检索结果-内蒙古大学图书馆

Explicit-Implicit Subgoal Planning for Long-Horizon Tasks with Sparse Rewards

IEEE Transactions on Automation science and engineering 2025年 22卷 16038-16049页

作者： Wang, Fangyuan Duan, Anqing Zhou, Peng Huo, Shengzeng Guo, Guodong Yang, Chenguang Navarro-Alarcon, David The Hong Kong Polytechnic University Department of Mechanical Engineering Kowloon Hong Kong Ningbo Institute of Digital Twin Ningbo China Mohamed Bin Zayed University of Artificial Intelligence Robotics Department Abu Dhabi United Arab Emirates The Great Bay University School of Advanced Engineering Dongguan China Ningbo Institute of Digital Twin Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin Ningbo China University of Liverpool Department of Computer Science Liverpool United Kingdom

The challenges inherent in long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To address these challenges, we have developed a novel algorithm, termed hlexplicit-implicit subgoal planning (EISP), designed to tackle long-horizon tasks through a divide-and-conquer approach. We utilize two primary criteria, feasibility and optimality, to ensure the quality of the generated subgoals. EISP consists of three components: a hybrid subgoal generator, a hindsight sampler, and a value selector. The hybrid subgoal generator uses an explicit model to infer subgoals and an implicit model to predict the final goal, inspired by way of human thinking that infers subgoals by using the current state and final goal as well as reason about the final goal conditioned on the current state and given subgoals. Additionally, the hindsight sampler selects valid subgoals from an offline dataset to enhance the feasibility of the generated subgoals. While the value selector utilizes the value function in reinforcement learning to filter the optimal subgoals from subgoal candidates. To validate our method, we conduct four long-horizon tasks in both simulation and the real world. The obtained quantitative and qualitative data indicate that our approach achieves promising performance compared to other baseline methods. © 2004-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fuzzy sets visualization for decision-making processes in social studies

Fuzzy sets visualization for decision-making processes in so...

引用

2020 International Conference on Information Technology in Business and Industry, ITBI 2020

作者： Berestneva, O. Marukhina, O. Romanchukov, S. Engineering School of Computer Science and Robotics National Research Tomsk Polytechnic University Lenin Avenue 30 Tomsk634050 Russia

This paper is devoted to visualization of multidimensional fuzzy series and describes analysis methodology based on images that can be built after the initial time series transformation. It is shown that the most rigid structure of a fuzzy number is the number of components with the highest value of membership function. Built in accordance with the proposed method a series of visual images reflect the tendency of the fuzzy time series. The application of fuzzy time series visualization facilitates the identification of high-quality bonds in the consideration of dynamical semi-system (including social and economic). The proposed approach allows a qualitative level to solve the problem of grouping, structuring and forecasting in such systems, but there are doubts in numerical accuracy and quality. © Published under licence by IOP Publishing Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction

arXiv

引用

arXiv 2023年

作者： Yang, Jing Chen, Yuehai Du, Shaoyi Chen, Badong Principe, Jose C. School of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong Xi'An710049 China Institute of Articial Intelligence and Robotics College of Articial Intelligence Xi'an Jiaotong University Shanxi Xi'An710049 China The Computational NeuroEngineering Laboratory Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States

Predicting the trajectory of pedestrians in crowd scenarios is indispensable in self-driving or autonomous mobile robot field because estimating the future locations of pedestrians around is beneficial for policy decision to avoid collision. It is a challenging issue because humans have different walking motions, and the interactions between humans and objects in the current environment, especially between humans themselves, are complex. Previous researchers focused on how to model human-human interactions but neglected the relative importance of interactions. To address this issue, a novel mechanism based on correntropy is introduced. The proposed mechanism not only can measure the relative importance of human-human interactions but also can build personal space for each pedestrian. An interaction module including this data-driven mechanism is further proposed. In the proposed module, the data-driven mechanism can effectively extract the feature representations of dynamic human-human interactions in the scene and calculate the corresponding weights to represent the importance of different interactions. To share such social messages among pedestrians, an interaction-aware architecture based on long short-term memory network for trajectory prediction is designed. Experiments are conducted on two public datasets. Experimental results demonstrate that our model can achieve better performance than several latest methods with good performance. © 2023, CC BY-NC-ND.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Air Particulate Matters Auto-Rule-Based Labeling to Support Long-Distance Run Environment Data Classification

Air Particulate Matters Auto-Rule-Based Labeling to Support ...

