检索结果-内蒙古大学图书馆

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

作者： Weiqiao Han Ashkan Jasour Brian Williams Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology

In this paper, we consider the closed-loop control problem of nonlinear robotic systems in the presence of probabilistic uncertainties and disturbances. More precisely, we design a state feedback controller that minimizes deviations of the states of the system from the nominal state trajectories due to uncertainties and disturbances. Existing approaches to address the control problem of probabilistic systems are limited to particular classes of uncertainties and systems such as Gaussian uncertainties and processes and linearized systems. We present an approach that deals with nonlinear dynamics models and arbitrary known probabilistic uncertainties. We formulate the controller design problem as an optimization problem in terms of statistics of the probability distributions including moments and characteristic functions. In particular, in the provided optimization problem, we use moments and characteristic functions to propagate uncertainties throughout the nonlinear motion model of robotic systems. In order to reduce the tracking deviations, we minimize the uncertainty of the probabilistic states around the nominal trajectory by minimizing the trace and the determinant of the covariance matrix of the probabilistic states. To obtain the state feedback gains, we solve deterministic optimization problems in terms of moments, characteristic functions, and state feedback gains using off-the-shelf interior-point optimization solvers. To illustrate the performance of the proposed method, we compare our method with existing probabilistic control methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Relational Inference with Fast Modular Meta-learning

arXiv

引用

arXiv 2023年

作者： Alet, Ferran Weng, Erica Pérez, Tomás Lozano Kaelbling, Leslie Pack MIT Computer Science and Artificial Intelligence Laboratory United States

Graph neural networks (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types of interactions. Relational inference is the problem of inferring these interactions and learning the dynamics from observational data. We frame relational inference as a modular meta-learning problem, where neural modules are trained to be composed in different ways to solve many tasks. This meta-learning framework allows us to implicitly encode time invariance and infer relations in context of one another rather than independently, which increases inference capacity. Framing inference as the inner-loop optimization of meta-learning leads to a model-based approach that is more data-efficient and capable of estimating the state of entities that we do not observe directly, but whose existence can be inferred from their effect on observed entities. To address the large search space of graph neural network compositions, we meta-learn a proposal function that speeds up the inner-loop simulated annealing search within the modular meta-learning algorithm, providing two orders of magnitude increase in the size of problems that can be addressed. © 2023, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning 41

Energy-Guided Diffusion Sampling for Offline-to-Online Reinf...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Xu-Hui Liu, Tian-Shuo Jiang, Shengyi Chen, Ruifeng Zhang, Zhilong Chen, Xinwei Yu, Yang National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Polixir Technologies China Department of Computer Science The University of Hong Kong Hong Kong

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, Energy-guided DIffusion Sampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at https://***/liuxhym/EDIS. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Hunger games search optimization with deep learning model for sustainable supply chain management

引用

Discover Internet of Things 2023年第1期3卷 10页

作者： Xu, Zheng Jain, Deepak Kumar Neelakandan, S. Abawajy, Jemal School of Computer and Information Engineering Institute for Artificial Intelligence Shanghai Polytechnic University Shanghai201209 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Artificial Intelligence Dalian China Symbiosis Institute of Technology Symbiosis International University Pune India Department of Computer Science and Engineering R.M.K Engineering College Taluk India Deakin University Geelong Australia

The supply chain network is one of the most important areas of focus in the majority of business circumstances. Blockchain technology is a feasible choice for secure information sharing in a supply chain network. Despite the fact that maintaining security at all levels of the blockchain is difficult, cryptographic methods are commonly used in existing works. Effective supply chain management (SCM) offers various benefits to organizations, such as enhanced customer satisfaction, increased operational efficiency, competitive advantage, and cost reduction. Potential SCM for agricultural and food supply chains needs distributors, coordination and collaboration among farmers, retailers, and stakeholders. The use of technology like Block Chain (BC), sensors, and data analytics, can boost traceability and visibility, decrease waste, and ensure safety and quality throughout the supply chain. Therefore, this study develops a Hunger Games Search Optimization with Deep Learning Model for Sustainable agricultural and food Supply Chain Management (HGSODL-ASCM) technique. The fundamental goal of the HGSODL-ASCM technique is to improve decision-making processes for agricultural and food commodity production and storage in order to optimise revenue. In the provided HGSODL-ASCM technique, a bidirectional long short-term memory (Bi-LSTM) model is built to determine the amount of productivity and storage required to maximise profit. In order to boost the performance of the Bi-LSTM classification process, the HGSO algorithm has been utilized in this work. The presented HGSODL-ASCM technique can independently achieve the SCM policies via interaction with complicated and adaptive environments. A brief set of simulations were performed to ensure the improved performance of the HGSODL-ASCM technique. The simulation results demonstrated how superior the HGSODL-ASCM method is to other methods already in use. © The Author(s) 2023.

