检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yufei Sun, Zhanyi Zhang, Jesse Xian, Zhou Bıyık, Erdem Held, David Erickson, Zackory Robotics Institute Carnegie Mellon University United States Department of Computer Science University of Southern California United States

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks, using only a text description of the task goal and the agent's visual observations, by leveraging feedbacks from vision language foundation models (VLMs). The key to our approach is to query these models to give preferences over pairs of the agent's image observations based on the text description of the task goal, and then learn a reward function from the preference labels, rather than directly prompting these models to output a raw reward score, which can be noisy and inconsistent. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains - including classic control, as well as manipulation of rigid, articulated, and deformable objects - without the need for human supervision, outperforming prior methods that use large pretrained models for reward generation under the same assumptions. Videos can be found on our project website: https://***/. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Navigation with Anti-Backtracking 27th

Audio-Visual Navigation with Anti-Backtracking

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Zhenghao Tang, Hao Yan, Yan Department of Computer Science University of Illinois Chicago Chicago United States Robotics Institute Carnegie Mellon University Pittsburgh United States

ISBN: (纸本)9783031784552

Embodied navigation, which involves robotic agents exploring an unknown environment to reach target locations with egocentric observation, is a complex problem in the field of embodied AI. Audio-visual navigation extends this concept by equipping agents with both visual and auditory sensors. Recent studies have explored the audio-visual navigation task, exploring its potential and intricacies. Current methodologies, despite their achievements, often fail to fully utilize the capabilities of these sensory modalities, leading to sub-optimal designs and inefficiencies. In addition, the prevalent backtracking problem in navigation tasks often leads to redundant movements by robots. To address these challenges, we introduce the Audio-Visual Guided Navigation (AVGN) model. At its core, AVGN champions the fusion of visual and auditory data through sophisticated modality fusion layers. Our model represents a significant advancement by employing transformers for visual encoding and deploying a novel Dual Stage Feature Integration (DSFI) to decode latent interrelationships between the visual and audio realms. With AVGN, the backtracking issue is mitigated, as the acoustic map synergizes more effectively with visual features for informed action decisions. Furthermore, targeting the backtracking problem, we propose a unique set of reward structures to guide and refine the actions of the agent. Benchmark evaluations on Replica and Matterport3D datasets validate our claims, and AVGN notably surpasses existing methodologies in audio-visual navigation tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DeepRice: A deep learning and deep feature based classification of Rice leaf disease subtypes

引用

Artificial Intelligence in Agriculture 2024年第1期11卷 34-49页

作者： P.Isaac Ritharson Kumudha Raimond X.Anitha Mary Jennifer Eunice Robert Andrew J Department of CSE Karunya Institute of Technology and Sciences CoimbatoreTamilnaduIndia Department of Robotics Engineering Karunya Institute of Technology and SciencesCoimbatoreIndia Department of Mechatronics Engineering Manipal Institute of TechnologyManipal Academy of Higher EducationManipalKarnataka 576104India Department of Computer Science and Engineering Manipal Institute of TechnologyManipal Academy of Higher EducationManipalKarnataka 576104India

Rice stands as a crucial staple food globally,with its enduring sustainability hinging on the prompt detection of rice leaf ***,efficiently detecting diseases when they have already occurred holds paramount importance for solving the cost of manual visual identification and chemical *** the recent past,the identification of leaf pathologies in crops predominantly relies on manual methods using specialized equipment,which proves to be time-consuming and *** study offers a remedy by harnessing Deep Learning(DL)and transfer learning techniques to accurately identify and classify rice leaf diseases.A comprehensive dataset comprising 5932 self-generated images of rice leaves was assembled along with the benchmark datasets,categorized into 9 classes irrespective of the extent of disease spread across the *** classes encompass diverse states including healthy leaves,mild and severe blight,mild and severe tungro,mild and severe blast,as well as mild and severe brown *** meticulous manual labelling and dataset segmentation,which was validated by horticulture experts,data augmentation strategies were implemented to amplify the number of *** datasets were subjected to evaluation using the proposed tailored Convolutional Neural Networks *** performance are scrutinized in conjunction with alternative transfer learning approaches like VGG16,Xception,ResNet50,DenseNet121,Inception ResnetV2,and Inception *** effectiveness of the proposed custom VGG16 model was gauged by its capacity to generalize to unseen images,yielding an exceptional accuracy of 99.94%,surpassing the benchmarks set by existing state-of-the-art ***,the layer wise feature extraction is also visualized as the interpretable AI.