引用

International Conference on computer Applications and Industrial Electronics (ICCAIE)

作者： Wandy Wandy Kusworo Adi Media Anugerah Ayu Doctoral Program of Information Systems School of Postgraduate Studies Diponegoro University Semarang Indonesia Department of Physics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia Department of Computer Science Faculty of Engineering and Technology Sampoerna University South Jakarta Indonesia

Sports science is an interdisciplinary and multidisciplinary science that strives to increase athletic performance and endurance. Sport science recognizes and prevents injuries. Sensors and statistics formalize Sports science. Runners need coaches and teams to support them before, during, and after the run race. Coaches generate running training plans to boost performance. Running race performances may be impacted by air pollution exposure while training, so coaches should consider limiting air pollution exposure when training. One of the external factors is Particulate Matter (PM 2.5 and PM 10 ). Sensors connecting to the Internet can record external factors and produce csv data. The foundation of supervised machine learning is the labeling process. Labeling a set of data is one of the laborious and time-consuming phases in every machine-learning application because it requires verifying the accuracy of the labels and making any necessary revisions. This research aimed to find a solution to automatically label numerous air particulate matter raw data using a rule based on parameters to reduce manual work, human errors and faster processes. This labeled data will later be used for supervised machine learning classification to support the coach in generating training programs for the runners in a Sports Information System. Based on Indonesia Air Quality index rule-based approach, labeled text data in csv has been generated and tested with PM 2.5 and PM 10 parameters in three scenarios with a 100% success rate. It was possible to automate the labeling process, and it explained how automation results in fast and accurate results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Explainable Convolutional Neural Networks for Automatic Segmentation of the Left Ventricle in Cardiac MRI 11

An Explainable Convolutional Neural Networks for Automatic S...

引用

11th International Conference on Electronics, Communications and Networks, CECNet 2021

作者： Liu, Jun Deng, Feng Yuan, Geng Lin, Xue Song, Houbing Wang, Yanzhi Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States Beijing Key Laboratory of High Dynamic Navigation Technology Beijing Information Science and Technology University Beijing China Department of Electrical and Computer Engineering College of Engineering Northeastern University BostonMA United States Embry-Riddle Aeronautical University Daytona BeachFL United States

ISBN: (纸本)9781643682402

Recently, the study on model interpretability has become a hot topic in deep learning research area. Especially in the field of medical imaging, the requirements for safety are extremely high;Moreover, it is very important for the model to be able to explain. However, the existing solutions for left ventricular segmentation by convolutional neural networks are black boxes;explainable CNNs remains a challenge;explainable deep learning models has always been a task often overlooked in the entire data science lifecycle by data scientists or deep learning engineers. Because of very limited medical imaging data, most solutions currently use transfer learning methods to transfer the model which used on large-scale benchmark data sets (such as ImageNet) to fine tune medical imaging models. Consequently, a large amount of useless parameters are generated, resulting in further barrier for the model to provide a convincing explanation. This paper presents a novel method to automatically segment the Left Ventricle in Cardiac MRI by explainable convolutional neural networks with optimized size and parameters by our enhanced Deep Learning GPU Training System. It is very suitable for deployment on mobile devices. We simplify deep learning tasks on DIGITS systems, monitoring performance, and displaying the heat map of each layer of the network with advanced visualizations in real time. Our experiment results demonstrated that the proposed method is feasible and efficient. © 2022 The authors and IOS Press.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Citrus Limon L. Ripeness Identification Using Feature Extraction of Mean RGB, HSV, LBP and K-Nearest Neighbor