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

Distributed Active Partial Label Learning

引用

Intelligent Automation & Soft Computing 2023年第9期37卷 2627-2650页

作者： Zhen Xu Weibin Chen Key Laboratory of Intelligent Informatics for Safety&Emergency of Zhejiang Province Wenzhou UniversityWenzhou325006China College of Computer Science and Artificial Intelligence Engineering Wenzhou UniversityWenzhou325006China

Active learning(AL)trains a high-precision predictor model from small numbers of labeled data by iteratively annotating the most valuable data sample from an unlabeled data pool with a class label throughout the learning ***,most current AL methods start with the premise that the labels queried at AL rounds must be free of ambiguity,which may be unrealistic in some real-world applications where only a set of candidate labels can be obtained for selected ***,most of the existing AL algorithms only consider the case of centralized processing,which necessitates gathering together all the unlabeled data in one fusion center for *** that data are collected/stored at different nodes over a network in many real-world scenarios,distributed processing is chosen *** this paper,the issue of distributed classification of partially labeled(PL)data obtained by a fully decentralized AL method is focused on,and a distributed active partial label learning(dAPLL)algorithm is *** proposed algorithm is composed of a fully decentralized sample selection strategy and a distributed partial label learning(PLL)*** the sample selection process,both the uncertainty and representativeness of the data are measured based on the global cluster centers obtained by a distributed clustering method,and the valuable samples are chosen in ***,using the disambiguation-free strategy,a series of binary classification problems can be constructed,and the corresponding cost-sensitive classifiers can be cooperatively trained in a distributed *** experiment results conducted on several datasets demonstrate that the performance of the dAPLL algorithm is comparable to that of the corresponding centralized method and is superior to the existing active PLL(APLL)method in different parameter ***,our proposed algorithm outperforms several current PLL methods using the random selection strategy,especially when only s

关键词： Active learning partial label learning distributed processing disambiguation-free strategy

来源：评论

学校读者我要写书评

暂无评论

Batch Process Monitoring with Attention-Based Two-Dimensional Stacked Graph Convolutional Autoencoder 6

Batch Process Monitoring with Attention-Based Two-Dimensiona...

引用

6th International Conference on Industrial artificial intelligence, IAI 2024

作者： Gao, Xingke Zhang, Zheng Gao, Furong Zhu, Jinlin School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Hong Kong University of Science and Technology Department of Chemical and Biological Engineering Hong Kong School of Food Science and Technology Jiangnan University State Key Laboratory of Food Science and Resources Wuxi China

ISBN: (纸本)9798350356618

In batch processes, the efficacy of statistical control is reportedly sensitive to the dynamics and nonlinearity found in the batch data, which can hamper the valid feature extraction for statistical analysis. Normally, a two-way window is applied to aggregate the samples across the batch and time direction to assuage this challenge. However, samples in the window are generally processed on par with each other such that irrelevant features can cause redundancy and make window size critical to be tediously tune during the training phase. In this paper, a linear correlation aided method is proposed to first determine the effective size of a regular-shaped sliding window, and, a Euclidean distance-based measure is used to construct a graph prior to the phase of feature extraction. With these efforts, we presented the Attention-based Two-dimensional Stacked Graph Convolutional Autoencoder (2D-ASGCA) for enhanced learning in the Statistical Process Control (SPC) of batch processes. Moreover, a technique called Deep Reconstruction-based Contribution (DRBC) chart has been applied to perform the variable-wise root cause diagnosis, when a fault is signaled. Finally, two case studies are provided to demonstrate the model validity. © 2024 IEEE.