关键词： Rice leaf disease Deep learning CNN Crop yield Agriculture Food security

来源：评论

学校读者我要写书评

暂无评论

Stress Detection Using CNN on the WESAD Dataset 4

Stress Detection Using CNN on the WESAD Dataset

引用

4th International Conference on Emerging Systems and Intelligent Computing, ESIC 2024

作者： Shirley Benita, D. Shamila Ebenezer, A. Susmitha, L. Subathra, M.S.P. Jeba Priya, S. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Karunya Institute of Technology and Sciences Departnemt of Robotics Engineering Coimbatore India

ISBN: (纸本)9798350349856

Stress, a pervasive psychological state, profoundly impacts individuals' well-being and may lead to various health issues. In this paper, the WESAD (Wearable Stress and Affect Detection) dataset serves as the primary data source, from which HRV (Heart Rate Variability) data extracted using PPG (Photoplethysmography) sensor is utilized. This data can be obtained in a non-invasive method and is instrumental in this analysis. The dataset comprises HRV data from 15 individual test subjects obtained from PPG sensors, providing a crucial foundation for the detection and classification of individuals into 'stressed' or 'not stressed' categories, thus offering a valuable tool for stress monitoring. This paper is a focused exploration into the CNN (Convolutional Neural Network) Deep Learning model, in which the feature selection process is carried out using Random Forest resulting in the selection of HR (Heart Rate), LF_BOXCOX (Low-Frequency Component - Box-Cox Transformed), MEDIAN_RR (Median of RR Intervals), SDI_BOXCOX (Standard Deviation 1 - Box-Cox Transformed), and SDRR_REL_RR (Standard Deviation of Relative RR Intervals) to optimize the model's performance. The model aims at advancing and refining stress detection methodologies to enhance overall well-being and achieves an accuracy of 98%. © 2024 IEEE.

关键词： Stresses

来源：评论

学校读者我要写书评

暂无评论

Continuous Query-based Data Trading

引用

Performance Evaluation Review 2024年第1期52卷 73-74页

作者： Cheng, Jin Ding, Ningning Lui, John C.S. Huang, Jianwei School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen Shenzhen China Department of Electrical and Computer Engineering Northwestern University Evanston United States Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong

In the era of big data, traditional data trading methods designed for one-time queries on static databases fail to meet the demands of continuous query-based trading on streaming data, often resulting in repeated and inaccurate charges due to neglecting computation sharing in continuous query execution. To address this, we introduce CQTrade, the first trading framework tailored for continuous queries, which incorporates computation sharing across different time windows and queries, enhancing integration with existing trading systems. Our contributions include a theoretical analysis of computation-sharing techniques, the development of a general optimization problem to maximize seller revenue adaptable to various techniques, and the proposal of a branch-and-price algorithm to handle the problem's complexity. Our evaluation shows that the proposed framework improves the success rate of data trading by 12.8% and boosts the seller's revenue by an average of 28.7%, compared to the one-time query-based data trading methods used in the current data market. © 2024 Owner/Author.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Arbitrarily Scalable Environment Generators via Neural Cellular Automata (Extended Abstract) 17th

Arbitrarily Scalable Environment Generators via Neural Cellu...

引用

17th International Symposium on Combinatorial Search, SoCS 2024

作者： Zhang, Yulun Fontaine, Matthew C. Bhatt, Varun Nikolaidis, Stefanos Li, Jiaoyang Robotics Institute Carnegie Mellon University United States Thomas Lord Department of Computer Science University of Southern California United States

ISBN: (纸本)9781577358916

We study the problem of generating arbitrarily large environments to improve the throughput of multi-robot systems. Prior work proposes Quality Diversity (QD) algorithms as an effective method for optimizing the environments of automated warehouses. However, these approaches optimize only relatively small environments, falling short when it comes to replicating real-world warehouse sizes. The challenge arises from the exponential increase in the search space as the environment size increases. Additionally, the previous methods have only been tested with up to 350 robots in simulations, while practical warehouses could host thousands of robots. In this paper, instead of optimizing environments, we propose to optimize Neural Cellular Automata (NCA) environment generators via QD algorithms. We train a collection of NCA generators with QD algorithms in small environments and then generate arbitrarily large environments from the generators at test time. We show that NCA environment generators maintain consistent, regularized patterns regardless of environment size, significantly enhancing the scalability of multi-robot systems in two different domains with up to 2,350 robots. Additionally, we demonstrate that our method scales a single-agent reinforcement learning policy to arbitrarily large environments with similar patterns. We include the source code at https://***/lunjohnzhang/warehouse_env_gen_nca_public. © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Coordination and Layout Design for Automated Warehousing (Extended Abstract) 17th

Multi-Robot Coordination and Layout Design for Automated War...