Citrus Limon L. Ripeness Identification Using Feature Extrac...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Ade Cahyo Priyo Utomo Christy Atika Sari Eko Hari Rachmawanto Heru Pramono Hadi Salama A. Mostafa Wisam Subhi Talib Al-Dayyeni Study Program in Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Study Program in Information Systems University of Dian Nuswantoro Semarang Indonesia Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia School of Information Technologies and Engineering ADA University Baku Azerbaijan

Citrus Limon L. (Lemon) is a type of fruit that is currently widely consumed, because it contains abundant vitamin C, fiber, and antioxidants. This fruit have high potential in the agribusiness sector and is widely cultivated by traditional farmers. However, during harvest time, traditional farmers generally still use manual methods using the human eye in distinguishing the maturity level of lemons which is less efficient because it has a low accuracy. Digital image processing is one solution to this problem. In the research on the classification of lemon maturity levels using digital image processing with the feature extraction method of the Mean RGB, HSV, and LBP methods and the K-Nearest Neighbor classification algorithm in this study, a total of 120 lemon images were used which were divided into 80 training image data and 40 image data. testing. The results of model performance measurements in the form of the highest accuracy level in the Mean RGB method of 100%, the highest accuracy in the HSV method of 98%, and the highest accuracy in the LBP method of 82.5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Trolley Transportation System with Autonomous Nonholonomic Robots

Collaborative Trolley Transportation System with Autonomous ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Bingyi Xia Hao Luan Ziqi Zhao Xuheng Gao Peijia Xie Anxing Xiao Jiankun Wang Max Q.-H. Meng Department of Electronic and Electrical Engineering Shenzhen Key Laboratory of Robotics Perception and Intelligence Southern University of Science and Technology Shenzhen China School of Computing National University of Singapore Singapore Jiaxing Research Institute Southern University of Science and Technology Jiaxing China Department of Electronic Engineering Department of Electrical and Computer Engineering Chinese University of Hong Kong in Hong Kong University of Alberta Canada

Cooperative object transportation using multiple robots has been intensively studied in the control and robotics literature, but most approaches are either only applicable to omnidirectional robots or lack a complete navigation and decision-making framework that operates in real time. This paper presents an autonomous nonholonomic multi-robot system and an end-to-end hierarchical autonomy framework for collaborative luggage trolley transportation. This framework finds kinematic-feasible paths, computes online motion plans, and provides feedback that enables the multi-robot system to handle long lines of luggage trolleys and navigate obstacles and pedestrians while dealing with multiple inherently complex and coupled constraints. We demonstrate the designed collaborative trolley transportation system through practical transportation tasks, and the experiment results reveal their effectiveness and reliability in complex and dynamic environments. (Video 1 1 Video demonstration: https://***/efnPERm0Rco.)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Fabrication of Bio-Inspired Robotic Modular Systems based on Biomechanics of Inching-Locomotion Caterpillars

Digital Fabrication of Bio-Inspired Robotic Modular Systems ...

引用

Colombian Caribbean Conference (C3), IEEE

作者： José Cornejo Sergio Marquez Sanchez J. Enrique Sierra Francisco Javier Gomez-Gil Ricardo Palomares Alfredo Weitzenfeld Department of Electromechanical Engineering University of Burgos Burgos Spain BISITE Research Group University of Salamanca Salamanca Spain Research Group of Robotics and Mechatronics (GI-ROMA) Professional School of Mechatronics Engineering Universidad Ricardo Palma Lima Peru Department of Computer Science and Engineering Biorobotics Laboratory University of South Florida FL USA

Inching-locomotion caterpillars have biomechanical features for good performance in manipulation tasks. This research focuses on the study of kinematic chains in 2 species of the Lepidoptera family. The motion analysis of both was distributed in 8 biomechanical gait steps (BGS) named from t0 to t7 for each one. The engineering design was carried out in 2 stages, the first (2-D) was implemented with the use of CorelDraw and its manufacture in 3 mm thick MDF material, where it was obtained that the system complied with the mechanical configuration of BGS from t0 to t2 and t5 to t7, then, for the second stage (3-D) SolidWorks was used where the parametric modeling was carried out. For the manufacture of the second prototype, the FDM method was used in PLA material, to have resistant parts, for which it was defined to use the Original Prusa i3 MK3S printer. Then, in order to process the STL files, the PrusaSlicer 2.5.0 software was used. In addition, their mechanical configurations comply with BGS from t0 to t3 and t5 to t7. The Geometridae system has a maximum length of 32.5 cm and a weight of 110.53 g and the Plusiinae has a maximum length of 44 cm and a weight of 147.83 g. Finally, the bio-design thinking methodology structured and adapted to each section presented in this work was successfully implemented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models