关键词： Batch data processing

来源：评论

学校读者我要写书评

暂无评论

Local Neural Descriptor Fields: Locally Conditioned Object Representations for Manipulation

arXiv

引用

arXiv 2023年

作者： Chun, Ethan Du, Yilun Simeonov, Anthony Lozano-Perez, Tomas Kaelbling, Leslie Computer Science and Artificial Intelligence Laboratory MIT United States

A robot operating in a household environment will see a wide range of unique and unfamiliar objects. While a system could train on many of these, it is infeasible to predict all the objects a robot will see. In this paper, we present a method to generalize object manipulation skills acquired from a limited number of demonstrations, to novel objects from unseen shape categories. Our approach, Local Neural Descriptor Fields (LNDF), utilizes neural descriptors defined on the local geometry of the object to effectively transfer manipulation demonstrations to novel objects at test time. In doing so, we leverage the local geometry shared between objects to produce a more general manipulation framework. We illustrate the efficacy of our approach in manipulating novel objects in novel poses – both in simulation and in the real world. Project website, videos, and code: https://***/lndf/. © 2023, CC0.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aptly: Making Mobile Apps from Natural Language

arXiv

引用

arXiv 2024年

作者： Patton, Evan W. Kim, David Y.J. Granquist, Ashley Liu, Robin Scott, Arianna Zamanova, Jennet Abelson, Harold MIT Computer Science and Artificial Intelligence Laboratory United States MIT Electrical Engineering and Computer Science United States

We present Aptly, an extension of the MIT App Inventor platform enabling mobile app development via natural language powered by code-generating large language models (LLMs). Aptly complements App Inventor’s block language with a text language designed to allow visual code generation via text-based LLMs. We detail the technical aspects of how the Aptly server integrates LLMs with a realtime collaboration function to facilitate the automated creation and editing of mobile apps given user instructions. The paper concludes with insights from a study of a pilot implementation involving high school students, which examines Aptly’s practicality and user experience. The findings underscore Aptly’s potential as a tool that democratizes app development and fosters technological creativity. © 2024, CC BY-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Dual-channel Feature Extraction Network for Camouflaged Small Object Detection 3

Dual-channel Feature Extraction Network for Camouflaged Smal...

引用

3rd International Conference on Optics and Machine Vision, ICOMV 2024

作者： Wang, Futian Huang, Mengyu Chen, Yitao Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China AHU-IAI AI Joint Laboratory Anhui University Hefei China

ISBN: (纸本)9781510680319

Small object detection is a challenging problem in object detection, in practice, we found a special kind of small object detection results are very poor, we call it camouflaged small object, the color of the object itself is similar to the surrounding environment, that is, the contrast between the object and the surrounding environment is low. Therefore, we propose a method to stretch the grayscale map to directly increase the contrast between the object and the surrounding environment. Then, as to how to effectively fuse the feature of object in grayscale map with the feature of object in original RGB image, we propose a dual-channel feature fusion module DCF, which allows the features extracted from the grayscale map to enhance the features extracted from the original RGB image. We also constructed a camouflaged small object detection dataset SSD, which is a smoking object detection dataset with only one smoking object, containing 4349 images and 4705 object instances. Our proposed DCF framework can be easily embedded into existing object detection frameworks. We experimented on a number of different excellent detectors, Faster R-CNN, RetinaNet, and YOLOv8, and the results show that our method is effective in all of these detectors. © 2024 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive dynamic surface control for quadrotor-slung load transportation system with uncertainties

引用

science China(Technological sciences) 2023年第10期66卷 2917-2929页

作者： DING Feng HUANG Jian SUN Chong AI Yong XU WenXia YANG ChenGuang School of Computer Science South-Central Minzu UniversityWuhan 430074China Key Laboratory of Ministryof EducationforImage Processing and Intelligent ControlHubei Key Laboratoryof Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Engineering Wuhan Institute of TechnologyWuhan 430205China Key Laboratory of Ministry of Education for Autonomous Systems and Networked Control Guangdong Engineering Technology Research Center of Control of Intelligent SystemsCollege of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510640China

Quadrotors play a significant role in our lives and are transforming our *** cable-suspended loads is an unavoidable quadrotor application trend and a hot research topic in the control ***,the load swing and unpredictability pose significant challenges to the quadrotor's *** this paper,an anti-swing controller with an inner-outer control strategy for the quadrotor-slung load transportation system is *** facilitate the controller design,the outer position dynamics are restructured in the form of ***,a virtual controller is created to force the underactuated states to the dynamic surface to ensure the position subsystem's *** improve robustness,an adaptive law is used to eliminate the effects of uncertain cable ***,a dynamic surface controller for the inner attitude subsystem is presented to drive the actual force to the virtual *** is demonstrated that the control strategy can stabilize the quadrotor despite mass and cable length *** results are provided to demonstrate the efficacy and durability of the proposed method.

关键词： quadrotor-slung load transportation system dynamic surface control adaptive law cascade system model uncertainties

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：