robot’s body. Our proposed direct light propagation structure demonstrates enhanced sensitivity and a broader measuring range compared to traditional reflection structures. Using Ecoflex as the elastomer, the sensor’s design incorporates a three-layer structure, including an LED layer, an elastomer layer, and a color sensor layer. Experimental results demonstrate that the proposed sensor performs well in localization tasks, achieving over 95% accuracy using multi-target regression for rendering poked positions. This study demonstrates the potential of single-pixel-based tactile sensors in various applications and provides a foundation for further exploration in this area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OffRIPP: Offline RL-based Informative Path Planning

arXiv

引用

arXiv 2024年

作者： Gadipudi, Srikar Babu Deolasee, Srujan Kailas, Siva Luo, Wenhao Sycara, Katia Kim, Woojun The Department of Electrical Engineering Indian Institute of Technology Madras India The Robotics Institute Carnegie Mellon University United States The School of Interactive Computing Georgia Institute of Technology United States The Department of Computer Science University of North Carolina at Charlotte United States

Informative path planning (IPP) is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment while adhering to resource constraints. Reinforcement learning (RL) has been shown to be effective for IPP, however, it requires environment interactions, which are risky and expensive in practice. To address this problem, we propose an offline RL-based IPP framework that optimizes information gain without requiring real-time interaction during training, offering safety and cost-efficiency by avoiding interaction, as well as superior performance and fast computation during execution—key advantages of RL. Our framework leverages batch-constrained reinforcement learning to mitigate extrapolation errors, enabling the agent to learn from pre-collected datasets generated by arbitrary algorithms. We validate the framework through extensive simulations and real-world experiments. The numerical results show that our framework outperforms the baselines, demonstrating the effectiveness of the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Estimating the Joint Angles of an Articulated Microrobotic Instrument Using Optical Coherence Tomography

Estimating the Joint Angles of an Articulated Microrobotic I...

引用

International Symposium on Medical robotics (ISMR)

作者： Erik Fredin Nirmal Pol Anton Zaliznyi Eric Diller Lueder A. Kahrs Department of Mechanical and Industrial Engineering University of Toronto Canada Institute of Biomedical Engineering University of Toronto Canada Institute of Computer Science University of Tartu Estonia Robotics Institute University of Toronto Canada Department of Mathematical and Computational Sciences University of Toronto Mississauga Canada

ISBN: (数字)9798350377118

ISBN: (纸本)9798350377125

Pose estimation of surgical tools is necessary for controlling and manipulating the tool in confined surgical regions for minimally invasive surgeries. Several studies have explored the application of robot assisted surgeries which require an imaging system to track the tool and navigate it with high accuracy and precision. Optical Coherence Tomog-raphy (OCT) is an emerging volumetric imaging modality in minimally invasive robot assisted surgery. We present a marker-based computer vision algorithm to estimate the wrist and finger joint angles of a neurosurgical gripper tool from an OCT volume. The tool's joint angles lie on two perpendicular planes. Markers of 1 mm diameter are placed on the tool and then the gripper is imaged under the OCT system. The raw volumetric images are pre-processed by downsampling and applying thresholds. The markers in the OCT volume are then detected using 3D template matching. False positive detections are algorithmically omitted by evaluating the relative distances between the markers. Finally, the positions of these detected markers are used to estimate the joint angles. Our approach yields an average error of 2.20 and a standard deviation of 3.4° for the wrist joint $(\theta_{1})$ . For the finger joint $(\theta_{2})$ , it yields an average error of 2° and a standard deviation of 1.5°• The estimations are provided within 0.5 seconds on a PC with a 16 core CPU.

关键词： Wrist Medical robotics Minimally invasive surgery Three-dimensional displays Optical coherence tomography Fingers Pose estimation

来源：评论

学校读者我要写书评

暂无评论

REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation

arXiv

引用

arXiv 2025年

作者： Yuan, Puzhen Ma, Angyuan Yao, Yunchao Yao, Huaxiu Tomizuka, Masayoshi Ding, Mingyu Xingjian College Tsinghua University China Robotics Institute Carnegie Mellon University United States Department of Computer Science UNC Chapel Hill United States Department of Mechanical Engineering UC Berkeley United States

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers several appealing benefits: 1) Robots can initially explore and reason about the environment without complex prompt design. 2) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 3) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC’s effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3-mini, QwQ, and Grok3, demonstrating REMAC’s superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline without any task-specific prompting or finetuning. Copyright © 2025, The Authors. All rights r

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Aeroengine remaining useful life prediction via integrating enhanced inverted transformer and spatiotemporal graph learning

引用

ISA Transactions 2025年

作者： Sun, Shilong Ding, Hao Zhao, Zida Zhou, Yu Wang, Dong Xu, Wenfu School of Robotics and Advanced Manufacturing College of Artificial Intelligence Harbin Institute of Technology Shenzhen China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China