arXiv

引用

arXiv 2024年

作者： Guo, Jiayi Chen, Zan Ji, Yingrui Zhang, Liyun Luo, Daqin Li, Zhigang Shen, Yiqin Glasgow College University of Electronic Science and Technology of China Chengdu China School of Engineering University of Glasgow Glasgow United Kingdom Toursun Synbio Shanghai China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Research Institute Ubtech Robotics Corp Shenzhen China Qiyuan Lab. Beijing China Department of Computer Science Johns Hopkins University MD United States

Automated Machine Learning (AutoML) can streamline the complexities of machine learning pipelines. However, existing AutoML frameworks focus on discriminative tasks leaving generative tasks unexplored. Moreover, existing AutoML frameworks often lack interpretability and user engagement during the model development and training process, due to the absence of human-centered designs. To address these challenges, we propose UniAutoML, a human-centered AutoML framework that leverages Large Language Models (LLMs) to unify the automation of both discriminative (e.g., Transformers and CNNs for classification or regression) and generative tasks (e.g., fine-tuning diffusion models or LLMs). UniAutoML enables natural language interactions between users and the framework to provide real-time feedback and progress updates, thus enhancing the interpretability, transparency, and user control, where users can seamlessly modify or refine the model training in response to evolving needs. To ensure the safety and reliability of LLM-generated content, UniAutoML incorporates a safety guard-line that filter inputs and censor outputs. We evaluated UniAutoML’s performance and usability through experiments conducted on eight diverse datasets and user studies involving 25 participants. Our results demonstrate that UniAutoML not only achieves higher performance but also improves user control and trust in the AutoML process, which makes ML more accessible and intuitive for a broader audience. The code for UniAutoML is available at: https://***/richarf22/UniAutoML. © 2024, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

NaFM: Pre-training a Foundation Model for Small-Molecule Natural Products

arXiv

引用

arXiv 2025年

作者： Ding, Yuheng Wang, Yusong Qiang, Bo Yu, Jie Li, Qi Zhou, Yiran Liu, Zhenmin State Key Laboratory of Natural and Biomimetic Drugs School of Pharmaceutical Sciences Peking University Beijing100191 China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Paul G. Allen School of Computer Science & Engineering University of Washington SeattleWA98105 United States

Natural products, as metabolites from microorganisms, animals, or plants, exhibit diverse biological activities, making them crucial for drug discovery. Nowadays, existing deep learning methods for natural products research primarily rely on supervised learning approaches designed for specific downstream tasks. However, such one-model-for-a-task paradigm often lacks generalizability and leaves significant room for performance improvement. Additionally, existing molecular characterization methods are not well-suited for the unique tasks associated with natural products. To address these limitations, we have pre-trained a foundation model for natural products based on their unique properties. Our approach employs a novel pretraining strategy that is especially tailored to natural products. By incorporating contrastive learning and masked graph learning objectives, we emphasize evolutional information from molecular scaffolds while capturing side-chain information. Our framework achieves state-of-the-art (SOTA) results in various downstream tasks related to natural product mining and drug discovery. We first compare taxonomy classification with synthesized molecule-focused baselines to demonstrate that current models are inadequate for understanding natural synthesis. Furthermore, by diving into a fine-grained analysis at both the gene and microbial levels, NaFM demonstrates the ability to capture evolutionary information. Eventually, our method is experimented with virtual screening, illustrating informative natural product representations that can lead to more effective identification of potential drug candidates. © 2025, CC BY.

关键词： Metabolites

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：