引用

17th International Symposium on Combinatorial Search, SoCS 2024

ISBN: (纸本)9781577358916

With the rapid progress in Multi-Agent Path Finding (MAPF), researchers have studied how MAPF algorithms can be deployed to coordinate hundreds of robots in large automated warehouses. While most works try to improve the throughput of such warehouses by developing better MAPF algorithms, we focus on improving the throughput by optimizing the warehouse layout. We show that, even with state-of-the-art MAPF algorithms, commonly used human-designed layouts can lead to congestion for warehouses with large numbers of robots and thus have limited scalability. We extend existing automatic scenario generation methods to optimize warehouse layouts. Results show that our optimized warehouse layouts (1) reduce traffic congestion and thus improve throughput, (2) improve the scalability of the automated warehouses by doubling the number of robots in some cases, and (3) are capable of generating layouts with user-specified diversity measures. We include the source code at: https://***/lunjohnzhang/warehouse_env_gen_public. © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

A novel medical image data protection scheme for smart healthcare system

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 821-836页

作者： Mujeeb Ur Rehman Arslan Shafique Muhammad Shahbaz Khan Maha Driss Wadii Boulila Yazeed Yasin Ghadi Suresh Babu Changalasetty Majed Alhaisoni Jawad Ahmad School of Computer Science and Informatics Cyber Technology InstituteDe Montfort UniversityLeicesterUK Department of Biomedical Engineering University of GlasgowGlasgowUK School of Computing Engineering and the Built EnvironmentEdinburgh Napier UniversityEdinburghUK Robotics and Internet‐of‐Things Laboratory Prince Sultan UniversityRiyadhSaudi Arabia Department of Computer Science Al Ain UniversityAl AinUnited Arab Emirates Department of Computer Engineering College of Computer Science King Khalid UniversityAbhaSaudi Arabia Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia

The Internet of Multimedia Things(IoMT)refers to a network of interconnected multimedia devices that communicate with each other over the ***,smart healthcare has emerged as a significant application of the IoMT,particularly in the context of knowledge‐based learning *** healthcare systems leverage knowledge‐based learning to become more context‐aware,adaptable,and auditable while maintain-ing the ability to learn from historical *** smart healthcare systems,devices capture images,such as X‐rays,Magnetic Resonance *** security and integrity of these images are crucial for the databases used in knowledge‐based learning systems to foster structured decision‐making and enhance the learning abilities of ***,in knowledge‐driven systems,the storage and transmission of HD medical images exert a burden on the limited bandwidth of the communication channel,leading to data trans-mission *** address the security and latency concerns,this paper presents a lightweight medical image encryption scheme utilising bit‐plane decomposition and chaos *** results of the experiment yield entropy,energy,and correlation values of 7.999,0.0156,and 0.0001,*** validates the effectiveness of the encryption system proposed in this paper,which offers high‐quality encryption,a large key space,key sensitivity,and resistance to statistical attacks.

关键词： data analysis medical image processing security

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based FOD Detection For Runway Health Monitoring 1

Deep Learning Based FOD Detection For Runway Health Monitori...

引用

1st International Conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Kumar, Amarjeet Mittal, Aanya Dixit, Abhishek Agrawal, Pooja School of Robotics Defence Institute of Advanced Technology Pune India Manipal University Jaipur Department of Computer Science Rajasthan India Defence Institute of Advanced Technology Department of Aerospace Pune India

ISBN: (纸本)9798350355611

This paper focuses on the safety of airport runways, which is crucial for aviation industries. Foreign Object Debris (FOD) i.e. objects like nails or bolts can cause significant harm to aircraft and potentially lead to catastrophic incidents and fatalities. This study delves into detecting objects on runways by using versions of the YOLO (You Only Look Once) model. Further, it also presents the differences in detecting objects and comparing the accuracy across a range of objects, paying attention to their ability to identify even the smallest things that have a potential danger. In order to identify the model variation and enable real-time runway surveillance, the proposed methodology considers the trade-off between detection speed and precision. The results illustrate the effectiveness of the latest YOLO model in object recognition over existing models, this can support the improvement of runway safety and the development of automated systems that monitor runway conditions. © 2025 IEEE.

关键词： Aircraft accidents

来源：评论

学校读者我要写书评

暂无评论

Lighting the Smart Way: A Technological Odyssey in Urban Street Illumination 10

Lighting the Smart Way: A Technological Odyssey in Urban Str...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Vinu, M.S. Priya, P Kanaga Thilakaveni, P. Hermina, J. M. Ashforn Prashanthini, K. Misba, M. Nehru Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Psg Polytechnic College Department of Computer Engineering Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Erode India Sri Ramakrishna Engineering College Department of Robotics and Automation Coimbatore India Bethlahem Institute of Engineering Department of Computer Science and Engineering Nagercoil Karungal India

ISBN: (纸本)9798350384369

The development of intelligent street light systems has ushered in a new era of efficiency and sustainability in urban infrastructure. The proposed work studies the integration of modern sensors and Internet of Things (IoT) technologies to increase the functionality of street lights. The major components include Light Dependent Resistors (LDR) for automatic light management, an MQ135 sensor for air quality monitoring, and a fog detection system employing a laser module and LDR. These sensors are integrated with the ESP8266, providing cloud integration for real-time data visualization and monitoring. Additionally, solar panels are employed to enhance energy efficiency. The proposed methodology digs into the precise implementation, data analysis, and the potential of this system to alter urban lighting infrastructure © 2024 IEEE.

关键词： Air quality

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：