Accurate prediction of aeroengine Remaining Useful Life (RUL) is critical for ensuring flight safety, minimizing maintenance costs, and improving operational efficiency. This study proposes a novel model, the Fourier-Enhanced Inverted Transformer with Graph-Augmented Spatiotemporal Modeling (FIT-GSTM), to enhance RUL prediction performance. FIT-GSTM combines an inverted Transformer with a Spatiotemporal Graph Convolutional Network (STGCN) to effectively capture global spatiotemporal dependencies across multi-sensor data. To further enrich feature representation, the model incorporates Fast Fourier Transform (FFT) to extract frequency-domain information and fuses it with time-domain features, enhancing robustness to noise. Additionally, the integration of Memory Tokens and Reversible Instance Normalization (RevIN) strengthens the model's ability to retain long-term dependencies and adapt to heterogeneous data distributions. Experimental evaluations on the C-MAPSS dataset demonstrate that FIT-GSTM achieves superior RUL prediction accuracy and generalization compared to existing methods, highlighting its potential for real-world deployment in aeroengine health management. © 2025 ISA

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Multitarget–Multidetection Tracking Using the Kernel SME Filter

Multitarget–Multidetection Tracking Using the Kernel SME Fi...

引用

International Conference on Information Fusion

作者： Eugen Ernst Florian Pfaff Marcus Baum Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology (KIT) Germany Data Fusion Group Institute of Computer Science Georg-August-University Göttingen Germany

With the growing availability of high-resolution sensors, processing more than one detection per target becomes increasingly critical when tracking multiple extended objects. However, contemporary sensors often generate spurious detections that need to be considered. Naively employing standard multitarget trackers may result in poor tracking performance for multitarget–multidetection tracking in cluttered environments, and the relevant extensions are nontrivial. This paper introduces a version of the kernel symmetric measurement equation (SME) filter that considers both multidetections and clutter. For a simulated scenario, our novel filter achieved a higher accuracy than the global nearest neighbor (GNN) and a fast variant of the joint probabilistic data association filter (JPDAF).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Prediction of Subsurface Oil Reservoir Pressure Using Spatio-Temporal Data 49

Deep Learning-Based Prediction of Subsurface Oil Reservoir P...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Cheng, Haibo He, Yunpeng Zeng, Peng Li, Shichao Vyatkin, Valeriy Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Luleå University of Technology Department of Computer Science Electrical and Space Engineering Luleå Sweden Aalto University Department of Electrical Engineering and Automation Helsinki Finland

ISBN: (纸本)9798350331820

Prediction of subsurface oil reservoir pressure are critical to hydrocarbon production. However, the accurate pressure estimation faces great challenges due to the complexity and uncertainty of reservoir. The underground seepage flow and petrophysical parameters (permeability and porosity) are important but difficult to measure in oilfield. Deep learning methods have been successfully used in reservoir engineering and oil & gas production process. In this study, the effective but inaccessible subsurface seepage fields are not used, only the spatial coordinates and temporal information are selected as model input to predict reservoir pressure. A stacked GRU-based deep learning model is proposed to map the relationship between spatio-temporal data and reservoir pressure. The proposed deep learning method is verified by using a three-dimensional reservoir model, and compared with commonly-used methods. The results show that the stacked GRU model has a better performance and higher accuracy than other deep learning or machine learning methods in pressure prediction. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Classification on MRI in Light of Molecular Markers

arXiv

引用

arXiv 2024年

作者： Liu, Jun Yuan, Geng Zeng, Weihao Tang, Hao Zhang, Wenbin Lin, Xue Xu, XiaoLin Huang, Dong Wang, Yanzhi Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States Department of Electrical & Computer Engineering College of Engineering Northeastern University BostonMA United States University of Maryland Baltimore CountyMD United States

In research findings, co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas. The ability to predict 1p19q status is critical for treatment planning and patient follow-up. This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection. Although public networks such as RestNet and AlexNet can effectively diagnose brain cancers using transfer learning, the model includes quite a few weights that have nothing to do with medical images. As a result, the diagnostic results are unreliable by the transfer learning model. To deal with the problem of trustworthiness, we create the model from the ground up, rather than depending on a pre-trained model. To enable flexibility, we combined convolution stacking with a dropout and full connect operation, it improved performance by reducing overfitting. During model training, we also supplement the given dataset and inject Gaussian noise. We use three–fold cross-validation to train the best selection model. Comparing InceptionV3, VGG16, and MobileNetV2 fine-tuned with pre-trained models, our model produces better results. On a validation set of 125 codeletion vs. 31 not codeletion images, the proposed network achieves 96.37% percent F1-score, 97.46% percent precision, and 96.34% percent recall when classifying 1p/19q codeletion and not codeletion images. © 2024, CC BY.

关键词： Diseases

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：